diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml index 64d8d9e5e47a..b36d74c1da7c 100644 --- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml +++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml @@ -17,9 +17,16 @@ properties: compatible: enum: - qcom,sc7180-dp + - qcom,sc8180x-dp + - qcom,sc8180x-edp reg: - maxItems: 1 + items: + - description: ahb register block + - description: aux register block + - description: link register block + - description: p0 register block + - description: p1 register block interrupts: maxItems: 1 @@ -100,7 +107,11 @@ examples: displayport-controller@ae90000 { compatible = "qcom,sc7180-dp"; - reg = <0xae90000 0x1400>; + reg = <0xae90000 0x200>, + <0xae90200 0x200>, + <0xae90400 0xc00>, + <0xae91000 0x400>, + <0xae91400 0x400>; interrupt-parent = <&mdss>; interrupts = <12>; clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>, diff --git a/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml b/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml new file mode 100644 index 000000000000..fbeb931a026e --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/dpu-sc7280.yaml @@ -0,0 +1,232 @@ +# SPDX-License-Identifier: GPL-2.0-only or BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/msm/dpu-sc7280.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Display DPU dt properties for SC7280 + +maintainers: + - Krishna Manikandan + +description: | + Device tree bindings for MSM Mobile Display Subsystem (MDSS) that encapsulates + sub-blocks like DPU display controller, DSI and DP interfaces etc. Device tree + bindings of MDSS and DPU are mentioned for SC7280. + +properties: + compatible: + const: qcom,sc7280-mdss + + reg: + maxItems: 1 + + reg-names: + const: mdss + + power-domains: + maxItems: 1 + + clocks: + items: + - description: Display AHB clock from gcc + - description: Display AHB clock from dispcc + - description: Display core clock + + clock-names: + items: + - const: iface + - const: ahb + - const: core + + interrupts: + maxItems: 1 + + interrupt-controller: true + + "#address-cells": true + + "#size-cells": true + + "#interrupt-cells": + const: 1 + + iommus: + items: + - description: Phandle to apps_smmu node with SID mask for Hard-Fail port0 + + ranges: true + + interconnects: + items: + - description: Interconnect path specifying the port ids for data bus + + interconnect-names: + const: mdp0-mem + +patternProperties: + "^display-controller@[0-9a-f]+$": + type: object + description: Node containing the properties of DPU. + + properties: + compatible: + const: qcom,sc7280-dpu + + reg: + items: + - description: Address offset and size for mdp register set + - description: Address offset and size for vbif register set + + reg-names: + items: + - const: mdp + - const: vbif + + clocks: + items: + - description: Display hf axi clock + - description: Display sf axi clock + - description: Display ahb clock + - description: Display lut clock + - description: Display core clock + - description: Display vsync clock + + clock-names: + items: + - const: bus + - const: nrt_bus + - const: iface + - const: lut + - const: core + - const: vsync + + interrupts: + maxItems: 1 + + power-domains: + maxItems: 1 + + operating-points-v2: true + + ports: + $ref: /schemas/graph.yaml#/properties/ports + description: | + Contains the list of output ports from DPU device. These ports + connect to interfaces that are external to the DPU hardware, + such as DSI, DP etc. Each output port contains an endpoint that + describes how it is connected to an external interface. + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: DPU_INTF1 (DSI) + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: DPU_INTF5 (EDP) + + required: + - port@0 + + required: + - compatible + - reg + - reg-names + - clocks + - interrupts + - power-domains + - operating-points-v2 + - ports + +required: + - compatible + - reg + - reg-names + - power-domains + - clocks + - interrupts + - interrupt-controller + - iommus + - ranges + +additionalProperties: false + +examples: + - | + #include + #include + #include + #include + #include + + display-subsystem@ae00000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "qcom,sc7280-mdss"; + reg = <0xae00000 0x1000>; + reg-names = "mdss"; + power-domains = <&dispcc DISP_CC_MDSS_CORE_GDSC>; + clocks = <&gcc GCC_DISP_AHB_CLK>, + <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&dispcc DISP_CC_MDSS_MDP_CLK>; + clock-names = "iface", + "ahb", + "core"; + + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + + interconnects = <&mmss_noc MASTER_MDP0 &mc_virt SLAVE_EBI1>; + interconnect-names = "mdp0-mem"; + + iommus = <&apps_smmu 0x900 0x402>; + ranges; + + display-controller@ae01000 { + compatible = "qcom,sc7280-dpu"; + reg = <0x0ae01000 0x8f000>, + <0x0aeb0000 0x2008>; + + reg-names = "mdp", "vbif"; + + clocks = <&gcc GCC_DISP_HF_AXI_CLK>, + <&gcc GCC_DISP_SF_AXI_CLK>, + <&dispcc DISP_CC_MDSS_AHB_CLK>, + <&dispcc DISP_CC_MDSS_MDP_LUT_CLK>, + <&dispcc DISP_CC_MDSS_MDP_CLK>, + <&dispcc DISP_CC_MDSS_VSYNC_CLK>; + clock-names = "bus", + "nrt_bus", + "iface", + "lut", + "core", + "vsync"; + + interrupt-parent = <&mdss>; + interrupts = <0>; + power-domains = <&rpmhpd SC7280_CX>; + operating-points-v2 = <&mdp_opp_table>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dpu_intf1_out: endpoint { + remote-endpoint = <&dsi0_in>; + }; + }; + + port@1 { + reg = <1>; + dpu_intf5_out: endpoint { + remote-endpoint = <&edp_in>; + }; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml index 064df50e21a5..81dbee4803c0 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml @@ -17,6 +17,7 @@ properties: enum: - qcom,dsi-phy-14nm - qcom,dsi-phy-14nm-660 + - qcom,dsi-phy-14nm-8953 reg: items: diff --git a/Documentation/devicetree/bindings/display/msm/gpu.txt b/Documentation/devicetree/bindings/display/msm/gpu.txt deleted file mode 100644 index 090dcb3fc34d..000000000000 --- a/Documentation/devicetree/bindings/display/msm/gpu.txt +++ /dev/null @@ -1,157 +0,0 @@ -Qualcomm adreno/snapdragon GPU - -Required properties: -- compatible: "qcom,adreno-XYZ.W", "qcom,adreno" or - "amd,imageon-XYZ.W", "amd,imageon" - for example: "qcom,adreno-306.0", "qcom,adreno" - Note that you need to list the less specific "qcom,adreno" (since this - is what the device is matched on), in addition to the more specific - with the chip-id. - If "amd,imageon" is used, there should be no top level msm device. -- reg: Physical base address and length of the controller's registers. -- interrupts: The interrupt signal from the gpu. -- clocks: device clocks (if applicable) - See ../clocks/clock-bindings.txt for details. -- clock-names: the following clocks are required by a3xx, a4xx and a5xx - cores: - * "core" - * "iface" - * "mem_iface" - For GMU attached devices the GPU clocks are not used and are not required. The - following devices should not list clocks: - - qcom,adreno-630.2 -- iommus: optional phandle to an adreno iommu instance -- operating-points-v2: optional phandle to the OPP operating points -- interconnects: optional phandle to an interconnect provider. See - ../interconnect/interconnect.txt for details. Some A3xx and all A4xx platforms - will have two paths; all others will have one path. -- interconnect-names: The names of the interconnect paths that correspond to the - interconnects property. Values must be gfx-mem and ocmem. -- qcom,gmu: For GMU attached devices a phandle to the GMU device that will - control the power for the GPU. Applicable targets: - - qcom,adreno-630.2 -- zap-shader: For a5xx and a6xx devices this node contains a memory-region that - points to reserved memory to store the zap shader that can be used to help - bring the GPU out of secure mode. -- firmware-name: optional property of the 'zap-shader' node, listing the - relative path of the device specific zap firmware. -- sram: phandle to the On Chip Memory (OCMEM) that's present on some a3xx and - a4xx Snapdragon SoCs. See - Documentation/devicetree/bindings/sram/qcom,ocmem.yaml. - -Optional properties: -- #cooling-cells: The value must be 2. For details, please refer - Documentation/devicetree/bindings/thermal/thermal-cooling-devices.yaml. - -Example 3xx/4xx: - -/ { - ... - - gpu: adreno@fdb00000 { - compatible = "qcom,adreno-330.2", - "qcom,adreno"; - reg = <0xfdb00000 0x10000>; - reg-names = "kgsl_3d0_reg_memory"; - interrupts = ; - interrupt-names = "kgsl_3d0_irq"; - clock-names = "core", - "iface", - "mem_iface"; - clocks = <&mmcc OXILI_GFX3D_CLK>, - <&mmcc OXILICX_AHB_CLK>, - <&mmcc OXILICX_AXI_CLK>; - sram = <&gpu_sram>; - power-domains = <&mmcc OXILICX_GDSC>; - operating-points-v2 = <&gpu_opp_table>; - iommus = <&gpu_iommu 0>; - #cooling-cells = <2>; - }; - - gpu_sram: ocmem@fdd00000 { - compatible = "qcom,msm8974-ocmem"; - - reg = <0xfdd00000 0x2000>, - <0xfec00000 0x180000>; - reg-names = "ctrl", - "mem"; - - clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>, - <&mmcc OCMEMCX_OCMEMNOC_CLK>; - clock-names = "core", - "iface"; - - #address-cells = <1>; - #size-cells = <1>; - - gpu_sram: gpu-sram@0 { - reg = <0x0 0x100000>; - ranges = <0 0 0xfec00000 0x100000>; - }; - }; -}; - -Example a6xx (with GMU): - -/ { - ... - - gpu@5000000 { - compatible = "qcom,adreno-630.2", "qcom,adreno"; - #stream-id-cells = <16>; - - reg = <0x5000000 0x40000>, <0x509e000 0x10>; - reg-names = "kgsl_3d0_reg_memory", "cx_mem"; - - #cooling-cells = <2>; - - /* - * Look ma, no clocks! The GPU clocks and power are - * controlled entirely by the GMU - */ - - interrupts = ; - - iommus = <&adreno_smmu 0>; - - operating-points-v2 = <&gpu_opp_table>; - - interconnects = <&rsc_hlos MASTER_GFX3D &rsc_hlos SLAVE_EBI1>; - interconnect-names = "gfx-mem"; - - gpu_opp_table: opp-table { - compatible = "operating-points-v2"; - - opp-430000000 { - opp-hz = /bits/ 64 <430000000>; - opp-level = ; - opp-peak-kBps = <5412000>; - }; - - opp-355000000 { - opp-hz = /bits/ 64 <355000000>; - opp-level = ; - opp-peak-kBps = <3072000>; - }; - - opp-267000000 { - opp-hz = /bits/ 64 <267000000>; - opp-level = ; - opp-peak-kBps = <3072000>; - }; - - opp-180000000 { - opp-hz = /bits/ 64 <180000000>; - opp-level = ; - opp-peak-kBps = <1804000>; - }; - }; - - qcom,gmu = <&gmu>; - - zap-shader { - memory-region = <&zap_shader_region>; - firmware-name = "qcom/LENOVO/81JL/qcdxkmsuc850.mbn" - }; - }; -}; diff --git a/Documentation/devicetree/bindings/display/msm/gpu.yaml b/Documentation/devicetree/bindings/display/msm/gpu.yaml new file mode 100644 index 000000000000..99a1ba3ada56 --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/gpu.yaml @@ -0,0 +1,288 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- + +$id: "http://devicetree.org/schemas/display/msm/gpu.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Devicetree bindings for the Adreno or Snapdragon GPUs + +maintainers: + - Rob Clark + +properties: + compatible: + oneOf: + - description: | + The driver is parsing the compat string for Adreno to + figure out the gpu-id and patch level. + items: + - pattern: '^qcom,adreno-[3-6][0-9][0-9]\.[0-9]$' + - const: qcom,adreno + - description: | + The driver is parsing the compat string for Imageon to + figure out the gpu-id and patch level. + items: + - pattern: '^amd,imageon-200\.[0-1]$' + - const: amd,imageon + + clocks: true + + clock-names: true + + reg: + minItems: 1 + maxItems: 3 + + reg-names: + minItems: 1 + items: + - const: kgsl_3d0_reg_memory + - const: cx_mem + - const: cx_dbgc + + interrupts: + maxItems: 1 + + interrupt-names: + maxItems: 1 + + interconnects: + minItems: 1 + maxItems: 2 + + interconnect-names: + minItems: 1 + items: + - const: gfx-mem + - const: ocmem + + iommus: + maxItems: 1 + + sram: + $ref: /schemas/types.yaml#/definitions/phandle-array + minItems: 1 + maxItems: 4 + description: | + phandles to one or more reserved on-chip SRAM regions. + phandle to the On Chip Memory (OCMEM) that's present on some a3xx and + a4xx Snapdragon SoCs. See + Documentation/devicetree/bindings/sram/qcom,ocmem.yaml + + operating-points-v2: true + opp-table: + type: object + + power-domains: + maxItems: 1 + + zap-shader: + type: object + description: | + For a5xx and a6xx devices this node contains a memory-region that + points to reserved memory to store the zap shader that can be used to + help bring the GPU out of secure mode. + properties: + memory-region: + $ref: /schemas/types.yaml#/definitions/phandle + + firmware-name: + description: | + Default name of the firmware to load to the remote processor. + + "#cooling-cells": + const: 2 + + nvmem-cell-names: + maxItems: 1 + + nvmem-cells: + description: efuse registers + maxItems: 1 + + qcom,gmu: + $ref: /schemas/types.yaml#/definitions/phandle + description: | + For GMU attached devices a phandle to the GMU device that will + control the power for the GPU. + + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +allOf: + - if: + properties: + compatible: + contains: + pattern: '^qcom,adreno-[3-5][0-9][0-9]\.[0-9]$' + + then: + properties: + clocks: + minItems: 2 + maxItems: 7 + + clock-names: + items: + anyOf: + - const: core + description: GPU Core clock + - const: iface + description: GPU Interface clock + - const: mem + description: GPU Memory clock + - const: mem_iface + description: GPU Memory Interface clock + - const: alt_mem_iface + description: GPU Alternative Memory Interface clock + - const: gfx3d + description: GPU 3D engine clock + - const: rbbmtimer + description: GPU RBBM Timer for Adreno 5xx series + minItems: 2 + maxItems: 7 + + required: + - clocks + - clock-names + - if: + properties: + compatible: + contains: + pattern: '^qcom,adreno-6[0-9][0-9]\.[0-9]$' + + then: # Since Adreno 6xx series clocks should be defined in GMU + properties: + clocks: false + clock-names: false + +examples: + - | + + // Example a3xx/4xx: + + #include + #include + #include + #include + + gpu: gpu@fdb00000 { + compatible = "qcom,adreno-330.2", "qcom,adreno"; + + reg = <0xfdb00000 0x10000>; + reg-names = "kgsl_3d0_reg_memory"; + + clock-names = "core", "iface", "mem_iface"; + clocks = <&mmcc OXILI_GFX3D_CLK>, + <&mmcc OXILICX_AHB_CLK>, + <&mmcc OXILICX_AXI_CLK>; + + interrupts = ; + interrupt-names = "kgsl_3d0_irq"; + + sram = <&gpu_sram>; + power-domains = <&mmcc OXILICX_GDSC>; + operating-points-v2 = <&gpu_opp_table>; + iommus = <&gpu_iommu 0>; + #cooling-cells = <2>; + }; + + ocmem@fdd00000 { + compatible = "qcom,msm8974-ocmem"; + + reg = <0xfdd00000 0x2000>, + <0xfec00000 0x180000>; + reg-names = "ctrl", "mem"; + + clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>, + <&mmcc OCMEMCX_OCMEMNOC_CLK>; + clock-names = "core", "iface"; + + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0xfec00000 0x100000>; + + gpu_sram: gpu-sram@0 { + reg = <0x0 0x100000>; + }; + }; + - | + + // Example a6xx (with GMU): + + #include + #include + #include + #include + #include + #include + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + + zap_shader_region: gpu@8f200000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x90b00000 0x0 0xa00000>; + no-map; + }; + }; + + gpu@5000000 { + compatible = "qcom,adreno-630.2", "qcom,adreno"; + + reg = <0x5000000 0x40000>, <0x509e000 0x10>; + reg-names = "kgsl_3d0_reg_memory", "cx_mem"; + + #cooling-cells = <2>; + + interrupts = ; + + iommus = <&adreno_smmu 0>; + + operating-points-v2 = <&gpu_opp_table>; + + interconnects = <&rsc_hlos MASTER_GFX3D &rsc_hlos SLAVE_EBI1>; + interconnect-names = "gfx-mem"; + + qcom,gmu = <&gmu>; + + gpu_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-430000000 { + opp-hz = /bits/ 64 <430000000>; + opp-level = ; + opp-peak-kBps = <5412000>; + }; + + opp-355000000 { + opp-hz = /bits/ 64 <355000000>; + opp-level = ; + opp-peak-kBps = <3072000>; + }; + + opp-267000000 { + opp-hz = /bits/ 64 <267000000>; + opp-level = ; + opp-peak-kBps = <3072000>; + }; + + opp-180000000 { + opp-hz = /bits/ 64 <180000000>; + opp-level = ; + opp-peak-kBps = <1804000>; + }; + }; + + zap-shader { + memory-region = <&zap_shader_region>; + firmware-name = "qcom/LENOVO/81JL/qcdxkmsuc850.mbn"; + }; + }; diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst index 311e10400708..b7d801993bfa 100644 --- a/Documentation/gpu/i915.rst +++ b/Documentation/gpu/i915.rst @@ -471,6 +471,14 @@ Object Tiling IOCTLs .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_tiling.c :doc: buffer object tiling +Protected Objects +----------------- + +.. kernel-doc:: drivers/gpu/drm/i915/pxp/intel_pxp.c + :doc: PXP + +.. kernel-doc:: drivers/gpu/drm/i915/pxp/intel_pxp_types.h + Microcontrollers ================ diff --git a/Documentation/gpu/rfc/i915_parallel_execbuf.h b/Documentation/gpu/rfc/i915_parallel_execbuf.h deleted file mode 100644 index 8cbe2c4e0172..000000000000 --- a/Documentation/gpu/rfc/i915_parallel_execbuf.h +++ /dev/null @@ -1,122 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2021 Intel Corporation - */ - -#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - -/** - * struct drm_i915_context_engines_parallel_submit - Configure engine for - * parallel submission. - * - * Setup a slot in the context engine map to allow multiple BBs to be submitted - * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU - * in parallel. Multiple hardware contexts are created internally in the i915 - * run these BBs. Once a slot is configured for N BBs only N BBs can be - * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user - * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how - * many BBs there are based on the slot's configuration. The N BBs are the last - * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. - * - * The default placement behavior is to create implicit bonds between each - * context if each context maps to more than 1 physical engine (e.g. context is - * a virtual engine). Also we only allow contexts of same engine class and these - * contexts must be in logically contiguous order. Examples of the placement - * behavior described below. Lastly, the default is to not allow BBs to - * preempted mid BB rather insert coordinated preemption on all hardware - * contexts between each set of BBs. Flags may be added in the future to change - * both of these default behaviors. - * - * Returns -EINVAL if hardware context placement configuration is invalid or if - * the placement configuration isn't supported on the platform / submission - * interface. - * Returns -ENODEV if extension isn't supported on the platform / submission - * interface. - * - * .. code-block:: none - * - * Example 1 pseudo code: - * CS[X] = generic engine of same class, logical instance X - * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE - * set_engines(INVALID) - * set_parallel(engine_index=0, width=2, num_siblings=1, - * engines=CS[0],CS[1]) - * - * Results in the following valid placement: - * CS[0], CS[1] - * - * Example 2 pseudo code: - * CS[X] = generic engine of same class, logical instance X - * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE - * set_engines(INVALID) - * set_parallel(engine_index=0, width=2, num_siblings=2, - * engines=CS[0],CS[2],CS[1],CS[3]) - * - * Results in the following valid placements: - * CS[0], CS[1] - * CS[2], CS[3] - * - * This can also be thought of as 2 virtual engines described by 2-D array - * in the engines the field with bonds placed between each index of the - * virtual engines. e.g. CS[0] is bonded to CS[1], CS[2] is bonded to - * CS[3]. - * VE[0] = CS[0], CS[2] - * VE[1] = CS[1], CS[3] - * - * Example 3 pseudo code: - * CS[X] = generic engine of same class, logical instance X - * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE - * set_engines(INVALID) - * set_parallel(engine_index=0, width=2, num_siblings=2, - * engines=CS[0],CS[1],CS[1],CS[3]) - * - * Results in the following valid and invalid placements: - * CS[0], CS[1] - * CS[1], CS[3] - Not logical contiguous, return -EINVAL - */ -struct drm_i915_context_engines_parallel_submit { - /** - * @base: base user extension. - */ - struct i915_user_extension base; - - /** - * @engine_index: slot for parallel engine - */ - __u16 engine_index; - - /** - * @width: number of contexts per parallel engine - */ - __u16 width; - - /** - * @num_siblings: number of siblings per context - */ - __u16 num_siblings; - - /** - * @mbz16: reserved for future use; must be zero - */ - __u16 mbz16; - - /** - * @flags: all undefined flags must be zero, currently not defined flags - */ - __u64 flags; - - /** - * @mbz64: reserved for future use; must be zero - */ - __u64 mbz64[3]; - - /** - * @engines: 2-d array of engine instances to configure parallel engine - * - * length = width (i) * num_siblings (j) - * index = j + i * num_siblings - */ - struct i915_engine_class_instance engines[0]; - -} __packed; - diff --git a/Documentation/gpu/rfc/i915_scheduler.rst b/Documentation/gpu/rfc/i915_scheduler.rst index cbda75065dad..d630f15ab795 100644 --- a/Documentation/gpu/rfc/i915_scheduler.rst +++ b/Documentation/gpu/rfc/i915_scheduler.rst @@ -135,8 +135,8 @@ Add I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT and drm_i915_context_engines_parallel_submit to the uAPI to implement this extension. -.. kernel-doc:: Documentation/gpu/rfc/i915_parallel_execbuf.h - :functions: drm_i915_context_engines_parallel_submit +.. kernel-doc:: include/uapi/drm/i915_drm.h + :functions: i915_context_engines_parallel_submit Extend execbuf2 IOCTL to support submitting N BBs in a single IOCTL ------------------------------------------------------------------- diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index 12e61869939e..6613543955e9 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -353,23 +353,6 @@ converted, except for struct drm_driver.gem_prime_mmap. Level: Intermediate -Use DRM_MODESET_LOCK_ALL_* helpers instead of boilerplate ---------------------------------------------------------- - -For cases where drivers are attempting to grab the modeset locks with a local -acquire context. Replace the boilerplate code surrounding -drm_modeset_lock_all_ctx() with DRM_MODESET_LOCK_ALL_BEGIN() and -DRM_MODESET_LOCK_ALL_END() instead. - -This should also be done for all places where drm_modeset_lock_all() is still -used. - -As a reference, take a look at the conversions already completed in drm core. - -Contact: Sean Paul, respective driver maintainers - -Level: Starter - Rename CMA helpers to DMA helpers --------------------------------- diff --git a/Documentation/locking/ww-mutex-design.rst b/Documentation/locking/ww-mutex-design.rst index 6a4d7319f8f0..6a8f8beb9ec4 100644 --- a/Documentation/locking/ww-mutex-design.rst +++ b/Documentation/locking/ww-mutex-design.rst @@ -60,7 +60,7 @@ Concepts Compared to normal mutexes two additional concepts/objects show up in the lock interface for w/w mutexes: -Acquire context: To ensure eventual forward progress it is important the a task +Acquire context: To ensure eventual forward progress it is important that a task trying to acquire locks doesn't grab a new reservation id, but keeps the one it acquired when starting the lock acquisition. This ticket is stored in the acquire context. Furthermore the acquire context keeps track of debugging state diff --git a/MAINTAINERS b/MAINTAINERS index ec453f733c45..453e1172c70d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -893,6 +893,7 @@ F: include/uapi/linux/psp-sev.h AMD DISPLAY CORE M: Harry Wentland M: Leo Li +M: Rodrigo Siqueira L: amd-gfx@lists.freedesktop.org S: Supported T: git https://gitlab.freedesktop.org/agd5f/linux.git diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index a6c1912fd522..b287727342ee 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -74,7 +74,7 @@ static void dma_buf_release(struct dentry *dentry) * If you hit this BUG() it means someone dropped their ref to the * dma-buf while still having pending operation to the buffer. */ - BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); dma_buf_stats_teardown(dmabuf); dmabuf->ops->release(dmabuf); @@ -206,16 +206,55 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) wake_up_locked_poll(dcb->poll, dcb->active); dcb->active = 0; spin_unlock_irqrestore(&dcb->poll->lock, flags); + dma_fence_put(fence); +} + +static bool dma_buf_poll_shared(struct dma_resv *resv, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_resv_list *fobj = dma_resv_shared_list(resv); + struct dma_fence *fence; + int i, r; + + if (!fobj) + return false; + + for (i = 0; i < fobj->shared_count; ++i) { + fence = rcu_dereference_protected(fobj->shared[i], + dma_resv_held(resv)); + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + } + + return false; +} + +static bool dma_buf_poll_excl(struct dma_resv *resv, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_fence *fence = dma_resv_excl_fence(resv); + int r; + + if (!fence) + return false; + + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + + return false; } static __poll_t dma_buf_poll(struct file *file, poll_table *poll) { struct dma_buf *dmabuf; struct dma_resv *resv; - struct dma_resv_list *fobj; - struct dma_fence *fence_excl; __poll_t events; - unsigned shared_count, seq; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -229,61 +268,12 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) if (!events) return 0; -retry: - seq = read_seqcount_begin(&resv->seq); - rcu_read_lock(); + dma_resv_lock(resv, NULL); - fobj = rcu_dereference(resv->fence); - if (fobj) - shared_count = fobj->shared_count; - else - shared_count = 0; - fence_excl = dma_resv_excl_fence(resv); - if (read_seqcount_retry(&resv->seq, seq)) { - rcu_read_unlock(); - goto retry; - } + if (events & EPOLLOUT) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_out; - if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; - __poll_t pevents = EPOLLIN; - - if (shared_count == 0) - pevents |= EPOLLOUT; - - spin_lock_irq(&dmabuf->poll.lock); - if (dcb->active) { - dcb->active |= pevents; - events &= ~pevents; - } else - dcb->active = pevents; - spin_unlock_irq(&dmabuf->poll.lock); - - if (events & pevents) { - if (!dma_fence_get_rcu(fence_excl)) { - /* force a recheck */ - events &= ~pevents; - dma_buf_poll_cb(NULL, &dcb->cb); - } else if (!dma_fence_add_callback(fence_excl, &dcb->cb, - dma_buf_poll_cb)) { - events &= ~pevents; - dma_fence_put(fence_excl); - } else { - /* - * No callback queued, wake up any additional - * waiters. - */ - dma_fence_put(fence_excl); - dma_buf_poll_cb(NULL, &dcb->cb); - } - } - } - - if ((events & EPOLLOUT) && shared_count > 0) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; - int i; - - /* Only queue a new callback if no event has fired yet */ + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) events &= ~EPOLLOUT; @@ -291,39 +281,37 @@ retry: dcb->active = EPOLLOUT; spin_unlock_irq(&dmabuf->poll.lock); - if (!(events & EPOLLOUT)) - goto out; - - for (i = 0; i < shared_count; ++i) { - struct dma_fence *fence = rcu_dereference(fobj->shared[i]); - - if (!dma_fence_get_rcu(fence)) { - /* - * fence refcount dropped to zero, this means - * that fobj has been freed - * - * call dma_buf_poll_cb and force a recheck! - */ - events &= ~EPOLLOUT; + if (events & EPOLLOUT) { + if (!dma_buf_poll_shared(resv, dcb) && + !dma_buf_poll_excl(resv, dcb)) + /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); - break; - } - if (!dma_fence_add_callback(fence, &dcb->cb, - dma_buf_poll_cb)) { - dma_fence_put(fence); + else events &= ~EPOLLOUT; - break; - } - dma_fence_put(fence); } - - /* No callback queued, wake up any additional waiters. */ - if (i == shared_count) - dma_buf_poll_cb(NULL, &dcb->cb); } -out: - rcu_read_unlock(); + if (events & EPOLLIN) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_in; + + /* Check that callback isn't busy */ + spin_lock_irq(&dmabuf->poll.lock); + if (dcb->active) + events &= ~EPOLLIN; + else + dcb->active = EPOLLIN; + spin_unlock_irq(&dmabuf->poll.lock); + + if (events & EPOLLIN) { + if (!dma_buf_poll_excl(resv, dcb)) + /* No callback queued, wake up any other waiters */ + dma_buf_poll_cb(NULL, &dcb->cb); + else + events &= ~EPOLLIN; + } + } + + dma_resv_unlock(resv); return events; } @@ -566,8 +554,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->owner = exp_info->owner; spin_lock_init(&dmabuf->name_lock); init_waitqueue_head(&dmabuf->poll); - dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; - dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; + dmabuf->cb_in.active = dmabuf->cb_out.active = 0; if (!resv) { resv = (struct dma_resv *)&dmabuf[1]; diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 84fbe60629e3..a480af9581bd 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -323,6 +323,106 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) } EXPORT_SYMBOL(dma_resv_add_excl_fence); +/** + * dma_resv_iter_restart_unlocked - restart the unlocked iterator + * @cursor: The dma_resv_iter object to restart + * + * Restart the unlocked iteration by initializing the cursor object. + */ +static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) +{ + cursor->seq = read_seqcount_begin(&cursor->obj->seq); + cursor->index = -1; + if (cursor->all_fences) + cursor->fences = dma_resv_shared_list(cursor->obj); + else + cursor->fences = NULL; + cursor->is_restarted = true; +} + +/** + * dma_resv_iter_walk_unlocked - walk over fences in a dma_resv obj + * @cursor: cursor to record the current position + * + * Return all the fences in the dma_resv object which are not yet signaled. + * The returned fence has an extra local reference so will stay alive. + * If a concurrent modify is detected the whole iteration is started over again. + */ +static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) +{ + struct dma_resv *obj = cursor->obj; + + do { + /* Drop the reference from the previous round */ + dma_fence_put(cursor->fence); + + if (cursor->index == -1) { + cursor->fence = dma_resv_excl_fence(obj); + cursor->index++; + if (!cursor->fence) + continue; + + } else if (!cursor->fences || + cursor->index >= cursor->fences->shared_count) { + cursor->fence = NULL; + break; + + } else { + struct dma_resv_list *fences = cursor->fences; + unsigned int idx = cursor->index++; + + cursor->fence = rcu_dereference(fences->shared[idx]); + } + cursor->fence = dma_fence_get_rcu(cursor->fence); + if (!cursor->fence || !dma_fence_is_signaled(cursor->fence)) + break; + } while (true); +} + +/** + * dma_resv_iter_first_unlocked - first fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Returns the first fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) +{ + rcu_read_lock(); + do { + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_first_unlocked); + +/** + * dma_resv_iter_next_unlocked - next fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Returns the next fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) +{ + bool restart; + + rcu_read_lock(); + cursor->is_restarted = false; + restart = read_seqcount_retry(&cursor->obj->seq, cursor->seq); + do { + if (restart) + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + restart = true; + } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_next_unlocked); + /** * dma_resv_copy_fences - Copy all fences from src to dst. * @dst: the destination reservation object @@ -332,74 +432,54 @@ EXPORT_SYMBOL(dma_resv_add_excl_fence); */ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) { - struct dma_resv_list *src_list, *dst_list; - struct dma_fence *old, *new; - unsigned int i; + struct dma_resv_iter cursor; + struct dma_resv_list *list; + struct dma_fence *f, *excl; dma_resv_assert_held(dst); - rcu_read_lock(); - src_list = dma_resv_shared_list(src); + list = NULL; + excl = NULL; -retry: - if (src_list) { - unsigned int shared_count = src_list->shared_count; + dma_resv_iter_begin(&cursor, src, true); + dma_resv_for_each_fence_unlocked(&cursor, f) { - rcu_read_unlock(); + if (dma_resv_iter_is_restarted(&cursor)) { + dma_resv_list_free(list); + dma_fence_put(excl); - dst_list = dma_resv_list_alloc(shared_count); - if (!dst_list) - return -ENOMEM; + if (cursor.fences) { + unsigned int cnt = cursor.fences->shared_count; - rcu_read_lock(); - src_list = dma_resv_shared_list(src); - if (!src_list || src_list->shared_count > shared_count) { - kfree(dst_list); - goto retry; + list = dma_resv_list_alloc(cnt); + if (!list) { + dma_resv_iter_end(&cursor); + return -ENOMEM; + } + + list->shared_count = 0; + + } else { + list = NULL; + } + excl = NULL; } - dst_list->shared_count = 0; - for (i = 0; i < src_list->shared_count; ++i) { - struct dma_fence __rcu **dst; - struct dma_fence *fence; - - fence = rcu_dereference(src_list->shared[i]); - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, - &fence->flags)) - continue; - - if (!dma_fence_get_rcu(fence)) { - dma_resv_list_free(dst_list); - src_list = dma_resv_shared_list(src); - goto retry; - } - - if (dma_fence_is_signaled(fence)) { - dma_fence_put(fence); - continue; - } - - dst = &dst_list->shared[dst_list->shared_count++]; - rcu_assign_pointer(*dst, fence); - } - } else { - dst_list = NULL; + dma_fence_get(f); + if (dma_resv_iter_is_exclusive(&cursor)) + excl = f; + else + RCU_INIT_POINTER(list->shared[list->shared_count++], f); } - - new = dma_fence_get_rcu_safe(&src->fence_excl); - rcu_read_unlock(); - - src_list = dma_resv_shared_list(dst); - old = dma_resv_excl_fence(dst); + dma_resv_iter_end(&cursor); write_seqcount_begin(&dst->seq); - /* write_seqcount_begin provides the necessary memory barrier */ - RCU_INIT_POINTER(dst->fence_excl, new); - RCU_INIT_POINTER(dst->fence, dst_list); + excl = rcu_replace_pointer(dst->fence_excl, excl, dma_resv_held(dst)); + list = rcu_replace_pointer(dst->fence, list, dma_resv_held(dst)); write_seqcount_end(&dst->seq); - dma_resv_list_free(src_list); - dma_fence_put(old); + dma_resv_list_free(list); + dma_fence_put(excl); return 0; } @@ -409,99 +489,61 @@ EXPORT_SYMBOL(dma_resv_copy_fences); * dma_resv_get_fences - Get an object's shared and exclusive * fences without update side lock held * @obj: the reservation object - * @pfence_excl: the returned exclusive fence (or NULL) - * @pshared_count: the number of shared fences returned - * @pshared: the array of shared fence ptrs returned (array is krealloc'd to + * @fence_excl: the returned exclusive fence (or NULL) + * @shared_count: the number of shared fences returned + * @shared: the array of shared fence ptrs returned (array is krealloc'd to * the required size, and must be freed by caller) * * Retrieve all fences from the reservation object. If the pointer for the * exclusive fence is not specified the fence is put into the array of the * shared fences as well. Returns either zero or -ENOMEM. */ -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, - unsigned int *pshared_count, - struct dma_fence ***pshared) +int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, + unsigned int *shared_count, struct dma_fence ***shared) { - struct dma_fence **shared = NULL; - struct dma_fence *fence_excl; - unsigned int shared_count; - int ret = 1; + struct dma_resv_iter cursor; + struct dma_fence *fence; - do { - struct dma_resv_list *fobj; - unsigned int i, seq; - size_t sz = 0; + *shared_count = 0; + *shared = NULL; - shared_count = i = 0; + if (fence_excl) + *fence_excl = NULL; - rcu_read_lock(); - seq = read_seqcount_begin(&obj->seq); + dma_resv_iter_begin(&cursor, obj, true); + dma_resv_for_each_fence_unlocked(&cursor, fence) { - fence_excl = dma_resv_excl_fence(obj); - if (fence_excl && !dma_fence_get_rcu(fence_excl)) - goto unlock; + if (dma_resv_iter_is_restarted(&cursor)) { + unsigned int count; - fobj = dma_resv_shared_list(obj); - if (fobj) - sz += sizeof(*shared) * fobj->shared_max; + while (*shared_count) + dma_fence_put((*shared)[--(*shared_count)]); - if (!pfence_excl && fence_excl) - sz += sizeof(*shared); + if (fence_excl) + dma_fence_put(*fence_excl); - if (sz) { - struct dma_fence **nshared; + count = cursor.fences ? cursor.fences->shared_count : 0; + count += fence_excl ? 0 : 1; - nshared = krealloc(shared, sz, - GFP_NOWAIT | __GFP_NOWARN); - if (!nshared) { - rcu_read_unlock(); - - dma_fence_put(fence_excl); - fence_excl = NULL; - - nshared = krealloc(shared, sz, GFP_KERNEL); - if (nshared) { - shared = nshared; - continue; - } - - ret = -ENOMEM; - break; - } - shared = nshared; - shared_count = fobj ? fobj->shared_count : 0; - for (i = 0; i < shared_count; ++i) { - shared[i] = rcu_dereference(fobj->shared[i]); - if (!dma_fence_get_rcu(shared[i])) - break; + /* Eventually re-allocate the array */ + *shared = krealloc_array(*shared, count, + sizeof(void *), + GFP_KERNEL); + if (count && !*shared) { + dma_resv_iter_end(&cursor); + return -ENOMEM; } } - if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) { - while (i--) - dma_fence_put(shared[i]); - dma_fence_put(fence_excl); - goto unlock; - } - - ret = 0; -unlock: - rcu_read_unlock(); - } while (ret); - - if (pfence_excl) - *pfence_excl = fence_excl; - else if (fence_excl) - shared[shared_count++] = fence_excl; - - if (!shared_count) { - kfree(shared); - shared = NULL; + dma_fence_get(fence); + if (dma_resv_iter_is_exclusive(&cursor) && fence_excl) + *fence_excl = fence; + else + (*shared)[(*shared_count)++] = fence; } + dma_resv_iter_end(&cursor); - *pshared_count = shared_count; - *pshared = shared; - return ret; + return 0; } EXPORT_SYMBOL_GPL(dma_resv_get_fences); @@ -523,94 +565,25 @@ long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, unsigned long timeout) { long ret = timeout ? timeout : 1; - unsigned int seq, shared_count; + struct dma_resv_iter cursor; struct dma_fence *fence; - int i; -retry: - shared_count = 0; - seq = read_seqcount_begin(&obj->seq); - rcu_read_lock(); - i = -1; - - fence = dma_resv_excl_fence(obj); - if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { - if (!dma_fence_get_rcu(fence)) - goto unlock_retry; - - if (dma_fence_is_signaled(fence)) { - dma_fence_put(fence); - fence = NULL; - } - - } else { - fence = NULL; - } - - if (wait_all) { - struct dma_resv_list *fobj = dma_resv_shared_list(obj); - - if (fobj) - shared_count = fobj->shared_count; - - for (i = 0; !fence && i < shared_count; ++i) { - struct dma_fence *lfence; - - lfence = rcu_dereference(fobj->shared[i]); - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, - &lfence->flags)) - continue; - - if (!dma_fence_get_rcu(lfence)) - goto unlock_retry; - - if (dma_fence_is_signaled(lfence)) { - dma_fence_put(lfence); - continue; - } - - fence = lfence; - break; - } - } - - rcu_read_unlock(); - if (fence) { - if (read_seqcount_retry(&obj->seq, seq)) { - dma_fence_put(fence); - goto retry; - } + dma_resv_iter_begin(&cursor, obj, wait_all); + dma_resv_for_each_fence_unlocked(&cursor, fence) { ret = dma_fence_wait_timeout(fence, intr, ret); - dma_fence_put(fence); - if (ret > 0 && wait_all && (i + 1 < shared_count)) - goto retry; + if (ret <= 0) { + dma_resv_iter_end(&cursor); + return ret; + } } - return ret; + dma_resv_iter_end(&cursor); -unlock_retry: - rcu_read_unlock(); - goto retry; + return ret; } EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); -static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) -{ - struct dma_fence *fence, *lfence = passed_fence; - int ret = 1; - - if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) { - fence = dma_fence_get_rcu(lfence); - if (!fence) - return -1; - - ret = !!dma_fence_is_signaled(fence); - dma_fence_put(fence); - } - return ret; -} - /** * dma_resv_test_signaled - Test if a reservation object's fences have been * signaled. @@ -627,43 +600,16 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) */ bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) { + struct dma_resv_iter cursor; struct dma_fence *fence; - unsigned int seq; - int ret; - rcu_read_lock(); -retry: - ret = true; - seq = read_seqcount_begin(&obj->seq); - - if (test_all) { - struct dma_resv_list *fobj = dma_resv_shared_list(obj); - unsigned int i, shared_count; - - shared_count = fobj ? fobj->shared_count : 0; - for (i = 0; i < shared_count; ++i) { - fence = rcu_dereference(fobj->shared[i]); - ret = dma_resv_test_signaled_single(fence); - if (ret < 0) - goto retry; - else if (!ret) - break; - } + dma_resv_iter_begin(&cursor, obj, test_all); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + dma_resv_iter_end(&cursor); + return false; } - - fence = dma_resv_excl_fence(obj); - if (ret && fence) { - ret = dma_resv_test_signaled_single(fence); - if (ret < 0) - goto retry; - - } - - if (read_seqcount_retry(&obj->seq, seq)) - goto retry; - - rcu_read_unlock(); - return ret; + dma_resv_iter_end(&cursor); + return true; } EXPORT_SYMBOL_GPL(dma_resv_test_signaled); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index b17e231ca6f7..2a926d0de423 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -103,7 +103,7 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" depends on DRM - depends on FB + depends on FB=y || FB=DRM select DRM_KMS_HELPER select FB_CFB_FILLRECT select FB_CFB_COPYAREA diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 8d0748184a14..653726588956 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -73,10 +73,8 @@ amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce amdgpu-y += \ vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \ - vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o navi10_reg_init.o navi14_reg_init.o \ - arct_reg_init.o navi12_reg_init.o mxgpu_nv.o sienna_cichlid_reg_init.o vangogh_reg_init.o \ - nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o \ - beige_goby_reg_init.o yellow_carp_reg_init.o cyan_skillfish_reg_init.o + vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \ + nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o # add DF block amdgpu-y += \ diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c index 148f6c3343ab..bcfdb63b1d42 100644 --- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c @@ -307,6 +307,8 @@ static int aldebaran_mode2_restore_ip(struct amdgpu_device *adev) adev->ip_blocks[i].status.late_initialized = true; } + amdgpu_ras_set_error_query_ready(adev, true); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE); amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d58e37fd01f4..b85b67a88a3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -205,6 +205,7 @@ extern struct amdgpu_mgpu_info mgpu_info; extern int amdgpu_ras_enable; extern uint amdgpu_ras_mask; extern int amdgpu_bad_page_threshold; +extern bool amdgpu_ignore_bad_page_threshold; extern struct amdgpu_watchdog_timer amdgpu_watchdog_timer; extern int amdgpu_async_gfx_ring; extern int amdgpu_mcbp; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 69de31754907..751557af09bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -279,6 +279,8 @@ int amdgpu_amdkfd_gpuvm_sync_memory( struct kgd_dev *kgd, struct kgd_mem *mem, bool intr); int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd, struct kgd_mem *mem, void **kptr, uint64_t *size); +void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem); + int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info, struct dma_fence **ef); int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 054c1a224def..0e9cfe99ae9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1503,7 +1503,7 @@ allocate_init_user_pages_failed: remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info); drm_vma_node_revoke(&gobj->vma_node, drm_priv); err_node_allow: - amdgpu_bo_unref(&bo); + drm_gem_object_put(gobj); /* Don't unreserve system mem limit twice */ goto err_reserve_limit; err_bo_create: @@ -1871,6 +1871,16 @@ bo_reserve_failed: return ret; } +void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem) +{ + struct amdgpu_bo *bo = mem->bo; + + amdgpu_bo_reserve(bo, true); + amdgpu_bo_kunmap(bo); + amdgpu_bo_unpin(bo); + amdgpu_bo_unreserve(bo); +} + int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd, struct kfd_vm_fault_info *mem) { @@ -2041,19 +2051,26 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, /* Get updated user pages */ ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); if (ret) { - pr_debug("%s: Failed to get user pages: %d\n", - __func__, ret); + pr_debug("Failed %d to get user pages\n", ret); - /* Return error -EBUSY or -ENOMEM, retry restore */ - return ret; + /* Return -EFAULT bad address error as success. It will + * fail later with a VM fault if the GPU tries to access + * it. Better than hanging indefinitely with stalled + * user mode queues. + * + * Return other error -EBUSY or -ENOMEM to retry restore + */ + if (ret != -EFAULT) + return ret; + } else { + + /* + * FIXME: Cannot ignore the return code, must hold + * notifier_lock + */ + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); } - /* - * FIXME: Cannot ignore the return code, must hold - * notifier_lock - */ - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); - /* Mark the BO as valid unless it was invalidated * again concurrently. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 239e71174855..6e40cc1bc6dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3839,10 +3839,10 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) amdgpu_fbdev_fini(adev); - amdgpu_irq_fini_hw(adev); - amdgpu_device_ip_fini_early(adev); + amdgpu_irq_fini_hw(adev); + ttm_device_clear_dma_mappings(&adev->mman.bdev); amdgpu_gart_dummy_page_fini(adev); @@ -3852,8 +3852,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) void amdgpu_device_fini_sw(struct amdgpu_device *adev) { - amdgpu_device_ip_fini(adev); amdgpu_fence_driver_sw_fini(adev); + amdgpu_device_ip_fini(adev); release_firmware(adev->firmware.gpu_info_fw); adev->firmware.gpu_info_fw = NULL; adev->accel_working = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 2bebd2ce6474..d7c8d9e3c203 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -108,6 +108,8 @@ static const char *hw_id_names[HW_ID_MAX] = { [HDP_HWID] = "HDP", [SDMA0_HWID] = "SDMA0", [SDMA1_HWID] = "SDMA1", + [SDMA2_HWID] = "SDMA2", + [SDMA3_HWID] = "SDMA3", [ISP_HWID] = "ISP", [DBGU_IO_HWID] = "DBGU_IO", [DF_HWID] = "DF", @@ -505,6 +507,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) break; } } + /* some IP discovery tables on Navy Flounder don't have this set correctly */ + if ((adev->ip_versions[UVD_HWIP][1] == IP_VERSION(3, 0, 1)) && + (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 2))) + adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1; if (vcn_harvest_count == adev->vcn.num_vcn_inst) { adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; @@ -736,6 +742,7 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(1, 0, 1): case IP_VERSION(2, 0, 2): case IP_VERSION(2, 0, 0): + case IP_VERSION(2, 0, 3): case IP_VERSION(2, 1, 0): case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 2): @@ -745,8 +752,6 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(3, 1, 3): amdgpu_device_ip_block_add(adev, &dm_ip_block); break; - case IP_VERSION(2, 0, 3): - break; default: return -EINVAL; } @@ -926,6 +931,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 0); adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 0); adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 0); + adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 0, 0); adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 1, 0); adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 1, 0); adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 0, 0); @@ -946,6 +952,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 1); adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 1); adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 1); + adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 0, 1); adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 5, 0); adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 2, 0); adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 0); @@ -1004,6 +1011,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 0); adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 0); adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 0); + adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 2, 0); adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 0); adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 0); adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 1); @@ -1013,6 +1021,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 2); adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 0); adev->ip_versions[UVD_HWIP][0] = IP_VERSION(7, 2, 0); + adev->ip_versions[UVD_HWIP][1] = IP_VERSION(7, 2, 0); adev->ip_versions[VCE_HWIP][0] = IP_VERSION(4, 1, 0); adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0); break; @@ -1025,6 +1034,13 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 1); adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 1); adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][1] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][2] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][3] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][4] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][5] = IP_VERSION(4, 2, 2); + adev->ip_versions[SDMA1_HWIP][6] = IP_VERSION(4, 2, 2); adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 1); adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 1); adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 2); @@ -1034,6 +1050,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 3); adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 1); adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 5, 0); + adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 5, 0); break; case CHIP_ALDEBARAN: aldebaran_reg_base_init(adev); @@ -1044,6 +1061,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 4, 0); adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 4, 0); adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 4, 0); + adev->ip_versions[SDMA0_HWIP][1] = IP_VERSION(4, 4, 0); + adev->ip_versions[SDMA0_HWIP][2] = IP_VERSION(4, 4, 0); + adev->ip_versions[SDMA0_HWIP][3] = IP_VERSION(4, 4, 0); + adev->ip_versions[SDMA0_HWIP][4] = IP_VERSION(4, 4, 0); adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 2); adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 4); adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 7, 0); @@ -1053,6 +1074,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(13, 0, 2); adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 2); adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 6, 0); + adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 6, 0); adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0); break; default: @@ -1120,10 +1142,13 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) break; case IP_VERSION(7, 4, 0): case IP_VERSION(7, 4, 1): - case IP_VERSION(7, 4, 4): adev->nbio.funcs = &nbio_v7_4_funcs; adev->nbio.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg; break; + case IP_VERSION(7, 4, 4): + adev->nbio.funcs = &nbio_v7_4_funcs; + adev->nbio.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg_ald; + break; case IP_VERSION(7, 2, 0): case IP_VERSION(7, 2, 1): case IP_VERSION(7, 5, 0): @@ -1134,12 +1159,15 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(2, 3, 0): case IP_VERSION(2, 3, 1): case IP_VERSION(2, 3, 2): + adev->nbio.funcs = &nbio_v2_3_funcs; + adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg; + break; case IP_VERSION(3, 3, 0): case IP_VERSION(3, 3, 1): case IP_VERSION(3, 3, 2): case IP_VERSION(3, 3, 3): adev->nbio.funcs = &nbio_v2_3_funcs; - adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg; + adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg_sc; break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 85e7854394fd..ad95de6399af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -878,7 +878,7 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444); * result in the GPU entering bad status when the number of total * faulty pages by ECC exceeds the threshold value. */ -MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)"); +MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement, -2 = ignore bad page threshold)"); module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444); MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d2955ea4a62b..dfe667ea8b05 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -340,32 +340,32 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, case AMDGPU_INFO_FW_TA: switch (query_fw->index) { case TA_FW_TYPE_PSP_XGMI: - fw_info->ver = adev->psp.ta_fw_version; + fw_info->ver = adev->psp.xgmi_context.context.bin_desc.fw_version; fw_info->feature = adev->psp.xgmi_context.context .bin_desc.feature_version; break; case TA_FW_TYPE_PSP_RAS: - fw_info->ver = adev->psp.ta_fw_version; + fw_info->ver = adev->psp.ras_context.context.bin_desc.fw_version; fw_info->feature = adev->psp.ras_context.context .bin_desc.feature_version; break; case TA_FW_TYPE_PSP_HDCP: - fw_info->ver = adev->psp.ta_fw_version; + fw_info->ver = adev->psp.hdcp_context.context.bin_desc.fw_version; fw_info->feature = adev->psp.hdcp_context.context .bin_desc.feature_version; break; case TA_FW_TYPE_PSP_DTM: - fw_info->ver = adev->psp.ta_fw_version; + fw_info->ver = adev->psp.dtm_context.context.bin_desc.fw_version; fw_info->feature = adev->psp.dtm_context.context .bin_desc.feature_version; break; case TA_FW_TYPE_PSP_RAP: - fw_info->ver = adev->psp.ta_fw_version; + fw_info->ver = adev->psp.rap_context.context.bin_desc.fw_version; fw_info->feature = adev->psp.rap_context.context .bin_desc.feature_version; break; case TA_FW_TYPE_PSP_SECUREDISPLAY: - fw_info->ver = adev->psp.ta_fw_version; + fw_info->ver = adev->psp.securedisplay_context.context.bin_desc.fw_version; fw_info->feature = adev->psp.securedisplay_context.context.bin_desc .feature_version; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 6b39e6c02dd8..c641f84649d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -65,7 +65,6 @@ static int psp_securedisplay_terminate(struct psp_context *psp); * * This new sequence is required for * - Arcturus and onwards - * - Navi12 and onwards */ static void psp_check_pmfw_centralized_cstate_management(struct psp_context *psp) { @@ -77,7 +76,9 @@ static void psp_check_pmfw_centralized_cstate_management(struct psp_context *psp } switch (adev->ip_versions[MP0_HWIP][0]) { + case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 4): + case IP_VERSION(11, 0, 5): case IP_VERSION(11, 0, 7): case IP_VERSION(11, 0, 9): case IP_VERSION(11, 0, 11): @@ -1114,7 +1115,7 @@ int psp_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id) static bool psp_xgmi_peer_link_info_supported(struct psp_context *psp) { return psp->adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 2) && - psp->xgmi_context.context.bin_desc.feature_version >= 0x2000000b; + psp->xgmi_context.context.bin_desc.fw_version >= 0x2000000b; } /* @@ -1291,6 +1292,29 @@ static int psp_ras_unload(struct psp_context *psp) return psp_ta_unload(psp, &psp->ras_context.context); } +static void psp_ras_ta_check_status(struct psp_context *psp) +{ + struct ta_ras_shared_memory *ras_cmd = + (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf; + + switch (ras_cmd->ras_status) { + case TA_RAS_STATUS__ERROR_UNSUPPORTED_IP: + dev_warn(psp->adev->dev, + "RAS WARNING: cmd failed due to unsupported ip\n"); + break; + case TA_RAS_STATUS__ERROR_UNSUPPORTED_ERROR_INJ: + dev_warn(psp->adev->dev, + "RAS WARNING: cmd failed due to unsupported error injection\n"); + break; + case TA_RAS_STATUS__SUCCESS: + break; + default: + dev_warn(psp->adev->dev, + "RAS WARNING: ras status = 0x%X\n", ras_cmd->ras_status); + break; + } +} + int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id) { struct ta_ras_shared_memory *ras_cmd; @@ -1325,10 +1349,7 @@ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id) dev_warn(psp->adev->dev, "RAS internal register access blocked\n"); - if (ras_cmd->ras_status == TA_RAS_STATUS__ERROR_UNSUPPORTED_IP) - dev_warn(psp->adev->dev, "RAS WARNING: cmd failed due to unsupported ip\n"); - else if (ras_cmd->ras_status) - dev_warn(psp->adev->dev, "RAS WARNING: ras status = 0x%X\n", ras_cmd->ras_status); + psp_ras_ta_check_status(psp); } return ret; @@ -2622,6 +2643,12 @@ static int psp_resume(void *handle) goto failed; } + ret = psp_rl_load(adev); + if (ret) { + dev_err(adev->dev, "PSP load RL failed!\n"); + goto failed; + } + if (adev->gmc.xgmi.num_physical_nodes > 1) { ret = psp_xgmi_initialize(psp, false, true); /* Warning the XGMI seesion initialize failure @@ -3081,32 +3108,32 @@ static int parse_ta_bin_descriptor(struct psp_context *psp, psp->asd_context.bin_desc.start_addr = ucode_start_addr; break; case TA_FW_TYPE_PSP_XGMI: - psp->xgmi_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version); + psp->xgmi_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version); psp->xgmi_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes); psp->xgmi_context.context.bin_desc.start_addr = ucode_start_addr; break; case TA_FW_TYPE_PSP_RAS: - psp->ras_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version); + psp->ras_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version); psp->ras_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes); psp->ras_context.context.bin_desc.start_addr = ucode_start_addr; break; case TA_FW_TYPE_PSP_HDCP: - psp->hdcp_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version); + psp->hdcp_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version); psp->hdcp_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes); psp->hdcp_context.context.bin_desc.start_addr = ucode_start_addr; break; case TA_FW_TYPE_PSP_DTM: - psp->dtm_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version); + psp->dtm_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version); psp->dtm_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes); psp->dtm_context.context.bin_desc.start_addr = ucode_start_addr; break; case TA_FW_TYPE_PSP_RAP: - psp->rap_context.context.bin_desc.feature_version = le32_to_cpu(desc->fw_version); + psp->rap_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version); psp->rap_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes); psp->rap_context.context.bin_desc.start_addr = ucode_start_addr; break; case TA_FW_TYPE_PSP_SECUREDISPLAY: - psp->securedisplay_context.context.bin_desc.feature_version = + psp->securedisplay_context.context.bin_desc.fw_version = le32_to_cpu(desc->fw_version); psp->securedisplay_context.context.bin_desc.size_bytes = le32_to_cpu(desc->size_bytes); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index e8875351967e..08133de21fdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -112,7 +112,12 @@ static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con, static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev, uint64_t addr); #ifdef CONFIG_X86_MCE_AMD -static void amdgpu_register_bad_pages_mca_notifier(void); +static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev); +struct mce_notifier_adev_list { + struct amdgpu_device *devs[MAX_GPU_INSTANCE]; + int num_gpu; +}; +static struct mce_notifier_adev_list mce_adev_list; #endif void amdgpu_ras_set_error_query_ready(struct amdgpu_device *adev, bool ready) @@ -2108,7 +2113,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev) #ifdef CONFIG_X86_MCE_AMD if ((adev->asic_type == CHIP_ALDEBARAN) && (adev->gmc.xgmi.connected_to_cpu)) - amdgpu_register_bad_pages_mca_notifier(); + amdgpu_register_bad_pages_mca_notifier(adev); #endif return 0; @@ -2605,24 +2610,18 @@ void amdgpu_release_ras_context(struct amdgpu_device *adev) #ifdef CONFIG_X86_MCE_AMD static struct amdgpu_device *find_adev(uint32_t node_id) { - struct amdgpu_gpu_instance *gpu_instance; int i; struct amdgpu_device *adev = NULL; - mutex_lock(&mgpu_info.mutex); + for (i = 0; i < mce_adev_list.num_gpu; i++) { + adev = mce_adev_list.devs[i]; - for (i = 0; i < mgpu_info.num_gpu; i++) { - gpu_instance = &(mgpu_info.gpu_ins[i]); - adev = gpu_instance->adev; - - if (adev->gmc.xgmi.connected_to_cpu && + if (adev && adev->gmc.xgmi.connected_to_cpu && adev->gmc.xgmi.physical_node_id == node_id) break; adev = NULL; } - mutex_unlock(&mgpu_info.mutex); - return adev; } @@ -2718,8 +2717,18 @@ static struct notifier_block amdgpu_bad_page_nb = { .priority = MCE_PRIO_UC, }; -static void amdgpu_register_bad_pages_mca_notifier(void) +static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev) { + /* + * Add the adev to the mce_adev_list. + * During mode2 reset, amdgpu device is temporarily + * removed from the mgpu_info list which can cause + * page retirement to fail. + * Use this list instead of mgpu_info to find the amdgpu + * device on which the UMC error was reported. + */ + mce_adev_list.devs[mce_adev_list.num_gpu++] = adev; + /* * Register the x86 notifier only once * with MCE subsystem. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 98732518543e..05117eda105b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -1077,6 +1077,13 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control, if (res) DRM_ERROR("RAS table incorrect checksum or error:%d\n", res); + + /* Warn if we are at 90% of the threshold or above + */ + if (10 * control->ras_num_recs >= 9 * ras->bad_page_cnt_threshold) + dev_warn(adev->dev, "RAS records:%u exceeds 90%% of threshold:%d", + control->ras_num_recs, + ras->bad_page_cnt_threshold); } else if (hdr->header == RAS_TABLE_HDR_BAD && amdgpu_bad_page_threshold != 0) { res = __verify_ras_table_checksum(control); @@ -1098,11 +1105,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control, res = amdgpu_ras_eeprom_correct_header_tag(control, RAS_TABLE_HDR_VAL); } else { - *exceed_err_limit = true; - dev_err(adev->dev, - "RAS records:%d exceed threshold:%d, " - "maybe retire this GPU?", + dev_err(adev->dev, "RAS records:%d exceed threshold:%d", control->ras_num_recs, ras->bad_page_cnt_threshold); + if (amdgpu_bad_page_threshold == -2) { + dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -2."); + res = 0; + } else { + *exceed_err_limit = true; + dev_err(adev->dev, + "RAS records:%d exceed threshold:%d, " + "GPU will not be initialized. Replace this GPU or increase the threshold", + control->ras_num_recs, ras->bad_page_cnt_threshold); + } } } else { DRM_INFO("Creating a new EEPROM table"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 5d5c42ae388b..17b5dd6adf8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -696,6 +696,9 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) true, NULL); out_unlock: mmap_read_unlock(mm); + if (r) + pr_debug("failed %d to get user pages 0x%lx\n", r, start); + mmput(mm); return r; @@ -894,7 +897,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev, DRM_ERROR("failed to pin userptr\n"); return r; } - } else if (ttm->page_flags & TTM_PAGE_FLAG_SG) { + } else if (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) { if (!ttm->sg) { struct dma_buf_attachment *attach; struct sg_table *sgt; @@ -1119,6 +1122,8 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev, { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); struct amdgpu_ttm_tt *gtt = (void *)ttm; + pgoff_t i; + int ret; /* user pages are bound by amdgpu_ttm_tt_pin_userptr() */ if (gtt->userptr) { @@ -1128,10 +1133,17 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev, return 0; } - if (ttm->page_flags & TTM_PAGE_FLAG_SG) + if (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) return 0; - return ttm_pool_alloc(&adev->mman.bdev.pool, ttm, ctx); + ret = ttm_pool_alloc(&adev->mman.bdev.pool, ttm, ctx); + if (ret) + return ret; + + for (i = 0; i < ttm->num_pages; ++i) + ttm->pages[i]->mapping = bdev->dev_mapping; + + return 0; } /* @@ -1145,6 +1157,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev, { struct amdgpu_ttm_tt *gtt = (void *)ttm; struct amdgpu_device *adev; + pgoff_t i; amdgpu_ttm_backend_unbind(bdev, ttm); @@ -1155,9 +1168,12 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev, return; } - if (ttm->page_flags & TTM_PAGE_FLAG_SG) + if (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) return; + for (i = 0; i < ttm->num_pages; ++i) + ttm->pages[i]->mapping = NULL; + adev = amdgpu_ttm_adev(bdev); return ttm_pool_free(&adev->mman.bdev.pool, ttm); } @@ -1185,8 +1201,8 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo, return -ENOMEM; } - /* Set TTM_PAGE_FLAG_SG before populate but after create. */ - bo->ttm->page_flags |= TTM_PAGE_FLAG_SG; + /* Set TTM_TT_FLAG_EXTERNAL before populate but after create. */ + bo->ttm->page_flags |= TTM_TT_FLAG_EXTERNAL; gtt = (void *)bo->ttm; gtt->userptr = addr; @@ -1222,7 +1238,7 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm) * */ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, - unsigned long end) + unsigned long end, unsigned long *userptr) { struct amdgpu_ttm_tt *gtt = (void *)ttm; unsigned long size; @@ -1237,6 +1253,8 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, if (gtt->userptr > end || gtt->userptr + size <= start) return false; + if (userptr) + *userptr = gtt->userptr; return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 639c7b41e30b..7346ecff4438 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -182,7 +182,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo, bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm); struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm); bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, - unsigned long end); + unsigned long end, unsigned long *userptr); bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm, int *last_invalidated); bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 0c3127f37686..ca3350502618 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -509,7 +509,7 @@ static ssize_t show_##name(struct device *dev, \ struct drm_device *ddev = dev_get_drvdata(dev); \ struct amdgpu_device *adev = drm_to_adev(ddev); \ \ - return snprintf(buf, PAGE_SIZE, "0x%08x\n", adev->field); \ + return sysfs_emit(buf, "0x%08x\n", adev->field); \ } \ static DEVICE_ATTR(name, mode, show_##name, NULL) @@ -527,8 +527,8 @@ FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version); FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version); FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version); FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_context.bin_desc.fw_version); -FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.feature_version); -FW_VERSION_ATTR(ta_xgmi_fw_version, 0444, psp.xgmi_context.context.bin_desc.feature_version); +FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.fw_version); +FW_VERSION_ATTR(ta_xgmi_fw_version, 0444, psp.xgmi_context.context.bin_desc.fw_version); FW_VERSION_ATTR(smc_fw_version, 0444, pm.fw_version); FW_VERSION_ATTR(sdma_fw_version, 0444, sdma.instance[0].fw_version); FW_VERSION_ATTR(sdma2_fw_version, 0444, sdma.instance[1].fw_version); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index c7d316850570..2658414c503d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -949,3 +949,30 @@ enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring) return AMDGPU_RING_PRIO_0; } } + +void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev) +{ + int i; + unsigned int idx; + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + const struct common_firmware_header *hdr; + hdr = (const struct common_firmware_header *)adev->vcn.fw->data; + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (adev->vcn.harvest_config & (1 << i)) + continue; + /* currently only support 2 FW instances */ + if (i >= 2) { + dev_info(adev->dev, "More then 2 VCN FW instances!\n"); + break; + } + idx = AMDGPU_UCODE_ID_VCN + i; + adev->firmware.ucode[idx].ucode_id = idx; + adev->firmware.ucode[idx].fw = adev->vcn.fw; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); + } + dev_info(adev->dev, "Will use PSP to load VCN firmware\n"); + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 795cbaa02ff8..bfa27ea94804 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -310,4 +310,6 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout); enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring); +void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 88c4177b708a..04cf9b207e62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -535,9 +535,9 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev) POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD, adev->psp.asd_context.bin_desc.fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_RAS, - adev->psp.ras_context.context.bin_desc.feature_version); + adev->psp.ras_context.context.bin_desc.fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_TA_XGMI, - adev->psp.xgmi_context.context.bin_desc.feature_version); + adev->psp.xgmi_context.context.bin_desc.fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SMC, adev->pm.fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA, adev->sdma.instance[0].fw_version); POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SDMA2, adev->sdma.instance[1].fw_version); @@ -584,6 +584,7 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) vf2pf_info->encode_usage = 0; vf2pf_info->decode_usage = 0; + vf2pf_info->dummy_page_addr = (uint64_t)adev->dummy_page_addr; vf2pf_info->checksum = amd_sriov_msg_checksum( vf2pf_info, vf2pf_info->header.size, 0, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 995899191288..7326b6c1b71c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -261,9 +261,10 @@ struct amd_sriov_msg_vf2pf_info { uint8_t id; uint32_t version; } ucode_info[AMD_SRIOV_MSG_RESERVE_UCODE]; + uint64_t dummy_page_addr; /* reserved */ - uint32_t reserved[256-68]; + uint32_t reserved[256-70]; }; /* mailbox message send from guest to host */ diff --git a/drivers/gpu/drm/amd/amdgpu/beige_goby_reg_init.c b/drivers/gpu/drm/amd/amdgpu/beige_goby_reg_init.c deleted file mode 100644 index 608a113ce354..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/beige_goby_reg_init.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "soc15_hw_ip.h" -#include "beige_goby_ip_offset.h" - -int beige_goby_reg_base_init(struct amdgpu_device *adev) -{ - /* HW has more IP blocks, only initialize the block needed by driver */ - uint32_t i; - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN0_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCN_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA2_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA3_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - } - return 0; -} diff --git a/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c deleted file mode 100644 index 58808814d8fb..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Copyright 2018 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "soc15_hw_ip.h" -#include "cyan_skillfish_ip_offset.h" - -int cyan_skillfish_reg_base_init(struct amdgpu_device *adev) -{ - /* HW has more IP blocks, only initialized the blocke needed by driver */ - uint32_t i; - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(UVD0_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DMU_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - } - return 0; -} diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 71bb3c0dc1da..90a834dc4008 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -270,25 +270,6 @@ MODULE_FIRMWARE("amdgpu/cyan_skillfish2_mec.bin"); MODULE_FIRMWARE("amdgpu/cyan_skillfish2_mec2.bin"); MODULE_FIRMWARE("amdgpu/cyan_skillfish2_rlc.bin"); -static const struct soc15_reg_golden golden_settings_gc_10_0[] = -{ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_INDEX, 0xffffffff, 0x00000000), - /* TA_GRAD_ADJ_UCONFIG -> TA_GRAD_ADJ */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2544c382), - /* VGT_TF_RING_SIZE_UMD -> VGT_TF_RING_SIZE */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2262c24e), - /* VGT_HS_OFFCHIP_PARAM_UMD -> VGT_HS_OFFCHIP_PARAM */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x226cc24f), - /* VGT_TF_MEMORY_BASE_UMD -> VGT_TF_MEMORY_BASE */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x226ec250), - /* VGT_TF_MEMORY_BASE_HI_UMD -> VGT_TF_MEMORY_BASE_HI */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2278c261), - /* VGT_ESGS_RING_SIZE_UMD -> VGT_ESGS_RING_SIZE */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2232c240), - /* VGT_GSVS_RING_SIZE_UMD -> VGT_GSVS_RING_SIZE */ - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGRBM_CAM_DATA, 0xffffffff, 0x2233c241), -}; - static const struct soc15_reg_golden golden_settings_gc_10_1[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014), @@ -3809,9 +3790,6 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev) (const u32)ARRAY_SIZE(golden_settings_gc_10_3_5)); break; case IP_VERSION(10, 1, 3): - soc15_program_register_sequence(adev, - golden_settings_gc_10_0, - (const u32)ARRAY_SIZE(golden_settings_gc_10_0)); soc15_program_register_sequence(adev, golden_settings_gc_10_0_cyan_skillfish, (const u32)ARRAY_SIZE(golden_settings_gc_10_0_cyan_skillfish)); @@ -8238,8 +8216,9 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG + CGLS === */ gfx_v10_0_update_coarse_grain_clock_gating(adev, enable); - if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 1, 10)) && - (adev->ip_versions[GC_HWIP][0] <= IP_VERSION(10, 1, 2))) + if ((adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 10)) || + (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 1)) || + (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 2))) gfx_v10_0_apply_medium_grain_clock_gating_workaround(adev); } else { /* CGCG/CGLS should be disabled before MGCG/MGLS diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c index 00a2b36a24b3..c4f37a161875 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c @@ -706,6 +706,11 @@ int gfx_v9_4_2_do_edc_gpr_workarounds(struct amdgpu_device *adev) if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) return 0; + /* Workaround for ALDEBARAN, skip GPRs init in GPU reset. + Will remove it once GPRs init algorithm works for all CU settings. */ + if (amdgpu_in_reset(adev)) + return 0; + gfx_v9_4_2_do_sgprs_init(adev); gfx_v9_4_2_do_vgprs_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 0e81e03e9b49..0fe714f54cca 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -841,12 +841,12 @@ static int gmc_v6_0_sw_init(void *handle) adev->gmc.mc_mask = 0xffffffffffULL; - r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(44)); + r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(40)); if (r) { dev_warn(adev->dev, "No suitable DMA available.\n"); return r; } - adev->need_swiotlb = drm_need_swiotlb(44); + adev->need_swiotlb = drm_need_swiotlb(40); r = gmc_v6_0_init_microcode(adev); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c deleted file mode 100644 index 88efaecf9f70..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c +++ /dev/null @@ -1,55 +0,0 @@ -/* - * Copyright 2018 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "navi10_ip_offset.h" - -int navi10_reg_base_init(struct amdgpu_device *adev) -{ - int i; - - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCN_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); - } - - return 0; -} - - diff --git a/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c b/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c deleted file mode 100644 index a786d159e5e9..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Copyright 2018 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "navi12_ip_offset.h" - -int navi12_reg_base_init(struct amdgpu_device *adev) -{ - /* HW has more IP blocks, only initialized the blocks needed by driver */ - uint32_t i; - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIF0_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(UVD0_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DMU_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); - } - return 0; -} diff --git a/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c b/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c deleted file mode 100644 index 4ea1e8fbb601..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c +++ /dev/null @@ -1,53 +0,0 @@ -/* - * Copyright 2018 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "navi14_ip_offset.h" - -int navi14_reg_base_init(struct amdgpu_device *adev) -{ - int i; - - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIF0_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(UVD0_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DMU_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); - } - - return 0; -} diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index b184b656b9b6..4ecd2b5808ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -53,6 +53,16 @@ #define smnPCIE_LC_LINK_WIDTH_CNTL 0x11140288 +#define GPU_HDP_FLUSH_DONE__RSVD_ENG0_MASK 0x00001000L /* Don't use. Firmware uses this bit internally */ +#define GPU_HDP_FLUSH_DONE__RSVD_ENG1_MASK 0x00002000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG2_MASK 0x00004000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG3_MASK 0x00008000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG4_MASK 0x00010000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG5_MASK 0x00020000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG6_MASK 0x00040000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG7_MASK 0x00080000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG8_MASK 0x00100000L + static void nbio_v2_3_remap_hdp_registers(struct amdgpu_device *adev) { WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL, @@ -318,6 +328,27 @@ const struct nbio_hdp_flush_reg nbio_v2_3_hdp_flush_reg = { .ref_and_mask_sdma1 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__SDMA1_MASK, }; +const struct nbio_hdp_flush_reg nbio_v2_3_hdp_flush_reg_sc = { + .ref_and_mask_cp0 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP0_MASK, + .ref_and_mask_cp1 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP1_MASK, + .ref_and_mask_cp2 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP2_MASK, + .ref_and_mask_cp3 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP3_MASK, + .ref_and_mask_cp4 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP4_MASK, + .ref_and_mask_cp5 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP5_MASK, + .ref_and_mask_cp6 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP6_MASK, + .ref_and_mask_cp7 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP7_MASK, + .ref_and_mask_cp8 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP8_MASK, + .ref_and_mask_cp9 = BIF_BX_PF_GPU_HDP_FLUSH_DONE__CP9_MASK, + .ref_and_mask_sdma0 = GPU_HDP_FLUSH_DONE__RSVD_ENG1_MASK, + .ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__RSVD_ENG2_MASK, + .ref_and_mask_sdma2 = GPU_HDP_FLUSH_DONE__RSVD_ENG3_MASK, + .ref_and_mask_sdma3 = GPU_HDP_FLUSH_DONE__RSVD_ENG4_MASK, + .ref_and_mask_sdma4 = GPU_HDP_FLUSH_DONE__RSVD_ENG5_MASK, + .ref_and_mask_sdma5 = GPU_HDP_FLUSH_DONE__RSVD_ENG6_MASK, + .ref_and_mask_sdma6 = GPU_HDP_FLUSH_DONE__RSVD_ENG7_MASK, + .ref_and_mask_sdma7 = GPU_HDP_FLUSH_DONE__RSVD_ENG8_MASK, +}; + static void nbio_v2_3_init_registers(struct amdgpu_device *adev) { uint32_t def, data; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h index a43b60acf7f6..6074dd3a1ed8 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h @@ -27,6 +27,7 @@ #include "soc15_common.h" extern const struct nbio_hdp_flush_reg nbio_v2_3_hdp_flush_reg; +extern const struct nbio_hdp_flush_reg nbio_v2_3_hdp_flush_reg_sc; extern const struct amdgpu_nbio_funcs nbio_v2_3_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 91b3afa946f5..b8bd03d16dba 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -56,12 +56,15 @@ * These are nbio v7_4_1 registers mask. Temporarily define these here since * nbio v7_4_1 header is incomplete. */ -#define GPU_HDP_FLUSH_DONE__RSVD_ENG0_MASK 0x00001000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG0_MASK 0x00001000L /* Don't use. Firmware uses this bit internally */ #define GPU_HDP_FLUSH_DONE__RSVD_ENG1_MASK 0x00002000L #define GPU_HDP_FLUSH_DONE__RSVD_ENG2_MASK 0x00004000L #define GPU_HDP_FLUSH_DONE__RSVD_ENG3_MASK 0x00008000L #define GPU_HDP_FLUSH_DONE__RSVD_ENG4_MASK 0x00010000L #define GPU_HDP_FLUSH_DONE__RSVD_ENG5_MASK 0x00020000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG6_MASK 0x00040000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG7_MASK 0x00080000L +#define GPU_HDP_FLUSH_DONE__RSVD_ENG8_MASK 0x00100000L #define mmBIF_MMSCH1_DOORBELL_RANGE 0x01dc #define mmBIF_MMSCH1_DOORBELL_RANGE_BASE_IDX 2 @@ -334,12 +337,27 @@ const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg = { .ref_and_mask_cp9 = GPU_HDP_FLUSH_DONE__CP9_MASK, .ref_and_mask_sdma0 = GPU_HDP_FLUSH_DONE__SDMA0_MASK, .ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK, - .ref_and_mask_sdma2 = GPU_HDP_FLUSH_DONE__RSVD_ENG0_MASK, - .ref_and_mask_sdma3 = GPU_HDP_FLUSH_DONE__RSVD_ENG1_MASK, - .ref_and_mask_sdma4 = GPU_HDP_FLUSH_DONE__RSVD_ENG2_MASK, - .ref_and_mask_sdma5 = GPU_HDP_FLUSH_DONE__RSVD_ENG3_MASK, - .ref_and_mask_sdma6 = GPU_HDP_FLUSH_DONE__RSVD_ENG4_MASK, - .ref_and_mask_sdma7 = GPU_HDP_FLUSH_DONE__RSVD_ENG5_MASK, +}; + +const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg_ald = { + .ref_and_mask_cp0 = GPU_HDP_FLUSH_DONE__CP0_MASK, + .ref_and_mask_cp1 = GPU_HDP_FLUSH_DONE__CP1_MASK, + .ref_and_mask_cp2 = GPU_HDP_FLUSH_DONE__CP2_MASK, + .ref_and_mask_cp3 = GPU_HDP_FLUSH_DONE__CP3_MASK, + .ref_and_mask_cp4 = GPU_HDP_FLUSH_DONE__CP4_MASK, + .ref_and_mask_cp5 = GPU_HDP_FLUSH_DONE__CP5_MASK, + .ref_and_mask_cp6 = GPU_HDP_FLUSH_DONE__CP6_MASK, + .ref_and_mask_cp7 = GPU_HDP_FLUSH_DONE__CP7_MASK, + .ref_and_mask_cp8 = GPU_HDP_FLUSH_DONE__CP8_MASK, + .ref_and_mask_cp9 = GPU_HDP_FLUSH_DONE__CP9_MASK, + .ref_and_mask_sdma0 = GPU_HDP_FLUSH_DONE__RSVD_ENG1_MASK, + .ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__RSVD_ENG2_MASK, + .ref_and_mask_sdma2 = GPU_HDP_FLUSH_DONE__RSVD_ENG3_MASK, + .ref_and_mask_sdma3 = GPU_HDP_FLUSH_DONE__RSVD_ENG4_MASK, + .ref_and_mask_sdma4 = GPU_HDP_FLUSH_DONE__RSVD_ENG5_MASK, + .ref_and_mask_sdma5 = GPU_HDP_FLUSH_DONE__RSVD_ENG6_MASK, + .ref_and_mask_sdma6 = GPU_HDP_FLUSH_DONE__RSVD_ENG7_MASK, + .ref_and_mask_sdma7 = GPU_HDP_FLUSH_DONE__RSVD_ENG8_MASK, }; static void nbio_v7_4_init_registers(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h index b8216581ec8d..cc5692db6f98 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h @@ -27,6 +27,7 @@ #include "soc15_common.h" extern const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg; +extern const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg_ald; extern const struct amdgpu_nbio_funcs nbio_v7_4_funcs; extern const struct amdgpu_nbio_ras_funcs nbio_v7_4_ras_funcs; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 5166a1573e7e..febc903adf58 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -607,304 +607,11 @@ const struct amdgpu_ip_block_version nv_common_ip_block = .funcs = &nv_common_ip_funcs, }; -static int nv_reg_base_init(struct amdgpu_device *adev) -{ - int r; - - if (amdgpu_discovery) { - r = amdgpu_discovery_reg_base_init(adev); - if (r) { - DRM_WARN("failed to init reg base from ip discovery table, " - "fallback to legacy init method\n"); - goto legacy_init; - } - - amdgpu_discovery_harvest_ip(adev); - - return 0; - } - -legacy_init: - switch (adev->asic_type) { - case CHIP_NAVI10: - navi10_reg_base_init(adev); - break; - case CHIP_NAVI14: - navi14_reg_base_init(adev); - break; - case CHIP_NAVI12: - navi12_reg_base_init(adev); - break; - case CHIP_SIENNA_CICHLID: - case CHIP_NAVY_FLOUNDER: - sienna_cichlid_reg_base_init(adev); - break; - case CHIP_VANGOGH: - vangogh_reg_base_init(adev); - break; - case CHIP_DIMGREY_CAVEFISH: - dimgrey_cavefish_reg_base_init(adev); - break; - case CHIP_BEIGE_GOBY: - beige_goby_reg_base_init(adev); - break; - case CHIP_YELLOW_CARP: - yellow_carp_reg_base_init(adev); - break; - case CHIP_CYAN_SKILLFISH: - cyan_skillfish_reg_base_init(adev); - break; - default: - return -EINVAL; - } - - return 0; -} - void nv_set_virt_ops(struct amdgpu_device *adev) { adev->virt.ops = &xgpu_nv_virt_ops; } -int nv_set_ip_blocks(struct amdgpu_device *adev) -{ - int r; - - if (adev->asic_type == CHIP_CYAN_SKILLFISH) { - adev->nbio.funcs = &nbio_v2_3_funcs; - adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg; - } else if (adev->flags & AMD_IS_APU) { - adev->nbio.funcs = &nbio_v7_2_funcs; - adev->nbio.hdp_flush_reg = &nbio_v7_2_hdp_flush_reg; - } else { - adev->nbio.funcs = &nbio_v2_3_funcs; - adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg; - } - adev->hdp.funcs = &hdp_v5_0_funcs; - - if (adev->asic_type >= CHIP_SIENNA_CICHLID) - adev->smuio.funcs = &smuio_v11_0_6_funcs; - else - adev->smuio.funcs = &smuio_v11_0_funcs; - - if (adev->asic_type == CHIP_SIENNA_CICHLID) - adev->gmc.xgmi.supported = true; - - /* Set IP register base before any HW register access */ - r = nv_reg_base_init(adev); - if (r) - return r; - - switch (adev->asic_type) { - case CHIP_NAVI10: - case CHIP_NAVI14: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP && - !amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && - !amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); - if (adev->enable_mes) - amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); - break; - case CHIP_NAVI12: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - if (!amdgpu_sriov_vf(adev)) { - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - } else { - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - } - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && - !amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); - if (!amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); - break; - case CHIP_SIENNA_CICHLID: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - if (!amdgpu_sriov_vf(adev)) { - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - } else { - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - } - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP && - is_support_sw_smu(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); - if (!amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - if (adev->enable_mes) - amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); - break; - case CHIP_NAVY_FLOUNDER: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP && - is_support_sw_smu(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && - is_support_sw_smu(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - break; - case CHIP_VANGOGH: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - break; - case CHIP_DIMGREY_CAVEFISH: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP && - is_support_sw_smu(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - break; - case CHIP_BEIGE_GOBY: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP && - is_support_sw_smu(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && - is_support_sw_smu(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); - break; - case CHIP_YELLOW_CARP: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block); - amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - break; - case CHIP_CYAN_SKILLFISH: - amdgpu_device_ip_block_add(adev, &nv_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block); - if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) { - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_8_ip_block); - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - } - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block); - break; - default: - return -EINVAL; - } - - return 0; -} - static uint32_t nv_get_rev_id(struct amdgpu_device *adev) { return adev->nbio.funcs->get_rev_id(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.h b/drivers/gpu/drm/amd/amdgpu/nv.h index 7df2f85bbcd0..83e9782aef39 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.h +++ b/drivers/gpu/drm/amd/amdgpu/nv.h @@ -31,15 +31,5 @@ extern const struct amdgpu_ip_block_version nv_common_ip_block; void nv_grbm_select(struct amdgpu_device *adev, u32 me, u32 pipe, u32 queue, u32 vmid); void nv_set_virt_ops(struct amdgpu_device *adev); -int nv_set_ip_blocks(struct amdgpu_device *adev); -int navi10_reg_base_init(struct amdgpu_device *adev); -int navi14_reg_base_init(struct amdgpu_device *adev); -int navi12_reg_base_init(struct amdgpu_device *adev); -int sienna_cichlid_reg_base_init(struct amdgpu_device *adev); -void vangogh_reg_base_init(struct amdgpu_device *adev); -int dimgrey_cavefish_reg_base_init(struct amdgpu_device *adev); -int beige_goby_reg_base_init(struct amdgpu_device *adev); -int yellow_carp_reg_base_init(struct amdgpu_device *adev); -int cyan_skillfish_reg_base_init(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c index 59644015dfc3..ed2293686f0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c @@ -84,7 +84,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp) ta_hdr = (const struct ta_firmware_header_v1_0 *) adev->psp.ta_fw->data; - adev->psp.hdcp_context.context.bin_desc.feature_version = + adev->psp.hdcp_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->hdcp.fw_version); adev->psp.hdcp_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->hdcp.size_bytes); @@ -92,7 +92,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp) (uint8_t *)ta_hdr + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); - adev->psp.dtm_context.context.bin_desc.feature_version = + adev->psp.dtm_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->dtm.fw_version); adev->psp.dtm_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->dtm.size_bytes); @@ -100,7 +100,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp) (uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr + le32_to_cpu(ta_hdr->dtm.offset_bytes); - adev->psp.securedisplay_context.context.bin_desc.feature_version = + adev->psp.securedisplay_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->securedisplay.fw_version); adev->psp.securedisplay_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->securedisplay.size_bytes); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 21a325ea49cb..2176ef85f137 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -151,7 +151,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) goto out2; ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.xgmi_context.context.bin_desc.feature_version = + adev->psp.xgmi_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->xgmi.fw_version); adev->psp.xgmi_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->xgmi.size_bytes); @@ -159,7 +159,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) (uint8_t *)ta_hdr + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - adev->psp.ras_context.context.bin_desc.feature_version = + adev->psp.ras_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->ras.fw_version); adev->psp.ras_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->ras.size_bytes); @@ -192,7 +192,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) goto out2; ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.hdcp_context.context.bin_desc.feature_version = + adev->psp.hdcp_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->hdcp.fw_version); adev->psp.hdcp_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->hdcp.size_bytes); @@ -203,7 +203,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - adev->psp.dtm_context.context.bin_desc.feature_version = + adev->psp.dtm_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->dtm.fw_version); adev->psp.dtm_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->dtm.size_bytes); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 281bc4d7f0a1..a2588200ea58 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -84,7 +84,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) ta_hdr = (const struct ta_firmware_header_v1_0 *) adev->psp.ta_fw->data; - adev->psp.hdcp_context.context.bin_desc.feature_version = + adev->psp.hdcp_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->hdcp.fw_version); adev->psp.hdcp_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->hdcp.size_bytes); @@ -94,7 +94,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version); - adev->psp.dtm_context.context.bin_desc.feature_version = + adev->psp.dtm_context.context.bin_desc.fw_version = le32_to_cpu(ta_hdr->dtm.fw_version); adev->psp.dtm_context.context.bin_desc.size_bytes = le32_to_cpu(ta_hdr->dtm.size_bytes); diff --git a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid_reg_init.c b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid_reg_init.c deleted file mode 100644 index 5ee69f70c49b..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid_reg_init.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Copyright 2019 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "soc15_hw_ip.h" -#include "sienna_cichlid_ip_offset.h" - -int sienna_cichlid_reg_base_init(struct amdgpu_device *adev) -{ - /* HW has more IP blocks, only initialized the blocke needed by driver */ - uint32_t i; - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCN_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA2_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SDMA3_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - } - return 0; -} diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 0640e143e7a5..0c316a2d42ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -780,185 +780,6 @@ void soc15_set_virt_ops(struct amdgpu_device *adev) soc15_reg_base_init(adev); } -int soc15_set_ip_blocks(struct amdgpu_device *adev) -{ - /* for bare metal case */ - if (!amdgpu_sriov_vf(adev)) - soc15_reg_base_init(adev); - - if (adev->flags & AMD_IS_APU) { - adev->nbio.funcs = &nbio_v7_0_funcs; - adev->nbio.hdp_flush_reg = &nbio_v7_0_hdp_flush_reg; - } else if (adev->asic_type == CHIP_VEGA20 || - adev->asic_type == CHIP_ARCTURUS || - adev->asic_type == CHIP_ALDEBARAN) { - adev->nbio.funcs = &nbio_v7_4_funcs; - adev->nbio.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg; - } else { - adev->nbio.funcs = &nbio_v6_1_funcs; - adev->nbio.hdp_flush_reg = &nbio_v6_1_hdp_flush_reg; - } - adev->hdp.funcs = &hdp_v4_0_funcs; - - if (adev->asic_type == CHIP_VEGA20 || - adev->asic_type == CHIP_ARCTURUS || - adev->asic_type == CHIP_ALDEBARAN) - adev->df.funcs = &df_v3_6_funcs; - else - adev->df.funcs = &df_v1_7_funcs; - - if (adev->asic_type == CHIP_VEGA20 || - adev->asic_type == CHIP_ARCTURUS) - adev->smuio.funcs = &smuio_v11_0_funcs; - else if (adev->asic_type == CHIP_ALDEBARAN) - adev->smuio.funcs = &smuio_v13_0_funcs; - else - adev->smuio.funcs = &smuio_v9_0_funcs; - - adev->rev_id = soc15_get_rev_id(adev); - - switch (adev->asic_type) { - case CHIP_VEGA10: - case CHIP_VEGA12: - case CHIP_VEGA20: - amdgpu_device_ip_block_add(adev, &vega10_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block); - - /* For Vega10 SR-IOV, PSP need to be initialized before IH */ - if (amdgpu_sriov_vf(adev)) { - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) { - if (adev->asic_type == CHIP_VEGA20) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - else - amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block); - } - if (adev->asic_type == CHIP_VEGA20) - amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block); - else - amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block); - } else { - if (adev->asic_type == CHIP_VEGA20) - amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block); - else - amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) { - if (adev->asic_type == CHIP_VEGA20) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - else - amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block); - } - } - amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block); - if (is_support_sw_smu(adev)) { - if (!amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - } else { - amdgpu_device_ip_block_add(adev, &pp_smu_ip_block); - } - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - if (!(adev->asic_type == CHIP_VEGA20 && amdgpu_sriov_vf(adev))) { - amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block); - amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block); - } - break; - case CHIP_RAVEN: - amdgpu_device_ip_block_add(adev, &vega10_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v10_0_ip_block); - amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block); - amdgpu_device_ip_block_add(adev, &pp_smu_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &vcn_v1_0_ip_block); - break; - case CHIP_ARCTURUS: - amdgpu_device_ip_block_add(adev, &vega10_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block); - - if (amdgpu_sriov_vf(adev)) { - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block); - } else { - amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block); - } - - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); - amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block); - amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - - if (amdgpu_sriov_vf(adev)) { - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block); - } else { - amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block); - } - if (!amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &jpeg_v2_5_ip_block); - break; - case CHIP_RENOIR: - amdgpu_device_ip_block_add(adev, &vega10_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v12_0_ip_block); - amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block); - amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block); - if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) - amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block); -#if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev)) - amdgpu_device_ip_block_add(adev, &dm_ip_block); -#endif - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); - break; - case CHIP_ALDEBARAN: - amdgpu_device_ip_block_add(adev, &vega10_common_ip_block); - amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block); - - if (amdgpu_sriov_vf(adev)) { - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block); - amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block); - } else { - amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block); - if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) - amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block); - } - - amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block); - amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block); - - amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v2_6_ip_block); - amdgpu_device_ip_block_add(adev, &jpeg_v2_6_ip_block); - break; - default: - return -EINVAL; - } - - return 0; -} - static bool soc15_need_full_reset(struct amdgpu_device *adev) { /* change this when we implement soft reset */ diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h index f9359003385d..efc2a253e8db 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15.h @@ -102,7 +102,6 @@ struct soc15_ras_field_entry { void soc15_grbm_select(struct amdgpu_device *adev, u32 me, u32 pipe, u32 queue, u32 vmid); void soc15_set_virt_ops(struct amdgpu_device *adev); -int soc15_set_ip_blocks(struct amdgpu_device *adev); void soc15_program_register_sequence(struct amdgpu_device *adev, const struct soc15_reg_golden *registers, diff --git a/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h b/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h index de24a0a97d5e..5093826a43d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h +++ b/drivers/gpu/drm/amd/amdgpu/ta_ras_if.h @@ -59,7 +59,12 @@ enum ta_ras_status { TA_RAS_STATUS__ERROR_SYS_DRV_REG_ACCESS = 0xA011, TA_RAS_STATUS__ERROR_RAS_READ_WRITE = 0xA012, TA_RAS_STATUS__ERROR_NULL_PTR = 0xA013, - TA_RAS_STATUS__ERROR_UNSUPPORTED_IP = 0xA014 + TA_RAS_STATUS__ERROR_UNSUPPORTED_IP = 0xA014, + TA_RAS_STATUS__ERROR_PCS_STATE_QUIET = 0xA015, + TA_RAS_STATUS__ERROR_PCS_STATE_ERROR = 0xA016, + TA_RAS_STATUS__ERROR_PCS_STATE_HANG = 0xA017, + TA_RAS_STATUS__ERROR_PCS_STATE_UNKNOWN = 0xA018, + TA_RAS_STATUS__ERROR_UNSUPPORTED_ERROR_INJ = 0xA019 }; enum ta_ras_block { diff --git a/drivers/gpu/drm/amd/amdgpu/vangogh_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vangogh_reg_init.c deleted file mode 100644 index d64d681a05dc..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/vangogh_reg_init.c +++ /dev/null @@ -1,50 +0,0 @@ -/* - * Copyright 2019 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "soc15_hw_ip.h" -#include "vangogh_ip_offset.h" - -void vangogh_reg_base_init(struct amdgpu_device *adev) -{ - /* HW has more IP blocks, only initialized the blocke needed by driver */ - uint32_t i; - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCN_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - } -} diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index ad0d2564087c..d54d720b3cf6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -111,15 +111,7 @@ static int vcn_v1_0_sw_init(void *handle) /* Override the work func */ adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler; - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - const struct common_firmware_header *hdr; - hdr = (const struct common_firmware_header *)adev->vcn.fw->data; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].ucode_id = AMDGPU_UCODE_ID_VCN; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - dev_info(adev->dev, "Will use PSP to load VCN firmware\n"); - } + amdgpu_vcn_setup_ucode(adev); r = amdgpu_vcn_resume(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 091d8c0f6801..313fc1b53999 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -115,15 +115,7 @@ static int vcn_v2_0_sw_init(void *handle) if (r) return r; - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - const struct common_firmware_header *hdr; - hdr = (const struct common_firmware_header *)adev->vcn.fw->data; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].ucode_id = AMDGPU_UCODE_ID_VCN; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - dev_info(adev->dev, "Will use PSP to load VCN firmware\n"); - } + amdgpu_vcn_setup_ucode(adev); r = amdgpu_vcn_resume(adev); if (r) @@ -1884,15 +1876,14 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev) /* mc resume*/ if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - tmp = AMDGPU_UCODE_ID_VCN; MMSCH_V2_0_INSERT_DIRECT_WT( SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), - adev->firmware.ucode[tmp].tmr_mc_addr_lo); + adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo); MMSCH_V2_0_INSERT_DIRECT_WT( SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), - adev->firmware.ucode[tmp].tmr_mc_addr_hi); + adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi); offset = 0; } else { MMSCH_V2_0_INSERT_DIRECT_WT( diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 59f469bab005..44fc4c218433 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -139,22 +139,7 @@ static int vcn_v2_5_sw_init(void *handle) if (r) return r; - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - const struct common_firmware_header *hdr; - hdr = (const struct common_firmware_header *)adev->vcn.fw->data; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].ucode_id = AMDGPU_UCODE_ID_VCN; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - - if (adev->vcn.num_vcn_inst == VCN25_MAX_HW_INSTANCES_ARCTURUS) { - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - } - dev_info(adev->dev, "Will use PSP to load VCN firmware\n"); - } + amdgpu_vcn_setup_ucode(adev); r = amdgpu_vcn_resume(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index dbfd92984655..da11ceba0698 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -60,11 +60,6 @@ static int amdgpu_ih_clientid_vcns[] = { SOC15_IH_CLIENTID_VCN1 }; -static int amdgpu_ucode_id_vcns[] = { - AMDGPU_UCODE_ID_VCN, - AMDGPU_UCODE_ID_VCN1 -}; - static int vcn_v3_0_start_sriov(struct amdgpu_device *adev); static void vcn_v3_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev); @@ -130,22 +125,7 @@ static int vcn_v3_0_sw_init(void *handle) if (r) return r; - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - const struct common_firmware_header *hdr; - hdr = (const struct common_firmware_header *)adev->vcn.fw->data; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].ucode_id = AMDGPU_UCODE_ID_VCN; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - - if (adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) { - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1; - adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - } - dev_info(adev->dev, "Will use PSP to load VCN firmware\n"); - } + amdgpu_vcn_setup_ucode(adev); r = amdgpu_vcn_resume(adev); if (r) @@ -1293,7 +1273,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) uint32_t param, resp, expected; uint32_t offset, cache_size; uint32_t tmp, timeout; - uint32_t id; struct amdgpu_mm_table *table = &adev->virt.mm_table; uint32_t *table_loc; @@ -1337,13 +1316,12 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) cache_size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4); if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - id = amdgpu_ucode_id_vcns[i]; MMSCH_V3_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), - adev->firmware.ucode[id].tmr_mc_addr_lo); + adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo); MMSCH_V3_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), - adev->firmware.ucode[id].tmr_mc_addr_hi); + adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi); offset = 0; MMSCH_V3_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CACHE_OFFSET0), diff --git a/drivers/gpu/drm/amd/amdgpu/yellow_carp_reg_init.c b/drivers/gpu/drm/amd/amdgpu/yellow_carp_reg_init.c deleted file mode 100644 index 3d89421275ed..000000000000 --- a/drivers/gpu/drm/amd/amdgpu/yellow_carp_reg_init.c +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Copyright 2019 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - */ -#include "amdgpu.h" -#include "nv.h" - -#include "soc15_common.h" -#include "soc15_hw_ip.h" -#include "yellow_carp_offset.h" - -int yellow_carp_reg_base_init(struct amdgpu_device *adev) -{ - /* HW has more IP blocks, only initialized the block needed by driver */ - uint32_t i; - for (i = 0 ; i < MAX_INSTANCE ; ++i) { - adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i])); - adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i])); - adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i])); - adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i])); - adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); - adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i])); - adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i])); - adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(VCN_BASE.instance[i])); - adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i])); - adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DCN_BASE.instance[i])); - adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i])); - adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(SDMA0_BASE.instance[i])); - adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); - adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); - } - return 0; -} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 86afd37b098d..24ebd61395d8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -405,7 +405,7 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p, mutex_lock(&p->mutex); - retval = pqm_update_queue(&p->pqm, args->queue_id, &properties); + retval = pqm_update_queue_properties(&p->pqm, args->queue_id, &properties); mutex_unlock(&p->mutex); @@ -418,7 +418,7 @@ static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p, int retval; const int max_num_cus = 1024; struct kfd_ioctl_set_cu_mask_args *args = data; - struct queue_properties properties; + struct mqd_update_info minfo = {0}; uint32_t __user *cu_mask_ptr = (uint32_t __user *)args->cu_mask_ptr; size_t cu_mask_size = sizeof(uint32_t) * (args->num_cu_mask / 32); @@ -428,8 +428,8 @@ static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p, return -EINVAL; } - properties.cu_mask_count = args->num_cu_mask; - if (properties.cu_mask_count == 0) { + minfo.cu_mask.count = args->num_cu_mask; + if (minfo.cu_mask.count == 0) { pr_debug("CU mask cannot be 0"); return -EINVAL; } @@ -438,32 +438,33 @@ static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p, * limit of max_num_cus bits. We can then just drop any CU mask bits * past max_num_cus bits and just use the first max_num_cus bits. */ - if (properties.cu_mask_count > max_num_cus) { + if (minfo.cu_mask.count > max_num_cus) { pr_debug("CU mask cannot be greater than 1024 bits"); - properties.cu_mask_count = max_num_cus; + minfo.cu_mask.count = max_num_cus; cu_mask_size = sizeof(uint32_t) * (max_num_cus/32); } - properties.cu_mask = kzalloc(cu_mask_size, GFP_KERNEL); - if (!properties.cu_mask) + minfo.cu_mask.ptr = kzalloc(cu_mask_size, GFP_KERNEL); + if (!minfo.cu_mask.ptr) return -ENOMEM; - retval = copy_from_user(properties.cu_mask, cu_mask_ptr, cu_mask_size); + retval = copy_from_user(minfo.cu_mask.ptr, cu_mask_ptr, cu_mask_size); if (retval) { pr_debug("Could not copy CU mask from userspace"); - kfree(properties.cu_mask); - return -EFAULT; + retval = -EFAULT; + goto out; } + minfo.update_flag = UPDATE_FLAG_CU_MASK; + mutex_lock(&p->mutex); - retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties); + retval = pqm_update_mqd(&p->pqm, args->queue_id, &minfo); mutex_unlock(&p->mutex); - if (retval) - kfree(properties.cu_mask); - +out: + kfree(minfo.cu_mask.ptr); return retval; } @@ -1011,11 +1012,6 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p, void *mem, *kern_addr; uint64_t size; - if (p->signal_page) { - pr_err("Event page is already set\n"); - return -EINVAL; - } - kfd = kfd_device_by_id(GET_GPU_ID(args->event_page_offset)); if (!kfd) { pr_err("Getting device by id failed in %s\n", __func__); @@ -1023,6 +1019,13 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p, } mutex_lock(&p->mutex); + + if (p->signal_page) { + pr_err("Event page is already set\n"); + err = -EINVAL; + goto out_unlock; + } + pdd = kfd_bind_process_to_device(kfd, p); if (IS_ERR(pdd)) { err = PTR_ERR(pdd); @@ -1037,20 +1040,24 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p, err = -EINVAL; goto out_unlock; } - mutex_unlock(&p->mutex); err = amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(kfd->kgd, mem, &kern_addr, &size); if (err) { pr_err("Failed to map event page to kernel\n"); - return err; + goto out_unlock; } err = kfd_event_page_set(p, kern_addr, size); if (err) { pr_err("Failed to set event page\n"); - return err; + amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(kfd->kgd, mem); + goto out_unlock; } + + p->signal_handle = args->event_page_offset; + + mutex_unlock(&p->mutex); } err = kfd_event_create(filp, p, args->event_type, @@ -1259,6 +1266,23 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, if (args->size == 0) return -EINVAL; +#if IS_ENABLED(CONFIG_HSA_AMD_SVM) + /* Flush pending deferred work to avoid racing with deferred actions + * from previous memory map changes (e.g. munmap). + */ + svm_range_list_lock_and_flush_work(&p->svms, current->mm); + mutex_lock(&p->svms.lock); + mmap_write_unlock(current->mm); + if (interval_tree_iter_first(&p->svms.objects, + args->va_addr >> PAGE_SHIFT, + (args->va_addr + args->size - 1) >> PAGE_SHIFT)) { + pr_err("Address: 0x%llx already allocated by SVM\n", + args->va_addr); + mutex_unlock(&p->svms.lock); + return -EADDRINUSE; + } + mutex_unlock(&p->svms.lock); +#endif dev = kfd_device_by_id(args->gpu_id); if (!dev) return -EINVAL; @@ -1351,6 +1375,15 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep, return -EINVAL; mutex_lock(&p->mutex); + /* + * Safeguard to prevent user space from freeing signal BO. + * It will be freed at process termination. + */ + if (p->signal_handle && (p->signal_handle == args->handle)) { + pr_err("Free signal BO is not allowed\n"); + ret = -EPERM; + goto err_unlock; + } pdd = kfd_get_process_device_data(dev, p); if (!pdd) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 064d42acd54e..0fffaf859c59 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -93,7 +93,6 @@ static const struct kfd_device_info carrizo_device_info = { .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, }; -#endif static const struct kfd_device_info raven_device_info = { .asic_family = CHIP_RAVEN, @@ -113,7 +112,9 @@ static const struct kfd_device_info raven_device_info = { .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, }; +#endif +#ifdef CONFIG_DRM_AMDGPU_CIK static const struct kfd_device_info hawaii_device_info = { .asic_family = CHIP_HAWAII, .asic_name = "hawaii", @@ -133,6 +134,7 @@ static const struct kfd_device_info hawaii_device_info = { .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, }; +#endif static const struct kfd_device_info tonga_device_info = { .asic_family = CHIP_TONGA, @@ -1021,6 +1023,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd_double_confirm_iommu_support(kfd); if (kfd_iommu_device_init(kfd)) { + kfd->use_iommu_v2 = false; dev_err(kfd_device, "Error initializing iommuv2\n"); goto device_iommu_error; } @@ -1029,6 +1032,9 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, svm_migrate_init((struct amdgpu_device *)kfd->kgd); + if(kgd2kfd_resume_iommu(kfd)) + goto device_iommu_error; + if (kfd_resume(kfd)) goto kfd_resume_error; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index f8fce9d05f50..533b27b35fc9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -557,7 +557,8 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, return retval; } -static int update_queue(struct device_queue_manager *dqm, struct queue *q) +static int update_queue(struct device_queue_manager *dqm, struct queue *q, + struct mqd_update_info *minfo) { int retval = 0; struct mqd_manager *mqd_mgr; @@ -605,7 +606,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q) } } - mqd_mgr->update_mqd(mqd_mgr, q->mqd, &q->properties); + mqd_mgr->update_mqd(mqd_mgr, q->mqd, &q->properties, minfo); /* * check active state vs. the previous state and modify diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index c8719682c4da..499fc0ea387f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -93,7 +93,7 @@ struct device_queue_manager_ops { struct queue *q); int (*update_queue)(struct device_queue_manager *dqm, - struct queue *q); + struct queue *q, struct mqd_update_info *minfo); int (*register_process)(struct device_queue_manager *dqm, struct qcm_process_device *qpd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index a2b77d1df854..64b4ac339904 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -136,7 +136,6 @@ static bool kq_initialize(struct kernel_queue *kq, struct kfd_dev *dev, prop.write_ptr = (uint32_t *) kq->wptr_gpu_addr; prop.eop_ring_buffer_address = kq->eop_gpu_addr; prop.eop_ring_buffer_size = PAGE_SIZE; - prop.cu_mask = NULL; if (init_queue(&kq->queue, &prop) != 0) goto err_init_queue; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index f53e17a94ad8..6d8634e40b3b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -20,7 +20,6 @@ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. */ - #include #include #include @@ -34,6 +33,11 @@ #include "kfd_svm.h" #include "kfd_migrate.h" +#ifdef dev_fmt +#undef dev_fmt +#endif +#define dev_fmt(fmt) "kfd_migrate: %s: " fmt, __func__ + static uint64_t svm_migrate_direct_mapping_addr(struct amdgpu_device *adev, uint64_t addr) { @@ -151,14 +155,14 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys, gart_d = svm_migrate_direct_mapping_addr(adev, *vram); } if (r) { - pr_debug("failed %d to create gart mapping\n", r); + dev_err(adev->dev, "fail %d create gart mapping\n", r); goto out_unlock; } r = amdgpu_copy_buffer(ring, gart_s, gart_d, size * PAGE_SIZE, NULL, &next, false, true, false); if (r) { - pr_debug("failed %d to copy memory\n", r); + dev_err(adev->dev, "fail %d to copy memory\n", r); goto out_unlock; } @@ -264,6 +268,19 @@ static void svm_migrate_put_sys_page(unsigned long addr) put_page(page); } +static unsigned long svm_migrate_successful_pages(struct migrate_vma *migrate) +{ + unsigned long cpages = 0; + unsigned long i; + + for (i = 0; i < migrate->npages; i++) { + if (migrate->src[i] & MIGRATE_PFN_VALID && + migrate->src[i] & MIGRATE_PFN_MIGRATE) + cpages++; + } + return cpages; +} + static int svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, @@ -285,7 +302,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, r = svm_range_vram_node_new(adev, prange, true); if (r) { - pr_debug("failed %d get 0x%llx pages from vram\n", r, npages); + dev_err(adev->dev, "fail %d to alloc vram\n", r); goto out; } @@ -305,7 +322,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, DMA_TO_DEVICE); r = dma_mapping_error(dev, src[i]); if (r) { - pr_debug("failed %d dma_map_page\n", r); + dev_err(adev->dev, "fail %d dma_map_page\n", r); goto out_free_vram_pages; } } else { @@ -325,8 +342,8 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, continue; } - pr_debug("dma mapping src to 0x%llx, page_to_pfn 0x%lx\n", - src[i] >> PAGE_SHIFT, page_to_pfn(spage)); + pr_debug_ratelimited("dma mapping src to 0x%llx, pfn 0x%lx\n", + src[i] >> PAGE_SHIFT, page_to_pfn(spage)); if (j >= (cursor.size >> PAGE_SHIFT) - 1 && i < npages - 1) { r = svm_migrate_copy_memory_gart(adev, src + i - j, @@ -372,7 +389,7 @@ out: return r; } -static int +static long svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end) @@ -381,6 +398,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; struct migrate_vma migrate; + unsigned long cpages = 0; dma_addr_t *scratch; size_t size; void *buf; @@ -405,23 +423,31 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, r = migrate_vma_setup(&migrate); if (r) { - pr_debug("failed %d prepare migrate svms 0x%p [0x%lx 0x%lx]\n", - r, prange->svms, prange->start, prange->last); + dev_err(adev->dev, "vma setup fail %d range [0x%lx 0x%lx]\n", r, + prange->start, prange->last); goto out_free; } - if (migrate.cpages != npages) { - pr_debug("Partial migration. 0x%lx/0x%llx pages can be migrated\n", - migrate.cpages, - npages); - } - if (migrate.cpages) { - r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, - scratch); - migrate_vma_pages(&migrate); - svm_migrate_copy_done(adev, mfence); - migrate_vma_finalize(&migrate); + cpages = migrate.cpages; + if (!cpages) { + pr_debug("failed collect migrate sys pages [0x%lx 0x%lx]\n", + prange->start, prange->last); + goto out_free; } + if (cpages != npages) + pr_debug("partial migration, 0x%lx/0x%llx pages migrated\n", + cpages, npages); + else + pr_debug("0x%lx pages migrated\n", cpages); + + r = svm_migrate_copy_to_vram(adev, prange, &migrate, &mfence, scratch); + migrate_vma_pages(&migrate); + + pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n", + svm_migrate_successful_pages(&migrate), cpages, migrate.npages); + + svm_migrate_copy_done(adev, mfence); + migrate_vma_finalize(&migrate); svm_range_dma_unmap(adev->dev, scratch, 0, npages); svm_range_free_dma_mappings(prange); @@ -429,12 +455,13 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, out_free: kvfree(buf); out: - if (!r) { + if (!r && cpages) { pdd = svm_range_get_pdd_by_adev(prange, adev); if (pdd) - WRITE_ONCE(pdd->page_in, pdd->page_in + migrate.cpages); - } + WRITE_ONCE(pdd->page_in, pdd->page_in + cpages); + return cpages; + } return r; } @@ -456,7 +483,8 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, unsigned long addr, start, end; struct vm_area_struct *vma; struct amdgpu_device *adev; - int r = 0; + unsigned long cpages = 0; + long r = 0; if (prange->actual_loc == best_loc) { pr_debug("svms 0x%p [0x%lx 0x%lx] already on best_loc 0x%x\n", @@ -488,17 +516,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, next = min(vma->vm_end, end); r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next); - if (r) { - pr_debug("failed to migrate\n"); + if (r < 0) { + pr_debug("failed %ld to migrate\n", r); break; + } else { + cpages += r; } addr = next; } - if (!r) + if (cpages) prange->actual_loc = best_loc; - return r; + return r < 0 ? r : 0; } static void svm_migrate_page_free(struct page *page) @@ -506,7 +536,7 @@ static void svm_migrate_page_free(struct page *page) struct svm_range_bo *svm_bo = page->zone_device_data; if (svm_bo) { - pr_debug("svm_bo ref left: %d\n", kref_read(&svm_bo->kref)); + pr_debug_ratelimited("ref: %d\n", kref_read(&svm_bo->kref)); svm_range_bo_unref(svm_bo); } } @@ -572,12 +602,12 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, dst[i] = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_FROM_DEVICE); r = dma_mapping_error(dev, dst[i]); if (r) { - pr_debug("failed %d dma_map_page\n", r); + dev_err(adev->dev, "fail %d dma_map_page\n", r); goto out_oom; } - pr_debug("dma mapping dst to 0x%llx, page_to_pfn 0x%lx\n", - dst[i] >> PAGE_SHIFT, page_to_pfn(dpage)); + pr_debug_ratelimited("dma mapping dst to 0x%llx, pfn 0x%lx\n", + dst[i] >> PAGE_SHIFT, page_to_pfn(dpage)); migrate->dst[i] = migrate_pfn(page_to_pfn(dpage)); migrate->dst[i] |= MIGRATE_PFN_LOCKED; @@ -599,7 +629,7 @@ out_oom: return r; } -static int +static long svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end) { @@ -607,6 +637,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; struct migrate_vma migrate; + unsigned long cpages = 0; dma_addr_t *scratch; size_t size; void *buf; @@ -631,34 +662,43 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, r = migrate_vma_setup(&migrate); if (r) { - pr_debug("failed %d prepare migrate svms 0x%p [0x%lx 0x%lx]\n", - r, prange->svms, prange->start, prange->last); + dev_err(adev->dev, "vma setup fail %d range [0x%lx 0x%lx]\n", r, + prange->start, prange->last); goto out_free; } - pr_debug("cpages %ld\n", migrate.cpages); - - if (migrate.cpages) { - r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, - scratch, npages); - migrate_vma_pages(&migrate); - svm_migrate_copy_done(adev, mfence); - migrate_vma_finalize(&migrate); - } else { + cpages = migrate.cpages; + if (!cpages) { pr_debug("failed collect migrate device pages [0x%lx 0x%lx]\n", prange->start, prange->last); + goto out_free; } + if (cpages != npages) + pr_debug("partial migration, 0x%lx/0x%llx pages migrated\n", + cpages, npages); + else + pr_debug("0x%lx pages migrated\n", cpages); + r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, + scratch, npages); + migrate_vma_pages(&migrate); + + pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n", + svm_migrate_successful_pages(&migrate), cpages, migrate.npages); + + svm_migrate_copy_done(adev, mfence); + migrate_vma_finalize(&migrate); svm_range_dma_unmap(adev->dev, scratch, 0, npages); out_free: kvfree(buf); out: - if (!r) { + if (!r && cpages) { pdd = svm_range_get_pdd_by_adev(prange, adev); if (pdd) - WRITE_ONCE(pdd->page_out, - pdd->page_out + migrate.cpages); + WRITE_ONCE(pdd->page_out, pdd->page_out + cpages); + + return cpages; } return r; } @@ -680,7 +720,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm) unsigned long addr; unsigned long start; unsigned long end; - int r = 0; + unsigned long cpages = 0; + long r = 0; if (!prange->actual_loc) { pr_debug("[0x%lx 0x%lx] already migrated to ram\n", @@ -711,18 +752,21 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm) next = min(vma->vm_end, end); r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next); - if (r) { - pr_debug("failed %d to migrate\n", r); + if (r < 0) { + pr_debug("failed %ld to migrate\n", r); break; + } else { + cpages += r; } addr = next; } - if (!r) { + if (cpages) { svm_range_vram_node_free(prange); prange->actual_loc = 0; } - return r; + + return r < 0 ? r : 0; } /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h index 6e6918ccedfd..965e17c5dbb4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h @@ -80,7 +80,8 @@ struct mqd_manager { struct mm_struct *mms); void (*update_mqd)(struct mqd_manager *mm, void *mqd, - struct queue_properties *q); + struct queue_properties *q, + struct mqd_update_info *minfo); int (*destroy_mqd)(struct mqd_manager *mm, void *mqd, enum kfd_preempt_type type, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c index 064914e1e8d6..8128f4d312f1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c @@ -42,16 +42,17 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd) } static void update_cu_mask(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct mqd_update_info *minfo) { struct cik_mqd *m; uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */ - if (q->cu_mask_count == 0) + if (!minfo || (minfo->update_flag != UPDATE_FLAG_CU_MASK) || + !minfo->cu_mask.ptr) return; mqd_symmetrically_map_cu_mask(mm, - q->cu_mask, q->cu_mask_count, se_mask); + minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask); m = get_mqd(mqd); m->compute_static_thread_mgmt_se0 = se_mask[0]; @@ -135,7 +136,7 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, *mqd = m; if (gart_addr) *gart_addr = addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, @@ -152,7 +153,7 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, if (gart_addr) *gart_addr = mqd_mem_obj->gpu_addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static void free_mqd(struct mqd_manager *mm, void *mqd, @@ -185,7 +186,8 @@ static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, } static void __update_mqd(struct mqd_manager *mm, void *mqd, - struct queue_properties *q, unsigned int atc_bit) + struct queue_properties *q, struct mqd_update_info *minfo, + unsigned int atc_bit) { struct cik_mqd *m; @@ -214,16 +216,17 @@ static void __update_mqd(struct mqd_manager *mm, void *mqd, if (q->format == KFD_QUEUE_FORMAT_AQL) m->cp_hqd_pq_control |= NO_UPDATE_RPTR; - update_cu_mask(mm, mqd, q); + update_cu_mask(mm, mqd, minfo); set_priority(m, q); q->is_active = QUEUE_IS_ACTIVE(*q); } static void update_mqd(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { - __update_mqd(mm, mqd, q, 1); + __update_mqd(mm, mqd, q, minfo, 1); } static uint32_t read_doorbell_id(void *mqd) @@ -234,13 +237,15 @@ static uint32_t read_doorbell_id(void *mqd) } static void update_mqd_hawaii(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { - __update_mqd(mm, mqd, q, 0); + __update_mqd(mm, mqd, q, minfo, 0); } static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct cik_sdma_rlc_registers *m; @@ -318,7 +323,8 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd, } static void update_mqd_hiq(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct cik_mqd *m; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index c7fb59ca597f..270160fc401b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -42,16 +42,17 @@ static inline struct v10_sdma_mqd *get_sdma_mqd(void *mqd) } static void update_cu_mask(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct mqd_update_info *minfo) { struct v10_compute_mqd *m; uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */ - if (q->cu_mask_count == 0) + if (!minfo || (minfo->update_flag != UPDATE_FLAG_CU_MASK) || + !minfo->cu_mask.ptr) return; mqd_symmetrically_map_cu_mask(mm, - q->cu_mask, q->cu_mask_count, se_mask); + minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask); m = get_mqd(mqd); m->compute_static_thread_mgmt_se0 = se_mask[0]; @@ -136,7 +137,7 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, *mqd = m; if (gart_addr) *gart_addr = addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static int load_mqd(struct mqd_manager *mm, void *mqd, @@ -162,7 +163,8 @@ static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd, } static void update_mqd(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct v10_compute_mqd *m; @@ -218,7 +220,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, if (mm->dev->cwsr_enabled) m->cp_hqd_ctx_save_control = 0; - update_cu_mask(mm, mqd, q); + update_cu_mask(mm, mqd, minfo); set_priority(m, q); q->is_active = QUEUE_IS_ACTIVE(*q); @@ -311,7 +313,7 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, if (gart_addr) *gart_addr = mqd_mem_obj->gpu_addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, @@ -326,7 +328,8 @@ static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, #define SDMA_RLC_DUMMY_DEFAULT 0xf static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct v10_sdma_mqd *m; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index 7f4e102ff4bd..4e5932f54b5a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -43,16 +43,17 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd) } static void update_cu_mask(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct mqd_update_info *minfo) { struct v9_mqd *m; uint32_t se_mask[KFD_MAX_NUM_SE] = {0}; - if (q->cu_mask_count == 0) + if (!minfo || (minfo->update_flag != UPDATE_FLAG_CU_MASK) || + !minfo->cu_mask.ptr) return; mqd_symmetrically_map_cu_mask(mm, - q->cu_mask, q->cu_mask_count, se_mask); + minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask); m = get_mqd(mqd); m->compute_static_thread_mgmt_se0 = se_mask[0]; @@ -188,7 +189,7 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, *mqd = m; if (gart_addr) *gart_addr = addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static int load_mqd(struct mqd_manager *mm, void *mqd, @@ -212,7 +213,8 @@ static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd, } static void update_mqd(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct v9_mqd *m; @@ -269,7 +271,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address) m->cp_hqd_ctx_save_control = 0; - update_cu_mask(mm, mqd, q); + update_cu_mask(mm, mqd, minfo); set_priority(m, q); q->is_active = QUEUE_IS_ACTIVE(*q); @@ -366,7 +368,7 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, if (gart_addr) *gart_addr = mqd_mem_obj->gpu_addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, @@ -381,7 +383,8 @@ static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, #define SDMA_RLC_DUMMY_DEFAULT 0xf static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct v9_sdma_mqd *m; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c index 33dbd22d290f..cd9220eb8a7a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c @@ -45,16 +45,17 @@ static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd) } static void update_cu_mask(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct mqd_update_info *minfo) { struct vi_mqd *m; uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */ - if (q->cu_mask_count == 0) + if (!minfo || (minfo->update_flag != UPDATE_FLAG_CU_MASK) || + !minfo->cu_mask.ptr) return; mqd_symmetrically_map_cu_mask(mm, - q->cu_mask, q->cu_mask_count, se_mask); + minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask); m = get_mqd(mqd); m->compute_static_thread_mgmt_se0 = se_mask[0]; @@ -150,7 +151,7 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, *mqd = m; if (gart_addr) *gart_addr = addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static int load_mqd(struct mqd_manager *mm, void *mqd, @@ -167,8 +168,8 @@ static int load_mqd(struct mqd_manager *mm, void *mqd, } static void __update_mqd(struct mqd_manager *mm, void *mqd, - struct queue_properties *q, unsigned int mtype, - unsigned int atc_bit) + struct queue_properties *q, struct mqd_update_info *minfo, + unsigned int mtype, unsigned int atc_bit) { struct vi_mqd *m; @@ -230,7 +231,7 @@ static void __update_mqd(struct mqd_manager *mm, void *mqd, atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT | mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT; - update_cu_mask(mm, mqd, q); + update_cu_mask(mm, mqd, minfo); set_priority(m, q); q->is_active = QUEUE_IS_ACTIVE(*q); @@ -238,9 +239,10 @@ static void __update_mqd(struct mqd_manager *mm, void *mqd, static void update_mqd(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { - __update_mqd(mm, mqd, q, MTYPE_CC, 1); + __update_mqd(mm, mqd, q, minfo, MTYPE_CC, 1); } static uint32_t read_doorbell_id(void *mqd) @@ -251,9 +253,10 @@ static uint32_t read_doorbell_id(void *mqd) } static void update_mqd_tonga(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { - __update_mqd(mm, mqd, q, MTYPE_UC, 0); + __update_mqd(mm, mqd, q, minfo, MTYPE_UC, 0); } static int destroy_mqd(struct mqd_manager *mm, void *mqd, @@ -317,9 +320,10 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd, } static void update_mqd_hiq(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { - __update_mqd(mm, mqd, q, MTYPE_UC, 0); + __update_mqd(mm, mqd, q, minfo, MTYPE_UC, 0); } static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, @@ -336,7 +340,7 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd, if (gart_addr) *gart_addr = mqd_mem_obj->gpu_addr; - mm->update_mqd(mm, m, q); + mm->update_mqd(mm, m, q, NULL); } static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, @@ -349,7 +353,8 @@ static int load_mqd_sdma(struct mqd_manager *mm, void *mqd, } static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, - struct queue_properties *q) + struct queue_properties *q, + struct mqd_update_info *minfo) { struct vi_sdma_mqd *m; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 6d8f9bb2d905..4104b167e721 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -472,9 +472,6 @@ struct queue_properties { uint32_t ctl_stack_size; uint64_t tba_addr; uint64_t tma_addr; - /* Relevant for CU */ - uint32_t cu_mask_count; /* Must be a multiple of 32 */ - uint32_t *cu_mask; }; #define QUEUE_IS_ACTIVE(q) ((q).queue_size > 0 && \ @@ -482,6 +479,20 @@ struct queue_properties { (q).queue_percent > 0 && \ !(q).is_evicted) +enum mqd_update_flag { + UPDATE_FLAG_CU_MASK = 0, +}; + +struct mqd_update_info { + union { + struct { + uint32_t count; /* Must be a multiple of 32 */ + uint32_t *ptr; + } cu_mask; + }; + enum mqd_update_flag update_flag; +}; + /** * struct queue * @@ -608,12 +619,14 @@ struct qcm_process_device { uint32_t sh_hidden_private_base; /* CWSR memory */ + struct kgd_mem *cwsr_mem; void *cwsr_kaddr; uint64_t cwsr_base; uint64_t tba_addr; uint64_t tma_addr; /* IB memory */ + struct kgd_mem *ib_mem; uint64_t ib_base; void *ib_kaddr; @@ -808,6 +821,7 @@ struct kfd_process { /* Event ID allocator and lookup */ struct idr event_idr; /* Event page */ + u64 signal_handle; struct kfd_signal_page *signal_page; size_t signal_mapped_size; size_t signal_event_count; @@ -1031,10 +1045,10 @@ int pqm_create_queue(struct process_queue_manager *pqm, unsigned int *qid, uint32_t *p_doorbell_offset_in_process); int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid); -int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid, - struct queue_properties *p); -int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid, +int pqm_update_queue_properties(struct process_queue_manager *pqm, unsigned int qid, struct queue_properties *p); +int pqm_update_mqd(struct process_queue_manager *pqm, unsigned int qid, + struct mqd_update_info *minfo); int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void *gws); struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 21ec8a18cad2..457863861d6f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -72,6 +72,8 @@ static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep); static void evict_process_worker(struct work_struct *work); static void restore_process_worker(struct work_struct *work); +static void kfd_process_device_destroy_cwsr_dgpu(struct kfd_process_device *pdd); + struct kfd_procfs_tree { struct kobject *kobj; }; @@ -685,10 +687,15 @@ void kfd_process_destroy_wq(void) } static void kfd_process_free_gpuvm(struct kgd_mem *mem, - struct kfd_process_device *pdd) + struct kfd_process_device *pdd, void *kptr) { struct kfd_dev *dev = pdd->dev; + if (kptr) { + amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(dev->kgd, mem); + kptr = NULL; + } + amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(dev->kgd, mem, pdd->drm_priv); amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd, mem, pdd->drm_priv, NULL); @@ -702,63 +709,46 @@ static void kfd_process_free_gpuvm(struct kgd_mem *mem, */ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd, uint64_t gpu_va, uint32_t size, - uint32_t flags, void **kptr) + uint32_t flags, struct kgd_mem **mem, void **kptr) { struct kfd_dev *kdev = pdd->dev; - struct kgd_mem *mem = NULL; - int handle; int err; err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(kdev->kgd, gpu_va, size, - pdd->drm_priv, &mem, NULL, flags); + pdd->drm_priv, mem, NULL, flags); if (err) goto err_alloc_mem; - err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, + err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, *mem, pdd->drm_priv, NULL); if (err) goto err_map_mem; - err = amdgpu_amdkfd_gpuvm_sync_memory(kdev->kgd, mem, true); + err = amdgpu_amdkfd_gpuvm_sync_memory(kdev->kgd, *mem, true); if (err) { pr_debug("Sync memory failed, wait interrupted by user signal\n"); goto sync_memory_failed; } - /* Create an obj handle so kfd_process_device_remove_obj_handle - * will take care of the bo removal when the process finishes. - * We do not need to take p->mutex, because the process is just - * created and the ioctls have not had the chance to run. - */ - handle = kfd_process_device_create_obj_handle(pdd, mem); - - if (handle < 0) { - err = handle; - goto free_gpuvm; - } - if (kptr) { err = amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(kdev->kgd, - (struct kgd_mem *)mem, kptr, NULL); + (struct kgd_mem *)*mem, kptr, NULL); if (err) { pr_debug("Map GTT BO to kernel failed\n"); - goto free_obj_handle; + goto sync_memory_failed; } } return err; -free_obj_handle: - kfd_process_device_remove_obj_handle(pdd, handle); -free_gpuvm: sync_memory_failed: - kfd_process_free_gpuvm(mem, pdd); - return err; + amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(kdev->kgd, *mem, pdd->drm_priv); err_map_mem: - amdgpu_amdkfd_gpuvm_free_memory_of_gpu(kdev->kgd, mem, pdd->drm_priv, + amdgpu_amdkfd_gpuvm_free_memory_of_gpu(kdev->kgd, *mem, pdd->drm_priv, NULL); err_alloc_mem: + *mem = NULL; *kptr = NULL; return err; } @@ -776,6 +766,7 @@ static int kfd_process_device_reserve_ib_mem(struct kfd_process_device *pdd) KFD_IOC_ALLOC_MEM_FLAGS_NO_SUBSTITUTE | KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE | KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE; + struct kgd_mem *mem; void *kaddr; int ret; @@ -784,15 +775,26 @@ static int kfd_process_device_reserve_ib_mem(struct kfd_process_device *pdd) /* ib_base is only set for dGPU */ ret = kfd_process_alloc_gpuvm(pdd, qpd->ib_base, PAGE_SIZE, flags, - &kaddr); + &mem, &kaddr); if (ret) return ret; + qpd->ib_mem = mem; qpd->ib_kaddr = kaddr; return 0; } +static void kfd_process_device_destroy_ib_mem(struct kfd_process_device *pdd) +{ + struct qcm_process_device *qpd = &pdd->qpd; + + if (!qpd->ib_kaddr || !qpd->ib_base) + return; + + kfd_process_free_gpuvm(qpd->ib_mem, pdd, qpd->ib_kaddr); +} + struct kfd_process *kfd_create_process(struct file *filep) { struct kfd_process *process; @@ -947,6 +949,37 @@ static void kfd_process_device_free_bos(struct kfd_process_device *pdd) } } +/* + * Just kunmap and unpin signal BO here. It will be freed in + * kfd_process_free_outstanding_kfd_bos() + */ +static void kfd_process_kunmap_signal_bo(struct kfd_process *p) +{ + struct kfd_process_device *pdd; + struct kfd_dev *kdev; + void *mem; + + kdev = kfd_device_by_id(GET_GPU_ID(p->signal_handle)); + if (!kdev) + return; + + mutex_lock(&p->mutex); + + pdd = kfd_get_process_device_data(kdev, p); + if (!pdd) + goto out; + + mem = kfd_process_device_translate_handle( + pdd, GET_IDR_HANDLE(p->signal_handle)); + if (!mem) + goto out; + + amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(kdev->kgd, mem); + +out: + mutex_unlock(&p->mutex); +} + static void kfd_process_free_outstanding_kfd_bos(struct kfd_process *p) { int i; @@ -965,6 +998,9 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) pr_debug("Releasing pdd (topology id %d) for process (pasid 0x%x)\n", pdd->dev->id, p->pasid); + kfd_process_device_destroy_cwsr_dgpu(pdd); + kfd_process_device_destroy_ib_mem(pdd); + if (pdd->drm_file) { amdgpu_amdkfd_gpuvm_release_process_vm( pdd->dev->kgd, pdd->drm_priv); @@ -1049,9 +1085,11 @@ static void kfd_process_wq_release(struct work_struct *work) { struct kfd_process *p = container_of(work, struct kfd_process, release_work); + kfd_process_remove_sysfs(p); kfd_iommu_unbind_process(p); + kfd_process_kunmap_signal_bo(p); kfd_process_free_outstanding_kfd_bos(p); svm_range_list_fini(p); @@ -1198,6 +1236,7 @@ static int kfd_process_device_init_cwsr_dgpu(struct kfd_process_device *pdd) uint32_t flags = KFD_IOC_ALLOC_MEM_FLAGS_GTT | KFD_IOC_ALLOC_MEM_FLAGS_NO_SUBSTITUTE | KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE; + struct kgd_mem *mem; void *kaddr; int ret; @@ -1206,10 +1245,11 @@ static int kfd_process_device_init_cwsr_dgpu(struct kfd_process_device *pdd) /* cwsr_base is only set for dGPU */ ret = kfd_process_alloc_gpuvm(pdd, qpd->cwsr_base, - KFD_CWSR_TBA_TMA_SIZE, flags, &kaddr); + KFD_CWSR_TBA_TMA_SIZE, flags, &mem, &kaddr); if (ret) return ret; + qpd->cwsr_mem = mem; qpd->cwsr_kaddr = kaddr; qpd->tba_addr = qpd->cwsr_base; @@ -1222,6 +1262,17 @@ static int kfd_process_device_init_cwsr_dgpu(struct kfd_process_device *pdd) return 0; } +static void kfd_process_device_destroy_cwsr_dgpu(struct kfd_process_device *pdd) +{ + struct kfd_dev *dev = pdd->dev; + struct qcm_process_device *qpd = &pdd->qpd; + + if (!dev->cwsr_enabled || !qpd->cwsr_kaddr || !qpd->cwsr_base) + return; + + kfd_process_free_gpuvm(qpd->cwsr_mem, pdd, qpd->cwsr_kaddr); +} + void kfd_process_set_trap_handler(struct qcm_process_device *qpd, uint64_t tba_addr, uint64_t tma_addr) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 243dd1efcdbf..3627e7ac161b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -121,7 +121,7 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, pdd->qpd.num_gws = gws ? amdgpu_amdkfd_get_num_gws(dev->kgd) : 0; return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm, - pqn->q); + pqn->q, NULL); } void kfd_process_dequeue_from_all_devices(struct kfd_process *p) @@ -394,8 +394,6 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) pdd->qpd.num_gws = 0; } - kfree(pqn->q->properties.cu_mask); - pqn->q->properties.cu_mask = NULL; uninit_queue(pqn->q); } @@ -411,8 +409,8 @@ err_destroy_queue: return retval; } -int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid, - struct queue_properties *p) +int pqm_update_queue_properties(struct process_queue_manager *pqm, + unsigned int qid, struct queue_properties *p) { int retval; struct process_queue_node *pqn; @@ -429,15 +427,15 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid, pqn->q->properties.priority = p->priority; retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm, - pqn->q); + pqn->q, NULL); if (retval != 0) return retval; return 0; } -int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid, - struct queue_properties *p) +int pqm_update_mqd(struct process_queue_manager *pqm, + unsigned int qid, struct mqd_update_info *minfo) { int retval; struct process_queue_node *pqn; @@ -448,16 +446,8 @@ int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid, return -EFAULT; } - /* Free the old CU mask memory if it is already allocated, then - * allocate memory for the new CU mask. - */ - kfree(pqn->q->properties.cu_mask); - - pqn->q->properties.cu_mask_count = p->cu_mask_count; - pqn->q->properties.cu_mask = p->cu_mask; - retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm, - pqn->q); + pqn->q, minfo); if (retval != 0) return retval; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 179080329af8..b691c8495d66 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -33,6 +33,11 @@ #include "kfd_svm.h" #include "kfd_migrate.h" +#ifdef dev_fmt +#undef dev_fmt +#endif +#define dev_fmt(fmt) "kfd_svm: %s: " fmt, __func__ + #define AMDGPU_SVM_RANGE_RESTORE_DELAY_MS 1 /* Long enough to ensure no retry fault comes after svm range is restored and @@ -45,7 +50,9 @@ static bool svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni, const struct mmu_notifier_range *range, unsigned long cur_seq); - +static int +svm_range_check_vm(struct kfd_process *p, uint64_t start, uint64_t last, + uint64_t *bo_s, uint64_t *bo_l); static const struct mmu_interval_notifier_ops svm_range_mn_ops = { .invalidate = svm_range_cpu_invalidate_pagetables, }; @@ -158,17 +165,17 @@ svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange, bo_adev->vm_manager.vram_base_offset - bo_adev->kfd.dev->pgmap.range.start; addr[i] |= SVM_RANGE_VRAM_DOMAIN; - pr_debug("vram address detected: 0x%llx\n", addr[i]); + pr_debug_ratelimited("vram address: 0x%llx\n", addr[i]); continue; } addr[i] = dma_map_page(dev, page, 0, PAGE_SIZE, dir); r = dma_mapping_error(dev, addr[i]); if (r) { - pr_debug("failed %d dma_map_page\n", r); + dev_err(dev, "failed %d dma_map_page\n", r); return r; } - pr_debug("dma mapping 0x%llx for page addr 0x%lx\n", - addr[i] >> PAGE_SHIFT, page_to_pfn(page)); + pr_debug_ratelimited("dma mapping 0x%llx for page addr 0x%lx\n", + addr[i] >> PAGE_SHIFT, page_to_pfn(page)); } return 0; } @@ -217,7 +224,7 @@ void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr, for (i = offset; i < offset + npages; i++) { if (!svm_is_valid_dma_mapping_addr(dev, dma_addr[i])) continue; - pr_debug("dma unmapping 0x%llx\n", dma_addr[i] >> PAGE_SHIFT); + pr_debug_ratelimited("unmap 0x%llx\n", dma_addr[i] >> PAGE_SHIFT); dma_unmap_page(dev, dma_addr[i], PAGE_SIZE, dir); dma_addr[i] = 0; } @@ -1454,7 +1461,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm, /* This should never happen. actual_loc gets set by * svm_migrate_ram_to_vram after allocating a BO. */ - WARN(1, "VRAM BO missing during validation\n"); + WARN_ONCE(1, "VRAM BO missing during validation\n"); return -EINVAL; } @@ -1547,7 +1554,7 @@ unreserve_out: * Context: Returns with mmap write lock held, pending deferred work flushed * */ -static void +void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_struct *mm) { @@ -2303,6 +2310,7 @@ svm_range_best_restore_location(struct svm_range *prange, return -1; } + static int svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, unsigned long *start, unsigned long *last) @@ -2350,8 +2358,59 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr, vma->vm_end >> PAGE_SHIFT, *last); return 0; - } + +static int +svm_range_check_vm_userptr(struct kfd_process *p, uint64_t start, uint64_t last, + uint64_t *bo_s, uint64_t *bo_l) +{ + struct amdgpu_bo_va_mapping *mapping; + struct interval_tree_node *node; + struct amdgpu_bo *bo = NULL; + unsigned long userptr; + uint32_t i; + int r; + + for (i = 0; i < p->n_pdds; i++) { + struct amdgpu_vm *vm; + + if (!p->pdds[i]->drm_priv) + continue; + + vm = drm_priv_to_vm(p->pdds[i]->drm_priv); + r = amdgpu_bo_reserve(vm->root.bo, false); + if (r) + return r; + + /* Check userptr by searching entire vm->va interval tree */ + node = interval_tree_iter_first(&vm->va, 0, ~0ULL); + while (node) { + mapping = container_of((struct rb_node *)node, + struct amdgpu_bo_va_mapping, rb); + bo = mapping->bo_va->base.bo; + + if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, + start << PAGE_SHIFT, + last << PAGE_SHIFT, + &userptr)) { + node = interval_tree_iter_next(node, 0, ~0ULL); + continue; + } + + pr_debug("[0x%llx 0x%llx] already userptr mapped\n", + start, last); + if (bo_s && bo_l) { + *bo_s = userptr >> PAGE_SHIFT; + *bo_l = *bo_s + bo->tbo.ttm->num_pages - 1; + } + amdgpu_bo_unreserve(vm->root.bo); + return -EADDRINUSE; + } + amdgpu_bo_unreserve(vm->root.bo); + } + return 0; +} + static struct svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev, struct kfd_process *p, @@ -2361,10 +2420,26 @@ svm_range *svm_range_create_unregistered_range(struct amdgpu_device *adev, struct svm_range *prange = NULL; unsigned long start, last; uint32_t gpuid, gpuidx; + uint64_t bo_s = 0; + uint64_t bo_l = 0; + int r; if (svm_range_get_range_boundaries(p, addr, &start, &last)) return NULL; + r = svm_range_check_vm(p, start, last, &bo_s, &bo_l); + if (r != -EADDRINUSE) + r = svm_range_check_vm_userptr(p, start, last, &bo_s, &bo_l); + + if (r == -EADDRINUSE) { + if (addr >= bo_s && addr <= bo_l) + return NULL; + + /* Create one page svm range if 2MB range overlapping */ + start = addr; + last = addr; + } + prange = svm_range_new(&p->svms, start, last); if (!prange) { pr_debug("Failed to create prange in address [0x%llx]\n", addr); @@ -2662,9 +2737,68 @@ int svm_range_list_init(struct kfd_process *p) return 0; } +/** + * svm_range_check_vm - check if virtual address range mapped already + * @p: current kfd_process + * @start: range start address, in pages + * @last: range last address, in pages + * @bo_s: mapping start address in pages if address range already mapped + * @bo_l: mapping last address in pages if address range already mapped + * + * The purpose is to avoid virtual address ranges already allocated by + * kfd_ioctl_alloc_memory_of_gpu ioctl. + * It looks for each pdd in the kfd_process. + * + * Context: Process context + * + * Return 0 - OK, if the range is not mapped. + * Otherwise error code: + * -EADDRINUSE - if address is mapped already by kfd_ioctl_alloc_memory_of_gpu + * -ERESTARTSYS - A wait for the buffer to become unreserved was interrupted by + * a signal. Release all buffer reservations and return to user-space. + */ +static int +svm_range_check_vm(struct kfd_process *p, uint64_t start, uint64_t last, + uint64_t *bo_s, uint64_t *bo_l) +{ + struct amdgpu_bo_va_mapping *mapping; + struct interval_tree_node *node; + uint32_t i; + int r; + + for (i = 0; i < p->n_pdds; i++) { + struct amdgpu_vm *vm; + + if (!p->pdds[i]->drm_priv) + continue; + + vm = drm_priv_to_vm(p->pdds[i]->drm_priv); + r = amdgpu_bo_reserve(vm->root.bo, false); + if (r) + return r; + + node = interval_tree_iter_first(&vm->va, start, last); + if (node) { + pr_debug("range [0x%llx 0x%llx] already TTM mapped\n", + start, last); + mapping = container_of((struct rb_node *)node, + struct amdgpu_bo_va_mapping, rb); + if (bo_s && bo_l) { + *bo_s = mapping->start; + *bo_l = mapping->last; + } + amdgpu_bo_unreserve(vm->root.bo); + return -EADDRINUSE; + } + amdgpu_bo_unreserve(vm->root.bo); + } + + return 0; +} + /** * svm_range_is_valid - check if virtual address range is valid - * @mm: current process mm_struct + * @p: current kfd_process * @start: range start address, in pages * @size: range size, in pages * @@ -2673,28 +2807,28 @@ int svm_range_list_init(struct kfd_process *p) * Context: Process context * * Return: - * true - valid svm range - * false - invalid svm range + * 0 - OK, otherwise error code */ -static bool -svm_range_is_valid(struct mm_struct *mm, uint64_t start, uint64_t size) +static int +svm_range_is_valid(struct kfd_process *p, uint64_t start, uint64_t size) { const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; struct vm_area_struct *vma; unsigned long end; + unsigned long start_unchg = start; start <<= PAGE_SHIFT; end = start + (size << PAGE_SHIFT); - do { - vma = find_vma(mm, start); + vma = find_vma(p->mm, start); if (!vma || start < vma->vm_start || (vma->vm_flags & device_vma)) - return false; + return -EFAULT; start = min(end, vma->vm_end); } while (start < end); - return true; + return svm_range_check_vm(p, start_unchg, (end - 1) >> PAGE_SHIFT, NULL, + NULL); } /** @@ -2997,9 +3131,9 @@ svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size, svm_range_list_lock_and_flush_work(svms, mm); - if (!svm_range_is_valid(mm, start, size)) { - pr_debug("invalid range\n"); - r = -EFAULT; + r = svm_range_is_valid(p, start, size); + if (r) { + pr_debug("invalid range r=%d\n", r); mmap_write_unlock(mm); goto out; } @@ -3101,6 +3235,7 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size, uint32_t flags_or = 0; int gpuidx; uint32_t i; + int r = 0; pr_debug("svms 0x%p [0x%llx 0x%llx] nattr 0x%x\n", &p->svms, start, start + size - 1, nattr); @@ -3114,12 +3249,12 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size, flush_work(&p->svms.deferred_list_work); mmap_read_lock(mm); - if (!svm_range_is_valid(mm, start, size)) { - pr_debug("invalid range\n"); - mmap_read_unlock(mm); - return -EINVAL; - } + r = svm_range_is_valid(p, start, size); mmap_read_unlock(mm); + if (r) { + pr_debug("invalid range r=%d\n", r); + return r; + } for (i = 0; i < nattr; i++) { switch (attrs[i].type) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h index c6ec55354c7b..6dc91c33e80f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h @@ -188,6 +188,7 @@ void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm, void *owner); struct kfd_process_device * svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev); +void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_struct *mm); /* SVM API and HMM page migration work together, device memory type * is initialized to not 0 when page migration register device memory. diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 98cca5f2b27f..dd593ad0614a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1296,6 +1296,24 @@ int kfd_topology_add_device(struct kfd_dev *gpu) proximity_domain = atomic_inc_return(&topology_crat_proximity_domain); + adev = (struct amdgpu_device *)(gpu->kgd); + + /* Include the CPU in xGMI hive if xGMI connected by assigning it the hive ID. */ + if (gpu->hive_id && adev->gmc.xgmi.connected_to_cpu) { + struct kfd_topology_device *top_dev; + + down_read(&topology_lock); + + list_for_each_entry(top_dev, &topology_device_list, list) { + if (top_dev->gpu) + break; + + top_dev->node_props.hive_id = gpu->hive_id; + } + + up_read(&topology_lock); + } + /* Check to see if this gpu device exists in the topology_device_list. * If so, assign the gpu to that device, * else create a Virtual CRAT for this gpu device and then parse that @@ -1457,7 +1475,6 @@ int kfd_topology_add_device(struct kfd_dev *gpu) dev->node_props.max_waves_per_simd = 10; } - adev = (struct amdgpu_device *)(dev->gpu->kgd); /* kfd only concerns sram ecc on GFX and HBM ecc on UMC */ dev->node_props.capability |= ((adev->ras_enabled & BIT(AMDGPU_RAS_BLOCK__GFX)) != 0) ? diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f35561b5a465..43e983e42c0f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -730,6 +730,8 @@ static void dm_handle_hpd_work(struct work_struct *work) dmub_hpd_wrk->adev->dm.dmub_callback[dmub_hpd_wrk->dmub_notify->type](dmub_hpd_wrk->adev, dmub_hpd_wrk->dmub_notify); } + + kfree(dmub_hpd_wrk->dmub_notify); kfree(dmub_hpd_wrk); } @@ -755,12 +757,6 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params) if (dc_enable_dmub_notifications(adev->dm.dc) && irq_params->irq_src == DC_IRQ_SOURCE_DMCUB_OUTBOX) { - dmub_hpd_wrk = kzalloc(sizeof(*dmub_hpd_wrk), GFP_ATOMIC); - if (!dmub_hpd_wrk) { - DRM_ERROR("Failed to allocate dmub_hpd_wrk"); - return; - } - INIT_WORK(&dmub_hpd_wrk->handle_hpd_work, dm_handle_hpd_work); do { dc_stat_get_dmub_notification(adev->dm.dc, ¬ify); @@ -769,7 +765,20 @@ static void dm_dmub_outbox1_low_irq(void *interrupt_params) continue; } if (dm->dmub_thread_offload[notify.type] == true) { - dmub_hpd_wrk->dmub_notify = ¬ify; + dmub_hpd_wrk = kzalloc(sizeof(*dmub_hpd_wrk), GFP_ATOMIC); + if (!dmub_hpd_wrk) { + DRM_ERROR("Failed to allocate dmub_hpd_wrk"); + return; + } + dmub_hpd_wrk->dmub_notify = kzalloc(sizeof(struct dmub_notification), GFP_ATOMIC); + if (!dmub_hpd_wrk->dmub_notify) { + kfree(dmub_hpd_wrk); + DRM_ERROR("Failed to allocate dmub_hpd_wrk->dmub_notify"); + return; + } + INIT_WORK(&dmub_hpd_wrk->handle_hpd_work, dm_handle_hpd_work); + if (dmub_hpd_wrk->dmub_notify) + memcpy(dmub_hpd_wrk->dmub_notify, ¬ify, sizeof(struct dmub_notification)); dmub_hpd_wrk->adev = adev; if (notify.type == DMUB_NOTIFICATION_HPD) { plink = adev->dm.dc->links[notify.link_index]; @@ -1008,6 +1017,7 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) const unsigned char *fw_inst_const, *fw_bss_data; uint32_t i, fw_inst_const_size, fw_bss_data_size; bool has_hw_support; + struct dc *dc = adev->dm.dc; if (!dmub_srv) /* DMUB isn't supported on the ASIC. */ @@ -1094,6 +1104,19 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) for (i = 0; i < fb_info->num_fb; ++i) hw_params.fb[i] = &fb_info->fb[i]; + switch (adev->asic_type) { + case CHIP_YELLOW_CARP: + if (dc->ctx->asic_id.hw_internal_rev != YELLOW_CARP_A0) { + hw_params.dpia_supported = true; +#if defined(CONFIG_DRM_AMD_DC_DCN) + hw_params.disable_dpia = dc->debug.dpia_debug.bits.disable_dpia; +#endif + } + break; + default: + break; + } + status = dmub_srv_hw_init(dmub_srv, &hw_params); if (status != DMUB_STATUS_OK) { DRM_ERROR("Error initializing DMUB HW: %d\n", status); @@ -1295,6 +1318,37 @@ static struct hpd_rx_irq_offload_work_queue *hpd_rx_irq_create_workqueue(struct return hpd_rx_offload_wq; } +struct amdgpu_stutter_quirk { + u16 chip_vendor; + u16 chip_device; + u16 subsys_vendor; + u16 subsys_device; + u8 revision; +}; + +static const struct amdgpu_stutter_quirk amdgpu_stutter_quirk_list[] = { + /* https://bugzilla.kernel.org/show_bug.cgi?id=214417 */ + { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, + { 0, 0, 0, 0, 0 }, +}; + +static bool dm_should_disable_stutter(struct pci_dev *pdev) +{ + const struct amdgpu_stutter_quirk *p = amdgpu_stutter_quirk_list; + + while (p && p->chip_device != 0) { + if (pdev->vendor == p->chip_vendor && + pdev->device == p->chip_device && + pdev->subsystem_vendor == p->subsys_vendor && + pdev->subsystem_device == p->subsys_device && + pdev->revision == p->revision) { + return true; + } + ++p; + } + return false; +} + static int amdgpu_dm_init(struct amdgpu_device *adev) { struct dc_init_data init_data; @@ -1356,8 +1410,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) switch (adev->ip_versions[DCE_HWIP][0]) { case IP_VERSION(2, 1, 0): init_data.flags.gpu_vm_support = true; - if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id)) - init_data.flags.disable_dmcu = true; + init_data.flags.disable_dmcu = true; break; case IP_VERSION(1, 0, 0): case IP_VERSION(1, 0, 1): @@ -1407,6 +1460,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY) adev->dm.dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true; + if (dm_should_disable_stutter(adev->pdev)) + adev->dm.dc->debug.disable_stutter = true; if (amdgpu_dc_debug_mask & DC_DISABLE_STUTTER) adev->dm.dc->debug.disable_stutter = true; @@ -1793,7 +1848,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) break; case IP_VERSION(3, 1, 2): case IP_VERSION(3, 1, 3): - dmub_asic = DMUB_ASIC_DCN31; + dmub_asic = (adev->external_rev_id == YELLOW_CARP_B0) ? DMUB_ASIC_DCN31B : DMUB_ASIC_DCN31; fw_name_dmub = FIRMWARE_YELLOW_CARP_DMUB; break; @@ -4031,6 +4086,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) int32_t primary_planes; enum dc_connection_type new_connection_type = dc_connection_none; const struct dc_plane_cap *plane; + bool psr_feature_enabled = false; dm->display_indexes_num = dm->dc->caps.max_streams; /* Update the actual used number of crtc */ @@ -4113,6 +4169,19 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) DRM_DEBUG_KMS("Unsupported DCN IP version for outbox: 0x%X\n", adev->ip_versions[DCE_HWIP][0]); } + + /* Determine whether to enable PSR support by default. */ + if (!(amdgpu_dc_debug_mask & DC_DISABLE_PSR)) { + switch (adev->ip_versions[DCE_HWIP][0]) { + case IP_VERSION(3, 1, 2): + case IP_VERSION(3, 1, 3): + psr_feature_enabled = true; + break; + default: + psr_feature_enabled = amdgpu_dc_feature_mask & DC_PSR_MASK; + break; + } + } #endif /* loops over all connectors on the board */ @@ -4156,7 +4225,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) } else if (dc_link_detect(link, DETECT_REASON_BOOT)) { amdgpu_dm_update_connector_after_detect(aconnector); register_backlight_device(dm, link); - if (amdgpu_dc_feature_mask & DC_PSR_MASK) + + if (psr_feature_enabled) amdgpu_dm_set_psr_caps(link); } @@ -10535,18 +10605,18 @@ static int dm_check_crtc_cursor(struct drm_atomic_state *state, struct drm_crtc *crtc, struct drm_crtc_state *new_crtc_state) { - struct drm_plane_state *new_cursor_state, *new_primary_state; - int cursor_scale_w, cursor_scale_h, primary_scale_w, primary_scale_h; + struct drm_plane *cursor = crtc->cursor, *underlying; + struct drm_plane_state *new_cursor_state, *new_underlying_state; + int i; + int cursor_scale_w, cursor_scale_h, underlying_scale_w, underlying_scale_h; /* On DCE and DCN there is no dedicated hardware cursor plane. We get a * cursor per pipe but it's going to inherit the scaling and * positioning from the underlying pipe. Check the cursor plane's - * blending properties match the primary plane's. */ + * blending properties match the underlying planes'. */ - new_cursor_state = drm_atomic_get_new_plane_state(state, crtc->cursor); - new_primary_state = drm_atomic_get_new_plane_state(state, crtc->primary); - if (!new_cursor_state || !new_primary_state || - !new_cursor_state->fb || !new_primary_state->fb) { + new_cursor_state = drm_atomic_get_new_plane_state(state, cursor); + if (!new_cursor_state || !new_cursor_state->fb) { return 0; } @@ -10555,15 +10625,34 @@ static int dm_check_crtc_cursor(struct drm_atomic_state *state, cursor_scale_h = new_cursor_state->crtc_h * 1000 / (new_cursor_state->src_h >> 16); - primary_scale_w = new_primary_state->crtc_w * 1000 / - (new_primary_state->src_w >> 16); - primary_scale_h = new_primary_state->crtc_h * 1000 / - (new_primary_state->src_h >> 16); + for_each_new_plane_in_state_reverse(state, underlying, new_underlying_state, i) { + /* Narrow down to non-cursor planes on the same CRTC as the cursor */ + if (new_underlying_state->crtc != crtc || underlying == crtc->cursor) + continue; - if (cursor_scale_w != primary_scale_w || - cursor_scale_h != primary_scale_h) { - drm_dbg_atomic(crtc->dev, "Cursor plane scaling doesn't match primary plane\n"); - return -EINVAL; + /* Ignore disabled planes */ + if (!new_underlying_state->fb) + continue; + + underlying_scale_w = new_underlying_state->crtc_w * 1000 / + (new_underlying_state->src_w >> 16); + underlying_scale_h = new_underlying_state->crtc_h * 1000 / + (new_underlying_state->src_h >> 16); + + if (cursor_scale_w != underlying_scale_w || + cursor_scale_h != underlying_scale_h) { + drm_dbg_atomic(crtc->dev, + "Cursor [PLANE:%d:%s] scaling doesn't match underlying [PLANE:%d:%s]\n", + cursor->base.id, cursor->name, underlying->base.id, underlying->name); + return -EINVAL; + } + + /* If this plane covers the whole CRTC, no need to check planes underneath */ + if (new_underlying_state->crtc_x <= 0 && + new_underlying_state->crtc_y <= 0 && + new_underlying_state->crtc_x + new_underlying_state->crtc_w >= new_crtc_state->mode.hdisplay && + new_underlying_state->crtc_y + new_underlying_state->crtc_h >= new_crtc_state->mode.vdisplay) + break; } return 0; @@ -10594,53 +10683,6 @@ static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm } #endif -static int validate_overlay(struct drm_atomic_state *state) -{ - int i; - struct drm_plane *plane; - struct drm_plane_state *new_plane_state; - struct drm_plane_state *primary_state, *overlay_state = NULL; - - /* Check if primary plane is contained inside overlay */ - for_each_new_plane_in_state_reverse(state, plane, new_plane_state, i) { - if (plane->type == DRM_PLANE_TYPE_OVERLAY) { - if (drm_atomic_plane_disabling(plane->state, new_plane_state)) - return 0; - - overlay_state = new_plane_state; - continue; - } - } - - /* check if we're making changes to the overlay plane */ - if (!overlay_state) - return 0; - - /* check if overlay plane is enabled */ - if (!overlay_state->crtc) - return 0; - - /* find the primary plane for the CRTC that the overlay is enabled on */ - primary_state = drm_atomic_get_plane_state(state, overlay_state->crtc->primary); - if (IS_ERR(primary_state)) - return PTR_ERR(primary_state); - - /* check if primary plane is enabled */ - if (!primary_state->crtc) - return 0; - - /* Perform the bounds check to ensure the overlay plane covers the primary */ - if (primary_state->crtc_x < overlay_state->crtc_x || - primary_state->crtc_y < overlay_state->crtc_y || - primary_state->crtc_x + primary_state->crtc_w > overlay_state->crtc_x + overlay_state->crtc_w || - primary_state->crtc_y + primary_state->crtc_h > overlay_state->crtc_y + overlay_state->crtc_h) { - DRM_DEBUG_ATOMIC("Overlay plane is enabled with hardware cursor but does not fully cover primary plane\n"); - return -EINVAL; - } - - return 0; -} - /** * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM. * @dev: The DRM device @@ -10683,6 +10725,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, struct dm_crtc_state *dm_old_crtc_state; #if defined(CONFIG_DRM_AMD_DC_DCN) struct dsc_mst_fairness_vars vars[MAX_PIPES]; + struct drm_dp_mst_topology_state *mst_state; + struct drm_dp_mst_topology_mgr *mgr; #endif trace_amdgpu_dm_atomic_check_begin(state); @@ -10822,10 +10866,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - ret = validate_overlay(state); - if (ret) - goto fail; - /* Add new/modified planes */ for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { ret = dm_update_plane_state(dc, state, plane, @@ -10891,6 +10931,33 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, lock_and_validation_needed = true; } +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* set the slot info for each mst_state based on the link encoding format */ + for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) { + struct amdgpu_dm_connector *aconnector; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + u8 link_coding_cap; + + if (!mgr->mst_state ) + continue; + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) { + int id = connector->index; + + if (id == mst_state->mgr->conn_base_id) { + aconnector = to_amdgpu_dm_connector(connector); + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link); + drm_dp_mst_update_slots(mst_state, link_coding_cap); + + break; + } + } + drm_connector_list_iter_end(&iter); + + } +#endif /** * Streams and planes are reset when there are changes that affect * bandwidth. Anything that affects bandwidth needs to go through diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index d2f4b3e670d6..3655663e079b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -294,6 +294,9 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, case LINK_RATE_RBR2: case LINK_RATE_HIGH2: case LINK_RATE_HIGH3: +#if defined(CONFIG_DRM_AMD_DC_DCN) + case LINK_RATE_UHBR10: +#endif break; default: valid_input = false; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index ff0f91c93ba4..8cbeeb7c986d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -219,6 +219,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( struct drm_dp_mst_topology_mgr *mst_mgr; struct drm_dp_mst_port *mst_port; bool ret; + u8 link_coding_cap = DP_8b_10b_ENCODING; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; /* Accessing the connector state is required for vcpi_slots allocation @@ -238,6 +239,10 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( mst_port = aconnector->port; +#if defined(CONFIG_DRM_AMD_DC_DCN) + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link); +#endif + if (enable) { ret = drm_dp_mst_allocate_vcpi(mst_mgr, mst_port, @@ -251,7 +256,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( } /* It's OK for this to fail */ - drm_dp_update_payload_part1(mst_mgr); + drm_dp_update_payload_part1(mst_mgr, (link_coding_cap == DP_CAP_ANSI_128B132B) ? 0:1); /* mst_mgr->->payloads are VC payload notify MST branch using DPCD or * AUX message. The sequence is slot 1-63 allocated sequence for each diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 1a99fcc27078..874a49b605c7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -64,6 +64,8 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, payload.i2c_over_aux = (msg->request & DP_AUX_NATIVE_WRITE) == 0; payload.write = (msg->request & DP_AUX_I2C_READ) == 0; payload.mot = (msg->request & DP_AUX_I2C_MOT) != 0; + payload.write_status_update = + (msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0; payload.defer_delay = 0; result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index 70a554f1e725..c022e56f9459 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -107,6 +107,8 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) */ // Init fail safe of 2 frames static unsigned int num_frames_static = 2; + unsigned int power_opt = 0; + bool psr_enable = true; DRM_DEBUG_DRIVER("Enabling psr...\n"); @@ -133,7 +135,9 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) &stream, 1, ¶ms); - return dc_link_set_psr_allow_active(link, true, false, false); + power_opt |= psr_power_opt_z10_static_screen; + + return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt); } /* @@ -144,10 +148,12 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) */ bool amdgpu_dm_psr_disable(struct dc_stream_state *stream) { + unsigned int power_opt = 0; + bool psr_enable = false; DRM_DEBUG_DRIVER("Disabling psr...\n"); - return dc_link_set_psr_allow_active(stream->link, false, true, false); + return dc_link_set_psr_allow_active(stream->link, &psr_enable, true, false, &power_opt); } /* diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index cdb5c027411a..a4bef4364afd 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -99,6 +99,10 @@ static enum bp_result get_firmware_info_v3_2( struct bios_parser *bp, struct dc_firmware_info *info); +static enum bp_result get_firmware_info_v3_4( + struct bios_parser *bp, + struct dc_firmware_info *info); + static struct atom_hpd_int_record *get_hpd_record(struct bios_parser *bp, struct atom_display_object_path_v2 *object); @@ -1426,8 +1430,10 @@ static enum bp_result bios_parser_get_firmware_info( break; case 2: case 3: - case 4: result = get_firmware_info_v3_2(bp, info); + break; + case 4: + result = get_firmware_info_v3_4(bp, info); break; default: break; @@ -1575,6 +1581,88 @@ static enum bp_result get_firmware_info_v3_2( return BP_RESULT_OK; } +static enum bp_result get_firmware_info_v3_4( + struct bios_parser *bp, + struct dc_firmware_info *info) +{ + struct atom_firmware_info_v3_4 *firmware_info; + struct atom_common_table_header *header; + struct atom_data_revision revision; + struct atom_display_controller_info_v4_1 *dce_info_v4_1 = NULL; + struct atom_display_controller_info_v4_4 *dce_info_v4_4 = NULL; + if (!info) + return BP_RESULT_BADINPUT; + + firmware_info = GET_IMAGE(struct atom_firmware_info_v3_4, + DATA_TABLES(firmwareinfo)); + + if (!firmware_info) + return BP_RESULT_BADBIOSTABLE; + + memset(info, 0, sizeof(*info)); + + header = GET_IMAGE(struct atom_common_table_header, + DATA_TABLES(dce_info)); + + get_atom_data_table_revision(header, &revision); + + switch (revision.major) { + case 4: + switch (revision.minor) { + case 4: + dce_info_v4_4 = GET_IMAGE(struct atom_display_controller_info_v4_4, + DATA_TABLES(dce_info)); + + if (!dce_info_v4_4) + return BP_RESULT_BADBIOSTABLE; + + /* 100MHz expected */ + info->pll_info.crystal_frequency = dce_info_v4_4->dce_refclk_10khz * 10; + info->dp_phy_ref_clk = dce_info_v4_4->dpphy_refclk_10khz * 10; + /* 50MHz expected */ + info->i2c_engine_ref_clk = dce_info_v4_4->i2c_engine_refclk_10khz * 10; + + /* Get SMU Display PLL VCO Frequency in KHz*/ + info->smu_gpu_pll_output_freq = dce_info_v4_4->dispclk_pll_vco_freq * 10; + break; + + default: + /* should not come here, keep as backup, as was before */ + dce_info_v4_1 = GET_IMAGE(struct atom_display_controller_info_v4_1, + DATA_TABLES(dce_info)); + + if (!dce_info_v4_1) + return BP_RESULT_BADBIOSTABLE; + + info->pll_info.crystal_frequency = dce_info_v4_1->dce_refclk_10khz * 10; + info->dp_phy_ref_clk = dce_info_v4_1->dpphy_refclk_10khz * 10; + info->i2c_engine_ref_clk = dce_info_v4_1->i2c_engine_refclk_10khz * 10; + break; + } + break; + + default: + ASSERT(0); + break; + } + + header = GET_IMAGE(struct atom_common_table_header, + DATA_TABLES(smu_info)); + get_atom_data_table_revision(header, &revision); + + // We need to convert from 10KHz units into KHz units. + info->default_memory_clk = firmware_info->bootup_mclk_in10khz * 10; + + if (firmware_info->board_i2c_feature_id == 0x2) { + info->oem_i2c_present = true; + info->oem_i2c_obj_id = firmware_info->board_i2c_feature_gpio_id; + } else { + info->oem_i2c_present = false; + } + + return BP_RESULT_OK; +} + static enum bp_result bios_parser_get_encoder_cap_info( struct dc_bios *dcb, struct graphics_object_id object_id, @@ -2233,6 +2321,8 @@ static enum bp_result get_integrated_info_v2_2( info->ext_disp_conn_info.checksum = info_v2_2->extdispconninfo.checksum; + info->ext_disp_conn_info.fixdpvoltageswing = + info_v2_2->extdispconninfo.fixdpvoltageswing; info->edp1_info.edp_backlight_pwm_hz = le16_to_cpu(info_v2_2->edp1_info.edp_backlight_pwm_hz); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index 1548b2a3fe03..26f96ee32472 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -100,11 +100,13 @@ void clk_mgr_exit_optimized_pwr_state(const struct dc *dc, struct clk_mgr *clk_m if (edp_num) { for (panel_inst = 0; panel_inst < edp_num; panel_inst++) { + bool allow_active = false; + edp_link = edp_links[panel_inst]; if (!edp_link->psr_settings.psr_feature_enabled) continue; clk_mgr->psr_allow_active_cache = edp_link->psr_settings.psr_allow_active; - dc_link_set_psr_allow_active(edp_link, false, false, false); + dc_link_set_psr_allow_active(edp_link, &allow_active, false, false, NULL); } } @@ -124,7 +126,7 @@ void clk_mgr_optimize_pwr_state(const struct dc *dc, struct clk_mgr *clk_mgr) if (!edp_link->psr_settings.psr_feature_enabled) continue; dc_link_set_psr_allow_active(edp_link, - clk_mgr->psr_allow_active_cache, false, false); + &clk_mgr->psr_allow_active_cache, false, false, NULL); } } @@ -283,13 +285,8 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p BREAK_TO_DEBUGGER(); return NULL; } - if (ASICREV_IS_YELLOW_CARP(asic_id.hw_internal_rev)) { - /* TODO: to add DCN31 clk_mgr support, once CLK IP header files are available, - * for now use DCN3.0 clk mgr. - */ - dcn31_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); - return &clk_mgr->base.base; - } + + dcn31_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); return &clk_mgr->base.base; } #endif @@ -326,7 +323,6 @@ void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr_base) break; case FAMILY_YELLOW_CARP: - if (ASICREV_IS_YELLOW_CARP(clk_mgr_base->ctx->asic_id.hw_internal_rev)) dcn31_clk_mgr_destroy(clk_mgr); break; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index 4696cd296fd8..f4c9a458ace8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -219,14 +219,17 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, update_dispclk = true; } - /* TODO: add back DTO programming when DPPCLK restore is fixed in FSDL*/ if (dpp_clock_lowered) { // increase per DPP DTO before lowering global dppclk + dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); dcn31_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz); } else { // increase global DPPCLK before lowering per DPP DTO if (update_dppclk || update_dispclk) dcn31_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz); + // always update dtos unless clock is lowered and not safe to lower + if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz) + dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); } // notify DMCUB of latest clocks diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index da942e9f5142..12e5470fa567 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -71,8 +71,6 @@ #include "dmub/dmub_srv.h" -#include "dcn30/dcn30_vpg.h" - #include "i2caux_interface.h" #include "dce/dmub_hw_lock_mgr.h" @@ -1899,12 +1897,14 @@ static bool is_flip_pending_in_pipes(struct dc *dc, struct dc_state *context) static void process_deferred_updates(struct dc *dc) { #ifdef CONFIG_DRM_AMD_DC_DCN - int i; + int i = 0; - if (dc->debug.enable_mem_low_power.bits.cm) + if (dc->debug.enable_mem_low_power.bits.cm) { + ASSERT(dc->dcn_ip->max_num_dpp); for (i = 0; i < dc->dcn_ip->max_num_dpp; i++) if (dc->res_pool->dpps[i]->funcs->dpp_deferred_update) dc->res_pool->dpps[i]->funcs->dpp_deferred_update(dc->res_pool->dpps[i]); + } #endif } @@ -2285,6 +2285,9 @@ static enum surface_update_type det_surface_update(const struct dc *dc, update_flags->bits.gamma_change = 1; } + if (u->lut3d_func || u->func_shaper) + update_flags->bits.lut_3d = 1; + if (u->hdr_mult.value) if (u->hdr_mult.value != u->surface->hdr_mult.value) { update_flags->bits.hdr_mult = 1; @@ -2298,6 +2301,7 @@ static enum surface_update_type det_surface_update(const struct dc *dc, if (update_flags->bits.input_csc_change || update_flags->bits.coeff_reduction_change + || update_flags->bits.lut_3d || update_flags->bits.gamma_change || update_flags->bits.gamut_remap_change) { type = UPDATE_TYPE_FULL; @@ -2356,6 +2360,11 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->dsc_config) su_flags->bits.dsc_changed = 1; +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (stream_update->mst_bw_update) + su_flags->bits.mst_bw = 1; +#endif + if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2674,9 +2683,6 @@ static void commit_planes_do_stream_update(struct dc *dc, enum surface_update_type update_type, struct dc_state *context) { -#if defined(CONFIG_DRM_AMD_DC_DCN) - struct vpg *vpg; -#endif int j; // Stream updates @@ -2697,11 +2703,6 @@ static void commit_planes_do_stream_update(struct dc *dc, stream_update->vrr_infopacket || stream_update->vsc_infopacket || stream_update->vsp_infopacket) { -#if defined(CONFIG_DRM_AMD_DC_DCN) - vpg = pipe_ctx->stream_res.stream_enc->vpg; - if (vpg && vpg->funcs->vpg_poweron) - vpg->funcs->vpg_poweron(vpg); -#endif resource_build_info_frame(pipe_ctx); dc->hwss.update_info_frame(pipe_ctx); } @@ -2741,6 +2742,15 @@ static void commit_planes_do_stream_update(struct dc *dc, if (stream_update->dsc_config) dp_update_dsc_config(pipe_ctx); +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (stream_update->mst_bw_update) { + if (stream_update->mst_bw_update->is_increase) + dc_link_increase_mst_payload(pipe_ctx, stream_update->mst_bw_update->mst_stream_bw); + else + dc_link_reduce_mst_payload(pipe_ctx, stream_update->mst_bw_update->mst_stream_bw); + } +#endif + if (stream_update->pending_test_pattern) { dc_link_dp_set_test_pattern(stream->link, stream->test_pattern.type, @@ -3118,8 +3128,13 @@ void dc_commit_updates_for_stream(struct dc *dc, if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state) new_pipe->plane_state->force_full_update = true; } - } else if (update_type == UPDATE_TYPE_FAST) { - /* Previous frame finished and HW is ready for optimization. */ + } else if (update_type == UPDATE_TYPE_FAST && dc_ctx->dce_version >= DCE_VERSION_MAX) { + /* + * Previous frame finished and HW is ready for optimization. + * + * Only relevant for DCN behavior where we can guarantee the optimization + * is safe to apply - retain the legacy behavior for DCE. + */ dc_post_update_surfaces_to_stream(dc); } @@ -3178,6 +3193,12 @@ void dc_commit_updates_for_stream(struct dc *dc, } } + /* Legacy optimization path for DCE. */ + if (update_type >= UPDATE_TYPE_FULL && dc_ctx->dce_version < DCE_VERSION_MAX) { + dc_post_update_surfaces_to_stream(dc); + TRACE_DCE_CLOCK_STATE(&context->bw_ctx.bw.dce); + } + return; } @@ -3478,6 +3499,7 @@ void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_ bool dc_set_psr_allow_active(struct dc *dc, bool enable) { int i; + bool allow_active; for (i = 0; i < dc->current_state->stream_count ; i++) { struct dc_link *link; @@ -3489,10 +3511,12 @@ bool dc_set_psr_allow_active(struct dc *dc, bool enable) if (link->psr_settings.psr_feature_enabled) { if (enable && !link->psr_settings.psr_allow_active) { - if (!dc_link_set_psr_allow_active(link, true, false, false)) + allow_active = true; + if (!dc_link_set_psr_allow_active(link, &allow_active, false, false, NULL)) return false; } else if (!enable && link->psr_settings.psr_allow_active) { - if (!dc_link_set_psr_allow_active(link, false, true, false)) + allow_active = false; + if (!dc_link_set_psr_allow_active(link, &allow_active, true, false, NULL)) return false; } } @@ -3726,6 +3750,60 @@ bool dc_process_dmub_set_config_async(struct dc *dc, return is_cmd_complete; } +/** + ***************************************************************************** + * Function: dc_process_dmub_set_mst_slots + * + * @brief + * Submits mst slot allocation command to dmub via inbox message + * + * @param + * [in] dc: dc structure + * [in] link_index: link index + * [in] mst_alloc_slots: mst slots to be allotted + * [out] mst_slots_in_use: mst slots in use returned in failure case + * + * @return + * DC_OK if successful, DC_ERROR if failure + ***************************************************************************** + */ +enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, + uint32_t link_index, + uint8_t mst_alloc_slots, + uint8_t *mst_slots_in_use) +{ + union dmub_rb_cmd cmd = {0}; + struct dc_dmub_srv *dmub_srv = dc->ctx->dmub_srv; + + /* prepare MST_ALLOC_SLOTS command */ + cmd.set_mst_alloc_slots.header.type = DMUB_CMD__DPIA; + cmd.set_mst_alloc_slots.header.sub_type = DMUB_CMD__DPIA_MST_ALLOC_SLOTS; + + cmd.set_mst_alloc_slots.mst_slots_control.instance = dc->links[link_index]->ddc_hw_inst; + cmd.set_mst_alloc_slots.mst_slots_control.mst_alloc_slots = mst_alloc_slots; + + if (!dc_dmub_srv_cmd_with_reply_data(dmub_srv, &cmd)) + /* command is not processed by dmub */ + return DC_ERROR_UNEXPECTED; + + /* command processed by dmub, if ret_status is 1 */ + if (cmd.set_config_access.header.ret_status != 1) + /* command processing error */ + return DC_ERROR_UNEXPECTED; + + /* command processed and we have a status of 2, mst not enabled in dpia */ + if (cmd.set_mst_alloc_slots.mst_slots_control.immed_status == 2) + return DC_FAIL_UNSUPPORTED_1; + + /* previously configured mst alloc and used slots did not match */ + if (cmd.set_mst_alloc_slots.mst_slots_control.immed_status == 3) { + *mst_slots_in_use = cmd.set_mst_alloc_slots.mst_slots_control.mst_slots_in_use; + return DC_NOT_SUPPORTED; + } + + return DC_OK; +} + /** * dc_disable_accelerated_mode - disable accelerated mode * @dc: dc structure diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index ca5dc3c168ec..2796bdd17de1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -674,13 +674,13 @@ static void query_hdcp_capability(enum signal_type signal, struct dc_link *link) static void read_current_link_settings_on_detect(struct dc_link *link) { - union lane_count_set lane_count_set = { {0} }; + union lane_count_set lane_count_set = {0}; uint8_t link_bw_set; uint8_t link_rate_set; uint32_t read_dpcd_retry_cnt = 10; enum dc_status status = DC_ERROR_UNEXPECTED; int i; - union max_down_spread max_down_spread = { {0} }; + union max_down_spread max_down_spread = {0}; // Read DPCD 00101h to find out the number of lanes currently set for (i = 0; i < read_dpcd_retry_cnt; i++) { @@ -1660,6 +1660,14 @@ static bool dc_link_construct_legacy(struct dc_link *link, DC_LOG_DC("BIOS object table - ddi_channel_mapping: 0x%04X", link->ddi_channel_mapping.raw); DC_LOG_DC("BIOS object table - chip_caps: %d", link->chip_caps); } + + if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) { + link->bios_forced_drive_settings.VOLTAGE_SWING = + (info->ext_disp_conn_info.fixdpvoltageswing & 0x3); + link->bios_forced_drive_settings.PRE_EMPHASIS = + ((info->ext_disp_conn_info.fixdpvoltageswing >> 2) & 0x3); + } + break; } } @@ -1757,6 +1765,9 @@ static bool dc_link_construct_dpia(struct dc_link *link, link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; + /* Some docks seem to NAK I2C writes to segment pointer with mot=0. */ + link->wa_flags.dp_mot_reset_segment = true; + return true; ddc_create_fail: @@ -1869,8 +1880,13 @@ static enum dc_status enable_link_dp(struct dc_state *state, do_fallback = true; #if defined(CONFIG_DRM_AMD_DC_DCN) + /* + * Temporary w/a to get DP2.0 link rates to work with SST. + * TODO DP2.0 - Workaround: Remove w/a if and when the issue is resolved. + */ if (dp_get_link_encoding_format(&link_settings) == DP_128b_132b_ENCODING && - pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT) { + pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT && + link->dc->debug.set_mst_en_for_sst) { dp_enable_mst_on_sink(link, true); } #endif @@ -1983,51 +1999,6 @@ static enum dc_status enable_link_dp_mst( return enable_link_dp(state, pipe_ctx); } -void blank_all_dp_displays(struct dc *dc, bool hw_init) -{ - unsigned int i, j, fe; - uint8_t dpcd_power_state = '\0'; - enum dc_status status = DC_ERROR_UNEXPECTED; - - for (i = 0; i < dc->link_count; i++) { - enum signal_type signal = dc->links[i]->connector_signal; - - if ((signal == SIGNAL_TYPE_EDP) || - (signal == SIGNAL_TYPE_DISPLAY_PORT)) { - if (hw_init && signal != SIGNAL_TYPE_EDP && dc->links[i]->priv != NULL) { - /* DP 2.0 spec requires that we read LTTPR caps first */ - dp_retrieve_lttpr_cap(dc->links[i]); - /* if any of the displays are lit up turn them off */ - status = core_link_read_dpcd(dc->links[i], DP_SET_POWER, - &dpcd_power_state, sizeof(dpcd_power_state)); - } - - if ((signal != SIGNAL_TYPE_EDP && status == DC_OK && dpcd_power_state == DP_POWER_STATE_D0) || - (!hw_init && dc->links[i]->link_enc && - dc->links[i]->link_enc->funcs->is_dig_enabled(dc->links[i]->link_enc))) { - if (dc->links[i]->link_enc->funcs->get_dig_frontend) { - fe = dc->links[i]->link_enc->funcs->get_dig_frontend(dc->links[i]->link_enc); - if (fe == ENGINE_ID_UNKNOWN) - continue; - - for (j = 0; j < dc->res_pool->stream_enc_count; j++) { - if (fe == dc->res_pool->stream_enc[j]->id) { - dc->res_pool->stream_enc[j]->funcs->dp_blank(dc->links[i], - dc->res_pool->stream_enc[j]); - break; - } - } - } - - if (!dc->links[i]->wa_flags.dp_keep_receiver_powered || - (hw_init && signal != SIGNAL_TYPE_EDP && dc->links[i]->priv != NULL)) - dp_receiver_power_ctrl(dc->links[i], false); - } - } - } - -} - static bool get_ext_hdmi_settings(struct pipe_ctx *pipe_ctx, enum engine_id eng_id, struct ext_hdmi_settings *settings) @@ -2956,8 +2927,8 @@ bool dc_link_set_backlight_level(const struct dc_link *link, return true; } -bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, - bool wait, bool force_static) +bool dc_link_set_psr_allow_active(struct dc_link *link, const bool *allow_active, + bool wait, bool force_static, const unsigned int *power_opts) { struct dc *dc = link->ctx->dc; struct dmcu *dmcu = dc->res_pool->dmcu; @@ -2970,20 +2941,33 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, if (!dc_get_edp_link_panel_inst(dc, link, &panel_inst)) return false; - link->psr_settings.psr_allow_active = allow_active; + /* Set power optimization flag */ + if (power_opts && link->psr_settings.psr_power_opt != *power_opts) { + link->psr_settings.psr_power_opt = *power_opts; + + if (psr != NULL && link->psr_settings.psr_feature_enabled && psr->funcs->psr_set_power_opt) + psr->funcs->psr_set_power_opt(psr, link->psr_settings.psr_power_opt); + } + + /* Enable or Disable PSR */ + if (allow_active && link->psr_settings.psr_allow_active != *allow_active) { + link->psr_settings.psr_allow_active = *allow_active; + #if defined(CONFIG_DRM_AMD_DC_DCN) - if (!allow_active) - dc_z10_restore(dc); + if (!link->psr_settings.psr_allow_active) + dc_z10_restore(dc); #endif - if (psr != NULL && link->psr_settings.psr_feature_enabled) { - if (force_static && psr->funcs->psr_force_static) - psr->funcs->psr_force_static(psr, panel_inst); - psr->funcs->psr_enable(psr, allow_active, wait, panel_inst); - } else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_settings.psr_feature_enabled) - dmcu->funcs->set_psr_enable(dmcu, allow_active, wait); - else - return false; + if (psr != NULL && link->psr_settings.psr_feature_enabled) { + if (force_static && psr->funcs->psr_force_static) + psr->funcs->psr_force_static(psr, panel_inst); + psr->funcs->psr_enable(psr, link->psr_settings.psr_allow_active, wait, panel_inst); + } else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && + link->psr_settings.psr_feature_enabled) + dmcu->funcs->set_psr_enable(dmcu, link->psr_settings.psr_allow_active, wait); + else + return false; + } return true; } @@ -3272,10 +3256,12 @@ static struct fixed31_32 get_pbn_from_timing(struct pipe_ctx *pipe_ctx) static void update_mst_stream_alloc_table( struct dc_link *link, struct stream_encoder *stream_enc, +#if defined(CONFIG_DRM_AMD_DC_DCN) + struct hpo_dp_stream_encoder *hpo_dp_stream_enc, // TODO: Rename stream_enc to dio_stream_enc? +#endif const struct dp_mst_stream_allocation_table *proposed_table) { - struct link_mst_stream_allocation work_table[MAX_CONTROLLER_NUM] = { - { 0 } }; + struct link_mst_stream_allocation work_table[MAX_CONTROLLER_NUM] = { 0 }; struct link_mst_stream_allocation *dc_alloc; int i; @@ -3308,6 +3294,9 @@ static void update_mst_stream_alloc_table( work_table[i].slot_count = proposed_table->stream_allocations[i].slot_count; work_table[i].stream_enc = stream_enc; +#if defined(CONFIG_DRM_AMD_DC_DCN) + work_table[i].hpo_dp_stream_enc = hpo_dp_stream_enc; +#endif } } @@ -3430,11 +3419,15 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx) struct dc_link *link = stream->link; struct link_encoder *link_encoder = NULL; struct stream_encoder *stream_encoder = pipe_ctx->stream_res.stream_enc; +#if defined(CONFIG_DRM_AMD_DC_DCN) + struct hpo_dp_link_encoder *hpo_dp_link_encoder = link->hpo_dp_link_enc; + struct hpo_dp_stream_encoder *hpo_dp_stream_encoder = pipe_ctx->stream_res.hpo_dp_stream_enc; +#endif struct dp_mst_stream_allocation_table proposed_table = {0}; struct fixed31_32 avg_time_slots_per_mtp; struct fixed31_32 pbn; struct fixed31_32 pbn_per_slot; - uint8_t i; + int i; enum act_return_status ret; DC_LOGGER_INIT(link->ctx->logger); @@ -3457,7 +3450,14 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx) &proposed_table, true)) { update_mst_stream_alloc_table( +#if defined(CONFIG_DRM_AMD_DC_DCN) + link, + pipe_ctx->stream_res.stream_enc, + pipe_ctx->stream_res.hpo_dp_stream_enc, + &proposed_table); +#else link, pipe_ctx->stream_res.stream_enc, &proposed_table); +#endif } else DC_LOG_WARNING("Failed to update" @@ -3471,6 +3471,20 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx) link->mst_stream_alloc_table.stream_count); for (i = 0; i < MAX_CONTROLLER_NUM; i++) { +#if defined(CONFIG_DRM_AMD_DC_DCN) + DC_LOG_MST("stream_enc[%d]: %p " + "stream[%d].hpo_dp_stream_enc: %p " + "stream[%d].vcp_id: %d " + "stream[%d].slot_count: %d\n", + i, + (void *) link->mst_stream_alloc_table.stream_allocations[i].stream_enc, + i, + (void *) link->mst_stream_alloc_table.stream_allocations[i].hpo_dp_stream_enc, + i, + link->mst_stream_alloc_table.stream_allocations[i].vcp_id, + i, + link->mst_stream_alloc_table.stream_allocations[i].slot_count); +#else DC_LOG_MST("stream_enc[%d]: %p " "stream[%d].vcp_id: %d " "stream[%d].slot_count: %d\n", @@ -3480,14 +3494,47 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx) link->mst_stream_alloc_table.stream_allocations[i].vcp_id, i, link->mst_stream_alloc_table.stream_allocations[i].slot_count); +#endif } ASSERT(proposed_table.stream_count > 0); + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + static enum dc_status status; + uint8_t mst_alloc_slots = 0, prev_mst_slots_in_use = 0xFF; + + for (i = 0; i < link->mst_stream_alloc_table.stream_count; i++) + mst_alloc_slots += link->mst_stream_alloc_table.stream_allocations[i].slot_count; + + status = dc_process_dmub_set_mst_slots(link->dc, link->link_index, + mst_alloc_slots, &prev_mst_slots_in_use); + ASSERT(status == DC_OK); + DC_LOG_MST("dpia : status[%d]: alloc_slots[%d]: used_slots[%d]\n", + status, mst_alloc_slots, prev_mst_slots_in_use); + } + /* program DP source TX for payload */ +#if defined(CONFIG_DRM_AMD_DC_DCN) + switch (dp_get_link_encoding_format(&link->cur_link_settings)) { + case DP_8b_10b_ENCODING: + link_encoder->funcs->update_mst_stream_allocation_table( + link_encoder, + &link->mst_stream_alloc_table); + break; + case DP_128b_132b_ENCODING: + hpo_dp_link_encoder->funcs->update_stream_allocation_table( + hpo_dp_link_encoder, + &link->mst_stream_alloc_table); + break; + case DP_UNKNOWN_ENCODING: + DC_LOG_ERROR("Failure: unknown encoding format\n"); + return DC_ERROR_UNEXPECTED; + } +#else link_encoder->funcs->update_mst_stream_allocation_table( link_encoder, &link->mst_stream_alloc_table); +#endif /* send down message */ ret = dm_helpers_dp_mst_poll_for_allocation_change_trigger( @@ -3510,23 +3557,205 @@ enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx) pbn = get_pbn_from_timing(pipe_ctx); avg_time_slots_per_mtp = dc_fixpt_div(pbn, pbn_per_slot); +#if defined(CONFIG_DRM_AMD_DC_DCN) + switch (dp_get_link_encoding_format(&link->cur_link_settings)) { + case DP_8b_10b_ENCODING: + stream_encoder->funcs->set_throttled_vcp_size( + stream_encoder, + avg_time_slots_per_mtp); + break; + case DP_128b_132b_ENCODING: + hpo_dp_link_encoder->funcs->set_throttled_vcp_size( + hpo_dp_link_encoder, + hpo_dp_stream_encoder->inst, + avg_time_slots_per_mtp); + break; + case DP_UNKNOWN_ENCODING: + DC_LOG_ERROR("Failure: unknown encoding format\n"); + return DC_ERROR_UNEXPECTED; + } +#else stream_encoder->funcs->set_throttled_vcp_size( stream_encoder, avg_time_slots_per_mtp); +#endif return DC_OK; } +#if defined(CONFIG_DRM_AMD_DC_DCN) +enum dc_status dc_link_reduce_mst_payload(struct pipe_ctx *pipe_ctx, uint32_t bw_in_kbps) +{ + struct dc_stream_state *stream = pipe_ctx->stream; + struct dc_link *link = stream->link; + struct fixed31_32 avg_time_slots_per_mtp; + struct fixed31_32 pbn; + struct fixed31_32 pbn_per_slot; + struct link_encoder *link_encoder = link->link_enc; + struct stream_encoder *stream_encoder = pipe_ctx->stream_res.stream_enc; + struct dp_mst_stream_allocation_table proposed_table = {0}; + uint8_t i; + enum act_return_status ret; + DC_LOGGER_INIT(link->ctx->logger); + + /* decrease throttled vcp size */ + pbn_per_slot = get_pbn_per_slot(stream); + pbn = get_pbn_from_bw_in_kbps(bw_in_kbps); + avg_time_slots_per_mtp = dc_fixpt_div(pbn, pbn_per_slot); + + stream_encoder->funcs->set_throttled_vcp_size( + stream_encoder, + avg_time_slots_per_mtp); + + /* send ALLOCATE_PAYLOAD sideband message with updated pbn */ + dm_helpers_dp_mst_send_payload_allocation( + stream->ctx, + stream, + true); + + /* notify immediate branch device table update */ + if (dm_helpers_dp_mst_write_payload_allocation_table( + stream->ctx, + stream, + &proposed_table, + true)) { + /* update mst stream allocation table software state */ + update_mst_stream_alloc_table( + link, + pipe_ctx->stream_res.stream_enc, + pipe_ctx->stream_res.hpo_dp_stream_enc, + &proposed_table); + } else { + DC_LOG_WARNING("Failed to update" + "MST allocation table for" + "pipe idx:%d\n", + pipe_ctx->pipe_idx); + } + + DC_LOG_MST("%s " + "stream_count: %d: \n ", + __func__, + link->mst_stream_alloc_table.stream_count); + + for (i = 0; i < MAX_CONTROLLER_NUM; i++) { + DC_LOG_MST("stream_enc[%d]: %p " + "stream[%d].vcp_id: %d " + "stream[%d].slot_count: %d\n", + i, + (void *) link->mst_stream_alloc_table.stream_allocations[i].stream_enc, + i, + link->mst_stream_alloc_table.stream_allocations[i].vcp_id, + i, + link->mst_stream_alloc_table.stream_allocations[i].slot_count); + } + + ASSERT(proposed_table.stream_count > 0); + + /* update mst stream allocation table hardware state */ + link_encoder->funcs->update_mst_stream_allocation_table( + link_encoder, + &link->mst_stream_alloc_table); + + /* poll for immediate branch device ACT handled */ + ret = dm_helpers_dp_mst_poll_for_allocation_change_trigger( + stream->ctx, + stream); + + return DC_OK; +} + +enum dc_status dc_link_increase_mst_payload(struct pipe_ctx *pipe_ctx, uint32_t bw_in_kbps) +{ + struct dc_stream_state *stream = pipe_ctx->stream; + struct dc_link *link = stream->link; + struct fixed31_32 avg_time_slots_per_mtp; + struct fixed31_32 pbn; + struct fixed31_32 pbn_per_slot; + struct link_encoder *link_encoder = link->link_enc; + struct stream_encoder *stream_encoder = pipe_ctx->stream_res.stream_enc; + struct dp_mst_stream_allocation_table proposed_table = {0}; + uint8_t i; + enum act_return_status ret; + DC_LOGGER_INIT(link->ctx->logger); + + /* notify immediate branch device table update */ + if (dm_helpers_dp_mst_write_payload_allocation_table( + stream->ctx, + stream, + &proposed_table, + true)) { + /* update mst stream allocation table software state */ + update_mst_stream_alloc_table( + link, + pipe_ctx->stream_res.stream_enc, + pipe_ctx->stream_res.hpo_dp_stream_enc, + &proposed_table); + } + + DC_LOG_MST("%s " + "stream_count: %d: \n ", + __func__, + link->mst_stream_alloc_table.stream_count); + + for (i = 0; i < MAX_CONTROLLER_NUM; i++) { + DC_LOG_MST("stream_enc[%d]: %p " + "stream[%d].vcp_id: %d " + "stream[%d].slot_count: %d\n", + i, + (void *) link->mst_stream_alloc_table.stream_allocations[i].stream_enc, + i, + link->mst_stream_alloc_table.stream_allocations[i].vcp_id, + i, + link->mst_stream_alloc_table.stream_allocations[i].slot_count); + } + + ASSERT(proposed_table.stream_count > 0); + + /* update mst stream allocation table hardware state */ + link_encoder->funcs->update_mst_stream_allocation_table( + link_encoder, + &link->mst_stream_alloc_table); + + /* poll for immediate branch device ACT handled */ + ret = dm_helpers_dp_mst_poll_for_allocation_change_trigger( + stream->ctx, + stream); + + if (ret != ACT_LINK_LOST) { + /* send ALLOCATE_PAYLOAD sideband message with updated pbn */ + dm_helpers_dp_mst_send_payload_allocation( + stream->ctx, + stream, + true); + } + + /* increase throttled vcp size */ + pbn = get_pbn_from_bw_in_kbps(bw_in_kbps); + pbn_per_slot = get_pbn_per_slot(stream); + avg_time_slots_per_mtp = dc_fixpt_div(pbn, pbn_per_slot); + + stream_encoder->funcs->set_throttled_vcp_size( + stream_encoder, + avg_time_slots_per_mtp); + + return DC_OK; +} +#endif + static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) { struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; struct link_encoder *link_encoder = NULL; struct stream_encoder *stream_encoder = pipe_ctx->stream_res.stream_enc; +#if defined(CONFIG_DRM_AMD_DC_DCN) + struct hpo_dp_link_encoder *hpo_dp_link_encoder = link->hpo_dp_link_enc; + struct hpo_dp_stream_encoder *hpo_dp_stream_encoder = pipe_ctx->stream_res.hpo_dp_stream_enc; +#endif struct dp_mst_stream_allocation_table proposed_table = {0}; struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0); - uint8_t i; + int i; bool mst_mode = (link->type == dc_connection_mst_branch); DC_LOGGER_INIT(link->ctx->logger); @@ -3545,9 +3774,28 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) */ /* slot X.Y */ +#if defined(CONFIG_DRM_AMD_DC_DCN) + switch (dp_get_link_encoding_format(&link->cur_link_settings)) { + case DP_8b_10b_ENCODING: + stream_encoder->funcs->set_throttled_vcp_size( + stream_encoder, + avg_time_slots_per_mtp); + break; + case DP_128b_132b_ENCODING: + hpo_dp_link_encoder->funcs->set_throttled_vcp_size( + hpo_dp_link_encoder, + hpo_dp_stream_encoder->inst, + avg_time_slots_per_mtp); + break; + case DP_UNKNOWN_ENCODING: + DC_LOG_ERROR("Failure: unknown encoding format\n"); + return DC_ERROR_UNEXPECTED; + } +#else stream_encoder->funcs->set_throttled_vcp_size( stream_encoder, avg_time_slots_per_mtp); +#endif /* TODO: which component is responsible for remove payload table? */ if (mst_mode) { @@ -3557,8 +3805,16 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) &proposed_table, false)) { +#if defined(CONFIG_DRM_AMD_DC_DCN) + update_mst_stream_alloc_table( + link, + pipe_ctx->stream_res.stream_enc, + pipe_ctx->stream_res.hpo_dp_stream_enc, + &proposed_table); +#else update_mst_stream_alloc_table( link, pipe_ctx->stream_res.stream_enc, &proposed_table); +#endif } else { DC_LOG_WARNING("Failed to update" @@ -3574,6 +3830,20 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) link->mst_stream_alloc_table.stream_count); for (i = 0; i < MAX_CONTROLLER_NUM; i++) { +#if defined(CONFIG_DRM_AMD_DC_DCN) + DC_LOG_MST("stream_enc[%d]: %p " + "stream[%d].hpo_dp_stream_enc: %p " + "stream[%d].vcp_id: %d " + "stream[%d].slot_count: %d\n", + i, + (void *) link->mst_stream_alloc_table.stream_allocations[i].stream_enc, + i, + (void *) link->mst_stream_alloc_table.stream_allocations[i].hpo_dp_stream_enc, + i, + link->mst_stream_alloc_table.stream_allocations[i].vcp_id, + i, + link->mst_stream_alloc_table.stream_allocations[i].slot_count); +#else DC_LOG_MST("stream_enc[%d]: %p " "stream[%d].vcp_id: %d " "stream[%d].slot_count: %d\n", @@ -3583,11 +3853,44 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) link->mst_stream_alloc_table.stream_allocations[i].vcp_id, i, link->mst_stream_alloc_table.stream_allocations[i].slot_count); +#endif } + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + enum dc_status status; + uint8_t mst_alloc_slots = 0, prev_mst_slots_in_use = 0xFF; + + for (i = 0; i < link->mst_stream_alloc_table.stream_count; i++) + mst_alloc_slots += link->mst_stream_alloc_table.stream_allocations[i].slot_count; + + status = dc_process_dmub_set_mst_slots(link->dc, link->link_index, + mst_alloc_slots, &prev_mst_slots_in_use); + ASSERT(status != DC_NOT_SUPPORTED); + DC_LOG_MST("dpia : status[%d]: alloc_slots[%d]: used_slots[%d]\n", + status, mst_alloc_slots, prev_mst_slots_in_use); + } + +#if defined(CONFIG_DRM_AMD_DC_DCN) + switch (dp_get_link_encoding_format(&link->cur_link_settings)) { + case DP_8b_10b_ENCODING: + link_encoder->funcs->update_mst_stream_allocation_table( + link_encoder, + &link->mst_stream_alloc_table); + break; + case DP_128b_132b_ENCODING: + hpo_dp_link_encoder->funcs->update_stream_allocation_table( + hpo_dp_link_encoder, + &link->mst_stream_alloc_table); + break; + case DP_UNKNOWN_ENCODING: + DC_LOG_ERROR("Failure: unknown encoding format\n"); + return DC_ERROR_UNEXPECTED; + } +#else link_encoder->funcs->update_mst_stream_allocation_table( link_encoder, &link->mst_stream_alloc_table); +#endif if (mst_mode) { dm_helpers_dp_mst_poll_for_allocation_change_trigger( @@ -3610,6 +3913,9 @@ static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) struct cp_psp *cp_psp = &pipe_ctx->stream->ctx->cp_psp; #if defined(CONFIG_DRM_AMD_DC_DCN) struct link_encoder *link_enc = NULL; + struct dc_state *state = pipe_ctx->stream->ctx->dc->current_state; + struct link_enc_assignment link_enc_assign; + int i; #endif if (cp_psp && cp_psp->funcs.update_stream_config) { @@ -3623,9 +3929,72 @@ static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) config.dig_be = pipe_ctx->stream->link->link_enc_hw_inst; #if defined(CONFIG_DRM_AMD_DC_DCN) config.stream_enc_idx = pipe_ctx->stream_res.stream_enc->id - ENGINE_ID_DIGA; - if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_PHY) { + + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_PHY || + pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { link_enc = pipe_ctx->stream->link->link_enc; + config.dio_output_type = pipe_ctx->stream->link->ep_type; + config.dio_output_idx = link_enc->transmitter - TRANSMITTER_UNIPHY_A; + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_PHY) + link_enc = pipe_ctx->stream->link->link_enc; + else if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + if (pipe_ctx->stream->link->dc->res_pool->funcs->link_encs_assign) { + link_enc = link_enc_cfg_get_link_enc_used_by_stream( + pipe_ctx->stream->ctx->dc, + pipe_ctx->stream); + } + // Initialize PHY ID with ABCDE - 01234 mapping except when it is B0 config.phy_idx = link_enc->transmitter - TRANSMITTER_UNIPHY_A; + + //look up the link_enc_assignment for the current pipe_ctx + for (i = 0; i < state->stream_count; i++) { + if (pipe_ctx->stream == state->streams[i]) { + link_enc_assign = state->res_ctx.link_enc_cfg_ctx.link_enc_assignments[i]; + } + } + // Add flag to guard new A0 DIG mapping + if (pipe_ctx->stream->ctx->dc->enable_c20_dtm_b0 == true) { + config.dig_be = link_enc_assign.eng_id; + config.dio_output_type = pipe_ctx->stream->link->ep_type; + config.dio_output_idx = link_enc->transmitter - TRANSMITTER_UNIPHY_A; + } else { + config.dio_output_type = 0; + config.dio_output_idx = 0; + } + + // Add flag to guard B0 implementation + if (pipe_ctx->stream->ctx->dc->enable_c20_dtm_b0 == true && + link_enc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) { + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + link_enc = link_enc_assign.stream->link_enc; + + // enum ID 1-4 maps to DPIA PHY ID 0-3 + config.phy_idx = link_enc_assign.ep_id.link_id.enum_id - ENUM_ID_1; + } else { // for non DPIA mode over B0, ABCDE maps to 01564 + + switch (link_enc->transmitter) { + case TRANSMITTER_UNIPHY_A: + config.phy_idx = 0; + break; + case TRANSMITTER_UNIPHY_B: + config.phy_idx = 1; + break; + case TRANSMITTER_UNIPHY_C: + config.phy_idx = 5; + break; + case TRANSMITTER_UNIPHY_D: + config.phy_idx = 6; + break; + case TRANSMITTER_UNIPHY_E: + config.phy_idx = 4; + break; + default: + config.phy_idx = 0; + break; + } + + } + } } else if (pipe_ctx->stream->link->dc->res_pool->funcs->link_encs_assign) { link_enc = link_enc_cfg_get_link_enc_used_by_stream( pipe_ctx->stream->ctx->dc, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index b0f1cd7268c8..60539b1f2a80 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -554,6 +554,7 @@ bool dal_ddc_service_query_ddc_data( payload.address = address; payload.reply = NULL; payload.defer_delay = get_defer_delay(ddc); + payload.write_status_update = false; if (write_size != 0) { payload.write = true; @@ -625,24 +626,24 @@ bool dal_ddc_submit_aux_command(struct ddc_service *ddc, do { struct aux_payload current_payload; bool is_end_of_payload = (retrieved + DEFAULT_AUX_MAX_DATA_SIZE) >= - payload->length; + payload->length ? true : false; + uint32_t payload_length = is_end_of_payload ? + payload->length - retrieved : DEFAULT_AUX_MAX_DATA_SIZE; current_payload.address = payload->address; current_payload.data = &payload->data[retrieved]; current_payload.defer_delay = payload->defer_delay; current_payload.i2c_over_aux = payload->i2c_over_aux; - current_payload.length = is_end_of_payload ? - payload->length - retrieved : DEFAULT_AUX_MAX_DATA_SIZE; - /* set mot (middle of transaction) to false - * if it is the last payload - */ + current_payload.length = payload_length; + /* set mot (middle of transaction) to false if it is the last payload */ current_payload.mot = is_end_of_payload ? payload->mot:true; + current_payload.write_status_update = false; current_payload.reply = payload->reply; current_payload.write = payload->write; ret = dc_link_aux_transfer_with_retries(ddc, ¤t_payload); - retrieved += current_payload.length; + retrieved += payload_length; } while (retrieved < payload->length && ret == true); return ret; @@ -763,7 +764,7 @@ void dal_ddc_service_read_scdc_data(struct ddc_service *ddc_service) dal_ddc_service_query_ddc_data(ddc_service, slave_address, &offset, sizeof(offset), &tmds_config, sizeof(tmds_config)); if (tmds_config & 0x1) { - union hdmi_scdc_status_flags_data status_data = { {0} }; + union hdmi_scdc_status_flags_data status_data = {0}; uint8_t scramble_status = 0; offset = HDMI_SCDC_SCRAMBLER_STATUS; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 54662d74c65a..cc25ba0ec7db 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -106,6 +106,10 @@ static bool decide_fallback_link_setting( static struct dc_link_settings get_common_supported_link_settings( struct dc_link_settings link_setting_a, struct dc_link_settings link_setting_b); +static void maximize_lane_settings(const struct link_training_settings *lt_settings, + struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]); +static void override_lane_settings(const struct link_training_settings *lt_settings, + struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]); static uint32_t get_cr_training_aux_rd_interval(struct dc_link *link, const struct dc_link_settings *link_settings) @@ -259,7 +263,7 @@ static void dpcd_set_training_pattern( struct dc_link *link, enum dc_dp_training_pattern training_pattern) { - union dpcd_training_pattern dpcd_pattern = { {0} }; + union dpcd_training_pattern dpcd_pattern = {0}; dpcd_pattern.v1_4.TRAINING_PATTERN_SET = dc_dp_training_pattern_to_dpcd_training_pattern( @@ -401,8 +405,8 @@ enum dc_status dpcd_set_link_settings( uint8_t rate; enum dc_status status; - union down_spread_ctrl downspread = { {0} }; - union lane_count_set lane_count_set = { {0} }; + union down_spread_ctrl downspread = {0}; + union lane_count_set lane_count_set = {0}; downspread.raw = (uint8_t) (lt_settings->link_settings.link_spread); @@ -515,12 +519,10 @@ static void dpcd_set_lt_pattern_and_lane_settings( enum dc_dp_training_pattern pattern, uint32_t offset) { - union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = { { {0} } }; - uint32_t dpcd_base_lt_offset; uint8_t dpcd_lt_buffer[5] = {0}; - union dpcd_training_pattern dpcd_pattern = { {0} }; + union dpcd_training_pattern dpcd_pattern = { 0 }; uint32_t size_in_bytes; bool edp_workaround = false; /* TODO link_prop.INTERNAL */ dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET; @@ -554,16 +556,14 @@ static void dpcd_set_lt_pattern_and_lane_settings( dpcd_pattern.v1_4.TRAINING_PATTERN_SET); } - dp_hw_to_dpcd_lane_settings(lt_settings, lt_settings->lane_settings, dpcd_lane); - /* concatenate everything into one buffer*/ - - size_in_bytes = lt_settings->link_settings.lane_count * sizeof(dpcd_lane[0]); + size_in_bytes = lt_settings->link_settings.lane_count * + sizeof(lt_settings->dpcd_lane_settings[0]); // 0x00103 - 0x00102 memmove( &dpcd_lt_buffer[DP_TRAINING_LANE0_SET - DP_TRAINING_PATTERN_SET], - dpcd_lane, + lt_settings->dpcd_lane_settings, size_in_bytes); if (is_repeater(link, offset)) { @@ -575,7 +575,7 @@ static void dpcd_set_lt_pattern_and_lane_settings( __func__, offset, dpcd_base_lt_offset, - dpcd_lane[0].tx_ffe.PRESET_VALUE); + lt_settings->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); else if (dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING) #endif @@ -584,10 +584,10 @@ static void dpcd_set_lt_pattern_and_lane_settings( __func__, offset, dpcd_base_lt_offset, - dpcd_lane[0].bits.VOLTAGE_SWING_SET, - dpcd_lane[0].bits.PRE_EMPHASIS_SET, - dpcd_lane[0].bits.MAX_SWING_REACHED, - dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED); + lt_settings->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET, + lt_settings->dpcd_lane_settings[0].bits.PRE_EMPHASIS_SET, + lt_settings->dpcd_lane_settings[0].bits.MAX_SWING_REACHED, + lt_settings->dpcd_lane_settings[0].bits.MAX_PRE_EMPHASIS_REACHED); } else { #if defined(CONFIG_DRM_AMD_DC_DCN) if (dp_get_link_encoding_format(<_settings->link_settings) == @@ -595,17 +595,17 @@ static void dpcd_set_lt_pattern_and_lane_settings( DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X TX_FFE_PRESET_VALUE = %x\n", __func__, dpcd_base_lt_offset, - dpcd_lane[0].tx_ffe.PRESET_VALUE); + lt_settings->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); else if (dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING) #endif DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X VS set = %x PE set = %x max VS Reached = %x max PE Reached = %x\n", __func__, dpcd_base_lt_offset, - dpcd_lane[0].bits.VOLTAGE_SWING_SET, - dpcd_lane[0].bits.PRE_EMPHASIS_SET, - dpcd_lane[0].bits.MAX_SWING_REACHED, - dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED); + lt_settings->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET, + lt_settings->dpcd_lane_settings[0].bits.PRE_EMPHASIS_SET, + lt_settings->dpcd_lane_settings[0].bits.MAX_SWING_REACHED, + lt_settings->dpcd_lane_settings[0].bits.MAX_PRE_EMPHASIS_REACHED); } if (edp_workaround) { /* for eDP write in 2 parts because the 5-byte burst is @@ -620,7 +620,7 @@ static void dpcd_set_lt_pattern_and_lane_settings( core_link_write_dpcd( link, DP_TRAINING_LANE0_SET, - (uint8_t *)(dpcd_lane), + (uint8_t *)(lt_settings->dpcd_lane_settings), size_in_bytes); #if defined(CONFIG_DRM_AMD_DC_DCN) @@ -711,34 +711,44 @@ void dp_hw_to_dpcd_lane_settings( } } -void dp_update_drive_settings( - struct link_training_settings *dest, - struct link_training_settings src) +void dp_decide_lane_settings( + const struct link_training_settings *lt_settings, + const union lane_adjust ln_adjust[LANE_COUNT_DP_MAX], + struct dc_lane_settings hw_lane_settings[LANE_COUNT_DP_MAX], + union dpcd_training_lane dpcd_lane_settings[LANE_COUNT_DP_MAX]) { uint32_t lane; - for (lane = 0; lane < src.link_settings.lane_count; lane++) { - if (dest->voltage_swing == NULL) - dest->lane_settings[lane].VOLTAGE_SWING = src.lane_settings[lane].VOLTAGE_SWING; - else - dest->lane_settings[lane].VOLTAGE_SWING = *dest->voltage_swing; - - if (dest->pre_emphasis == NULL) - dest->lane_settings[lane].PRE_EMPHASIS = src.lane_settings[lane].PRE_EMPHASIS; - else - dest->lane_settings[lane].PRE_EMPHASIS = *dest->pre_emphasis; - - if (dest->post_cursor2 == NULL) - dest->lane_settings[lane].POST_CURSOR2 = src.lane_settings[lane].POST_CURSOR2; - else - dest->lane_settings[lane].POST_CURSOR2 = *dest->post_cursor2; + for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) { + if (dp_get_link_encoding_format(<_settings->link_settings) == + DP_8b_10b_ENCODING) { + hw_lane_settings[lane].VOLTAGE_SWING = + (enum dc_voltage_swing)(ln_adjust[lane].bits. + VOLTAGE_SWING_LANE); + hw_lane_settings[lane].PRE_EMPHASIS = + (enum dc_pre_emphasis)(ln_adjust[lane].bits. + PRE_EMPHASIS_LANE); + } #if defined(CONFIG_DRM_AMD_DC_DCN) - if (dest->ffe_preset == NULL) - dest->lane_settings[lane].FFE_PRESET = src.lane_settings[lane].FFE_PRESET; - else - dest->lane_settings[lane].FFE_PRESET = *dest->ffe_preset; + else if (dp_get_link_encoding_format(<_settings->link_settings) == + DP_128b_132b_ENCODING) { + hw_lane_settings[lane].FFE_PRESET.raw = + ln_adjust[lane].tx_ffe.PRESET_VALUE; + } #endif } + dp_hw_to_dpcd_lane_settings(lt_settings, hw_lane_settings, dpcd_lane_settings); + + if (lt_settings->disallow_per_lane_settings) { + /* we find the maximum of the requested settings across all lanes*/ + /* and set this maximum for all lanes*/ + maximize_lane_settings(lt_settings, hw_lane_settings); + override_lane_settings(lt_settings, hw_lane_settings); + + if (lt_settings->always_match_dpcd_with_hw_lane_settings) + dp_hw_to_dpcd_lane_settings(lt_settings, hw_lane_settings, dpcd_lane_settings); + } + } static uint8_t get_nibble_at_index(const uint8_t *buf, @@ -768,55 +778,29 @@ static enum dc_pre_emphasis get_max_pre_emphasis_for_voltage_swing( } -static void find_max_drive_settings( - const struct link_training_settings *link_training_setting, - struct link_training_settings *max_lt_setting) +static void maximize_lane_settings(const struct link_training_settings *lt_settings, + struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]) { uint32_t lane; struct dc_lane_settings max_requested; - max_requested.VOLTAGE_SWING = - link_training_setting-> - lane_settings[0].VOLTAGE_SWING; - max_requested.PRE_EMPHASIS = - link_training_setting-> - lane_settings[0].PRE_EMPHASIS; - /*max_requested.postCursor2 = - * link_training_setting->laneSettings[0].postCursor2;*/ + max_requested.VOLTAGE_SWING = lane_settings[0].VOLTAGE_SWING; + max_requested.PRE_EMPHASIS = lane_settings[0].PRE_EMPHASIS; #if defined(CONFIG_DRM_AMD_DC_DCN) - max_requested.FFE_PRESET = - link_training_setting->lane_settings[0].FFE_PRESET; + max_requested.FFE_PRESET = lane_settings[0].FFE_PRESET; #endif /* Determine what the maximum of the requested settings are*/ - for (lane = 1; lane < link_training_setting->link_settings.lane_count; - lane++) { - if (link_training_setting->lane_settings[lane].VOLTAGE_SWING > - max_requested.VOLTAGE_SWING) + for (lane = 1; lane < lt_settings->link_settings.lane_count; lane++) { + if (lane_settings[lane].VOLTAGE_SWING > max_requested.VOLTAGE_SWING) + max_requested.VOLTAGE_SWING = lane_settings[lane].VOLTAGE_SWING; - max_requested.VOLTAGE_SWING = - link_training_setting-> - lane_settings[lane].VOLTAGE_SWING; - - if (link_training_setting->lane_settings[lane].PRE_EMPHASIS > - max_requested.PRE_EMPHASIS) - max_requested.PRE_EMPHASIS = - link_training_setting-> - lane_settings[lane].PRE_EMPHASIS; - - /* - if (link_training_setting->laneSettings[lane].postCursor2 > - max_requested.postCursor2) - { - max_requested.postCursor2 = - link_training_setting->laneSettings[lane].postCursor2; - } - */ + if (lane_settings[lane].PRE_EMPHASIS > max_requested.PRE_EMPHASIS) + max_requested.PRE_EMPHASIS = lane_settings[lane].PRE_EMPHASIS; #if defined(CONFIG_DRM_AMD_DC_DCN) - if (link_training_setting->lane_settings[lane].FFE_PRESET.settings.level > + if (lane_settings[lane].FFE_PRESET.settings.level > max_requested.FFE_PRESET.settings.level) max_requested.FFE_PRESET.settings.level = - link_training_setting-> lane_settings[lane].FFE_PRESET.settings.level; #endif } @@ -828,10 +812,6 @@ static void find_max_drive_settings( if (max_requested.PRE_EMPHASIS > PRE_EMPHASIS_MAX_LEVEL) max_requested.PRE_EMPHASIS = PRE_EMPHASIS_MAX_LEVEL; - /* - if (max_requested.postCursor2 > PostCursor2_MaxLevel) - max_requested.postCursor2 = PostCursor2_MaxLevel; - */ #if defined(CONFIG_DRM_AMD_DC_DCN) if (max_requested.FFE_PRESET.settings.level > DP_FFE_PRESET_MAX_LEVEL) max_requested.FFE_PRESET.settings.level = DP_FFE_PRESET_MAX_LEVEL; @@ -845,61 +825,58 @@ static void find_max_drive_settings( get_max_pre_emphasis_for_voltage_swing( max_requested.VOLTAGE_SWING); - /* - * Post Cursor2 levels are completely independent from - * pre-emphasis (Post Cursor1) levels. But Post Cursor2 levels - * can only be applied to each allowable combination of voltage - * swing and pre-emphasis levels */ - /* if ( max_requested.postCursor2 > - * getMaxPostCursor2ForVoltageSwing(max_requested.voltageSwing)) - * max_requested.postCursor2 = - * getMaxPostCursor2ForVoltageSwing(max_requested.voltageSwing); - */ - - max_lt_setting->link_settings.link_rate = - link_training_setting->link_settings.link_rate; - max_lt_setting->link_settings.lane_count = - link_training_setting->link_settings.lane_count; - max_lt_setting->link_settings.link_spread = - link_training_setting->link_settings.link_spread; - - for (lane = 0; lane < - link_training_setting->link_settings.lane_count; - lane++) { - max_lt_setting->lane_settings[lane].VOLTAGE_SWING = - max_requested.VOLTAGE_SWING; - max_lt_setting->lane_settings[lane].PRE_EMPHASIS = - max_requested.PRE_EMPHASIS; - /*max_lt_setting->laneSettings[lane].postCursor2 = - * max_requested.postCursor2; - */ + for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) { + lane_settings[lane].VOLTAGE_SWING = max_requested.VOLTAGE_SWING; + lane_settings[lane].PRE_EMPHASIS = max_requested.PRE_EMPHASIS; #if defined(CONFIG_DRM_AMD_DC_DCN) - max_lt_setting->lane_settings[lane].FFE_PRESET = - max_requested.FFE_PRESET; + lane_settings[lane].FFE_PRESET = max_requested.FFE_PRESET; #endif } - } -enum dc_status dp_get_lane_status_and_drive_settings( +static void override_lane_settings(const struct link_training_settings *lt_settings, + struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]) +{ + uint32_t lane; + + if (lt_settings->voltage_swing == NULL && + lt_settings->pre_emphasis == NULL && +#if defined(CONFIG_DRM_AMD_DC_DCN) + lt_settings->ffe_preset == NULL && +#endif + lt_settings->post_cursor2 == NULL) + + return; + + for (lane = 1; lane < LANE_COUNT_DP_MAX; lane++) { + if (lt_settings->voltage_swing) + lane_settings[lane].VOLTAGE_SWING = *lt_settings->voltage_swing; + if (lt_settings->pre_emphasis) + lane_settings[lane].PRE_EMPHASIS = *lt_settings->pre_emphasis; + if (lt_settings->post_cursor2) + lane_settings[lane].POST_CURSOR2 = *lt_settings->post_cursor2; +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (lt_settings->ffe_preset) + lane_settings[lane].FFE_PRESET = *lt_settings->ffe_preset; +#endif + } +} + +enum dc_status dp_get_lane_status_and_lane_adjust( struct dc_link *link, const struct link_training_settings *link_training_setting, - union lane_status *ln_status, - union lane_align_status_updated *ln_status_updated, - struct link_training_settings *req_settings, + union lane_status ln_status[LANE_COUNT_DP_MAX], + union lane_align_status_updated *ln_align, + union lane_adjust ln_adjust[LANE_COUNT_DP_MAX], uint32_t offset) { unsigned int lane01_status_address = DP_LANE0_1_STATUS; uint8_t lane_adjust_offset = 4; unsigned int lane01_adjust_address; uint8_t dpcd_buf[6] = {0}; - union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; - struct link_training_settings request_settings = { {0} }; uint32_t lane; enum dc_status status; - memset(req_settings, '\0', sizeof(struct link_training_settings)); - if (is_repeater(link, offset)) { lane01_status_address = DP_LANE0_1_STATUS_PHY_REPEATER1 + @@ -919,11 +896,11 @@ enum dc_status dp_get_lane_status_and_drive_settings( ln_status[lane].raw = get_nibble_at_index(&dpcd_buf[0], lane); - dpcd_lane_adjust[lane].raw = + ln_adjust[lane].raw = get_nibble_at_index(&dpcd_buf[lane_adjust_offset], lane); } - ln_status_updated->raw = dpcd_buf[2]; + ln_align->raw = dpcd_buf[2]; if (is_repeater(link, offset)) { DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n" @@ -962,55 +939,6 @@ enum dc_status dp_get_lane_status_and_drive_settings( dpcd_buf[lane_adjust_offset + 1]); } - /*copy to req_settings*/ - request_settings.link_settings.lane_count = - link_training_setting->link_settings.lane_count; - request_settings.link_settings.link_rate = - link_training_setting->link_settings.link_rate; - request_settings.link_settings.link_spread = - link_training_setting->link_settings.link_spread; - - for (lane = 0; lane < - (uint32_t)(link_training_setting->link_settings.lane_count); - lane++) { - -#if defined(CONFIG_DRM_AMD_DC_DCN) - if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_128b_132b_ENCODING) { - request_settings.lane_settings[lane].FFE_PRESET.raw = - dpcd_lane_adjust[lane].tx_ffe.PRESET_VALUE; - } else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_8b_10b_ENCODING) { - request_settings.lane_settings[lane].VOLTAGE_SWING = - (enum dc_voltage_swing)(dpcd_lane_adjust[lane].bits. - VOLTAGE_SWING_LANE); - request_settings.lane_settings[lane].PRE_EMPHASIS = - (enum dc_pre_emphasis)(dpcd_lane_adjust[lane].bits. - PRE_EMPHASIS_LANE); - } -#else - request_settings.lane_settings[lane].VOLTAGE_SWING = - (enum dc_voltage_swing)(dpcd_lane_adjust[lane].bits. - VOLTAGE_SWING_LANE); - request_settings.lane_settings[lane].PRE_EMPHASIS = - (enum dc_pre_emphasis)(dpcd_lane_adjust[lane].bits. - PRE_EMPHASIS_LANE); -#endif - } - - /*Note: for postcursor2, read adjusted - * postcursor2 settings from*/ - /*DpcdAddress_AdjustRequestPostCursor2 = - *0x020C (not implemented yet)*/ - - /* we find the maximum of the requested settings across all lanes*/ - /* and set this maximum for all lanes*/ - find_max_drive_settings(&request_settings, req_settings); - - /* if post cursor 2 is needed in the future, - * read DpcdAddress_AdjustRequestPostCursor2 = 0x020C - */ - return status; } @@ -1019,7 +947,6 @@ enum dc_status dpcd_set_lane_settings( const struct link_training_settings *link_training_setting, uint32_t offset) { - union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = {{{0}}}; unsigned int lane0_set_address; enum dc_status status; @@ -1029,34 +956,11 @@ enum dc_status dpcd_set_lane_settings( lane0_set_address = DP_TRAINING_LANE0_SET_PHY_REPEATER1 + ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1)); - dp_hw_to_dpcd_lane_settings(link_training_setting, - link_training_setting->lane_settings, - dpcd_lane); - status = core_link_write_dpcd(link, lane0_set_address, - (uint8_t *)(dpcd_lane), + (uint8_t *)(link_training_setting->dpcd_lane_settings), link_training_setting->link_settings.lane_count); - /* - if (LTSettings.link.rate == LinkRate_High2) - { - DpcdTrainingLaneSet2 dpcd_lane2[lane_count_DPMax] = {0}; - for ( uint32_t lane = 0; - lane < lane_count_DPMax; lane++) - { - dpcd_lane2[lane].bits.post_cursor2_set = - static_cast( - LTSettings.laneSettings[lane].postCursor2); - dpcd_lane2[lane].bits.max_post_cursor2_reached = 0; - } - m_pDpcdAccessSrv->WriteDpcdData( - DpcdAddress_Lane0Set2, - reinterpret_cast(dpcd_lane2), - LTSettings.link.lanes); - } - */ - if (is_repeater(link, offset)) { #if defined(CONFIG_DRM_AMD_DC_DCN) if (dp_get_link_encoding_format(&link_training_setting->link_settings) == @@ -1066,7 +970,7 @@ enum dc_status dpcd_set_lane_settings( __func__, offset, lane0_set_address, - dpcd_lane[0].tx_ffe.PRESET_VALUE); + link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == DP_8b_10b_ENCODING) #endif @@ -1075,10 +979,10 @@ enum dc_status dpcd_set_lane_settings( __func__, offset, lane0_set_address, - dpcd_lane[0].bits.VOLTAGE_SWING_SET, - dpcd_lane[0].bits.PRE_EMPHASIS_SET, - dpcd_lane[0].bits.MAX_SWING_REACHED, - dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED); + link_training_setting->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET, + link_training_setting->dpcd_lane_settings[0].bits.PRE_EMPHASIS_SET, + link_training_setting->dpcd_lane_settings[0].bits.MAX_SWING_REACHED, + link_training_setting->dpcd_lane_settings[0].bits.MAX_PRE_EMPHASIS_REACHED); } else { #if defined(CONFIG_DRM_AMD_DC_DCN) @@ -1087,17 +991,17 @@ enum dc_status dpcd_set_lane_settings( DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X TX_FFE_PRESET_VALUE = %x\n", __func__, lane0_set_address, - dpcd_lane[0].tx_ffe.PRESET_VALUE); + link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == DP_8b_10b_ENCODING) #endif DC_LOG_HW_LINK_TRAINING("%s\n 0x%X VS set = %x PE set = %x max VS Reached = %x max PE Reached = %x\n", __func__, lane0_set_address, - dpcd_lane[0].bits.VOLTAGE_SWING_SET, - dpcd_lane[0].bits.PRE_EMPHASIS_SET, - dpcd_lane[0].bits.MAX_SWING_REACHED, - dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED); + link_training_setting->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET, + link_training_setting->dpcd_lane_settings[0].bits.PRE_EMPHASIS_SET, + link_training_setting->dpcd_lane_settings[0].bits.MAX_SWING_REACHED, + link_training_setting->dpcd_lane_settings[0].bits.MAX_PRE_EMPHASIS_REACHED); } return status; @@ -1110,7 +1014,7 @@ bool dp_is_max_vs_reached( for (lane = 0; lane < (uint32_t)(lt_settings->link_settings.lane_count); lane++) { - if (lt_settings->lane_settings[lane].VOLTAGE_SWING + if (lt_settings->dpcd_lane_settings[lane].bits.VOLTAGE_SWING_SET == VOLTAGE_SWING_MAX_LEVEL) return true; } @@ -1140,17 +1044,17 @@ static bool perform_post_lt_adj_req_sequence( adj_req_timer < POST_LT_ADJ_REQ_TIMEOUT; adj_req_timer++) { - struct link_training_settings req_settings; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX]; union lane_align_status_updated dpcd_lane_status_updated; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; - dp_get_lane_status_and_drive_settings( + dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, DPRX); if (dpcd_lane_status_updated.bits. @@ -1168,11 +1072,10 @@ static bool perform_post_lt_adj_req_sequence( for (lane = 0; lane < (uint32_t)(lane_count); lane++) { if (lt_settings-> - lane_settings[lane].VOLTAGE_SWING != - req_settings.lane_settings[lane]. - VOLTAGE_SWING || - lt_settings->lane_settings[lane].PRE_EMPHASIS != - req_settings.lane_settings[lane].PRE_EMPHASIS) { + dpcd_lane_settings[lane].bits.VOLTAGE_SWING_SET != + dpcd_lane_adjust[lane].bits.VOLTAGE_SWING_LANE || + lt_settings->dpcd_lane_settings[lane].bits.PRE_EMPHASIS_SET != + dpcd_lane_adjust[lane].bits.PRE_EMPHASIS_LANE) { req_drv_setting_changed = true; break; @@ -1180,8 +1083,8 @@ static bool perform_post_lt_adj_req_sequence( } if (req_drv_setting_changed) { - dp_update_drive_settings( - lt_settings, req_settings); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); dc_link_dp_set_drive_settings(link, lt_settings); @@ -1261,16 +1164,15 @@ static enum link_training_result perform_channel_equalization_sequence( struct link_training_settings *lt_settings, uint32_t offset) { - struct link_training_settings req_settings; enum dc_dp_training_pattern tr_pattern; uint32_t retries_ch_eq; uint32_t wait_time_microsec; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; - union lane_align_status_updated dpcd_lane_status_updated = { {0} }; - union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; + union lane_align_status_updated dpcd_lane_status_updated = {0}; + union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0}; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = {0}; /* Note: also check that TPS4 is a supported feature*/ - tr_pattern = lt_settings->pattern_for_eq; #if defined(CONFIG_DRM_AMD_DC_DCN) @@ -1316,12 +1218,12 @@ static enum link_training_result perform_channel_equalization_sequence( /* 4. Read lane status and requested * drive settings as set by the sink*/ - dp_get_lane_status_and_drive_settings( + dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, offset); /* 5. check CR done*/ @@ -1335,7 +1237,8 @@ static enum link_training_result perform_channel_equalization_sequence( return LINK_TRAINING_SUCCESS; /* 7. update VS/PE/PC2 in lt_settings*/ - dp_update_drive_settings(lt_settings, req_settings); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } return LINK_TRAINING_EQ_FAIL_EQ; @@ -1361,10 +1264,10 @@ static enum link_training_result perform_clock_recovery_sequence( uint32_t retries_cr; uint32_t retry_count; uint32_t wait_time_microsec; - struct link_training_settings req_settings; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX]; union lane_align_status_updated dpcd_lane_status_updated; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; retries_cr = 0; retry_count = 0; @@ -1418,12 +1321,12 @@ static enum link_training_result perform_clock_recovery_sequence( /* 4. Read lane status and requested drive * settings as set by the sink */ - dp_get_lane_status_and_drive_settings( + dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, offset); /* 5. check CR done*/ @@ -1441,33 +1344,25 @@ static enum link_training_result perform_clock_recovery_sequence( break; #endif -#if defined(CONFIG_DRM_AMD_DC_DCN) - if ((dp_get_link_encoding_format(<_settings->link_settings) == DP_128b_132b_ENCODING) && - lt_settings->lane_settings[0].FFE_PRESET.settings.level == - req_settings.lane_settings[0].FFE_PRESET.settings.level) - retries_cr++; - else if ((dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING) && - lt_settings->lane_settings[0].VOLTAGE_SWING == - req_settings.lane_settings[0].VOLTAGE_SWING) - retries_cr++; - else - retries_cr = 0; -#else /* 7. same lane settings*/ /* Note: settings are the same for all lanes, * so comparing first lane is sufficient*/ - if ((lt_settings->lane_settings[0].VOLTAGE_SWING == - req_settings.lane_settings[0].VOLTAGE_SWING) - && (lt_settings->lane_settings[0].PRE_EMPHASIS == - req_settings.lane_settings[0].PRE_EMPHASIS)) + if ((dp_get_link_encoding_format(<_settings->link_settings) == DP_8b_10b_ENCODING) && + lt_settings->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET == + dpcd_lane_adjust[0].bits.VOLTAGE_SWING_LANE) retries_cr++; +#if defined(CONFIG_DRM_AMD_DC_DCN) + else if ((dp_get_link_encoding_format(<_settings->link_settings) == DP_128b_132b_ENCODING) && + lt_settings->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE == + dpcd_lane_adjust[0].tx_ffe.PRESET_VALUE) + retries_cr++; +#endif else retries_cr = 0; -#endif /* 8. update VS/PE/PC2 in lt_settings*/ - dp_update_drive_settings(lt_settings, req_settings); - + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); retry_count++; } @@ -1487,7 +1382,7 @@ static inline enum link_training_result dp_transition_to_video_idle( struct link_training_settings *lt_settings, enum link_training_result status) { - union lane_count_set lane_count_set = { {0} }; + union lane_count_set lane_count_set = {0}; /* 4. mainlink output idle pattern*/ dp_set_hw_test_pattern(link, DP_TEST_PATTERN_VIDEO_MODE, NULL, 0); @@ -1596,6 +1491,9 @@ static inline void decide_8b_10b_training_settings( lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting); lt_settings->enhanced_framing = 1; lt_settings->should_set_fec_ready = true; + lt_settings->disallow_per_lane_settings = true; + lt_settings->always_match_dpcd_with_hw_lane_settings = true; + dp_hw_to_dpcd_lane_settings(lt_settings, lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } #if defined(CONFIG_DRM_AMD_DC_DCN) @@ -1621,6 +1519,9 @@ static inline void decide_128b_132b_training_settings(struct dc_link *link, link->dpcd_caps.lttpr_caps.phy_repeater_cnt) + 1) * 20000; lt_settings->lttpr_mode = dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) ? LTTPR_MODE_NON_TRANSPARENT : LTTPR_MODE_TRANSPARENT; + lt_settings->disallow_per_lane_settings = true; + dp_hw_to_dpcd_lane_settings(lt_settings, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } #endif @@ -1661,7 +1562,13 @@ static void override_training_settings( if (overrides->ffe_preset != NULL) lt_settings->ffe_preset = overrides->ffe_preset; #endif - + /* Override HW lane settings with BIOS forced values if present */ + if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN && + link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { + lt_settings->voltage_swing = &link->bios_forced_drive_settings.VOLTAGE_SWING; + lt_settings->pre_emphasis = &link->bios_forced_drive_settings.PRE_EMPHASIS; + lt_settings->always_match_dpcd_with_hw_lane_settings = false; + } for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) { lt_settings->lane_settings[lane].VOLTAGE_SWING = lt_settings->voltage_swing != NULL ? @@ -1677,6 +1584,9 @@ static void override_training_settings( : POST_CURSOR2_DISABLED; } + dp_hw_to_dpcd_lane_settings(lt_settings, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); + /* Initialize training timings */ if (overrides->cr_pattern_time != NULL) lt_settings->cr_pattern_time = *overrides->cr_pattern_time; @@ -1800,7 +1710,7 @@ static enum dc_status configure_lttpr_mode_non_transparent( static void repeater_training_done(struct dc_link *link, uint32_t offset) { - union dpcd_training_pattern dpcd_pattern = { {0} }; + union dpcd_training_pattern dpcd_pattern = {0}; const uint32_t dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET_PHY_REPEATER1 + @@ -1947,6 +1857,9 @@ void dc_link_dp_set_drive_settings( /* program ASIC PHY settings*/ dp_set_hw_lane_settings(link, lt_settings, DPRX); + dp_hw_to_dpcd_lane_settings(lt_settings, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); + /* Notify DP sink the PHY settings from source */ dpcd_set_lane_settings(link, lt_settings, DPRX); } @@ -2074,38 +1987,43 @@ static enum link_training_result dp_perform_128b_132b_channel_eq_done_sequence( struct dc_link *link, struct link_training_settings *lt_settings) { - uint8_t loop_count = 0; + uint8_t loop_count; uint32_t aux_rd_interval = 0; uint32_t wait_time = 0; - struct link_training_settings req_settings; - union lane_align_status_updated dpcd_lane_status_updated = { {0} }; - union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; + union lane_align_status_updated dpcd_lane_status_updated = {0}; + union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0}; enum link_training_result status = LINK_TRAINING_SUCCESS; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = {0}; - /* Transmit 128b/132b_TPS1 over Main-Link and Set TRAINING_PATTERN_SET to 01h */ + /* Transmit 128b/132b_TPS1 over Main-Link */ dp_set_hw_training_pattern(link, lt_settings->pattern_for_cr, DPRX); + /* Set TRAINING_PATTERN_SET to 01h */ dpcd_set_training_pattern(link, lt_settings->pattern_for_cr); - /* Adjust TX_FFE_PRESET_VALUE as requested */ - dp_get_lane_status_and_drive_settings(link, lt_settings, dpcd_lane_status, - &dpcd_lane_status_updated, &req_settings, DPRX); - dp_update_drive_settings(lt_settings, req_settings); + /* Adjust TX_FFE_PRESET_VALUE and Transmit 128b/132b_TPS2 over Main-Link */ dpcd_128b_132b_get_aux_rd_interval(link, &aux_rd_interval); + dp_get_lane_status_and_lane_adjust(link, lt_settings, dpcd_lane_status, + &dpcd_lane_status_updated, dpcd_lane_adjust, DPRX); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); dp_set_hw_lane_settings(link, lt_settings, DPRX); - dpcd_set_lane_settings(link, lt_settings, DPRX); - - /* Transmit 128b/132b_TPS2 over Main-Link and Set TRAINING_PATTERN_SET to 02h */ dp_set_hw_training_pattern(link, lt_settings->pattern_for_eq, DPRX); - dpcd_set_training_pattern(link, lt_settings->pattern_for_eq); + + /* Set loop counter to start from 1 */ + loop_count = 1; + + /* Set TRAINING_PATTERN_SET to 02h and TX_FFE_PRESET_VALUE in one AUX transaction */ + dpcd_set_lt_pattern_and_lane_settings(link, lt_settings, + lt_settings->pattern_for_eq, DPRX); /* poll for channel EQ done */ while (status == LINK_TRAINING_SUCCESS) { - loop_count++; dp_wait_for_training_aux_rd_interval(link, aux_rd_interval); wait_time += aux_rd_interval; - dp_get_lane_status_and_drive_settings(link, lt_settings, dpcd_lane_status, - &dpcd_lane_status_updated, &req_settings, DPRX); - dp_update_drive_settings(lt_settings, req_settings); + dp_get_lane_status_and_lane_adjust(link, lt_settings, dpcd_lane_status, + &dpcd_lane_status_updated, dpcd_lane_adjust, DPRX); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); dpcd_128b_132b_get_aux_rd_interval(link, &aux_rd_interval); if (dp_is_ch_eq_done(lt_settings->link_settings.lane_count, dpcd_lane_status)) { @@ -2119,6 +2037,7 @@ static enum link_training_result dp_perform_128b_132b_channel_eq_done_sequence( dp_set_hw_lane_settings(link, lt_settings, DPRX); dpcd_set_lane_settings(link, lt_settings, DPRX); } + loop_count++; } /* poll for EQ interlane align done */ @@ -2134,8 +2053,8 @@ static enum link_training_result dp_perform_128b_132b_channel_eq_done_sequence( dp_wait_for_training_aux_rd_interval(link, lt_settings->eq_pattern_time); wait_time += lt_settings->eq_pattern_time; - dp_get_lane_status_and_drive_settings(link, lt_settings, dpcd_lane_status, - &dpcd_lane_status_updated, &req_settings, DPRX); + dp_get_lane_status_and_lane_adjust(link, lt_settings, dpcd_lane_status, + &dpcd_lane_status_updated, dpcd_lane_adjust, DPRX); } } @@ -2148,9 +2067,9 @@ static enum link_training_result dp_perform_128b_132b_cds_done_sequence( { /* Assumption: assume hardware has transmitted eq pattern */ enum link_training_result status = LINK_TRAINING_SUCCESS; - struct link_training_settings req_settings; - union lane_align_status_updated dpcd_lane_status_updated = { {0} }; - union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; + union lane_align_status_updated dpcd_lane_status_updated = {0}; + union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0}; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; uint32_t wait_time = 0; /* initiate CDS done sequence */ @@ -2161,8 +2080,8 @@ static enum link_training_result dp_perform_128b_132b_cds_done_sequence( dp_wait_for_training_aux_rd_interval(link, lt_settings->cds_pattern_time); wait_time += lt_settings->cds_pattern_time; - dp_get_lane_status_and_drive_settings(link, lt_settings, dpcd_lane_status, - &dpcd_lane_status_updated, &req_settings, DPRX); + dp_get_lane_status_and_lane_adjust(link, lt_settings, dpcd_lane_status, + &dpcd_lane_status_updated, dpcd_lane_adjust, DPRX); if (dp_is_symbol_locked(lt_settings->link_settings.lane_count, dpcd_lane_status) && dpcd_lane_status_updated.bits.CDS_INTERLANE_ALIGN_DONE_128b_132b) { /* pass */ @@ -2219,7 +2138,7 @@ static enum link_training_result dp_perform_8b_10b_link_training( } for (lane = 0; lane < (uint8_t)lt_settings->link_settings.lane_count; lane++) - lt_settings->lane_settings[lane].VOLTAGE_SWING = VOLTAGE_SWING_LEVEL0; + lt_settings->dpcd_lane_settings[lane].bits.VOLTAGE_SWING_SET = VOLTAGE_SWING_LEVEL0; } if (status == LINK_TRAINING_SUCCESS) { @@ -2863,7 +2782,7 @@ bool dp_verify_link_cap( link->verified_link_cap = *known_limit_link_setting; return true; } else if (link->link_enc && link->dc->res_pool->funcs->link_encs_assign && - !link_enc_cfg_is_link_enc_avail(link->ctx->dc, link->link_enc->preferred_engine)) { + !link_enc_cfg_is_link_enc_avail(link->ctx->dc, link->link_enc->preferred_engine, link)) { link->verified_link_cap = initial_link_settings; return true; } @@ -3523,6 +3442,8 @@ static bool handle_hpd_irq_psr_sink(struct dc_link *link) if (psr_error_status.bits.LINK_CRC_ERROR || psr_error_status.bits.RFB_STORAGE_ERROR || psr_error_status.bits.VSC_SDP_ERROR) { + bool allow_active; + /* Acknowledge and clear error bits */ dm_helpers_dp_write_dpcd( link->ctx, @@ -3532,8 +3453,10 @@ static bool handle_hpd_irq_psr_sink(struct dc_link *link) sizeof(psr_error_status.raw)); /* PSR error, disable and re-enable PSR */ - dc_link_set_psr_allow_active(link, false, true, false); - dc_link_set_psr_allow_active(link, true, true, false); + allow_active = false; + dc_link_set_psr_allow_active(link, &allow_active, true, false, NULL); + allow_active = true; + dc_link_set_psr_allow_active(link, &allow_active, true, false, NULL); return true; } else if (psr_sink_psr_status.bits.SINK_SELF_REFRESH_STATUS == @@ -3591,15 +3514,13 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) #endif unsigned int test_pattern_size = 0; enum dp_test_pattern test_pattern; - struct dc_link_training_settings link_settings; union lane_adjust dpcd_lane_adjust; unsigned int lane; struct link_training_settings link_training_settings; - int i = 0; dpcd_test_pattern.raw = 0; memset(dpcd_lane_adjustment, 0, sizeof(dpcd_lane_adjustment)); - memset(&link_settings, 0, sizeof(link_settings)); + memset(&link_training_settings, 0, sizeof(link_training_settings)); /* get phy test pattern and pattern parameters from DP receiver */ core_link_read_dpcd( @@ -3720,48 +3641,37 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link) #endif /* prepare link training settings */ - link_settings.link = link->cur_link_settings; + link_training_settings.link_settings = link->cur_link_settings; for (lane = 0; lane < (unsigned int)(link->cur_link_settings.lane_count); lane++) { dpcd_lane_adjust.raw = get_nibble_at_index(&dpcd_lane_adjustment[0].raw, lane); -#if defined(CONFIG_DRM_AMD_DC_DCN) if (dp_get_link_encoding_format(&link->cur_link_settings) == - DP_128b_132b_ENCODING) { - link_settings.lane_settings[lane].FFE_PRESET.raw = - dpcd_lane_adjust.tx_ffe.PRESET_VALUE; - } else if (dp_get_link_encoding_format(&link->cur_link_settings) == DP_8b_10b_ENCODING) { - link_settings.lane_settings[lane].VOLTAGE_SWING = + link_training_settings.hw_lane_settings[lane].VOLTAGE_SWING = (enum dc_voltage_swing) (dpcd_lane_adjust.bits.VOLTAGE_SWING_LANE); - link_settings.lane_settings[lane].PRE_EMPHASIS = + link_training_settings.hw_lane_settings[lane].PRE_EMPHASIS = (enum dc_pre_emphasis) (dpcd_lane_adjust.bits.PRE_EMPHASIS_LANE); - link_settings.lane_settings[lane].POST_CURSOR2 = + link_training_settings.hw_lane_settings[lane].POST_CURSOR2 = (enum dc_post_cursor2) ((dpcd_post_cursor_2_adjustment >> (lane * 2)) & 0x03); } -#else - link_settings.lane_settings[lane].VOLTAGE_SWING = - (enum dc_voltage_swing) - (dpcd_lane_adjust.bits.VOLTAGE_SWING_LANE); - link_settings.lane_settings[lane].PRE_EMPHASIS = - (enum dc_pre_emphasis) - (dpcd_lane_adjust.bits.PRE_EMPHASIS_LANE); - link_settings.lane_settings[lane].POST_CURSOR2 = - (enum dc_post_cursor2) - ((dpcd_post_cursor_2_adjustment >> (lane * 2)) & 0x03); +#if defined(CONFIG_DRM_AMD_DC_DCN) + else if (dp_get_link_encoding_format(&link->cur_link_settings) == + DP_128b_132b_ENCODING) { + link_training_settings.hw_lane_settings[lane].FFE_PRESET.raw = + dpcd_lane_adjust.tx_ffe.PRESET_VALUE; + } #endif } - for (i = 0; i < 4; i++) - link_training_settings.lane_settings[i] = - link_settings.lane_settings[i]; - link_training_settings.link_settings = link_settings.link; - link_training_settings.allow_invalid_msa_timing_param = false; + dp_hw_to_dpcd_lane_settings(&link_training_settings, + link_training_settings.hw_lane_settings, + link_training_settings.dpcd_lane_settings); /*Usage: Measure DP physical lane signal * by DP SI test equipment automatically. * PHY test pattern request is generated by equipment via HPD interrupt. @@ -4065,8 +3975,8 @@ void dc_link_dp_handle_link_loss(struct dc_link *link) bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss, bool defer_handling, bool *has_left_work) { - union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } }; - union device_service_irq device_service_clear = { { 0 } }; + union hpd_irq_data hpd_irq_dpcd_data = {0}; + union device_service_irq device_service_clear = {0}; enum dc_status result; bool status = false; @@ -5939,7 +5849,7 @@ bool is_edp_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timin uint8_t link_bw_set; uint8_t link_rate_set; uint32_t req_bw; - union lane_count_set lane_count_set = { {0} }; + union lane_count_set lane_count_set = {0}; ASSERT(link || crtc_timing); // invalid input @@ -5993,6 +5903,25 @@ enum dp_link_encoding dp_get_link_encoding_format(const struct dc_link_settings } #if defined(CONFIG_DRM_AMD_DC_DCN) +enum dp_link_encoding dc_link_dp_mst_decide_link_encoding_format(const struct dc_link *link) +{ + struct dc_link_settings link_settings = {0}; + + if (!dc_is_dp_signal(link->connector_signal)) + return DP_UNKNOWN_ENCODING; + + if (link->preferred_link_setting.lane_count != + LANE_COUNT_UNKNOWN && + link->preferred_link_setting.link_rate != + LINK_RATE_UNKNOWN) { + link_settings = link->preferred_link_setting; + } else { + decide_mst_link_settings(link, &link_settings); + } + + return dp_get_link_encoding_format(&link_settings); +} + // TODO - DP2.0 Link: Fix get_lane_status to handle LTTPR offset (SST and MST) static void get_lane_status( struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c index e9006d099393..b1c9f77d6bf4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpia.c @@ -263,10 +263,10 @@ static enum link_training_result dpia_training_cr_non_transparent(struct dc_link uint32_t retry_count = 0; /* From DP spec, CR read interval is always 100us. */ uint32_t wait_time_microsec = TRAINING_AUX_RD_INTERVAL; - struct link_training_settings req_settings; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; union lane_align_status_updated dpcd_lane_status_updated = { {0} }; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; uint8_t set_cfg_data; enum dpia_set_config_ts ts; @@ -345,11 +345,12 @@ static enum link_training_result dpia_training_cr_non_transparent(struct dc_link dp_wait_for_training_aux_rd_interval(link, wait_time_microsec); /* Read status and adjustment requests from DPCD. */ - status = dp_get_lane_status_and_drive_settings(link, + status = dp_get_lane_status_and_lane_adjust( + link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, hop); if (status != DC_OK) { result = LINK_TRAINING_ABORT; @@ -371,16 +372,18 @@ static enum link_training_result dpia_training_cr_non_transparent(struct dc_link * Note: settings are the same for all lanes, * so comparing first lane is sufficient. */ - if (lt_settings->lane_settings[0].VOLTAGE_SWING == - req_settings.lane_settings[0].VOLTAGE_SWING && - lt_settings->lane_settings[0].PRE_EMPHASIS == - req_settings.lane_settings[0].PRE_EMPHASIS) + if ((lt_settings->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET == + dpcd_lane_adjust[0].bits.VOLTAGE_SWING_LANE) + && (lt_settings->dpcd_lane_settings[0].bits.PRE_EMPHASIS_SET == + dpcd_lane_adjust[0].bits.PRE_EMPHASIS_LANE)) retries_cr++; else retries_cr = 0; /* Update VS/PE. */ - dp_update_drive_settings(lt_settings, req_settings); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->lane_settings, + lt_settings->dpcd_lane_settings); retry_count++; } @@ -416,10 +419,10 @@ static enum link_training_result dpia_training_cr_transparent(struct dc_link *li uint32_t retries_cr = 0; /* Number of consecutive attempts with same VS or PE. */ uint32_t retry_count = 0; uint32_t wait_time_microsec = lt_settings->cr_pattern_time; - struct link_training_settings req_settings; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; union lane_align_status_updated dpcd_lane_status_updated = { {0} }; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; /* Cap of LINK_TRAINING_MAX_CR_RETRY attempts at clock recovery. * Fix inherited from perform_clock_recovery_sequence() - @@ -445,11 +448,12 @@ static enum link_training_result dpia_training_cr_transparent(struct dc_link *li dp_wait_for_training_aux_rd_interval(link, wait_time_microsec); /* Read status and adjustment requests from DPCD. */ - status = dp_get_lane_status_and_drive_settings(link, + status = dp_get_lane_status_and_lane_adjust( + link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, DPRX); if (status != DC_OK) { result = LINK_TRAINING_ABORT; @@ -471,16 +475,17 @@ static enum link_training_result dpia_training_cr_transparent(struct dc_link *li * Note: settings are the same for all lanes, * so comparing first lane is sufficient. */ - if (lt_settings->lane_settings[0].VOLTAGE_SWING == - req_settings.lane_settings[0].VOLTAGE_SWING && - lt_settings->lane_settings[0].PRE_EMPHASIS == - req_settings.lane_settings[0].PRE_EMPHASIS) + if ((lt_settings->dpcd_lane_settings[0].bits.VOLTAGE_SWING_SET == + dpcd_lane_adjust[0].bits.VOLTAGE_SWING_LANE) + && (lt_settings->dpcd_lane_settings[0].bits.PRE_EMPHASIS_SET == + dpcd_lane_adjust[0].bits.PRE_EMPHASIS_LANE)) retries_cr++; else retries_cr = 0; /* Update VS/PE. */ - dp_update_drive_settings(lt_settings, req_settings); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); retry_count++; } @@ -566,10 +571,10 @@ static enum link_training_result dpia_training_eq_non_transparent(struct dc_link enum dc_status status; enum dc_dp_training_pattern tr_pattern; uint32_t wait_time_microsec; - struct link_training_settings req_settings; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; union lane_align_status_updated dpcd_lane_status_updated = { {0} }; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; uint8_t set_cfg_data; enum dpia_set_config_ts ts; @@ -639,11 +644,12 @@ static enum link_training_result dpia_training_eq_non_transparent(struct dc_link dp_wait_for_training_aux_rd_interval(link, wait_time_microsec); /* Read status and adjustment requests from DPCD. */ - status = dp_get_lane_status_and_drive_settings(link, + status = dp_get_lane_status_and_lane_adjust( + link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, hop); if (status != DC_OK) { result = LINK_TRAINING_ABORT; @@ -664,7 +670,8 @@ static enum link_training_result dpia_training_eq_non_transparent(struct dc_link } /* Update VS/PE. */ - dp_update_drive_settings(lt_settings, req_settings); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } /* Abort link training if equalization failed due to HPD unplug. */ @@ -701,10 +708,10 @@ static enum link_training_result dpia_training_eq_transparent(struct dc_link *li enum dc_status status; enum dc_dp_training_pattern tr_pattern = lt_settings->pattern_for_eq; uint32_t wait_time_microsec; - struct link_training_settings req_settings; enum dc_lane_count lane_count = lt_settings->link_settings.lane_count; union lane_align_status_updated dpcd_lane_status_updated = { {0} }; union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } }; + union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } }; wait_time_microsec = dpia_get_eq_aux_rd_interval(link, lt_settings, DPRX); @@ -720,11 +727,12 @@ static enum link_training_result dpia_training_eq_transparent(struct dc_link *li dp_wait_for_training_aux_rd_interval(link, wait_time_microsec); /* Read status and adjustment requests from DPCD. */ - status = dp_get_lane_status_and_drive_settings(link, + status = dp_get_lane_status_and_lane_adjust( + link, lt_settings, dpcd_lane_status, &dpcd_lane_status_updated, - &req_settings, + dpcd_lane_adjust, DPRX); if (status != DC_OK) { result = LINK_TRAINING_ABORT; @@ -745,7 +753,8 @@ static enum link_training_result dpia_training_eq_transparent(struct dc_link *li } /* Update VS/PE. */ - dp_update_drive_settings(lt_settings, req_settings); + dp_decide_lane_settings(lt_settings, dpcd_lane_adjust, + lt_settings->hw_lane_settings, lt_settings->dpcd_lane_settings); } /* Abort link training if equalization failed due to HPD unplug. */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c index 1cab4bf06abe..72b0f8594b4a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c @@ -488,16 +488,19 @@ struct link_encoder *link_enc_cfg_get_link_enc_used_by_stream( return link_enc; } -bool link_enc_cfg_is_link_enc_avail(struct dc *dc, enum engine_id eng_id) +bool link_enc_cfg_is_link_enc_avail(struct dc *dc, enum engine_id eng_id, struct dc_link *link) { bool is_avail = true; int i; - /* Add assigned encoders to list. */ + /* An encoder is not available if it has already been assigned to a different endpoint. */ for (i = 0; i < MAX_PIPES; i++) { struct link_enc_assignment assignment = get_assignment(dc, i); + struct display_endpoint_id ep_id = (struct display_endpoint_id) { + .link_id = link->link_id, + .ep_type = link->ep_type}; - if (assignment.valid && assignment.eng_id == eng_id) { + if (assignment.valid && assignment.eng_id == eng_id && !are_ep_ids_equal(&ep_id, &assignment.ep_id)) { is_avail = false; break; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 561c10a92bb5..c32fdccd4d92 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1155,9 +1155,17 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) pipe_ctx->plane_res.scl_data.recout.x += pipe_ctx->plane_res.scl_data.recout.width; } - if (pipe_ctx->plane_res.scl_data.viewport.height < MIN_VIEWPORT_SIZE || - pipe_ctx->plane_res.scl_data.viewport.width < MIN_VIEWPORT_SIZE) - res = false; + if (!pipe_ctx->stream->ctx->dc->config.enable_windowed_mpo_odm) { + if (pipe_ctx->plane_res.scl_data.viewport.height < MIN_VIEWPORT_SIZE || + pipe_ctx->plane_res.scl_data.viewport.width < MIN_VIEWPORT_SIZE) + res = false; + } else { + /* Clamp minimum viewport size */ + if (pipe_ctx->plane_res.scl_data.viewport.height < MIN_VIEWPORT_SIZE) + pipe_ctx->plane_res.scl_data.viewport.height = MIN_VIEWPORT_SIZE; + if (pipe_ctx->plane_res.scl_data.viewport.width < MIN_VIEWPORT_SIZE) + pipe_ctx->plane_res.scl_data.viewport.width = MIN_VIEWPORT_SIZE; + } DC_LOG_SCALER("%s pipe %d:\nViewport: height:%d width:%d x:%d y:%d Recout: height:%d width:%d x:%d y:%d HACTIVE:%d VACTIVE:%d\n" "src_rect: height:%d width:%d x:%d y:%d dst_rect: height:%d width:%d x:%d y:%d clip_rect: height:%d width:%d x:%d y:%d\n", @@ -3009,6 +3017,11 @@ enum dc_status dc_validate_plane(struct dc *dc, const struct dc_plane_state *pla { enum dc_status res = DC_OK; + /* check if surface has invalid dimensions */ + if (plane_state->src_rect.width == 0 || plane_state->src_rect.height == 0 || + plane_state->dst_rect.width == 0 || plane_state->dst_rect.height == 0) + return DC_FAIL_SURFACE_VALIDATE; + /* TODO For now validates pixel format only */ if (dc->res_pool->funcs->validate_plane) return dc->res_pool->funcs->validate_plane(plane_state, &dc->caps); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index f0f54f4d3d9b..57cf4cb82370 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -202,6 +202,10 @@ struct dc_stream_state *dc_copy_stream(const struct dc_stream_state *stream) new_stream->stream_id = new_stream->ctx->dc_stream_id_count; new_stream->ctx->dc_stream_id_count++; + /* If using dynamic encoder assignment, wait till stream committed to assign encoder. */ + if (new_stream->ctx->dc->res_pool->funcs->link_encs_assign) + new_stream->link_enc = NULL; + kref_init(&new_stream->refcount); return new_stream; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index dd995905b0cb..a5339796902a 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.156" +#define DC_VER "3.2.159" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -211,12 +211,12 @@ struct dc_dcc_setting { unsigned int max_uncompressed_blk_size; bool independent_64b_blks; #if defined(CONFIG_DRM_AMD_DC_DCN) - //These bitfields to be used starting with DCN 3.0 + //These bitfields to be used starting with DCN struct { - uint32_t dcc_256_64_64 : 1;//available in ASICs before DCN 3.0 (the worst compression case) - uint32_t dcc_128_128_uncontrained : 1; //available in ASICs before DCN 3.0 - uint32_t dcc_256_128_128 : 1; //available starting with DCN 3.0 - uint32_t dcc_256_256_unconstrained : 1; //available in ASICs before DCN 3.0 (the best compression case) + uint32_t dcc_256_64_64 : 1;//available in ASICs before DCN (the worst compression case) + uint32_t dcc_128_128_uncontrained : 1; //available in ASICs before DCN + uint32_t dcc_256_128_128 : 1; //available starting with DCN + uint32_t dcc_256_256_unconstrained : 1; //available in ASICs before DCN (the best compression case) } dcc_controls; #endif }; @@ -323,6 +323,7 @@ struct dc_config { bool multi_mon_pp_mclk_switch; bool disable_dmcu; bool enable_4to1MPC; + bool enable_windowed_mpo_odm; bool allow_edp_hotplug_detection; #if defined(CONFIG_DRM_AMD_DC_DCN) bool clamp_min_dcfclk; @@ -342,6 +343,12 @@ enum visual_confirm { VISUAL_CONFIRM_SWIZZLE = 9, }; +enum dc_psr_power_opts { + psr_power_opt_invalid = 0x0, + psr_power_opt_smu_opt_static_screen = 0x1, + psr_power_opt_z10_static_screen = 0x10, +}; + enum dcc_option { DCC_ENABLE = 0, DCC_DISABLE = 1, @@ -664,6 +671,7 @@ struct dc_debug_options { #if defined(CONFIG_DRM_AMD_DC_DCN) /* TODO - remove once tested */ bool legacy_dp2_lt; + bool set_mst_en_for_sst; #endif union mem_low_power_enable_options enable_mem_low_power; union root_clock_optimization_options root_clock_optimization; @@ -724,6 +732,9 @@ struct dc { #if defined(CONFIG_DRM_AMD_DC_DCN) bool idle_optimizations_allowed; #endif +#if defined(CONFIG_DRM_AMD_DC_DCN) + bool enable_c20_dtm_b0; +#endif /* Require to maintain clocks and bandwidth for UEFI enabled HW */ @@ -930,6 +941,7 @@ union surface_update_flags { uint32_t bandwidth_change:1; uint32_t clock_change:1; uint32_t stereo_format_change:1; + uint32_t lut_3d:1; uint32_t full_update:1; } bits; @@ -1416,6 +1428,12 @@ bool dc_process_dmub_set_config_async(struct dc *dc, uint32_t link_index, struct set_config_cmd_payload *payload, struct dmub_notification *notify); + +enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, + uint32_t link_index, + uint8_t mst_alloc_slots, + uint8_t *mst_slots_in_use); + /******************************************************************************* * DSC Interfaces ******************************************************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index a23937e1dc5c..bc87ea0adf94 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -174,11 +174,6 @@ struct dc_lane_settings { #endif }; -struct dc_link_training_settings { - struct dc_link_settings link; - struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]; -}; - struct dc_link_training_overrides { enum dc_voltage_swing *voltage_swing; enum dc_pre_emphasis *pre_emphasis; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index 69b008bafbbc..180ecd860296 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -85,6 +85,7 @@ struct psr_settings { */ bool psr_frame_capture_indication_req; unsigned int psr_sdp_transmit_line_num_deadline; + unsigned int psr_power_opt; }; /* @@ -123,6 +124,10 @@ struct dc_link { struct dc_link_settings cur_link_settings; struct dc_lane_settings cur_lane_setting[LANE_COUNT_DP_MAX]; struct dc_link_settings preferred_link_setting; + /* preferred_training_settings are override values that + * come from DM. DM is responsible for the memory + * management of the override pointers. + */ struct dc_link_training_overrides preferred_training_settings; struct dp_audio_test_data audio_test_data; @@ -177,11 +182,15 @@ struct dc_link { struct psr_settings psr_settings; + /* Drive settings read from integrated info table */ + struct dc_lane_settings bios_forced_drive_settings; + /* MST record stream using this link */ struct link_flags { bool dp_keep_receiver_powered; bool dp_skip_DID2; bool dp_skip_reset_segment; + bool dp_mot_reset_segment; } wa_flags; struct link_mst_stream_allocation_table mst_stream_alloc_table; @@ -267,8 +276,8 @@ int dc_link_get_backlight_level(const struct dc_link *dc_link); int dc_link_get_target_backlight_pwm(const struct dc_link *link); -bool dc_link_set_psr_allow_active(struct dc_link *dc_link, bool enable, - bool wait, bool force_static); +bool dc_link_set_psr_allow_active(struct dc_link *dc_link, const bool *enable, + bool wait, bool force_static, const unsigned int *power_opts); bool dc_link_get_psr_state(const struct dc_link *dc_link, enum dc_psr_state *state); @@ -277,7 +286,6 @@ bool dc_link_setup_psr(struct dc_link *dc_link, struct psr_context *psr_context); void dc_link_get_psr_residency(const struct dc_link *link, uint32_t *residency); -void blank_all_dp_displays(struct dc *dc, bool hw_init); /* Request DC to detect if there is a Panel connected. * boot - If this call is during initial boot. @@ -296,6 +304,10 @@ enum dc_detect_reason { bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason); bool dc_link_get_hpd_state(struct dc_link *dc_link); enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx); +#if defined(CONFIG_DRM_AMD_DC_DCN) +enum dc_status dc_link_reduce_mst_payload(struct pipe_ctx *pipe_ctx, uint32_t req_pbn); +enum dc_status dc_link_increase_mst_payload(struct pipe_ctx *pipe_ctx, uint32_t req_pbn); +#endif /* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt). * Return: @@ -425,4 +437,7 @@ uint32_t dc_bandwidth_in_kbps_from_timing( bool dc_link_is_fec_supported(const struct dc_link *link); bool dc_link_should_enable_fec(const struct dc_link *link); +#if defined(CONFIG_DRM_AMD_DC_DCN) +enum dp_link_encoding dc_link_dp_mst_decide_link_encoding_format(const struct dc_link *link); +#endif #endif /* DC_LINK_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index b8ebc1f09538..e37c4a10bfd5 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -115,6 +115,13 @@ struct periodic_interrupt_config { int lines_offset; }; +#if defined(CONFIG_DRM_AMD_DC_DCN) +struct dc_mst_stream_bw_update { + bool is_increase; // is bandwidth reduced or increased + uint32_t mst_stream_bw; // new mst bandwidth in kbps +}; +#endif + union stream_update_flags { struct { uint32_t scaling:1; @@ -125,6 +132,9 @@ union stream_update_flags { uint32_t gamut_remap:1; uint32_t wb_update:1; uint32_t dsc_changed : 1; +#if defined(CONFIG_DRM_AMD_DC_DCN) + uint32_t mst_bw : 1; +#endif } bits; uint32_t raw; @@ -278,6 +288,9 @@ struct dc_stream_update { struct dc_writeback_update *wb_update; struct dc_dsc_config *dsc_config; +#if defined(CONFIG_DRM_AMD_DC_DCN) + struct dc_mst_stream_bw_update *mst_bw_update; +#endif struct dc_transfer_func *func_shaper; struct dc_3dlut *lut3d_func; diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 15c353c389d8..388457ffc0a8 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -653,6 +653,7 @@ enum dc_psr_state { PSR_STATE1a, PSR_STATE2, PSR_STATE2a, + PSR_STATE2b, PSR_STATE3, PSR_STATE3Init, PSR_STATE4, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c index 7866cf2a668f..27218ede150a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c @@ -514,13 +514,15 @@ void dce_aud_az_configure( union audio_sample_rates sample_rates = audio_mode->sample_rates; uint8_t byte2 = audio_mode->max_bit_rate; + uint8_t channel_count = audio_mode->channel_count; /* adjust specific properties */ switch (audio_format_code) { case AUDIO_FORMAT_CODE_LINEARPCM: { + check_audio_bandwidth( crtc_info, - audio_mode->channel_count, + channel_count, signal, &sample_rates); @@ -548,7 +550,7 @@ void dce_aud_az_configure( /* fill audio format data */ set_reg_field_value(value, - audio_mode->channel_count - 1, + channel_count - 1, AZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR0, MAX_CHANNELS); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 95cb4d7cc76a..6d42a9cc9916 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -534,17 +534,26 @@ struct dce_aux *dce110_aux_engine_construct(struct aux_engine_dce110 *aux_engine static enum i2caux_transaction_action i2caux_action_from_payload(struct aux_payload *payload) { if (payload->i2c_over_aux) { + if (payload->write_status_update) { + if (payload->mot) + return I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT; + else + return I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST; + } if (payload->write) { if (payload->mot) return I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT; - return I2CAUX_TRANSACTION_ACTION_I2C_WRITE; + else + return I2CAUX_TRANSACTION_ACTION_I2C_WRITE; } if (payload->mot) return I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT; + return I2CAUX_TRANSACTION_ACTION_I2C_READ; } if (payload->write) return I2CAUX_TRANSACTION_ACTION_DP_WRITE; + return I2CAUX_TRANSACTION_ACTION_DP_READ; } @@ -698,7 +707,8 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, aux_defer_retries = 0, aux_i2c_defer_retries = 0, aux_timeout_retries = 0, - aux_invalid_reply_retries = 0; + aux_invalid_reply_retries = 0, + aux_ack_m_retries = 0; if (ddc_pin) { aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]; @@ -758,9 +768,27 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, aux_defer_retries, AUX_MAX_RETRIES); goto fail; - } else { + } else udelay(300); + } else if (payload->write && ret > 0) { + /* sink requested more time to complete the write via AUX_ACKM */ + if (++aux_ack_m_retries >= AUX_MAX_RETRIES) { + DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR, + LOG_FLAG_Error_I2cAux, + "dce_aux_transfer_with_retries: FAILURE: aux_ack_m_retries=%d >= AUX_MAX_RETRIES=%d", + aux_ack_m_retries, + AUX_MAX_RETRIES); + goto fail; } + + /* retry reading the write status until complete + * NOTE: payload is modified here + */ + payload->write = false; + payload->write_status_update = true; + payload->length = 0; + udelay(300); + } else return true; break; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h index 296b2f80a1ec..989f5b6907e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h @@ -1151,7 +1151,8 @@ struct dce_hwseq_registers { type DOMAIN_POWER_GATE;\ type DOMAIN_PGFSM_PWR_STATUS;\ type HPO_HDMISTREAMCLK_G_GATE_DIS;\ - type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE; + type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;\ + type I2C_LIGHT_SLEEP_FORCE; struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index aa8403bc4c83..90eb8eedacf2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -50,6 +50,8 @@ static enum dc_psr_state convert_psr_state(uint32_t raw_state) state = PSR_STATE2; else if (raw_state == 0x21) state = PSR_STATE2a; + else if (raw_state == 0x22) + state = PSR_STATE2b; else if (raw_state == 0x30) state = PSR_STATE3; else if (raw_state == 0x31) @@ -225,6 +227,25 @@ static void dmub_psr_set_level(struct dmub_psr *dmub, uint16_t psr_level, uint8_ dc_dmub_srv_wait_idle(dc->dmub_srv); } +/** + * Set PSR power optimization flags. + */ +static void dmub_psr_set_power_opt(struct dmub_psr *dmub, unsigned int power_opt) +{ + union dmub_rb_cmd cmd; + struct dc_context *dc = dmub->ctx; + + memset(&cmd, 0, sizeof(cmd)); + cmd.psr_set_power_opt.header.type = DMUB_CMD__PSR; + cmd.psr_set_power_opt.header.sub_type = DMUB_CMD__SET_PSR_POWER_OPT; + cmd.psr_set_power_opt.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_power_opt_data); + cmd.psr_set_power_opt.psr_set_power_opt_data.power_opt = power_opt; + + dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd); + dc_dmub_srv_cmd_execute(dc->dmub_srv); + dc_dmub_srv_wait_idle(dc->dmub_srv); +} + /* * Setup PSR by programming phy registers and sending psr hw context values to firmware. */ @@ -356,6 +377,7 @@ static const struct dmub_psr_funcs psr_funcs = { .psr_set_level = dmub_psr_set_level, .psr_force_static = dmub_psr_force_static, .psr_get_residency = dmub_psr_get_residency, + .psr_set_power_opt = dmub_psr_set_power_opt, }; /* diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h index 9675c269e649..5dbd479660f1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h @@ -46,6 +46,7 @@ struct dmub_psr_funcs { void (*psr_force_static)(struct dmub_psr *dmub, uint8_t panel_inst); void (*psr_get_residency)(struct dmub_psr *dmub, uint32_t *residency, uint8_t panel_inst); + void (*psr_set_power_opt)(struct dmub_psr *dmub, unsigned int power_opt); }; struct dmub_psr *dmub_psr_create(struct dc_context *ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 8108f9ae2638..af3e68d3e747 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1649,13 +1649,31 @@ static enum dc_status apply_single_controller_ctx_to_hw( static void power_down_encoders(struct dc *dc) { - int i; - - blank_all_dp_displays(dc, false); + int i, j; for (i = 0; i < dc->link_count; i++) { enum signal_type signal = dc->links[i]->connector_signal; + if ((signal == SIGNAL_TYPE_EDP) || + (signal == SIGNAL_TYPE_DISPLAY_PORT)) { + if (dc->links[i]->link_enc->funcs->get_dig_frontend && + dc->links[i]->link_enc->funcs->is_dig_enabled(dc->links[i]->link_enc)) { + unsigned int fe = dc->links[i]->link_enc->funcs->get_dig_frontend( + dc->links[i]->link_enc); + + for (j = 0; j < dc->res_pool->stream_enc_count; j++) { + if (fe == dc->res_pool->stream_enc[j]->id) { + dc->res_pool->stream_enc[j]->funcs->dp_blank(dc->links[i], + dc->res_pool->stream_enc[j]); + break; + } + } + } + + if (!dc->links[i]->wa_flags.dp_keep_receiver_powered) + dp_receiver_power_ctrl(dc->links[i], false); + } + if (signal != SIGNAL_TYPE_EDP) signal = SIGNAL_TYPE_NONE; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c index cb9767ddf93d..44293d66b46b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c @@ -205,9 +205,17 @@ static void dpp1_power_on_dscl( struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base); if (dpp->tf_regs->DSCL_MEM_PWR_CTRL) { - REG_UPDATE(DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, power_on ? 0 : 3); - if (power_on) + if (power_on) { + REG_UPDATE(DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, 0); REG_WAIT(DSCL_MEM_PWR_STATUS, LUT_MEM_PWR_STATE, 0, 1, 5); + } else { + if (dpp->base.ctx->dc->debug.enable_mem_low_power.bits.dscl) { + dpp->base.ctx->dc->optimized_required = true; + dpp->base.deferred_reg_writes.bits.disable_dscl = true; + } else { + REG_UPDATE(DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, 3); + } + } } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index bc3ec05bf34b..a25732d07222 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1366,7 +1366,7 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context) void dcn10_init_hw(struct dc *dc) { - int i; + int i, j; struct abm *abm = dc->res_pool->abm; struct dmcu *dmcu = dc->res_pool->dmcu; struct dce_hwseq *hws = dc->hwseq; @@ -1378,6 +1378,12 @@ void dcn10_init_hw(struct dc *dc) if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); + /* Align bw context with hw config when system resume. */ + if (dc->clk_mgr->clks.dispclk_khz != 0 && dc->clk_mgr->clks.dppclk_khz != 0) { + dc->current_state->bw_ctx.bw.dcn.clk.dispclk_khz = dc->clk_mgr->clks.dispclk_khz; + dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz = dc->clk_mgr->clks.dppclk_khz; + } + // Initialize the dccg if (dc->res_pool->dccg && dc->res_pool->dccg->funcs->dccg_init) dc->res_pool->dccg->funcs->dccg_init(res_pool->dccg); @@ -1462,8 +1468,43 @@ void dcn10_init_hw(struct dc *dc) dmub_enable_outbox_notification(dc); /* we want to turn off all dp displays before doing detection */ - if (dc->config.power_down_display_on_boot) - blank_all_dp_displays(dc, true); + if (dc->config.power_down_display_on_boot) { + uint8_t dpcd_power_state = '\0'; + enum dc_status status = DC_ERROR_UNEXPECTED; + + for (i = 0; i < dc->link_count; i++) { + if (dc->links[i]->connector_signal != SIGNAL_TYPE_DISPLAY_PORT) + continue; + + /* DP 2.0 requires that LTTPR Caps be read first */ + dp_retrieve_lttpr_cap(dc->links[i]); + + /* + * If any of the displays are lit up turn them off. + * The reason is that some MST hubs cannot be turned off + * completely until we tell them to do so. + * If not turned off, then displays connected to MST hub + * won't light up. + */ + status = core_link_read_dpcd(dc->links[i], DP_SET_POWER, + &dpcd_power_state, sizeof(dpcd_power_state)); + if (status == DC_OK && dpcd_power_state == DP_POWER_STATE_D0) { + /* blank dp stream before power off receiver*/ + if (dc->links[i]->link_enc->funcs->get_dig_frontend) { + unsigned int fe = dc->links[i]->link_enc->funcs->get_dig_frontend(dc->links[i]->link_enc); + + for (j = 0; j < dc->res_pool->stream_enc_count; j++) { + if (fe == dc->res_pool->stream_enc[j]->id) { + dc->res_pool->stream_enc[j]->funcs->dp_blank(dc->links[i], + dc->res_pool->stream_enc[j]); + break; + } + } + } + dp_receiver_power_ctrl(dc->links[i], false); + } + } + } /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which @@ -2304,8 +2345,8 @@ static void mmhub_read_vm_context0_settings(struct dcn10_hubp *hubp1, void dcn10_program_pte_vm(struct dce_hwseq *hws, struct hubp *hubp) { struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp); - struct vm_system_aperture_param apt = { {{ 0 } } }; - struct vm_context0_param vm0 = { { { 0 } } }; + struct vm_system_aperture_param apt = {0}; + struct vm_context0_param vm0 = {0}; mmhub_read_vm_system_aperture_settings(hubp1, &apt, hws); mmhub_read_vm_context0_settings(hubp1, &vm0, hws); @@ -2478,7 +2519,7 @@ void dcn10_update_visual_confirm_color(struct dc *dc, struct pipe_ctx *pipe_ctx, void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) { struct hubp *hubp = pipe_ctx->plane_res.hubp; - struct mpcc_blnd_cfg blnd_cfg = {{0}}; + struct mpcc_blnd_cfg blnd_cfg = {0}; bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe; int mpcc_id; struct mpcc *new_mpcc; @@ -3635,7 +3676,7 @@ void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx) void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx, struct dc_link_settings *link_settings) { - struct encoder_unblank_param params = { { 0 } }; + struct encoder_unblank_param params = {0}; struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; struct dce_hwseq *hws = link->dc->hwseq; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h index ede65100a050..f98aba308028 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h @@ -169,7 +169,29 @@ type DTBCLK_DTO_DIV[MAX_PIPES];\ type DCCG_AUDIO_DTO_SEL;\ type DCCG_AUDIO_DTO0_SOURCE_SEL;\ - type DENTIST_DISPCLK_CHG_MODE; + type DENTIST_DISPCLK_CHG_MODE;\ + type DSCCLK0_DTO_PHASE;\ + type DSCCLK0_DTO_MODULO;\ + type DSCCLK1_DTO_PHASE;\ + type DSCCLK1_DTO_MODULO;\ + type DSCCLK2_DTO_PHASE;\ + type DSCCLK2_DTO_MODULO;\ + type DSCCLK0_DTO_ENABLE;\ + type DSCCLK1_DTO_ENABLE;\ + type DSCCLK2_DTO_ENABLE;\ + type SYMCLK32_ROOT_SE0_GATE_DISABLE;\ + type SYMCLK32_ROOT_SE1_GATE_DISABLE;\ + type SYMCLK32_ROOT_SE2_GATE_DISABLE;\ + type SYMCLK32_ROOT_SE3_GATE_DISABLE;\ + type SYMCLK32_ROOT_LE0_GATE_DISABLE;\ + type SYMCLK32_ROOT_LE1_GATE_DISABLE;\ + type DPSTREAMCLK_ROOT_GATE_DISABLE;\ + type DPSTREAMCLK_GATE_DISABLE;\ + type HDMISTREAMCLK0_DTO_PHASE;\ + type HDMISTREAMCLK0_DTO_MODULO;\ + type HDMICHARCLK0_GATE_DISABLE;\ + type HDMICHARCLK0_ROOT_GATE_DISABLE; + struct dccg_shift { DCCG_REG_FIELD_LIST(uint8_t) @@ -205,6 +227,16 @@ struct dccg_registers { uint32_t SYMCLK32_SE_CNTL; uint32_t SYMCLK32_LE_CNTL; uint32_t DENTIST_DISPCLK_CNTL; + uint32_t DSCCLK_DTO_CTRL; + uint32_t DSCCLK0_DTO_PARAM; + uint32_t DSCCLK1_DTO_PARAM; + uint32_t DSCCLK2_DTO_PARAM; + uint32_t DPSTREAMCLK_ROOT_GATE_DISABLE; + uint32_t DPSTREAMCLK_GATE_DISABLE; + uint32_t DCCG_GATE_DISABLE_CNTL3; + uint32_t HDMISTREAMCLK0_DTO_PARAM; + uint32_t DCCG_GATE_DISABLE_CNTL4; + }; struct dcn_dccg { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index fc83744149d9..cfee456c6c9a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2123,7 +2123,7 @@ void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx) void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx, struct dc_link_settings *link_settings) { - struct encoder_unblank_param params = { { 0 } }; + struct encoder_unblank_param params = {0}; struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; struct dce_hwseq *hws = link->dc->hwseq; @@ -2298,7 +2298,7 @@ void dcn20_update_visual_confirm_color(struct dc *dc, struct pipe_ctx *pipe_ctx, void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) { struct hubp *hubp = pipe_ctx->plane_res.hubp; - struct mpcc_blnd_cfg blnd_cfg = { {0} }; + struct mpcc_blnd_cfg blnd_cfg = {0}; bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha; int mpcc_id; struct mpcc *new_mpcc; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 756f5d411d9a..3883f918b3bb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3660,9 +3660,6 @@ static enum dml_project get_dml_project_version(uint32_t hw_internal_rev) return DML_PROJECT_NAVI10v2; } -#define fixed16_to_double(x) (((double) x) / ((double) (1 << 16))) -#define fixed16_to_double_to_cpu(x) fixed16_to_double(le32_to_cpu(x)) - static bool init_soc_bounding_box(struct dc *dc, struct dcn20_resource_pool *pool) { @@ -3698,16 +3695,22 @@ static bool init_soc_bounding_box(struct dc *dc, clock_limits_available = (status == PP_SMU_RESULT_OK); } - if (clock_limits_available && uclk_states_available && num_states) + if (clock_limits_available && uclk_states_available && num_states) { + DC_FP_START(); dcn20_update_bounding_box(dc, loaded_bb, &max_clocks, uclk_states, num_states); - else if (clock_limits_available) + DC_FP_END(); + } else if (clock_limits_available) { + DC_FP_START(); dcn20_cap_soc_clocks(loaded_bb, max_clocks); + DC_FP_END(); + } } loaded_ip->max_num_otg = pool->base.res_cap->num_timing_generator; loaded_ip->max_num_dpp = pool->base.pipe_count; + DC_FP_START(); dcn20_patch_bounding_box(dc, loaded_bb); - + DC_FP_END(); return true; } @@ -3727,8 +3730,6 @@ static bool dcn20_resource_construct( enum dml_project dml_project_version = get_dml_project_version(ctx->asic_id.hw_internal_rev); - DC_FP_START(); - ctx->dc_bios->regs = &bios_regs; pool->base.funcs = &dcn20_res_pool_funcs; @@ -4077,12 +4078,10 @@ static bool dcn20_resource_construct( pool->base.oem_device = NULL; } - DC_FP_END(); return true; create_fail: - DC_FP_END(); dcn20_resource_destruct(pool); return false; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index ef5f6da5248a..c1d967ed6551 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -494,6 +494,20 @@ void dpp3_deferred_update( int bypass_state; struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base); + if (dpp_base->deferred_reg_writes.bits.disable_dscl) { + REG_UPDATE(DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, 3); + dpp_base->deferred_reg_writes.bits.disable_dscl = false; + } + + if (dpp_base->deferred_reg_writes.bits.disable_gamcor) { + REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_MODE_CURRENT, &bypass_state); + if (bypass_state == 0) { // only program if bypass was latched + REG_UPDATE(CM_MEM_PWR_CTRL, GAMCOR_MEM_PWR_FORCE, 3); + } else + ASSERT(0); // LUT select was updated again before vupdate + dpp_base->deferred_reg_writes.bits.disable_gamcor = false; + } + if (dpp_base->deferred_reg_writes.bits.disable_blnd_lut) { REG_GET(CM_BLNDGAM_CONTROL, CM_BLNDGAM_MODE_CURRENT, &bypass_state); if (bypass_state == 0) { // only program if bypass was latched diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c index 72c5687adc68..387eec616162 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c @@ -136,9 +136,13 @@ static void dpp3_power_on_gamcor_lut( struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base); if (dpp_base->ctx->dc->debug.enable_mem_low_power.bits.cm) { - REG_UPDATE(CM_MEM_PWR_CTRL, GAMCOR_MEM_PWR_FORCE, power_on ? 0 : 3); - if (power_on) + if (power_on) { + REG_UPDATE(CM_MEM_PWR_CTRL, GAMCOR_MEM_PWR_FORCE, 0); REG_WAIT(CM_MEM_PWR_STATUS, GAMCOR_MEM_PWR_STATE, 0, 1, 5); + } else { + dpp_base->ctx->dc->optimized_required = true; + dpp_base->deferred_reg_writes.bits.disable_gamcor = true; + } } else REG_SET(CM_MEM_PWR_CTRL, 0, GAMCOR_MEM_PWR_DIS, power_on == true ? 0:1); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 01a90badd173..df2717116604 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -437,7 +437,7 @@ void dcn30_init_hw(struct dc *dc) struct dce_hwseq *hws = dc->hwseq; struct dc_bios *dcb = dc->ctx->dc_bios; struct resource_pool *res_pool = dc->res_pool; - int i; + int i, j; int edp_num; uint32_t backlight = MAX_BACKLIGHT_LEVEL; @@ -534,8 +534,41 @@ void dcn30_init_hw(struct dc *dc) hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); /* we want to turn off all dp displays before doing detection */ - if (dc->config.power_down_display_on_boot) - blank_all_dp_displays(dc, true); + if (dc->config.power_down_display_on_boot) { + uint8_t dpcd_power_state = '\0'; + enum dc_status status = DC_ERROR_UNEXPECTED; + + for (i = 0; i < dc->link_count; i++) { + if (dc->links[i]->connector_signal != SIGNAL_TYPE_DISPLAY_PORT) + continue; + /* DP 2.0 states that LTTPR regs must be read first */ + dp_retrieve_lttpr_cap(dc->links[i]); + + /* if any of the displays are lit up turn them off */ + status = core_link_read_dpcd(dc->links[i], DP_SET_POWER, + &dpcd_power_state, sizeof(dpcd_power_state)); + if (status == DC_OK && dpcd_power_state == DP_POWER_STATE_D0) { + /* blank dp stream before power off receiver*/ + if (dc->links[i]->link_enc->funcs->get_dig_frontend) { + unsigned int fe; + + fe = dc->links[i]->link_enc->funcs->get_dig_frontend( + dc->links[i]->link_enc); + if (fe == ENGINE_ID_UNKNOWN) + continue; + + for (j = 0; j < dc->res_pool->stream_enc_count; j++) { + if (fe == dc->res_pool->stream_enc[j]->id) { + dc->res_pool->stream_enc[j]->funcs->dp_blank(dc->links[i], + dc->res_pool->stream_enc[j]); + break; + } + } + } + dp_receiver_power_ctrl(dc->links[i], false); + } + } + } /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which @@ -969,7 +1002,8 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, /* turning off DPG */ pipe_ctx->plane_res.hubp->funcs->set_blank(pipe_ctx->plane_res.hubp, false); for (mpcc_pipe = pipe_ctx->bottom_pipe; mpcc_pipe; mpcc_pipe = mpcc_pipe->bottom_pipe) - mpcc_pipe->plane_res.hubp->funcs->set_blank(mpcc_pipe->plane_res.hubp, false); + if (mpcc_pipe->plane_res.hubp) + mpcc_pipe->plane_res.hubp->funcs->set_blank(mpcc_pipe->plane_res.hubp, false); stream_res->opp->funcs->opp_set_disp_pattern_generator(stream_res->opp, test_pattern, color_space, color_depth, solid_color, width, height, offset); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 3a8a3214f770..e50c695e3c96 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -1707,9 +1707,6 @@ bool dcn30_release_post_bldn_3dlut( return ret; } -#define fixed16_to_double(x) (((double) x) / ((double) (1 << 16))) -#define fixed16_to_double_to_cpu(x) fixed16_to_double(le32_to_cpu(x)) - static bool is_soc_bounding_box_valid(struct dc *dc) { uint32_t hw_internal_rev = dc->ctx->asic_id.hw_internal_rev; @@ -1929,23 +1926,25 @@ noinline bool dcn30_internal_validate_bw( if (vlevel == context->bw_ctx.dml.soc.num_states) goto validate_fail; - for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - struct pipe_ctx *mpo_pipe = pipe->bottom_pipe; + if (!dc->config.enable_windowed_mpo_odm) { + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *mpo_pipe = pipe->bottom_pipe; - if (!pipe->stream) - continue; + if (!pipe->stream) + continue; - /* We only support full screen mpo with ODM */ - if (vba->ODMCombineEnabled[vba->pipe_plane[pipe_idx]] != dm_odm_combine_mode_disabled - && pipe->plane_state && mpo_pipe - && memcmp(&mpo_pipe->plane_res.scl_data.recout, - &pipe->plane_res.scl_data.recout, - sizeof(struct rect)) != 0) { - ASSERT(mpo_pipe->plane_state != pipe->plane_state); - goto validate_fail; + /* We only support full screen mpo with ODM */ + if (vba->ODMCombineEnabled[vba->pipe_plane[pipe_idx]] != dm_odm_combine_mode_disabled + && pipe->plane_state && mpo_pipe + && memcmp(&mpo_pipe->plane_res.scl_data.recout, + &pipe->plane_res.scl_data.recout, + sizeof(struct rect)) != 0) { + ASSERT(mpo_pipe->plane_state != pipe->plane_state); + goto validate_fail; + } + pipe_idx++; } - pipe_idx++; } /* merge pipes if necessary */ @@ -2323,7 +2322,9 @@ bool dcn30_validate_bandwidth(struct dc *dc, goto validate_out; } + DC_FP_START(); dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel); + DC_FP_END(); BW_VAL_TRACE_END_WATERMARKS(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile index 09264716d1dc..7aa628c21973 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile @@ -13,32 +13,6 @@ DCN301 = dcn301_init.o dcn301_resource.o dcn301_dccg.o \ dcn301_dio_link_encoder.o dcn301_hwseq.o dcn301_panel_cntl.o dcn301_hubbub.o -ifdef CONFIG_X86 -CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -msse -endif - -ifdef CONFIG_PPC64 -CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mhard-float -maltivec -endif - -ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) -IS_OLD_GCC = 1 -endif -CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o += -mhard-float -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o += -mpreferred-stack-boundary=4 -else -CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o += -msse2 -endif -endif - AMD_DAL_DCN301 = $(addprefix $(AMDDALPATH)/dc/dcn301/,$(DCN301)) AMD_DISPLAY_FILES += $(AMD_DAL_DCN301) diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 5350c93d7772..fbaa03f26d8b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -82,6 +82,7 @@ #include "dce/dce_i2c.h" #include "dml/dcn30/display_mode_vba_30.h" +#include "dml/dcn301/dcn301_fpu.h" #include "vm_helper.h" #include "dcn20/dcn20_vmid.h" #include "amdgpu_socbb.h" @@ -91,184 +92,6 @@ #define DC_LOGGER_INIT(logger) -struct _vcs_dpi_ip_params_st dcn3_01_ip = { - .odm_capable = 1, - .gpuvm_enable = 1, - .hostvm_enable = 1, - .gpuvm_max_page_table_levels = 1, - .hostvm_max_page_table_levels = 2, - .hostvm_cached_page_table_levels = 0, - .pte_group_size_bytes = 2048, - .num_dsc = 3, - .rob_buffer_size_kbytes = 184, - .det_buffer_size_kbytes = 184, - .dpte_buffer_size_in_pte_reqs_luma = 64, - .dpte_buffer_size_in_pte_reqs_chroma = 32, - .pde_proc_buffer_size_64k_reqs = 48, - .dpp_output_buffer_pixels = 2560, - .opp_output_buffer_lines = 1, - .pixel_chunk_size_kbytes = 8, - .meta_chunk_size_kbytes = 2, - .writeback_chunk_size_kbytes = 8, - .line_buffer_size_bits = 789504, - .is_line_buffer_bpp_fixed = 0, // ? - .line_buffer_fixed_bpp = 48, // ? - .dcc_supported = true, - .writeback_interface_buffer_size_kbytes = 90, - .writeback_line_buffer_buffer_size = 656640, - .max_line_buffer_lines = 12, - .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 - .writeback_chroma_buffer_size_kbytes = 8, - .writeback_chroma_line_buffer_width_pixels = 4, - .writeback_max_hscl_ratio = 1, - .writeback_max_vscl_ratio = 1, - .writeback_min_hscl_ratio = 1, - .writeback_min_vscl_ratio = 1, - .writeback_max_hscl_taps = 1, - .writeback_max_vscl_taps = 1, - .writeback_line_buffer_luma_buffer_size = 0, - .writeback_line_buffer_chroma_buffer_size = 14643, - .cursor_buffer_size = 8, - .cursor_chunk_size = 2, - .max_num_otg = 4, - .max_num_dpp = 4, - .max_num_wb = 1, - .max_dchub_pscl_bw_pix_per_clk = 4, - .max_pscl_lb_bw_pix_per_clk = 2, - .max_lb_vscl_bw_pix_per_clk = 4, - .max_vscl_hscl_bw_pix_per_clk = 4, - .max_hscl_ratio = 6, - .max_vscl_ratio = 6, - .hscl_mults = 4, - .vscl_mults = 4, - .max_hscl_taps = 8, - .max_vscl_taps = 8, - .dispclk_ramp_margin_percent = 1, - .underscan_factor = 1.11, - .min_vblank_lines = 32, - .dppclk_delay_subtotal = 46, - .dynamic_metadata_vm_enabled = true, - .dppclk_delay_scl_lb_only = 16, - .dppclk_delay_scl = 50, - .dppclk_delay_cnvc_formatter = 27, - .dppclk_delay_cnvc_cursor = 6, - .dispclk_delay_subtotal = 119, - .dcfclk_cstate_latency = 5.2, // SRExitTime - .max_inter_dcn_tile_repeaters = 8, - .max_num_hdmi_frl_outputs = 0, - .odm_combine_4to1_supported = true, - - .xfc_supported = false, - .xfc_fill_bw_overhead_percent = 10.0, - .xfc_fill_constant_bytes = 0, - .gfx7_compat_tiling_supported = 0, - .number_of_cursors = 1, -}; - -struct _vcs_dpi_soc_bounding_box_st dcn3_01_soc = { - .clock_limits = { - { - .state = 0, - .dram_speed_mts = 2400.0, - .fabricclk_mhz = 600, - .socclk_mhz = 278.0, - .dcfclk_mhz = 400.0, - .dscclk_mhz = 206.0, - .dppclk_mhz = 1015.0, - .dispclk_mhz = 1015.0, - .phyclk_mhz = 600.0, - }, - { - .state = 1, - .dram_speed_mts = 2400.0, - .fabricclk_mhz = 688, - .socclk_mhz = 278.0, - .dcfclk_mhz = 400.0, - .dscclk_mhz = 206.0, - .dppclk_mhz = 1015.0, - .dispclk_mhz = 1015.0, - .phyclk_mhz = 600.0, - }, - { - .state = 2, - .dram_speed_mts = 4267.0, - .fabricclk_mhz = 1067, - .socclk_mhz = 278.0, - .dcfclk_mhz = 608.0, - .dscclk_mhz = 296.0, - .dppclk_mhz = 1015.0, - .dispclk_mhz = 1015.0, - .phyclk_mhz = 810.0, - }, - - { - .state = 3, - .dram_speed_mts = 4267.0, - .fabricclk_mhz = 1067, - .socclk_mhz = 715.0, - .dcfclk_mhz = 676.0, - .dscclk_mhz = 338.0, - .dppclk_mhz = 1015.0, - .dispclk_mhz = 1015.0, - .phyclk_mhz = 810.0, - }, - - { - .state = 4, - .dram_speed_mts = 4267.0, - .fabricclk_mhz = 1067, - .socclk_mhz = 953.0, - .dcfclk_mhz = 810.0, - .dscclk_mhz = 338.0, - .dppclk_mhz = 1015.0, - .dispclk_mhz = 1015.0, - .phyclk_mhz = 810.0, - }, - }, - - .sr_exit_time_us = 9.0, - .sr_enter_plus_exit_time_us = 11.0, - .urgent_latency_us = 4.0, - .urgent_latency_pixel_data_only_us = 4.0, - .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, - .urgent_latency_vm_data_only_us = 4.0, - .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, - .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, - .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0, - .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 75.0, - .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, - .max_avg_sdp_bw_use_normal_percent = 60.0, - .max_avg_dram_bw_use_normal_percent = 60.0, - .writeback_latency_us = 12.0, - .max_request_size_bytes = 256, - .dram_channel_width_bytes = 4, - .fabric_datapath_to_dcn_data_return_bytes = 32, - .dcn_downspread_percent = 0.5, - .downspread_percent = 0.38, - .dram_page_open_time_ns = 50.0, - .dram_rw_turnaround_time_ns = 17.5, - .dram_return_buffer_per_channel_bytes = 8192, - .round_trip_ping_latency_dcfclk_cycles = 191, - .urgent_out_of_order_return_per_channel_bytes = 4096, - .channel_interleave_bytes = 256, - .num_banks = 8, - .num_chans = 4, - .gpuvm_min_page_size_bytes = 4096, - .hostvm_min_page_size_bytes = 4096, - .dram_clock_change_latency_us = 23.84, - .writeback_dram_clock_change_latency_us = 23.0, - .return_bus_width_bytes = 64, - .dispclk_dppclk_vco_speed_mhz = 3550, - .xfc_bus_transport_time_us = 20, // ? - .xfc_xbuf_latency_tolerance_us = 4, // ? - .use_urgent_burst_bw = 1, // ? - .num_states = 5, - .do_urgent_latency_adjustment = false, - .urgent_latency_adjustment_fabric_clock_component_us = 0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, -}; - enum dcn301_clk_src_array_id { DCN301_CLK_SRC_PLL0, DCN301_CLK_SRC_PLL1, @@ -1480,8 +1303,6 @@ static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; -#define fixed16_to_double(x) (((double) x) / ((double) (1 << 16))) -#define fixed16_to_double_to_cpu(x) fixed16_to_double(le32_to_cpu(x)) static bool is_soc_bounding_box_valid(struct dc *dc) { @@ -1508,26 +1329,24 @@ static bool init_soc_bounding_box(struct dc *dc, loaded_ip->max_num_otg = pool->base.res_cap->num_timing_generator; loaded_ip->max_num_dpp = pool->base.pipe_count; + DC_FP_START(); dcn20_patch_bounding_box(dc, loaded_bb); + DC_FP_END(); if (dc->ctx->dc_bios->funcs->get_soc_bb_info) { struct bp_soc_bb_info bb_info = {0}; if (dc->ctx->dc_bios->funcs->get_soc_bb_info(dc->ctx->dc_bios, &bb_info) == BP_RESULT_OK) { - if (bb_info.dram_clock_change_latency_100ns > 0) - dcn3_01_soc.dram_clock_change_latency_us = bb_info.dram_clock_change_latency_100ns * 10; - - if (bb_info.dram_sr_enter_exit_latency_100ns > 0) - dcn3_01_soc.sr_enter_plus_exit_time_us = bb_info.dram_sr_enter_exit_latency_100ns * 10; - - if (bb_info.dram_sr_exit_latency_100ns > 0) - dcn3_01_soc.sr_exit_time_us = bb_info.dram_sr_exit_latency_100ns * 10; + DC_FP_START(); + dcn301_fpu_init_soc_bounding_box(bb_info); + DC_FP_END(); } } return true; } + static void set_wm_ranges( struct pp_smu_funcs *pp_smu, struct _vcs_dpi_soc_bounding_box_st *loaded_bb) @@ -1550,9 +1369,9 @@ static void set_wm_ranges( ranges.reader_wm_sets[i].wm_inst = i; ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN; ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; - ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0; - ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16; - + DC_FP_START(); + dcn301_fpu_set_wm_ranges(i, &ranges, loaded_bb); + DC_FP_END(); ranges.num_reader_wm_sets = i + 1; } @@ -1572,154 +1391,6 @@ static void set_wm_ranges( pp_smu->nv_funcs.set_wm_ranges(&pp_smu->nv_funcs.pp_smu, &ranges); } -static void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) -{ - struct dcn301_resource_pool *pool = TO_DCN301_RES_POOL(dc->res_pool); - struct clk_limit_table *clk_table = &bw_params->clk_table; - struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; - unsigned int i, closest_clk_lvl; - int j; - - // Default clock levels are used for diags, which may lead to overclocking. - if (!IS_DIAG_DC(dc->ctx->dce_environment)) { - dcn3_01_ip.max_num_otg = pool->base.res_cap->num_timing_generator; - dcn3_01_ip.max_num_dpp = pool->base.pipe_count; - dcn3_01_soc.num_chans = bw_params->num_channels; - - ASSERT(clk_table->num_entries); - for (i = 0; i < clk_table->num_entries; i++) { - /* loop backwards*/ - for (closest_clk_lvl = 0, j = dcn3_01_soc.num_states - 1; j >= 0; j--) { - if ((unsigned int) dcn3_01_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { - closest_clk_lvl = j; - break; - } - } - - clock_limits[i].state = i; - clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; - clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz; - clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz; - clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; - - clock_limits[i].dispclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dispclk_mhz; - clock_limits[i].dppclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dppclk_mhz; - clock_limits[i].dram_bw_per_chan_gbps = dcn3_01_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps; - clock_limits[i].dscclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dscclk_mhz; - clock_limits[i].dtbclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dtbclk_mhz; - clock_limits[i].phyclk_d18_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz; - clock_limits[i].phyclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].phyclk_mhz; - } - for (i = 0; i < clk_table->num_entries; i++) - dcn3_01_soc.clock_limits[i] = clock_limits[i]; - if (clk_table->num_entries) { - dcn3_01_soc.num_states = clk_table->num_entries; - /* duplicate last level */ - dcn3_01_soc.clock_limits[dcn3_01_soc.num_states] = dcn3_01_soc.clock_limits[dcn3_01_soc.num_states - 1]; - dcn3_01_soc.clock_limits[dcn3_01_soc.num_states].state = dcn3_01_soc.num_states; - } - } - - dcn3_01_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; - dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; - - dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30); -} - -static void calculate_wm_set_for_vlevel( - int vlevel, - struct wm_range_table_entry *table_entry, - struct dcn_watermarks *wm_set, - struct display_mode_lib *dml, - display_e2e_pipe_params_st *pipes, - int pipe_cnt) -{ - double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; - - ASSERT(vlevel < dml->soc.num_states); - /* only pipe 0 is read for voltage and dcf/soc clocks */ - pipes[0].clks_cfg.voltage = vlevel; - pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; - pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; - - dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; - dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; - dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; - - wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; - wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; - wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; - wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; - wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; - wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; - wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; - wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; - dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; - -} - -static void dcn301_calculate_wm_and_dlg( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int pipe_cnt, - int vlevel_req) -{ - int i, pipe_idx; - int vlevel, vlevel_max; - struct wm_range_table_entry *table_entry; - struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; - - ASSERT(bw_params); - - vlevel_max = bw_params->clk_table.num_entries - 1; - - /* WM Set D */ - table_entry = &bw_params->wm_table.entries[WM_D]; - if (table_entry->wm_type == WM_TYPE_RETRAINING) - vlevel = 0; - else - vlevel = vlevel_max; - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, - &context->bw_ctx.dml, pipes, pipe_cnt); - /* WM Set C */ - table_entry = &bw_params->wm_table.entries[WM_C]; - vlevel = min(max(vlevel_req, 2), vlevel_max); - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, - &context->bw_ctx.dml, pipes, pipe_cnt); - /* WM Set B */ - table_entry = &bw_params->wm_table.entries[WM_B]; - vlevel = min(max(vlevel_req, 1), vlevel_max); - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, - &context->bw_ctx.dml, pipes, pipe_cnt); - - /* WM Set A */ - table_entry = &bw_params->wm_table.entries[WM_A]; - vlevel = min(vlevel_req, vlevel_max); - calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, - &context->bw_ctx.dml, pipes, pipe_cnt); - - for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { - if (!context->res_ctx.pipe_ctx[i].stream) - continue; - - pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); - pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); - - if (dc->config.forced_clocks) { - pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; - pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; - } - if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000) - pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; - if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) - pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; - - pipe_idx++; - } - - dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); -} - static struct resource_funcs dcn301_res_pool_funcs = { .destroy = dcn301_destroy_resource_pool, .link_enc_create = dcn301_link_encoder_create, diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.h b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.h index 17e4e91ff4b8..ae8672680cdd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.h @@ -32,6 +32,9 @@ struct dc; struct resource_pool; struct _vcs_dpi_display_pipe_params_st; +extern struct _vcs_dpi_ip_params_st dcn3_01_ip; +extern struct _vcs_dpi_soc_bounding_box_st dcn3_01_soc; + struct dcn301_resource_pool { struct resource_pool base; }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 2ce6eae7535d..4a9b64023675 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -1344,6 +1344,20 @@ void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz; dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz; } + + // WA: patch strobe modes to compensate for DCN303 BW issue + if (dcn3_03_soc.num_chans <= 4) { + for (i = 0; i < dcn3_03_soc.num_states; i++) { + if (dcn3_03_soc.clock_limits[i].dram_speed_mts > 1700) + break; + + if (dcn3_03_soc.clock_limits[i].dram_speed_mts >= 1500) { + dcn3_03_soc.clock_limits[i].dcfclk_mhz = 100; + dcn3_03_soc.clock_limits[i].fabricclk_mhz = 100; + } + } + } + /* re-init DML with updated bb */ dml_init_instance(&dc->dml, &dcn3_03_soc, &dcn3_03_ip, DML_PROJECT_DCN30); if (dc->current_state) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_apg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_apg.c index 6bd7a0626665..de5e18c2a3ac 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_apg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_apg.c @@ -129,7 +129,7 @@ static void apg31_se_audio_setup( /* When running in "pair mode", pairs of audio channels have their own enable * this is for really old audio drivers */ - REG_UPDATE(APG_DBG_GEN_CONTROL, APG_DBG_AUDIO_CHANNEL_ENABLE, 0xF); + REG_UPDATE(APG_DBG_GEN_CONTROL, APG_DBG_AUDIO_CHANNEL_ENABLE, 0xFF); // REG_UPDATE(APG_DBG_GEN_CONTROL, APG_DBG_AUDIO_CHANNEL_ENABLE, channels); /* Disable forced mem power off */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c index 9896adf67425..815481a3ef54 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c @@ -26,6 +26,7 @@ #include "reg_helper.h" #include "core_types.h" #include "dcn31_dccg.h" +#include "dal_asic_id.h" #define TO_DCN_DCCG(dccg)\ container_of(dccg, struct dcn_dccg, base) @@ -42,10 +43,58 @@ #define DC_LOGGER \ dccg->ctx->logger -void dccg31_set_dpstreamclk( - struct dccg *dccg, - enum hdmistreamclk_source src, - int otg_inst) +static void dccg31_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + + if (dccg->ref_dppclk && req_dppclk) { + int ref_dppclk = dccg->ref_dppclk; + int modulo, phase; + + // phase / modulo = dpp pipe clk / dpp global clk + modulo = 0xff; // use FF at the end + phase = ((modulo * req_dppclk) + ref_dppclk - 1) / ref_dppclk; + + if (phase > 0xff) { + ASSERT(false); + phase = 0xff; + } + + REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0, + DPPCLK0_DTO_PHASE, phase, + DPPCLK0_DTO_MODULO, modulo); + REG_UPDATE(DPPCLK_DTO_CTRL, + DPPCLK_DTO_ENABLE[dpp_inst], 1); + } else { + //DTO must be enabled to generate a 0Hz clock output + if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) { + REG_UPDATE(DPPCLK_DTO_CTRL, + DPPCLK_DTO_ENABLE[dpp_inst], 1); + REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0, + DPPCLK0_DTO_PHASE, 0, + DPPCLK0_DTO_MODULO, 1); + } else { + REG_UPDATE(DPPCLK_DTO_CTRL, + DPPCLK_DTO_ENABLE[dpp_inst], 0); + } + } + dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk; +} + +static enum phyd32clk_clock_source get_phy_mux_symclk( + struct dcn_dccg *dccg_dcn, + enum phyd32clk_clock_source src) +{ + if (dccg_dcn->base.ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) { + if (src == PHYD32CLKC) + src = PHYD32CLKF; + if (src == PHYD32CLKD) + src = PHYD32CLKG; + } + return src; +} + +static void dccg31_enable_dpstreamclk(struct dccg *dccg, int otg_inst) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); @@ -53,24 +102,69 @@ void dccg31_set_dpstreamclk( switch (otg_inst) { case 0: REG_UPDATE(DPSTREAMCLK_CNTL, - DPSTREAMCLK_PIPE0_EN, (src == REFCLK) ? 0 : 1); + DPSTREAMCLK_PIPE0_EN, 1); break; case 1: REG_UPDATE(DPSTREAMCLK_CNTL, - DPSTREAMCLK_PIPE1_EN, (src == REFCLK) ? 0 : 1); + DPSTREAMCLK_PIPE1_EN, 1); break; case 2: REG_UPDATE(DPSTREAMCLK_CNTL, - DPSTREAMCLK_PIPE2_EN, (src == REFCLK) ? 0 : 1); + DPSTREAMCLK_PIPE2_EN, 1); break; case 3: REG_UPDATE(DPSTREAMCLK_CNTL, - DPSTREAMCLK_PIPE3_EN, (src == REFCLK) ? 0 : 1); + DPSTREAMCLK_PIPE3_EN, 1); break; default: BREAK_TO_DEBUGGER(); return; } + if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + DPSTREAMCLK_ROOT_GATE_DISABLE, 1); +} + +static void dccg31_disable_dpstreamclk(struct dccg *dccg, int otg_inst) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + + if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + DPSTREAMCLK_ROOT_GATE_DISABLE, 0); + + switch (otg_inst) { + case 0: + REG_UPDATE(DPSTREAMCLK_CNTL, + DPSTREAMCLK_PIPE0_EN, 0); + break; + case 1: + REG_UPDATE(DPSTREAMCLK_CNTL, + DPSTREAMCLK_PIPE1_EN, 0); + break; + case 2: + REG_UPDATE(DPSTREAMCLK_CNTL, + DPSTREAMCLK_PIPE2_EN, 0); + break; + case 3: + REG_UPDATE(DPSTREAMCLK_CNTL, + DPSTREAMCLK_PIPE3_EN, 0); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } +} + +void dccg31_set_dpstreamclk( + struct dccg *dccg, + enum hdmistreamclk_source src, + int otg_inst) +{ + if (src == REFCLK) + dccg31_disable_dpstreamclk(dccg, otg_inst); + else + dccg31_enable_dpstreamclk(dccg, otg_inst); } void dccg31_enable_symclk32_se( @@ -80,24 +174,38 @@ void dccg31_enable_symclk32_se( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + phyd32clk = get_phy_mux_symclk(dccg_dcn, phyd32clk); + /* select one of the PHYD32CLKs as the source for symclk32_se */ switch (hpo_se_inst) { case 0: + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE0_GATE_DISABLE, 1); REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE0_SRC_SEL, phyd32clk, SYMCLK32_SE0_EN, 1); break; case 1: + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE1_GATE_DISABLE, 1); REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE1_SRC_SEL, phyd32clk, SYMCLK32_SE1_EN, 1); break; case 2: + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE2_GATE_DISABLE, 1); REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE2_SRC_SEL, phyd32clk, SYMCLK32_SE2_EN, 1); break; case 3: + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE3_GATE_DISABLE, 1); REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE3_SRC_SEL, phyd32clk, SYMCLK32_SE3_EN, 1); @@ -120,21 +228,33 @@ void dccg31_disable_symclk32_se( REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE0_SRC_SEL, 0, SYMCLK32_SE0_EN, 0); + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE0_GATE_DISABLE, 0); break; case 1: REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE1_SRC_SEL, 0, SYMCLK32_SE1_EN, 0); + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE1_GATE_DISABLE, 0); break; case 2: REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE2_SRC_SEL, 0, SYMCLK32_SE2_EN, 0); + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE2_GATE_DISABLE, 0); break; case 3: REG_UPDATE_2(SYMCLK32_SE_CNTL, SYMCLK32_SE3_SRC_SEL, 0, SYMCLK32_SE3_EN, 0); + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_SE3_GATE_DISABLE, 0); break; default: BREAK_TO_DEBUGGER(); @@ -149,14 +269,22 @@ void dccg31_enable_symclk32_le( { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + phyd32clk = get_phy_mux_symclk(dccg_dcn, phyd32clk); + /* select one of the PHYD32CLKs as the source for symclk32_le */ switch (hpo_le_inst) { case 0: + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_LE0_GATE_DISABLE, 1); REG_UPDATE_2(SYMCLK32_LE_CNTL, SYMCLK32_LE0_SRC_SEL, phyd32clk, SYMCLK32_LE0_EN, 1); break; case 1: + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_LE1_GATE_DISABLE, 1); REG_UPDATE_2(SYMCLK32_LE_CNTL, SYMCLK32_LE1_SRC_SEL, phyd32clk, SYMCLK32_LE1_EN, 1); @@ -179,11 +307,87 @@ void dccg31_disable_symclk32_le( REG_UPDATE_2(SYMCLK32_LE_CNTL, SYMCLK32_LE0_SRC_SEL, 0, SYMCLK32_LE0_EN, 0); + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_LE0_GATE_DISABLE, 0); break; case 1: REG_UPDATE_2(SYMCLK32_LE_CNTL, SYMCLK32_LE1_SRC_SEL, 0, SYMCLK32_LE1_EN, 0); + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le) + REG_UPDATE(DCCG_GATE_DISABLE_CNTL3, + SYMCLK32_ROOT_LE1_GATE_DISABLE, 0); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } +} + +static void dccg31_disable_dscclk(struct dccg *dccg, int inst) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) + return; + //DTO must be enabled to generate a 0 Hz clock output + switch (inst) { + case 0: + REG_UPDATE(DSCCLK_DTO_CTRL, + DSCCLK0_DTO_ENABLE, 1); + REG_UPDATE_2(DSCCLK0_DTO_PARAM, + DSCCLK0_DTO_PHASE, 0, + DSCCLK0_DTO_MODULO, 1); + break; + case 1: + REG_UPDATE(DSCCLK_DTO_CTRL, + DSCCLK1_DTO_ENABLE, 1); + REG_UPDATE_2(DSCCLK1_DTO_PARAM, + DSCCLK1_DTO_PHASE, 0, + DSCCLK1_DTO_MODULO, 1); + break; + case 2: + REG_UPDATE(DSCCLK_DTO_CTRL, + DSCCLK2_DTO_ENABLE, 1); + REG_UPDATE_2(DSCCLK2_DTO_PARAM, + DSCCLK2_DTO_PHASE, 0, + DSCCLK2_DTO_MODULO, 1); + break; + default: + BREAK_TO_DEBUGGER(); + return; + } +} + +static void dccg31_enable_dscclk(struct dccg *dccg, int inst) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) + return; + //Disable DTO + switch (inst) { + case 0: + REG_UPDATE_2(DSCCLK0_DTO_PARAM, + DSCCLK0_DTO_PHASE, 0, + DSCCLK0_DTO_MODULO, 0); + REG_UPDATE(DSCCLK_DTO_CTRL, + DSCCLK0_DTO_ENABLE, 0); + break; + case 1: + REG_UPDATE_2(DSCCLK1_DTO_PARAM, + DSCCLK1_DTO_PHASE, 0, + DSCCLK1_DTO_MODULO, 0); + REG_UPDATE(DSCCLK_DTO_CTRL, + DSCCLK1_DTO_ENABLE, 0); + break; + case 2: + REG_UPDATE_2(DSCCLK2_DTO_PARAM, + DSCCLK2_DTO_PHASE, 0, + DSCCLK2_DTO_MODULO, 0); + REG_UPDATE(DSCCLK_DTO_CTRL, + DSCCLK2_DTO_ENABLE, 0); break; default: BREAK_TO_DEBUGGER(); @@ -398,10 +602,23 @@ void dccg31_init(struct dccg *dccg) dccg31_disable_symclk32_se(dccg, 1); dccg31_disable_symclk32_se(dccg, 2); dccg31_disable_symclk32_se(dccg, 3); + + if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_le) { + dccg31_disable_symclk32_le(dccg, 0); + dccg31_disable_symclk32_le(dccg, 1); + } + + if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpstream) { + dccg31_disable_dpstreamclk(dccg, 0); + dccg31_disable_dpstreamclk(dccg, 1); + dccg31_disable_dpstreamclk(dccg, 2); + dccg31_disable_dpstreamclk(dccg, 3); + } + } static const struct dccg_funcs dccg31_funcs = { - .update_dpp_dto = dccg2_update_dpp_dto, + .update_dpp_dto = dccg31_update_dpp_dto, .get_dccg_ref_freq = dccg31_get_dccg_ref_freq, .dccg_init = dccg31_init, .set_dpstreamclk = dccg31_set_dpstreamclk, @@ -413,6 +630,8 @@ static const struct dccg_funcs dccg31_funcs = { .set_dtbclk_dto = dccg31_set_dtbclk_dto, .set_audio_dtbclk_dto = dccg31_set_audio_dtbclk_dto, .set_dispclk_change_mode = dccg31_set_dispclk_change_mode, + .disable_dsc = dccg31_disable_dscclk, + .enable_dsc = dccg31_enable_dscclk, }; struct dccg *dccg31_create( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.h index 1e5aabcb7799..a013a32bbaf7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.h @@ -61,7 +61,13 @@ SR(DCCG_AUDIO_DTBCLK_DTO_MODULO),\ SR(DCCG_AUDIO_DTBCLK_DTO_PHASE),\ SR(DCCG_AUDIO_DTO_SOURCE),\ - SR(DENTIST_DISPCLK_CNTL) + SR(DENTIST_DISPCLK_CNTL),\ + SR(DSCCLK0_DTO_PARAM),\ + SR(DSCCLK1_DTO_PARAM),\ + SR(DSCCLK2_DTO_PARAM),\ + SR(DSCCLK_DTO_CTRL),\ + SR(DCCG_GATE_DISABLE_CNTL3),\ + SR(HDMISTREAMCLK0_DTO_PARAM) #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \ @@ -119,7 +125,26 @@ DCCG_SFII(OTG, PIXEL_RATE_CNTL, DTBCLK_DTO, DIV, 3, mask_sh),\ DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO_SEL, mask_sh),\ DCCG_SF(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL, mask_sh),\ - DCCG_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_MODE, mask_sh) + DCCG_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_MODE, mask_sh), \ + DCCG_SF(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_PHASE, mask_sh),\ + DCCG_SF(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_MODULO, mask_sh),\ + DCCG_SF(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_PHASE, mask_sh),\ + DCCG_SF(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_MODULO, mask_sh),\ + DCCG_SF(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_PHASE, mask_sh),\ + DCCG_SF(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_MODULO, mask_sh),\ + DCCG_SF(DSCCLK_DTO_CTRL, DSCCLK0_DTO_ENABLE, mask_sh),\ + DCCG_SF(DSCCLK_DTO_CTRL, DSCCLK1_DTO_ENABLE, mask_sh),\ + DCCG_SF(DSCCLK_DTO_CTRL, DSCCLK2_DTO_ENABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, DPSTREAMCLK_ROOT_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, DPSTREAMCLK_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE0_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE1_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE2_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_SE3_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_LE0_GATE_DISABLE, mask_sh),\ + DCCG_SF(DCCG_GATE_DISABLE_CNTL3, SYMCLK32_ROOT_LE1_GATE_DISABLE, mask_sh),\ + DCCG_SF(HDMISTREAMCLK0_DTO_PARAM, HDMISTREAMCLK0_DTO_PHASE, mask_sh),\ + DCCG_SF(HDMISTREAMCLK0_DTO_PARAM, HDMISTREAMCLK0_DTO_MODULO, mask_sh) struct dccg *dccg31_create( @@ -130,6 +155,11 @@ struct dccg *dccg31_create( void dccg31_init(struct dccg *dccg); +void dccg31_set_dpstreamclk( + struct dccg *dccg, + enum hdmistreamclk_source src, + int otg_inst); + void dccg31_enable_symclk32_se( struct dccg *dccg, int hpo_se_inst, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c index 8f8eee475144..ee6f13bef377 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c @@ -431,7 +431,7 @@ void dcn31_link_encoder_enable_dp_output( if (link) { dpia_control.dpia_id = link->ddc_hw_inst; - dpia_control.fec_rdy = link->fec_state == dc_link_fec_ready ? 1 : 0; + dpia_control.fec_rdy = dc_link_should_enable_fec(link); } else { DC_LOG_ERROR("%s: Failed to execute DPIA enable DMUB command.\n", __func__); BREAK_TO_DEBUGGER(); @@ -476,7 +476,7 @@ void dcn31_link_encoder_enable_dp_mst_output( if (link) { dpia_control.dpia_id = link->ddc_hw_inst; - dpia_control.fec_rdy = link->fec_state == dc_link_fec_ready ? 1 : 0; + dpia_control.fec_rdy = dc_link_should_enable_fec(link); } else { DC_LOG_ERROR("%s: Failed to execute DPIA enable DMUB command.\n", __func__); BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 03cdd8eaff00..d24ad7754d71 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -49,6 +49,8 @@ #include "inc/link_dpcd.h" #include "dcn10/dcn10_hw_sequencer.h" #include "inc/link_enc_cfg.h" +#include "dcn30/dcn30_vpg.h" +#include "dce/dce_i2c_hw.h" #define DC_LOGGER_INIT(logger) @@ -71,8 +73,7 @@ void dcn31_init_hw(struct dc *dc) struct dc_bios *dcb = dc->ctx->dc_bios; struct resource_pool *res_pool = dc->res_pool; uint32_t backlight = MAX_BACKLIGHT_LEVEL; - int i; - int edp_num; + int i, j; if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); @@ -125,6 +126,18 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, 1); } +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (dc->debug.enable_mem_low_power.bits.vpg && dc->res_pool->stream_enc[0]->vpg->funcs->vpg_powerdown) { + // Power down VPGs + for (i = 0; i < dc->res_pool->stream_enc_count; i++) + dc->res_pool->stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->stream_enc[i]->vpg); +#if defined(CONFIG_DRM_AMD_DC_DP2_0) + for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++) + dc->res_pool->hpo_dp_stream_enc[i]->vpg->funcs->vpg_powerdown(dc->res_pool->hpo_dp_stream_enc[i]->vpg); +#endif + } +#endif + if (dc->ctx->dc_bios->fw_info_valid) { res_pool->ref_clocks.xtalin_clock_inKhz = dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency; @@ -178,9 +191,40 @@ void dcn31_init_hw(struct dc *dc) dmub_enable_outbox_notification(dc); /* we want to turn off all dp displays before doing detection */ - if (dc->config.power_down_display_on_boot) - blank_all_dp_displays(dc, true); + if (dc->config.power_down_display_on_boot) { + uint8_t dpcd_power_state = '\0'; + enum dc_status status = DC_ERROR_UNEXPECTED; + for (i = 0; i < dc->link_count; i++) { + if (dc->links[i]->connector_signal != SIGNAL_TYPE_DISPLAY_PORT) + continue; + + /* if any of the displays are lit up turn them off */ + status = core_link_read_dpcd(dc->links[i], DP_SET_POWER, + &dpcd_power_state, sizeof(dpcd_power_state)); + if (status == DC_OK && dpcd_power_state == DP_POWER_STATE_D0) { + /* blank dp stream before power off receiver*/ + if (dc->links[i]->ep_type == DISPLAY_ENDPOINT_PHY && + dc->links[i]->link_enc->funcs->get_dig_frontend) { + unsigned int fe; + + fe = dc->links[i]->link_enc->funcs->get_dig_frontend( + dc->links[i]->link_enc); + if (fe == ENGINE_ID_UNKNOWN) + continue; + + for (j = 0; j < dc->res_pool->stream_enc_count; j++) { + if (fe == dc->res_pool->stream_enc[j]->id) { + dc->res_pool->stream_enc[j]->funcs->dp_blank(dc->links[i], + dc->res_pool->stream_enc[j]); + break; + } + } + } + dp_receiver_power_ctrl(dc->links[i], false); + } + } + } /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which @@ -195,48 +239,6 @@ void dcn31_init_hw(struct dc *dc) !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter); } - /* In headless boot cases, DIG may be turned - * on which causes HW/SW discrepancies. - * To avoid this, power down hardware on boot - * if DIG is turned on and seamless boot not enabled - */ - if (dc->config.power_down_display_on_boot) { - struct dc_link *edp_links[MAX_NUM_EDP]; - struct dc_link *edp_link; - bool power_down = false; - - get_edp_links(dc, edp_links, &edp_num); - if (edp_num) { - for (i = 0; i < edp_num; i++) { - edp_link = edp_links[i]; - if (edp_link->link_enc->funcs->is_dig_enabled && - edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && - dc->hwss.edp_backlight_control && - dc->hwss.power_down && - dc->hwss.edp_power_control) { - dc->hwss.edp_backlight_control(edp_link, false); - dc->hwss.power_down(dc); - dc->hwss.edp_power_control(edp_link, false); - power_down = true; - } - } - } - if (!power_down) { - for (i = 0; i < dc->link_count; i++) { - struct dc_link *link = dc->links[i]; - - if (link->ep_type == DISPLAY_ENDPOINT_PHY && - link->link_enc->funcs->is_dig_enabled && - link->link_enc->funcs->is_dig_enabled(link->link_enc) && - dc->hwss.power_down) { - dc->hwss.power_down(dc); - break; - } - - } - } - } - for (i = 0; i < res_pool->audio_count; i++) { struct audio *audio = res_pool->audios[i]; @@ -258,6 +260,10 @@ void dcn31_init_hw(struct dc *dc) /* power AFMT HDMI memory TODO: may move to dis/en output save power*/ REG_WRITE(DIO_MEM_PWR_CTRL, 0); + // Set i2c to light sleep until engine is setup + if (dc->debug.enable_mem_low_power.bits.i2c) + REG_UPDATE(DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, 1); + if (!dc->debug.disable_clock_gate) { /* enable all DCN clock gating */ REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0); @@ -299,6 +305,12 @@ void dcn31_dsc_pg_control( if (hws->ctx->dc->debug.disable_dsc_power_gate) return; + if (hws->ctx->dc->debug.root_clock_optimization.bits.dsc && + hws->ctx->dc->res_pool->dccg->funcs->enable_dsc && + power_on) + hws->ctx->dc->res_pool->dccg->funcs->enable_dsc( + hws->ctx->dc->res_pool->dccg, dsc_inst); + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); if (org_ip_request_cntl == 0) REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); @@ -335,6 +347,13 @@ void dcn31_dsc_pg_control( if (org_ip_request_cntl == 0) REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); + + if (hws->ctx->dc->debug.root_clock_optimization.bits.dsc) { + if (hws->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) + hws->ctx->dc->res_pool->dccg->funcs->disable_dsc( + hws->ctx->dc->res_pool->dccg, dsc_inst); + } + } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 7a850d74218e..87b2c2428842 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -101,8 +101,6 @@ #include "link_enc_cfg.h" #define DC_LOGGER_INIT(logger) -#define fixed16_to_double(x) (((double) x) / ((double) (1 << 16))) -#define fixed16_to_double_to_cpu(x) fixed16_to_double(le32_to_cpu(x)) #define DCN3_1_DEFAULT_DET_SIZE 384 @@ -899,7 +897,8 @@ static const struct dce_hwseq_registers hwseq_reg = { HWS_SF(, DMU_MEM_PWR_CNTL, DMCU_ERAM_MEM_PWR_FORCE, mask_sh), \ HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_UNASSIGNED_PWR_MODE, mask_sh), \ HWS_SF(, ODM_MEM_PWR_CTRL3, ODM_MEM_VBLANK_PWR_MODE, mask_sh), \ - HWS_SF(, MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, mask_sh) + HWS_SF(, MMHUBBUB_MEM_PWR_CNTL, VGA_MEM_PWR_FORCE, mask_sh), \ + HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh) static const struct dce_hwseq_shift hwseq_shift = { HWSEQ_DCN31_MASK_SH_LIST(__SHIFT) @@ -1312,10 +1311,6 @@ static struct vpg *dcn31_vpg_create( &vpg_shift, &vpg_mask); - // Will re-enable hw block when we enable stream - // Check for enabled stream before powering down? - vpg31_powerdown(&vpg31->base); - return &vpg31->base; } @@ -1837,7 +1832,7 @@ static int dcn31_populate_dml_pipes_from_context( return pipe_cnt; } -static void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) +void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) { if (dc->clk_mgr->bw_params->wm_table.entries[WM_A].valid) { context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.entries[WM_A].pstate_latency_us; @@ -1981,7 +1976,7 @@ static void dcn31_calculate_wm_and_dlg_fp( dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); } -static void dcn31_calculate_wm_and_dlg( +void dcn31_calculate_wm_and_dlg( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, @@ -2463,6 +2458,8 @@ static bool dcn31_resource_construct( dc->cap_funcs = cap_funcs; + dc->dcn_ip->max_num_dpp = dcn3_1_ip.max_num_dpp; + DC_FP_END(); return true; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h index 93571c976996..416fe7a721d8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h @@ -35,6 +35,16 @@ struct dcn31_resource_pool { struct resource_pool base; }; +bool dcn31_validate_bandwidth(struct dc *dc, + struct dc_state *context, + bool fast_validate); +void dcn31_calculate_wm_and_dlg( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel); +void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context); + struct resource_pool *dcn31_create_resource_pool( const struct dc_init_data *init_data, struct dc *dc); diff --git a/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h b/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h index 43f33e186088..511f9e1159c7 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h +++ b/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h @@ -35,6 +35,8 @@ struct cp_psp_stream_config { uint8_t link_enc_idx; uint8_t stream_enc_idx; uint8_t phy_idx; + uint8_t dio_output_idx; + uint8_t dio_output_type; uint8_t assr_enabled; uint8_t mst_enabled; uint8_t dp2_enabled; diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 169a4e68f86e..eee6672bd32d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -70,6 +70,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_ccflags) +CFLAGS_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn2x/dcn2x.o := $(dml_rcflags) @@ -83,7 +85,9 @@ CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_rcflags) +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_rcflags) +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_rcflags) endif CFLAGS_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_ccflags) @@ -99,6 +103,8 @@ DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o DML += dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o +DML += dcn301/dcn301_fpu.o +DML += dsc/rc_calc_fpu.o endif AMD_DAL_DML = $(addprefix $(AMDDALPATH)/dc/dml/,$(DML)) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c new file mode 100644 index 000000000000..94c32832a0e7 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c @@ -0,0 +1,390 @@ +/* + * Copyright 2019-2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ +#include "resource.h" +#include "clk_mgr.h" +#include "dcn20/dcn20_resource.h" +#include "dcn301/dcn301_resource.h" + +#include "dml/dcn20/dcn20_fpu.h" +#include "dcn301_fpu.h" + +#define TO_DCN301_RES_POOL(pool)\ + container_of(pool, struct dcn301_resource_pool, base) + +/* Based on: //vidip/dc/dcn3/doc/architecture/DCN3x_Display_Mode.xlsm#83 */ +struct _vcs_dpi_ip_params_st dcn3_01_ip = { + .odm_capable = 1, + .gpuvm_enable = 1, + .hostvm_enable = 1, + .gpuvm_max_page_table_levels = 1, + .hostvm_max_page_table_levels = 2, + .hostvm_cached_page_table_levels = 0, + .pte_group_size_bytes = 2048, + .num_dsc = 3, + .rob_buffer_size_kbytes = 184, + .det_buffer_size_kbytes = 184, + .dpte_buffer_size_in_pte_reqs_luma = 64, + .dpte_buffer_size_in_pte_reqs_chroma = 32, + .pde_proc_buffer_size_64k_reqs = 48, + .dpp_output_buffer_pixels = 2560, + .opp_output_buffer_lines = 1, + .pixel_chunk_size_kbytes = 8, + .meta_chunk_size_kbytes = 2, + .writeback_chunk_size_kbytes = 8, + .line_buffer_size_bits = 789504, + .is_line_buffer_bpp_fixed = 0, // ? + .line_buffer_fixed_bpp = 48, // ? + .dcc_supported = true, + .writeback_interface_buffer_size_kbytes = 90, + .writeback_line_buffer_buffer_size = 656640, + .max_line_buffer_lines = 12, + .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 + .writeback_chroma_buffer_size_kbytes = 8, + .writeback_chroma_line_buffer_width_pixels = 4, + .writeback_max_hscl_ratio = 1, + .writeback_max_vscl_ratio = 1, + .writeback_min_hscl_ratio = 1, + .writeback_min_vscl_ratio = 1, + .writeback_max_hscl_taps = 1, + .writeback_max_vscl_taps = 1, + .writeback_line_buffer_luma_buffer_size = 0, + .writeback_line_buffer_chroma_buffer_size = 14643, + .cursor_buffer_size = 8, + .cursor_chunk_size = 2, + .max_num_otg = 4, + .max_num_dpp = 4, + .max_num_wb = 1, + .max_dchub_pscl_bw_pix_per_clk = 4, + .max_pscl_lb_bw_pix_per_clk = 2, + .max_lb_vscl_bw_pix_per_clk = 4, + .max_vscl_hscl_bw_pix_per_clk = 4, + .max_hscl_ratio = 6, + .max_vscl_ratio = 6, + .hscl_mults = 4, + .vscl_mults = 4, + .max_hscl_taps = 8, + .max_vscl_taps = 8, + .dispclk_ramp_margin_percent = 1, + .underscan_factor = 1.11, + .min_vblank_lines = 32, + .dppclk_delay_subtotal = 46, + .dynamic_metadata_vm_enabled = true, + .dppclk_delay_scl_lb_only = 16, + .dppclk_delay_scl = 50, + .dppclk_delay_cnvc_formatter = 27, + .dppclk_delay_cnvc_cursor = 6, + .dispclk_delay_subtotal = 119, + .dcfclk_cstate_latency = 5.2, // SRExitTime + .max_inter_dcn_tile_repeaters = 8, + .max_num_hdmi_frl_outputs = 0, + .odm_combine_4to1_supported = true, + + .xfc_supported = false, + .xfc_fill_bw_overhead_percent = 10.0, + .xfc_fill_constant_bytes = 0, + .gfx7_compat_tiling_supported = 0, + .number_of_cursors = 1, +}; + +struct _vcs_dpi_soc_bounding_box_st dcn3_01_soc = { + .clock_limits = { + { + .state = 0, + .dram_speed_mts = 2400.0, + .fabricclk_mhz = 600, + .socclk_mhz = 278.0, + .dcfclk_mhz = 400.0, + .dscclk_mhz = 206.0, + .dppclk_mhz = 1015.0, + .dispclk_mhz = 1015.0, + .phyclk_mhz = 600.0, + }, + + { + .state = 1, + .dram_speed_mts = 2400.0, + .fabricclk_mhz = 688, + .socclk_mhz = 278.0, + .dcfclk_mhz = 400.0, + .dscclk_mhz = 206.0, + .dppclk_mhz = 1015.0, + .dispclk_mhz = 1015.0, + .phyclk_mhz = 600.0, + }, + + { + .state = 2, + .dram_speed_mts = 4267.0, + .fabricclk_mhz = 1067, + .socclk_mhz = 278.0, + .dcfclk_mhz = 608.0, + .dscclk_mhz = 296.0, + .dppclk_mhz = 1015.0, + .dispclk_mhz = 1015.0, + .phyclk_mhz = 810.0, + }, + + { + .state = 3, + .dram_speed_mts = 4267.0, + .fabricclk_mhz = 1067, + .socclk_mhz = 715.0, + .dcfclk_mhz = 676.0, + .dscclk_mhz = 338.0, + .dppclk_mhz = 1015.0, + .dispclk_mhz = 1015.0, + .phyclk_mhz = 810.0, + }, + + { + .state = 4, + .dram_speed_mts = 4267.0, + .fabricclk_mhz = 1067, + .socclk_mhz = 953.0, + .dcfclk_mhz = 810.0, + .dscclk_mhz = 338.0, + .dppclk_mhz = 1015.0, + .dispclk_mhz = 1015.0, + .phyclk_mhz = 810.0, + }, + }, + + .sr_exit_time_us = 9.0, + .sr_enter_plus_exit_time_us = 11.0, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 80.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 75.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 60.0, + .max_avg_dram_bw_use_normal_percent = 60.0, + .writeback_latency_us = 12.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 4, + .fabric_datapath_to_dcn_data_return_bytes = 32, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 191, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 4, + .gpuvm_min_page_size_bytes = 4096, + .hostvm_min_page_size_bytes = 4096, + .dram_clock_change_latency_us = 23.84, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3550, + .xfc_bus_transport_time_us = 20, // ? + .xfc_xbuf_latency_tolerance_us = 4, // ? + .use_urgent_burst_bw = 1, // ? + .num_states = 5, + .do_urgent_latency_adjustment = false, + .urgent_latency_adjustment_fabric_clock_component_us = 0, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, +}; + +static void calculate_wm_set_for_vlevel(int vlevel, + struct wm_range_table_entry *table_entry, + struct dcn_watermarks *wm_set, + struct display_mode_lib *dml, + display_e2e_pipe_params_st *pipes, + int pipe_cnt) +{ + double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us; + + ASSERT(vlevel < dml->soc.num_states); + /* only pipe 0 is read for voltage and dcf/soc clocks */ + pipes[0].clks_cfg.voltage = vlevel; + pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz; + pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz; + + dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us; + dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us; + dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us; + + wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000; + wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000; + wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000; + wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000; + wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000; + dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached; + +} + +void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) +{ + struct dcn301_resource_pool *pool = TO_DCN301_RES_POOL(dc->res_pool); + struct clk_limit_table *clk_table = &bw_params->clk_table; + struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; + unsigned int i, closest_clk_lvl; + int j; + + dc_assert_fp_enabled(); + + /* Default clock levels are used for diags, which may lead to overclocking. */ + if (!IS_DIAG_DC(dc->ctx->dce_environment)) { + dcn3_01_ip.max_num_otg = pool->base.res_cap->num_timing_generator; + dcn3_01_ip.max_num_dpp = pool->base.pipe_count; + dcn3_01_soc.num_chans = bw_params->num_channels; + + ASSERT(clk_table->num_entries); + for (i = 0; i < clk_table->num_entries; i++) { + /* loop backwards*/ + for (closest_clk_lvl = 0, j = dcn3_01_soc.num_states - 1; j >= 0; j--) { + if ((unsigned int) dcn3_01_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { + closest_clk_lvl = j; + break; + } + } + + clock_limits[i].state = i; + clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; + clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz; + clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz; + clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; + + clock_limits[i].dispclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dispclk_mhz; + clock_limits[i].dppclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dppclk_mhz; + clock_limits[i].dram_bw_per_chan_gbps = dcn3_01_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps; + clock_limits[i].dscclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dscclk_mhz; + clock_limits[i].dtbclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dtbclk_mhz; + clock_limits[i].phyclk_d18_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz; + clock_limits[i].phyclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].phyclk_mhz; + } + + for (i = 0; i < clk_table->num_entries; i++) + dcn3_01_soc.clock_limits[i] = clock_limits[i]; + + if (clk_table->num_entries) { + dcn3_01_soc.num_states = clk_table->num_entries; + /* duplicate last level */ + dcn3_01_soc.clock_limits[dcn3_01_soc.num_states] = dcn3_01_soc.clock_limits[dcn3_01_soc.num_states - 1]; + dcn3_01_soc.clock_limits[dcn3_01_soc.num_states].state = dcn3_01_soc.num_states; + } + } + + dcn3_01_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; + dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; + + dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30); +} + +void dcn301_fpu_set_wm_ranges(int i, + struct pp_smu_wm_range_sets *ranges, + struct _vcs_dpi_soc_bounding_box_st *loaded_bb) +{ + dc_assert_fp_enabled(); + + ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0; + ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16; +} + +void dcn301_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info) +{ + dc_assert_fp_enabled(); + + if (bb_info.dram_clock_change_latency_100ns > 0) + dcn3_01_soc.dram_clock_change_latency_us = bb_info.dram_clock_change_latency_100ns * 10; + + if (bb_info.dram_sr_enter_exit_latency_100ns > 0) + dcn3_01_soc.sr_enter_plus_exit_time_us = bb_info.dram_sr_enter_exit_latency_100ns * 10; + + if (bb_info.dram_sr_exit_latency_100ns > 0) + dcn3_01_soc.sr_exit_time_us = bb_info.dram_sr_exit_latency_100ns * 10; +} + +void dcn301_calculate_wm_and_dlg(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel_req) +{ + int i, pipe_idx; + int vlevel, vlevel_max; + struct wm_range_table_entry *table_entry; + struct clk_bw_params *bw_params = dc->clk_mgr->bw_params; + + ASSERT(bw_params); + dc_assert_fp_enabled(); + + vlevel_max = bw_params->clk_table.num_entries - 1; + + /* WM Set D */ + table_entry = &bw_params->wm_table.entries[WM_D]; + if (table_entry->wm_type == WM_TYPE_RETRAINING) + vlevel = 0; + else + vlevel = vlevel_max; + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set C */ + table_entry = &bw_params->wm_table.entries[WM_C]; + vlevel = min(max(vlevel_req, 2), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c, + &context->bw_ctx.dml, pipes, pipe_cnt); + /* WM Set B */ + table_entry = &bw_params->wm_table.entries[WM_B]; + vlevel = min(max(vlevel_req, 1), vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b, + &context->bw_ctx.dml, pipes, pipe_cnt); + + /* WM Set A */ + table_entry = &bw_params->wm_table.entries[WM_A]; + vlevel = min(vlevel_req, vlevel_max); + calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a, + &context->bw_ctx.dml, pipes, pipe_cnt); + + for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { + if (!context->res_ctx.pipe_ctx[i].stream) + continue; + + pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); + pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + + if (dc->config.forced_clocks) { + pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz; + pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz; + } + if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0; + if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) + pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0; + pipe_idx++; + } + + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h new file mode 100644 index 000000000000..fc7065d17842 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h @@ -0,0 +1,42 @@ +/* + * Copyright 2019-2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#ifndef __DCN301_FPU_H__ +#define __DCN301_FPU_H__ + +void dcn301_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params); + +void dcn301_fpu_set_wm_ranges(int i, + struct pp_smu_wm_range_sets *ranges, + struct _vcs_dpi_soc_bounding_box_st *loaded_bb); + +void dcn301_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info); + +void dcn301_calculate_wm_and_dlg(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel_req); +#endif /* __DCN301_FPU_H__*/ diff --git a/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h b/drivers/gpu/drm/amd/display/dc/dml/dsc/qp_tables.h similarity index 100% rename from drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h rename to drivers/gpu/drm/amd/display/dc/dml/dsc/qp_tables.h diff --git a/drivers/gpu/drm/amd/display/dc/dml/dsc/rc_calc_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dsc/rc_calc_fpu.c new file mode 100644 index 000000000000..3ee858f311d1 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dml/dsc/rc_calc_fpu.c @@ -0,0 +1,291 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#include "rc_calc_fpu.h" + +#include "qp_tables.h" +#include "amdgpu_dm/dc_fpu.h" + +#define table_hash(mode, bpc, max_min) ((mode << 16) | (bpc << 8) | max_min) + +#define MODE_SELECT(val444, val422, val420) \ + (cm == CM_444 || cm == CM_RGB) ? (val444) : (cm == CM_422 ? (val422) : (val420)) + + +#define TABLE_CASE(mode, bpc, max) case (table_hash(mode, BPC_##bpc, max)): \ + table = qp_table_##mode##_##bpc##bpc_##max; \ + table_size = sizeof(qp_table_##mode##_##bpc##bpc_##max)/sizeof(*qp_table_##mode##_##bpc##bpc_##max); \ + break + +static int median3(int a, int b, int c) +{ + if (a > b) + swap(a, b); + if (b > c) + swap(b, c); + if (a > b) + swap(b, c); + + return b; +} + +static double dsc_roundf(double num) +{ + if (num < 0.0) + num = num - 0.5; + else + num = num + 0.5; + + return (int)(num); +} + +static double dsc_ceil(double num) +{ + double retval = (int)num; + + if (retval != num && num > 0) + retval = num + 1; + + return (int)retval; +} + +static void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, + enum max_min max_min, float bpp) +{ + int mode = MODE_SELECT(444, 422, 420); + int sel = table_hash(mode, bpc, max_min); + int table_size = 0; + int index; + const struct qp_entry *table = 0L; + + // alias enum + enum { min = DAL_MM_MIN, max = DAL_MM_MAX }; + switch (sel) { + TABLE_CASE(444, 8, max); + TABLE_CASE(444, 8, min); + TABLE_CASE(444, 10, max); + TABLE_CASE(444, 10, min); + TABLE_CASE(444, 12, max); + TABLE_CASE(444, 12, min); + TABLE_CASE(422, 8, max); + TABLE_CASE(422, 8, min); + TABLE_CASE(422, 10, max); + TABLE_CASE(422, 10, min); + TABLE_CASE(422, 12, max); + TABLE_CASE(422, 12, min); + TABLE_CASE(420, 8, max); + TABLE_CASE(420, 8, min); + TABLE_CASE(420, 10, max); + TABLE_CASE(420, 10, min); + TABLE_CASE(420, 12, max); + TABLE_CASE(420, 12, min); + } + + if (table == 0) + return; + + index = (bpp - table[0].bpp) * 2; + + /* requested size is bigger than the table */ + if (index >= table_size) { + dm_error("ERROR: Requested rc_calc to find a bpp entry that exceeds the table size\n"); + return; + } + + memcpy(qps, table[index].qps, sizeof(qp_set)); +} + +static void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp) +{ + int *p = ofs; + + if (mode == CM_444 || mode == CM_RGB) { + *p++ = (bpp <= 6) ? (0) : ((((bpp >= 8) && (bpp <= 12))) ? (2) : ((bpp >= 15) ? (10) : ((((bpp > 6) && (bpp < 8))) ? (0 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (2 + dsc_roundf((bpp - 12) * (8 / 3.0)))))); + *p++ = (bpp <= 6) ? (-2) : ((((bpp >= 8) && (bpp <= 12))) ? (0) : ((bpp >= 15) ? (8) : ((((bpp > 6) && (bpp < 8))) ? (-2 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (0 + dsc_roundf((bpp - 12) * (8 / 3.0)))))); + *p++ = (bpp <= 6) ? (-2) : ((((bpp >= 8) && (bpp <= 12))) ? (0) : ((bpp >= 15) ? (6) : ((((bpp > 6) && (bpp < 8))) ? (-2 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (0 + dsc_roundf((bpp - 12) * (6 / 3.0)))))); + *p++ = (bpp <= 6) ? (-4) : ((((bpp >= 8) && (bpp <= 12))) ? (-2) : ((bpp >= 15) ? (4) : ((((bpp > 6) && (bpp < 8))) ? (-4 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (-2 + dsc_roundf((bpp - 12) * (6 / 3.0)))))); + *p++ = (bpp <= 6) ? (-6) : ((((bpp >= 8) && (bpp <= 12))) ? (-4) : ((bpp >= 15) ? (2) : ((((bpp > 6) && (bpp < 8))) ? (-6 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (-4 + dsc_roundf((bpp - 12) * (6 / 3.0)))))); + *p++ = (bpp <= 12) ? (-6) : ((bpp >= 15) ? (0) : (-6 + dsc_roundf((bpp - 12) * (6 / 3.0)))); + *p++ = (bpp <= 12) ? (-8) : ((bpp >= 15) ? (-2) : (-8 + dsc_roundf((bpp - 12) * (6 / 3.0)))); + *p++ = (bpp <= 12) ? (-8) : ((bpp >= 15) ? (-4) : (-8 + dsc_roundf((bpp - 12) * (4 / 3.0)))); + *p++ = (bpp <= 12) ? (-8) : ((bpp >= 15) ? (-6) : (-8 + dsc_roundf((bpp - 12) * (2 / 3.0)))); + *p++ = (bpp <= 12) ? (-10) : ((bpp >= 15) ? (-8) : (-10 + dsc_roundf((bpp - 12) * (2 / 3.0)))); + *p++ = -10; + *p++ = (bpp <= 6) ? (-12) : ((bpp >= 8) ? (-10) : (-12 + dsc_roundf((bpp - 6) * (2 / 2.0)))); + *p++ = -12; + *p++ = -12; + *p++ = -12; + } else if (mode == CM_422) { + *p++ = (bpp <= 8) ? (2) : ((bpp >= 10) ? (10) : (2 + dsc_roundf((bpp - 8) * (8 / 2.0)))); + *p++ = (bpp <= 8) ? (0) : ((bpp >= 10) ? (8) : (0 + dsc_roundf((bpp - 8) * (8 / 2.0)))); + *p++ = (bpp <= 8) ? (0) : ((bpp >= 10) ? (6) : (0 + dsc_roundf((bpp - 8) * (6 / 2.0)))); + *p++ = (bpp <= 8) ? (-2) : ((bpp >= 10) ? (4) : (-2 + dsc_roundf((bpp - 8) * (6 / 2.0)))); + *p++ = (bpp <= 8) ? (-4) : ((bpp >= 10) ? (2) : (-4 + dsc_roundf((bpp - 8) * (6 / 2.0)))); + *p++ = (bpp <= 8) ? (-6) : ((bpp >= 10) ? (0) : (-6 + dsc_roundf((bpp - 8) * (6 / 2.0)))); + *p++ = (bpp <= 8) ? (-8) : ((bpp >= 10) ? (-2) : (-8 + dsc_roundf((bpp - 8) * (6 / 2.0)))); + *p++ = (bpp <= 8) ? (-8) : ((bpp >= 10) ? (-4) : (-8 + dsc_roundf((bpp - 8) * (4 / 2.0)))); + *p++ = (bpp <= 8) ? (-8) : ((bpp >= 10) ? (-6) : (-8 + dsc_roundf((bpp - 8) * (2 / 2.0)))); + *p++ = (bpp <= 8) ? (-10) : ((bpp >= 10) ? (-8) : (-10 + dsc_roundf((bpp - 8) * (2 / 2.0)))); + *p++ = -10; + *p++ = (bpp <= 6) ? (-12) : ((bpp >= 7) ? (-10) : (-12 + dsc_roundf((bpp - 6) * (2.0 / 1)))); + *p++ = -12; + *p++ = -12; + *p++ = -12; + } else { + *p++ = (bpp <= 6) ? (2) : ((bpp >= 8) ? (10) : (2 + dsc_roundf((bpp - 6) * (8 / 2.0)))); + *p++ = (bpp <= 6) ? (0) : ((bpp >= 8) ? (8) : (0 + dsc_roundf((bpp - 6) * (8 / 2.0)))); + *p++ = (bpp <= 6) ? (0) : ((bpp >= 8) ? (6) : (0 + dsc_roundf((bpp - 6) * (6 / 2.0)))); + *p++ = (bpp <= 6) ? (-2) : ((bpp >= 8) ? (4) : (-2 + dsc_roundf((bpp - 6) * (6 / 2.0)))); + *p++ = (bpp <= 6) ? (-4) : ((bpp >= 8) ? (2) : (-4 + dsc_roundf((bpp - 6) * (6 / 2.0)))); + *p++ = (bpp <= 6) ? (-6) : ((bpp >= 8) ? (0) : (-6 + dsc_roundf((bpp - 6) * (6 / 2.0)))); + *p++ = (bpp <= 6) ? (-8) : ((bpp >= 8) ? (-2) : (-8 + dsc_roundf((bpp - 6) * (6 / 2.0)))); + *p++ = (bpp <= 6) ? (-8) : ((bpp >= 8) ? (-4) : (-8 + dsc_roundf((bpp - 6) * (4 / 2.0)))); + *p++ = (bpp <= 6) ? (-8) : ((bpp >= 8) ? (-6) : (-8 + dsc_roundf((bpp - 6) * (2 / 2.0)))); + *p++ = (bpp <= 6) ? (-10) : ((bpp >= 8) ? (-8) : (-10 + dsc_roundf((bpp - 6) * (2 / 2.0)))); + *p++ = -10; + *p++ = (bpp <= 4) ? (-12) : ((bpp >= 5) ? (-10) : (-12 + dsc_roundf((bpp - 4) * (2 / 1.0)))); + *p++ = -12; + *p++ = -12; + *p++ = -12; + } +} + +void _do_calc_rc_params(struct rc_params *rc, + enum colour_mode cm, + enum bits_per_comp bpc, + u16 drm_bpp, + bool is_navite_422_or_420, + int slice_width, + int slice_height, + int minor_version) +{ + float bpp; + float bpp_group; + float initial_xmit_delay_factor; + int padding_pixels; + int i; + + dc_assert_fp_enabled(); + + bpp = ((float)drm_bpp / 16.0); + /* in native_422 or native_420 modes, the bits_per_pixel is double the + * target bpp (the latter is what calc_rc_params expects) + */ + if (is_navite_422_or_420) + bpp /= 2.0; + + rc->rc_quant_incr_limit0 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); + rc->rc_quant_incr_limit1 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); + + bpp_group = MODE_SELECT(bpp, bpp * 2.0, bpp * 2.0); + + switch (cm) { + case CM_420: + rc->initial_fullness_offset = (bpp >= 6) ? (2048) : ((bpp <= 4) ? (6144) : ((((bpp > 4) && (bpp <= 5))) ? (6144 - dsc_roundf((bpp - 4) * (512))) : (5632 - dsc_roundf((bpp - 5) * (3584))))); + rc->first_line_bpg_offset = median3(0, (12 + (int) (0.09 * min(34, slice_height - 8))), (int)((3 * bpc * 3) - (3 * bpp_group))); + rc->second_line_bpg_offset = median3(0, 12, (int)((3 * bpc * 3) - (3 * bpp_group))); + break; + case CM_422: + rc->initial_fullness_offset = (bpp >= 8) ? (2048) : ((bpp <= 7) ? (5632) : (5632 - dsc_roundf((bpp - 7) * (3584)))); + rc->first_line_bpg_offset = median3(0, (12 + (int) (0.09 * min(34, slice_height - 8))), (int)((3 * bpc * 4) - (3 * bpp_group))); + rc->second_line_bpg_offset = 0; + break; + case CM_444: + case CM_RGB: + rc->initial_fullness_offset = (bpp >= 12) ? (2048) : ((bpp <= 8) ? (6144) : ((((bpp > 8) && (bpp <= 10))) ? (6144 - dsc_roundf((bpp - 8) * (512 / 2))) : (5632 - dsc_roundf((bpp - 10) * (3584 / 2))))); + rc->first_line_bpg_offset = median3(0, (12 + (int) (0.09 * min(34, slice_height - 8))), (int)(((3 * bpc + (cm == CM_444 ? 0 : 2)) * 3) - (3 * bpp_group))); + rc->second_line_bpg_offset = 0; + break; + } + + initial_xmit_delay_factor = (cm == CM_444 || cm == CM_RGB) ? 1.0 : 2.0; + rc->initial_xmit_delay = dsc_roundf(8192.0/2.0/bpp/initial_xmit_delay_factor); + + if (cm == CM_422 || cm == CM_420) + slice_width /= 2; + + padding_pixels = ((slice_width % 3) != 0) ? (3 - (slice_width % 3)) * (rc->initial_xmit_delay / slice_width) : 0; + if (3 * bpp_group >= (((rc->initial_xmit_delay + 2) / 3) * (3 + (cm == CM_422)))) { + if ((rc->initial_xmit_delay + padding_pixels) % 3 == 1) + rc->initial_xmit_delay++; + } + + rc->flatness_min_qp = ((bpc == BPC_8) ? (3) : ((bpc == BPC_10) ? (7) : (11))) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); + rc->flatness_max_qp = ((bpc == BPC_8) ? (12) : ((bpc == BPC_10) ? (16) : (20))) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); + rc->flatness_det_thresh = 2 << (bpc - 8); + + get_qp_set(rc->qp_min, cm, bpc, DAL_MM_MIN, bpp); + get_qp_set(rc->qp_max, cm, bpc, DAL_MM_MAX, bpp); + if (cm == CM_444 && minor_version == 1) { + for (i = 0; i < QP_SET_SIZE; ++i) { + rc->qp_min[i] = rc->qp_min[i] > 0 ? rc->qp_min[i] - 1 : 0; + rc->qp_max[i] = rc->qp_max[i] > 0 ? rc->qp_max[i] - 1 : 0; + } + } + get_ofs_set(rc->ofs, cm, bpp); + + /* fixed parameters */ + rc->rc_model_size = 8192; + rc->rc_edge_factor = 6; + rc->rc_tgt_offset_hi = 3; + rc->rc_tgt_offset_lo = 3; + + rc->rc_buf_thresh[0] = 896; + rc->rc_buf_thresh[1] = 1792; + rc->rc_buf_thresh[2] = 2688; + rc->rc_buf_thresh[3] = 3584; + rc->rc_buf_thresh[4] = 4480; + rc->rc_buf_thresh[5] = 5376; + rc->rc_buf_thresh[6] = 6272; + rc->rc_buf_thresh[7] = 6720; + rc->rc_buf_thresh[8] = 7168; + rc->rc_buf_thresh[9] = 7616; + rc->rc_buf_thresh[10] = 7744; + rc->rc_buf_thresh[11] = 7872; + rc->rc_buf_thresh[12] = 8000; + rc->rc_buf_thresh[13] = 8064; +} + +u32 _do_bytes_per_pixel_calc(int slice_width, + u16 drm_bpp, + bool is_navite_422_or_420) +{ + float bpp; + u32 bytes_per_pixel; + double d_bytes_per_pixel; + + dc_assert_fp_enabled(); + + bpp = ((float)drm_bpp / 16.0); + d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width; + // TODO: Make sure the formula for calculating this is precise (ceiling + // vs. floor, and at what point they should be applied) + if (is_navite_422_or_420) + d_bytes_per_pixel /= 2; + + bytes_per_pixel = (u32)dsc_ceil(d_bytes_per_pixel * 0x10000000); + + return bytes_per_pixel; +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dsc/rc_calc_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dsc/rc_calc_fpu.h new file mode 100644 index 000000000000..b93b95409fbe --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/dml/dsc/rc_calc_fpu.h @@ -0,0 +1,94 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#ifndef __RC_CALC_FPU_H__ +#define __RC_CALC_FPU_H__ + +#include "os_types.h" +#include + +#define QP_SET_SIZE 15 + +typedef int qp_set[QP_SET_SIZE]; + +struct rc_params { + int rc_quant_incr_limit0; + int rc_quant_incr_limit1; + int initial_fullness_offset; + int initial_xmit_delay; + int first_line_bpg_offset; + int second_line_bpg_offset; + int flatness_min_qp; + int flatness_max_qp; + int flatness_det_thresh; + qp_set qp_min; + qp_set qp_max; + qp_set ofs; + int rc_model_size; + int rc_edge_factor; + int rc_tgt_offset_hi; + int rc_tgt_offset_lo; + int rc_buf_thresh[QP_SET_SIZE - 1]; +}; + +enum colour_mode { + CM_RGB, /* 444 RGB */ + CM_444, /* 444 YUV or simple 422 */ + CM_422, /* native 422 */ + CM_420 /* native 420 */ +}; + +enum bits_per_comp { + BPC_8 = 8, + BPC_10 = 10, + BPC_12 = 12 +}; + +enum max_min { + DAL_MM_MIN = 0, + DAL_MM_MAX = 1 +}; + +struct qp_entry { + float bpp; + const qp_set qps; +}; + +typedef struct qp_entry qp_table[]; + +u32 _do_bytes_per_pixel_calc(int slice_width, + u16 drm_bpp, + bool is_navite_422_or_420); + +void _do_calc_rc_params(struct rc_params *rc, + enum colour_mode cm, + enum bits_per_comp bpc, + u16 drm_bpp, + bool is_navite_422_or_420, + int slice_width, + int slice_height, + int minor_version); + +#endif diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile index 8d31eb75c6a6..a2537229ee88 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile @@ -1,35 +1,6 @@ # SPDX-License-Identifier: MIT # # Makefile for the 'dsc' sub-component of DAL. - -ifdef CONFIG_X86 -dsc_ccflags := -mhard-float -msse -endif - -ifdef CONFIG_PPC64 -dsc_ccflags := -mhard-float -maltivec -endif - -ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) -IS_OLD_GCC = 1 -endif -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -dsc_ccflags += -mpreferred-stack-boundary=4 -else -dsc_ccflags += -msse2 -endif -endif - -CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags) -CFLAGS_REMOVE_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_rcflags) - DSC = dc_dsc.o rc_calc.o rc_calc_dpi.o AMD_DAL_DSC = $(addprefix $(AMDDALPATH)/dc/dsc/,$(DSC)) diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c index 7b294f637881..b19d3aeb5962 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c @@ -23,266 +23,7 @@ * Authors: AMD * */ -#include - -#include "os_types.h" #include "rc_calc.h" -#include "qp_tables.h" - -#define table_hash(mode, bpc, max_min) ((mode << 16) | (bpc << 8) | max_min) - -#define MODE_SELECT(val444, val422, val420) \ - (cm == CM_444 || cm == CM_RGB) ? (val444) : (cm == CM_422 ? (val422) : (val420)) - - -#define TABLE_CASE(mode, bpc, max) case (table_hash(mode, BPC_##bpc, max)): \ - table = qp_table_##mode##_##bpc##bpc_##max; \ - table_size = sizeof(qp_table_##mode##_##bpc##bpc_##max)/sizeof(*qp_table_##mode##_##bpc##bpc_##max); \ - break - - -static void get_qp_set(qp_set qps, enum colour_mode cm, enum bits_per_comp bpc, - enum max_min max_min, float bpp) -{ - int mode = MODE_SELECT(444, 422, 420); - int sel = table_hash(mode, bpc, max_min); - int table_size = 0; - int index; - const struct qp_entry *table = 0L; - - // alias enum - enum { min = DAL_MM_MIN, max = DAL_MM_MAX }; - switch (sel) { - TABLE_CASE(444, 8, max); - TABLE_CASE(444, 8, min); - TABLE_CASE(444, 10, max); - TABLE_CASE(444, 10, min); - TABLE_CASE(444, 12, max); - TABLE_CASE(444, 12, min); - TABLE_CASE(422, 8, max); - TABLE_CASE(422, 8, min); - TABLE_CASE(422, 10, max); - TABLE_CASE(422, 10, min); - TABLE_CASE(422, 12, max); - TABLE_CASE(422, 12, min); - TABLE_CASE(420, 8, max); - TABLE_CASE(420, 8, min); - TABLE_CASE(420, 10, max); - TABLE_CASE(420, 10, min); - TABLE_CASE(420, 12, max); - TABLE_CASE(420, 12, min); - } - - if (table == 0) - return; - - index = (bpp - table[0].bpp) * 2; - - /* requested size is bigger than the table */ - if (index >= table_size) { - dm_error("ERROR: Requested rc_calc to find a bpp entry that exceeds the table size\n"); - return; - } - - memcpy(qps, table[index].qps, sizeof(qp_set)); -} - -static double dsc_roundf(double num) -{ - if (num < 0.0) - num = num - 0.5; - else - num = num + 0.5; - - return (int)(num); -} - -static double dsc_ceil(double num) -{ - double retval = (int)num; - - if (retval != num && num > 0) - retval = num + 1; - - return (int)retval; -} - -static void get_ofs_set(qp_set ofs, enum colour_mode mode, float bpp) -{ - int *p = ofs; - - if (mode == CM_444 || mode == CM_RGB) { - *p++ = (bpp <= 6) ? (0) : ((((bpp >= 8) && (bpp <= 12))) ? (2) : ((bpp >= 15) ? (10) : ((((bpp > 6) && (bpp < 8))) ? (0 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (2 + dsc_roundf((bpp - 12) * (8 / 3.0)))))); - *p++ = (bpp <= 6) ? (-2) : ((((bpp >= 8) && (bpp <= 12))) ? (0) : ((bpp >= 15) ? (8) : ((((bpp > 6) && (bpp < 8))) ? (-2 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (0 + dsc_roundf((bpp - 12) * (8 / 3.0)))))); - *p++ = (bpp <= 6) ? (-2) : ((((bpp >= 8) && (bpp <= 12))) ? (0) : ((bpp >= 15) ? (6) : ((((bpp > 6) && (bpp < 8))) ? (-2 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (0 + dsc_roundf((bpp - 12) * (6 / 3.0)))))); - *p++ = (bpp <= 6) ? (-4) : ((((bpp >= 8) && (bpp <= 12))) ? (-2) : ((bpp >= 15) ? (4) : ((((bpp > 6) && (bpp < 8))) ? (-4 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (-2 + dsc_roundf((bpp - 12) * (6 / 3.0)))))); - *p++ = (bpp <= 6) ? (-6) : ((((bpp >= 8) && (bpp <= 12))) ? (-4) : ((bpp >= 15) ? (2) : ((((bpp > 6) && (bpp < 8))) ? (-6 + dsc_roundf((bpp - 6) * (2 / 2.0))) : (-4 + dsc_roundf((bpp - 12) * (6 / 3.0)))))); - *p++ = (bpp <= 12) ? (-6) : ((bpp >= 15) ? (0) : (-6 + dsc_roundf((bpp - 12) * (6 / 3.0)))); - *p++ = (bpp <= 12) ? (-8) : ((bpp >= 15) ? (-2) : (-8 + dsc_roundf((bpp - 12) * (6 / 3.0)))); - *p++ = (bpp <= 12) ? (-8) : ((bpp >= 15) ? (-4) : (-8 + dsc_roundf((bpp - 12) * (4 / 3.0)))); - *p++ = (bpp <= 12) ? (-8) : ((bpp >= 15) ? (-6) : (-8 + dsc_roundf((bpp - 12) * (2 / 3.0)))); - *p++ = (bpp <= 12) ? (-10) : ((bpp >= 15) ? (-8) : (-10 + dsc_roundf((bpp - 12) * (2 / 3.0)))); - *p++ = -10; - *p++ = (bpp <= 6) ? (-12) : ((bpp >= 8) ? (-10) : (-12 + dsc_roundf((bpp - 6) * (2 / 2.0)))); - *p++ = -12; - *p++ = -12; - *p++ = -12; - } else if (mode == CM_422) { - *p++ = (bpp <= 8) ? (2) : ((bpp >= 10) ? (10) : (2 + dsc_roundf((bpp - 8) * (8 / 2.0)))); - *p++ = (bpp <= 8) ? (0) : ((bpp >= 10) ? (8) : (0 + dsc_roundf((bpp - 8) * (8 / 2.0)))); - *p++ = (bpp <= 8) ? (0) : ((bpp >= 10) ? (6) : (0 + dsc_roundf((bpp - 8) * (6 / 2.0)))); - *p++ = (bpp <= 8) ? (-2) : ((bpp >= 10) ? (4) : (-2 + dsc_roundf((bpp - 8) * (6 / 2.0)))); - *p++ = (bpp <= 8) ? (-4) : ((bpp >= 10) ? (2) : (-4 + dsc_roundf((bpp - 8) * (6 / 2.0)))); - *p++ = (bpp <= 8) ? (-6) : ((bpp >= 10) ? (0) : (-6 + dsc_roundf((bpp - 8) * (6 / 2.0)))); - *p++ = (bpp <= 8) ? (-8) : ((bpp >= 10) ? (-2) : (-8 + dsc_roundf((bpp - 8) * (6 / 2.0)))); - *p++ = (bpp <= 8) ? (-8) : ((bpp >= 10) ? (-4) : (-8 + dsc_roundf((bpp - 8) * (4 / 2.0)))); - *p++ = (bpp <= 8) ? (-8) : ((bpp >= 10) ? (-6) : (-8 + dsc_roundf((bpp - 8) * (2 / 2.0)))); - *p++ = (bpp <= 8) ? (-10) : ((bpp >= 10) ? (-8) : (-10 + dsc_roundf((bpp - 8) * (2 / 2.0)))); - *p++ = -10; - *p++ = (bpp <= 6) ? (-12) : ((bpp >= 7) ? (-10) : (-12 + dsc_roundf((bpp - 6) * (2.0 / 1)))); - *p++ = -12; - *p++ = -12; - *p++ = -12; - } else { - *p++ = (bpp <= 6) ? (2) : ((bpp >= 8) ? (10) : (2 + dsc_roundf((bpp - 6) * (8 / 2.0)))); - *p++ = (bpp <= 6) ? (0) : ((bpp >= 8) ? (8) : (0 + dsc_roundf((bpp - 6) * (8 / 2.0)))); - *p++ = (bpp <= 6) ? (0) : ((bpp >= 8) ? (6) : (0 + dsc_roundf((bpp - 6) * (6 / 2.0)))); - *p++ = (bpp <= 6) ? (-2) : ((bpp >= 8) ? (4) : (-2 + dsc_roundf((bpp - 6) * (6 / 2.0)))); - *p++ = (bpp <= 6) ? (-4) : ((bpp >= 8) ? (2) : (-4 + dsc_roundf((bpp - 6) * (6 / 2.0)))); - *p++ = (bpp <= 6) ? (-6) : ((bpp >= 8) ? (0) : (-6 + dsc_roundf((bpp - 6) * (6 / 2.0)))); - *p++ = (bpp <= 6) ? (-8) : ((bpp >= 8) ? (-2) : (-8 + dsc_roundf((bpp - 6) * (6 / 2.0)))); - *p++ = (bpp <= 6) ? (-8) : ((bpp >= 8) ? (-4) : (-8 + dsc_roundf((bpp - 6) * (4 / 2.0)))); - *p++ = (bpp <= 6) ? (-8) : ((bpp >= 8) ? (-6) : (-8 + dsc_roundf((bpp - 6) * (2 / 2.0)))); - *p++ = (bpp <= 6) ? (-10) : ((bpp >= 8) ? (-8) : (-10 + dsc_roundf((bpp - 6) * (2 / 2.0)))); - *p++ = -10; - *p++ = (bpp <= 4) ? (-12) : ((bpp >= 5) ? (-10) : (-12 + dsc_roundf((bpp - 4) * (2 / 1.0)))); - *p++ = -12; - *p++ = -12; - *p++ = -12; - } -} - -static int median3(int a, int b, int c) -{ - if (a > b) - swap(a, b); - if (b > c) - swap(b, c); - if (a > b) - swap(b, c); - - return b; -} - -static void _do_calc_rc_params(struct rc_params *rc, enum colour_mode cm, - enum bits_per_comp bpc, u16 drm_bpp, - bool is_navite_422_or_420, - int slice_width, int slice_height, - int minor_version) -{ - float bpp; - float bpp_group; - float initial_xmit_delay_factor; - int padding_pixels; - int i; - - bpp = ((float)drm_bpp / 16.0); - /* in native_422 or native_420 modes, the bits_per_pixel is double the - * target bpp (the latter is what calc_rc_params expects) - */ - if (is_navite_422_or_420) - bpp /= 2.0; - - rc->rc_quant_incr_limit0 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); - rc->rc_quant_incr_limit1 = ((bpc == BPC_8) ? 11 : (bpc == BPC_10 ? 15 : 19)) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); - - bpp_group = MODE_SELECT(bpp, bpp * 2.0, bpp * 2.0); - - switch (cm) { - case CM_420: - rc->initial_fullness_offset = (bpp >= 6) ? (2048) : ((bpp <= 4) ? (6144) : ((((bpp > 4) && (bpp <= 5))) ? (6144 - dsc_roundf((bpp - 4) * (512))) : (5632 - dsc_roundf((bpp - 5) * (3584))))); - rc->first_line_bpg_offset = median3(0, (12 + (int) (0.09 * min(34, slice_height - 8))), (int)((3 * bpc * 3) - (3 * bpp_group))); - rc->second_line_bpg_offset = median3(0, 12, (int)((3 * bpc * 3) - (3 * bpp_group))); - break; - case CM_422: - rc->initial_fullness_offset = (bpp >= 8) ? (2048) : ((bpp <= 7) ? (5632) : (5632 - dsc_roundf((bpp - 7) * (3584)))); - rc->first_line_bpg_offset = median3(0, (12 + (int) (0.09 * min(34, slice_height - 8))), (int)((3 * bpc * 4) - (3 * bpp_group))); - rc->second_line_bpg_offset = 0; - break; - case CM_444: - case CM_RGB: - rc->initial_fullness_offset = (bpp >= 12) ? (2048) : ((bpp <= 8) ? (6144) : ((((bpp > 8) && (bpp <= 10))) ? (6144 - dsc_roundf((bpp - 8) * (512 / 2))) : (5632 - dsc_roundf((bpp - 10) * (3584 / 2))))); - rc->first_line_bpg_offset = median3(0, (12 + (int) (0.09 * min(34, slice_height - 8))), (int)(((3 * bpc + (cm == CM_444 ? 0 : 2)) * 3) - (3 * bpp_group))); - rc->second_line_bpg_offset = 0; - break; - } - - initial_xmit_delay_factor = (cm == CM_444 || cm == CM_RGB) ? 1.0 : 2.0; - rc->initial_xmit_delay = dsc_roundf(8192.0/2.0/bpp/initial_xmit_delay_factor); - - if (cm == CM_422 || cm == CM_420) - slice_width /= 2; - - padding_pixels = ((slice_width % 3) != 0) ? (3 - (slice_width % 3)) * (rc->initial_xmit_delay / slice_width) : 0; - if (3 * bpp_group >= (((rc->initial_xmit_delay + 2) / 3) * (3 + (cm == CM_422)))) { - if ((rc->initial_xmit_delay + padding_pixels) % 3 == 1) - rc->initial_xmit_delay++; - } - - rc->flatness_min_qp = ((bpc == BPC_8) ? (3) : ((bpc == BPC_10) ? (7) : (11))) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); - rc->flatness_max_qp = ((bpc == BPC_8) ? (12) : ((bpc == BPC_10) ? (16) : (20))) - ((minor_version == 1 && cm == CM_444) ? 1 : 0); - rc->flatness_det_thresh = 2 << (bpc - 8); - - get_qp_set(rc->qp_min, cm, bpc, DAL_MM_MIN, bpp); - get_qp_set(rc->qp_max, cm, bpc, DAL_MM_MAX, bpp); - if (cm == CM_444 && minor_version == 1) { - for (i = 0; i < QP_SET_SIZE; ++i) { - rc->qp_min[i] = rc->qp_min[i] > 0 ? rc->qp_min[i] - 1 : 0; - rc->qp_max[i] = rc->qp_max[i] > 0 ? rc->qp_max[i] - 1 : 0; - } - } - get_ofs_set(rc->ofs, cm, bpp); - - /* fixed parameters */ - rc->rc_model_size = 8192; - rc->rc_edge_factor = 6; - rc->rc_tgt_offset_hi = 3; - rc->rc_tgt_offset_lo = 3; - - rc->rc_buf_thresh[0] = 896; - rc->rc_buf_thresh[1] = 1792; - rc->rc_buf_thresh[2] = 2688; - rc->rc_buf_thresh[3] = 3584; - rc->rc_buf_thresh[4] = 4480; - rc->rc_buf_thresh[5] = 5376; - rc->rc_buf_thresh[6] = 6272; - rc->rc_buf_thresh[7] = 6720; - rc->rc_buf_thresh[8] = 7168; - rc->rc_buf_thresh[9] = 7616; - rc->rc_buf_thresh[10] = 7744; - rc->rc_buf_thresh[11] = 7872; - rc->rc_buf_thresh[12] = 8000; - rc->rc_buf_thresh[13] = 8064; -} - -static u32 _do_bytes_per_pixel_calc(int slice_width, u16 drm_bpp, - bool is_navite_422_or_420) -{ - float bpp; - u32 bytes_per_pixel; - double d_bytes_per_pixel; - - bpp = ((float)drm_bpp / 16.0); - d_bytes_per_pixel = dsc_ceil(bpp * slice_width / 8.0) / slice_width; - // TODO: Make sure the formula for calculating this is precise (ceiling - // vs. floor, and at what point they should be applied) - if (is_navite_422_or_420) - d_bytes_per_pixel /= 2; - - bytes_per_pixel = (u32)dsc_ceil(d_bytes_per_pixel * 0x10000000); - - return bytes_per_pixel; -} /** * calc_rc_params - reads the user's cmdline mode diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h index 262f06afcbf9..c2340e001b57 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h +++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h @@ -27,55 +27,7 @@ #ifndef __RC_CALC_H__ #define __RC_CALC_H__ - -#define QP_SET_SIZE 15 - -typedef int qp_set[QP_SET_SIZE]; - -struct rc_params { - int rc_quant_incr_limit0; - int rc_quant_incr_limit1; - int initial_fullness_offset; - int initial_xmit_delay; - int first_line_bpg_offset; - int second_line_bpg_offset; - int flatness_min_qp; - int flatness_max_qp; - int flatness_det_thresh; - qp_set qp_min; - qp_set qp_max; - qp_set ofs; - int rc_model_size; - int rc_edge_factor; - int rc_tgt_offset_hi; - int rc_tgt_offset_lo; - int rc_buf_thresh[QP_SET_SIZE - 1]; -}; - -enum colour_mode { - CM_RGB, /* 444 RGB */ - CM_444, /* 444 YUV or simple 422 */ - CM_422, /* native 422 */ - CM_420 /* native 420 */ -}; - -enum bits_per_comp { - BPC_8 = 8, - BPC_10 = 10, - BPC_12 = 12 -}; - -enum max_min { - DAL_MM_MIN = 0, - DAL_MM_MAX = 1 -}; - -struct qp_entry { - float bpp; - const qp_set qps; -}; - -typedef struct qp_entry qp_table[]; +#include "dml/dsc/rc_calc_fpu.h" void calc_rc_params(struct rc_params *rc, const struct drm_dsc_config *pps); u32 calc_dsc_bytes_per_pixel(const struct drm_dsc_config *pps); diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c index ef830aded5b1..1e19dd674e5a 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c @@ -22,7 +22,6 @@ * Authors: AMD * */ -#include "os_types.h" #include #include "dscc_types.h" #include "rc_calc.h" diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index c70375117519..a6d3d859754a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -121,12 +121,12 @@ enum dc_status dpcd_set_lane_settings( const struct link_training_settings *link_training_setting, uint32_t offset); /* Read training status and adjustment requests from DPCD. */ -enum dc_status dp_get_lane_status_and_drive_settings( +enum dc_status dp_get_lane_status_and_lane_adjust( struct dc_link *link, const struct link_training_settings *link_training_setting, - union lane_status *ln_status, - union lane_align_status_updated *ln_status_updated, - struct link_training_settings *req_settings, + union lane_status ln_status[LANE_COUNT_DP_MAX], + union lane_align_status_updated *ln_align, + union lane_adjust ln_adjust[LANE_COUNT_DP_MAX], uint32_t offset); void dp_wait_for_training_aux_rd_interval( @@ -151,9 +151,11 @@ void dp_hw_to_dpcd_lane_settings( const struct link_training_settings *lt_settings, const struct dc_lane_settings hw_lane_settings[LANE_COUNT_DP_MAX], union dpcd_training_lane dpcd_lane_settings[LANE_COUNT_DP_MAX]); -void dp_update_drive_settings( - struct link_training_settings *dest, - struct link_training_settings src); +void dp_decide_lane_settings( + const struct link_training_settings *lt_settings, + const union lane_adjust ln_adjust[LANE_COUNT_DP_MAX], + struct dc_lane_settings hw_lane_settings[LANE_COUNT_DP_MAX], + union dpcd_training_lane dpcd_lane_settings[LANE_COUNT_DP_MAX]); uint32_t dp_translate_training_aux_read_interval(uint32_t dpcd_aux_read_interval); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h index 09237d5819f4..c940fdfda144 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h @@ -123,6 +123,15 @@ struct dccg_funcs { void (*set_dispclk_change_mode)( struct dccg *dccg, enum dentist_dispclk_change_mode change_mode); + + void (*disable_dsc)( + struct dccg *dccg, + int inst); + + void (*enable_dsc)( + struct dccg *dccg, + int inst); + }; #endif //__DAL_DCCG_H__ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index 9f12792b7e59..3ef7faa92052 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -34,6 +34,8 @@ union defer_reg_writes { bool disable_blnd_lut:1; bool disable_3dlut:1; bool disable_shaper:1; + bool disable_gamcor:1; + bool disable_dscl:1; } bits; uint32_t raw; }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h b/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h index 83b2199b2c83..10dcf6a5e9b1 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h @@ -97,7 +97,7 @@ struct link_encoder *link_enc_cfg_get_link_enc_used_by_stream( const struct dc_stream_state *stream); /* Return true if encoder available to use. */ -bool link_enc_cfg_is_link_enc_avail(struct dc *dc, enum engine_id eng_id); +bool link_enc_cfg_is_link_enc_avail(struct dc *dc, enum engine_id eng_id, struct dc_link *link); /* Returns true if encoder assignments in supplied state pass validity checks. */ bool link_enc_cfg_validate(struct dc *dc, struct dc_state *state); diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index 365fbc4758e1..717c0e572d2f 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -97,6 +97,7 @@ enum dmub_asic { DMUB_ASIC_DCN302, DMUB_ASIC_DCN303, DMUB_ASIC_DCN31, + DMUB_ASIC_DCN31B, DMUB_ASIC_MAX, }; @@ -237,6 +238,7 @@ struct dmub_srv_hw_params { bool load_inst_const; bool skip_panel_power_sequence; bool disable_z10; + bool dpia_supported; bool disable_dpia; }; diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 0b9d6bf4886d..0293c58f0701 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -46,10 +46,10 @@ /* Firmware versioning. */ #ifdef DMUB_EXPOSE_VERSION -#define DMUB_FW_VERSION_GIT_HASH 0xf0c64c97 +#define DMUB_FW_VERSION_GIT_HASH 0x9525efb5 #define DMUB_FW_VERSION_MAJOR 0 #define DMUB_FW_VERSION_MINOR 0 -#define DMUB_FW_VERSION_REVISION 87 +#define DMUB_FW_VERSION_REVISION 90 #define DMUB_FW_VERSION_TEST 0 #define DMUB_FW_VERSION_VBIOS 0 #define DMUB_FW_VERSION_HOTFIX 0 @@ -370,8 +370,13 @@ union dmub_fw_boot_options { uint32_t z10_disable: 1; /**< 1 to disable z10 */ uint32_t enable_dpia: 1; /**< 1 if DPIA should be enabled */ uint32_t invalid_vbios_data: 1; /**< 1 if VBIOS data table is invalid */ - uint32_t reserved_unreleased2: 1; /**< reserved for an unreleased feature */ - uint32_t reserved : 22; /**< reserved */ + uint32_t dpia_supported: 1; /**< 1 if DPIA is supported on this platform */ + uint32_t sel_mux_phy_c_d_phy_f_g: 1; /**< 1 if PHYF/PHYG should be enabled */ + /**< 1 if all root clock gating is enabled and low power memory is enabled*/ + uint32_t power_optimization: 1; + uint32_t diag_env: 1; /* 1 if diagnostic environment */ + + uint32_t reserved : 19; /**< reserved */ } bits; /**< boot bits */ uint32_t all; /**< 32-bit access to bits */ }; @@ -692,6 +697,7 @@ enum dmub_out_cmd_type { enum dmub_cmd_dpia_type { DMUB_CMD__DPIA_DIG1_DPIA_CONTROL = 0, DMUB_CMD__DPIA_SET_CONFIG_ACCESS = 1, + DMUB_CMD__DPIA_MST_ALLOC_SLOTS = 2, }; #pragma pack(push, 1) @@ -1066,6 +1072,24 @@ struct dmub_rb_cmd_set_config_access { struct dmub_cmd_set_config_control_data set_config_control; /* set config data */ }; +/** + * Data passed from driver to FW in a DMUB_CMD__DPIA_MST_ALLOC_SLOTS command. + */ +struct dmub_cmd_mst_alloc_slots_control_data { + uint8_t mst_alloc_slots; /* mst slots to be allotted */ + uint8_t instance; /* DPIA instance */ + uint8_t immed_status; /* Immediate status returned as there is no outbox msg posted */ + uint8_t mst_slots_in_use; /* returns slots in use for error cases */ +}; + +/** + * DMUB command structure for SET_ command. + */ +struct dmub_rb_cmd_set_mst_alloc_slots { + struct dmub_cmd_header header; /* header */ + struct dmub_cmd_mst_alloc_slots_control_data mst_slots_control; /* mst slots control */ +}; + /** * struct dmub_rb_cmd_dpphy_init - DPPHY init. */ @@ -1378,6 +1402,10 @@ enum dmub_cmd_psr_type { * Forces PSR enabled until an explicit PSR disable call. */ DMUB_CMD__PSR_FORCE_STATIC = 5, + /** + * Set PSR power option + */ + DMUB_CMD__SET_PSR_POWER_OPT = 7, }; /** @@ -1675,6 +1703,44 @@ struct dmub_rb_cmd_psr_force_static { struct dmub_cmd_psr_force_static_data psr_force_static_data; }; +/** + * Data passed from driver to FW in a DMUB_CMD__SET_PSR_POWER_OPT command. + */ +struct dmub_cmd_psr_set_power_opt_data { + /** + * PSR control version. + */ + uint8_t cmd_version; + /** + * Panel Instance. + * Panel isntance to identify which psr_state to use + * Currently the support is only for 0 or 1 + */ + uint8_t panel_inst; + /** + * Explicit padding to 4 byte boundary. + */ + uint8_t pad[2]; + /** + * PSR power option + */ + uint32_t power_opt; +}; + +/** + * Definition of a DMUB_CMD__SET_PSR_POWER_OPT command. + */ +struct dmub_rb_cmd_psr_set_power_opt { + /** + * Command header. + */ + struct dmub_cmd_header header; + /** + * Definition of a DMUB_CMD__SET_PSR_POWER_OPT command. + */ + struct dmub_cmd_psr_set_power_opt_data psr_set_power_opt_data; +}; + /** * Set of HW components that can be locked. * @@ -2458,6 +2524,10 @@ union dmub_rb_cmd { * Definition of a DMUB_CMD__PSR_FORCE_STATIC command. */ struct dmub_rb_cmd_psr_force_static psr_force_static; + /** + * Definition of a DMUB_CMD__SET_PSR_POWER_OPT command. + */ + struct dmub_rb_cmd_psr_set_power_opt psr_set_power_opt; /** * Definition of a DMUB_CMD__PLAT_54186_WA command. */ @@ -2542,6 +2612,10 @@ union dmub_rb_cmd { * Definition of a DMUB_CMD__DPIA_SET_CONFIG_ACCESS command. */ struct dmub_rb_cmd_set_config_access set_config_access; + /** + * Definition of a DMUB_CMD__DPIA_MST_ALLOC_SLOTS command. + */ + struct dmub_rb_cmd_set_mst_alloc_slots set_mst_alloc_slots; /** * Definition of a DMUB_CMD__EDID_CEA command. */ diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index 3988f65f1ea4..10ebf20eaa41 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -338,8 +338,11 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu union dmub_fw_boot_options boot_options = {0}; boot_options.bits.z10_disable = params->disable_z10; + boot_options.bits.dpia_supported = params->dpia_supported; boot_options.bits.enable_dpia = params->disable_dpia ? 0 : 1; + boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0; + REG_WRITE(DMCUB_SCRATCH14, boot_options.all); } diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 77c67222cabd..56d400ffa7ac 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -208,6 +208,7 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) break; case DMUB_ASIC_DCN31: + case DMUB_ASIC_DCN31B: dmub->regs_dcn31 = &dmub_srv_dcn31_regs; funcs->reset = dmub_dcn31_reset; funcs->reset_release = dmub_dcn31_reset_release; diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index a9974f12f7fb..e4a2dfacab4c 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -228,7 +228,7 @@ enum { #define FAMILY_YELLOW_CARP 146 #define YELLOW_CARP_A0 0x01 -#define YELLOW_CARP_B0 0x1A +#define YELLOW_CARP_B0 0x20 #define YELLOW_CARP_UNKNOWN 0xFF #ifndef ASICREV_IS_YELLOW_CARP diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index 792652236c61..dd974c428d23 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -328,6 +328,7 @@ struct integrated_info { uint8_t gu_id[NUMBER_OF_UCHAR_FOR_GUID]; uint8_t checksum; + uint8_t fixdpvoltageswing; } ext_disp_conn_info; /* exiting long long time */ struct available_s_clk_list { diff --git a/drivers/gpu/drm/amd/display/include/i2caux_interface.h b/drivers/gpu/drm/amd/display/include/i2caux_interface.h index c7fbb9c3ad6b..418fbf8c5c3a 100644 --- a/drivers/gpu/drm/amd/display/include/i2caux_interface.h +++ b/drivers/gpu/drm/amd/display/include/i2caux_interface.h @@ -41,6 +41,8 @@ struct aux_payload { * reset it to read data */ bool write; bool mot; + bool write_status_update; + uint32_t address; uint32_t length; uint8_t *data; @@ -53,6 +55,7 @@ struct aux_payload { * zero means "use default value" */ uint32_t defer_delay; + }; struct aux_command { diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h index 9ffea7b40545..424bccd36434 100644 --- a/drivers/gpu/drm/amd/display/include/link_service_types.h +++ b/drivers/gpu/drm/amd/display/include/link_service_types.h @@ -90,8 +90,11 @@ enum lttpr_mode { struct link_training_settings { struct dc_link_settings link_settings; - struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]; + /* TODO: turn lane settings below into mandatory fields + * as initial lane configuration + */ + struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]; enum dc_voltage_swing *voltage_swing; enum dc_pre_emphasis *pre_emphasis; enum dc_post_cursor2 *post_cursor2; @@ -115,8 +118,30 @@ struct link_training_settings { #endif bool enhanced_framing; - bool allow_invalid_msa_timing_param; enum lttpr_mode lttpr_mode; + + /* disallow different lanes to have different lane settings */ + bool disallow_per_lane_settings; + /* dpcd lane settings will always use the same hw lane settings + * even if it doesn't match requested lane adjust */ + bool always_match_dpcd_with_hw_lane_settings; + + /***************************************************************** + * training states - parameters that can change in link training + *****************************************************************/ + /* TODO: Move hw_lane_settings and dpcd_lane_settings + * along with lane adjust, lane align, offset and all + * other training states into a new structure called + * training states, so link_training_settings becomes + * a constant input pre-decided prior to link training. + * + * The goal is to strictly decouple link training settings + * decision making process from link training states to + * prevent it from messy code practice of changing training + * decision on the fly. + */ + struct dc_lane_settings hw_lane_settings[LANE_COUNT_DP_MAX]; + union dpcd_training_lane dpcd_lane_settings[LANE_COUNT_DP_MAX]; }; /*TODO: Move this enum test harness*/ diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index b99aa232bd8b..bd1d1dc93629 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -155,9 +155,18 @@ static unsigned int calc_v_total_from_duration( if (duration_in_us > vrr->max_duration_in_us) duration_in_us = vrr->max_duration_in_us; - v_total = div64_u64(div64_u64(((unsigned long long)( - duration_in_us) * (stream->timing.pix_clk_100hz / 10)), - stream->timing.h_total), 1000); + if (dc_is_hdmi_signal(stream->signal)) { + uint32_t h_total_up_scaled; + + h_total_up_scaled = stream->timing.h_total * 10000; + v_total = div_u64((unsigned long long)duration_in_us + * stream->timing.pix_clk_100hz + (h_total_up_scaled - 1), + h_total_up_scaled); + } else { + v_total = div64_u64(div64_u64(((unsigned long long)( + duration_in_us) * (stream->timing.pix_clk_100hz / 10)), + stream->timing.h_total), 1000); + } /* v_total cannot be less than nominal */ if (v_total < stream->timing.v_total) { diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index f37101f5a777..6d648c889866 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -249,6 +249,8 @@ struct mod_hdcp_link { uint8_t ddc_line; uint8_t link_enc_idx; uint8_t phy_idx; + uint8_t dio_output_type; + uint8_t dio_output_id; uint8_t hdcp_supported_informational; union { struct mod_hdcp_displayport dp; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 257f280d3d53..f1a46d16f7ea 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -228,7 +228,7 @@ enum DC_FEATURE_MASK { DC_FBC_MASK = (1 << 0), //0x1, disabled by default DC_MULTI_MON_PP_MCLK_SWITCH_MASK = (1 << 1), //0x2, enabled by default DC_DISABLE_FRACTIONAL_PWM_MASK = (1 << 2), //0x4, disabled by default - DC_PSR_MASK = (1 << 3), //0x8, disabled by default + DC_PSR_MASK = (1 << 3), //0x8, disabled by default for dcn < 3.1 DC_EDP_NO_POWER_SEQUENCING = (1 << 4), //0x10, disabled by default }; @@ -236,7 +236,8 @@ enum DC_DEBUG_MASK { DC_DISABLE_PIPE_SPLIT = 0x1, DC_DISABLE_STUTTER = 0x2, DC_DISABLE_DSC = 0x4, - DC_DISABLE_CLOCK_GATING = 0x8 + DC_DISABLE_CLOCK_GATING = 0x8, + DC_DISABLE_PSR = 0x10, }; enum amd_dpm_forced_level; diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_offset.h index 312c50ea30f3..f268d33c4744 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_offset.h @@ -436,6 +436,8 @@ #define regPHYESYMCLK_CLOCK_CNTL_BASE_IDX 2 #define regDCCG_GATE_DISABLE_CNTL3 0x005a #define regDCCG_GATE_DISABLE_CNTL3_BASE_IDX 2 +#define regHDMISTREAMCLK0_DTO_PARAM 0x005b +#define regHDMISTREAMCLK0_DTO_PARAM_BASE_IDX 2 #define regDCCG_AUDIO_DTBCLK_DTO_PHASE 0x0061 #define regDCCG_AUDIO_DTBCLK_DTO_PHASE_BASE_IDX 2 #define regDCCG_AUDIO_DTBCLK_DTO_MODULO 0x0062 diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h index a9d553ef26c0..1f21f313bd1d 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h @@ -1438,6 +1438,14 @@ #define DCCG_GATE_DISABLE_CNTL3__SYMCLK32_LE0_GATE_DISABLE_MASK 0x00200000L #define DCCG_GATE_DISABLE_CNTL3__SYMCLK32_ROOT_LE1_GATE_DISABLE_MASK 0x00400000L #define DCCG_GATE_DISABLE_CNTL3__SYMCLK32_LE1_GATE_DISABLE_MASK 0x00800000L +//HDMISTREAMCLK0_DTO_PARAM +#define HDMISTREAMCLK0_DTO_PARAM__HDMISTREAMCLK0_DTO_PHASE__SHIFT 0x0 +#define HDMISTREAMCLK0_DTO_PARAM__HDMISTREAMCLK0_DTO_MODULO__SHIFT 0x8 +#define HDMISTREAMCLK0_DTO_PARAM__HDMISTREAMCLK0_DTO_EN__SHIFT 0x10 +#define HDMISTREAMCLK0_DTO_PARAM__HDMISTREAMCLK0_DTO_PHASE_MASK 0x000000FFL +#define HDMISTREAMCLK0_DTO_PARAM__HDMISTREAMCLK0_DTO_MODULO_MASK 0x0000FF00L +#define HDMISTREAMCLK0_DTO_PARAM__HDMISTREAMCLK0_DTO_EN_MASK 0x00010000L + //DCCG_AUDIO_DTBCLK_DTO_PHASE #define DCCG_AUDIO_DTBCLK_DTO_PHASE__DCCG_AUDIO_DTBCLK_DTO_PHASE__SHIFT 0x0 #define DCCG_AUDIO_DTBCLK_DTO_PHASE__DCCG_AUDIO_DTBCLK_DTO_PHASE_MASK 0xFFFFFFFFL diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index c255b4b8e685..49fe4155c374 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -310,7 +310,7 @@ static ssize_t amdgpu_set_power_dpm_force_performance_level(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; enum amd_dpm_forced_level level; - enum amd_dpm_forced_level current_level = 0xff; + enum amd_dpm_forced_level current_level; int ret = 0; if (amdgpu_in_reset(adev)) @@ -350,6 +350,8 @@ static ssize_t amdgpu_set_power_dpm_force_performance_level(struct device *dev, if (pp_funcs->get_performance_level) current_level = amdgpu_dpm_get_performance_level(adev); + else + current_level = adev->pm.dpm.forced_level; if (current_level == level) { pm_runtime_mark_last_busy(ddev->dev); @@ -2019,15 +2021,15 @@ static struct amdgpu_device_attr amdgpu_device_attrs[] = { AMDGPU_DEVICE_ATTR_RW(pp_dpm_pcie, ATTR_FLAG_BASIC), AMDGPU_DEVICE_ATTR_RW(pp_sclk_od, ATTR_FLAG_BASIC), AMDGPU_DEVICE_ATTR_RW(pp_mclk_od, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RW(pp_power_profile_mode, ATTR_FLAG_BASIC), + AMDGPU_DEVICE_ATTR_RW(pp_power_profile_mode, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RW(pp_od_clk_voltage, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RO(gpu_busy_percent, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RO(mem_busy_percent, ATTR_FLAG_BASIC), + AMDGPU_DEVICE_ATTR_RO(gpu_busy_percent, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), + AMDGPU_DEVICE_ATTR_RO(mem_busy_percent, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RO(pcie_bw, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RW(pp_features, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RO(unique_id, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RW(thermal_throttling_logging, ATTR_FLAG_BASIC), - AMDGPU_DEVICE_ATTR_RO(gpu_metrics, ATTR_FLAG_BASIC), + AMDGPU_DEVICE_ATTR_RW(pp_features, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), + AMDGPU_DEVICE_ATTR_RO(unique_id, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), + AMDGPU_DEVICE_ATTR_RW(thermal_throttling_logging, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), + AMDGPU_DEVICE_ATTR_RO(gpu_metrics, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RO(smartshift_apu_power, ATTR_FLAG_BASIC, .attr_update = ss_power_attr_update), AMDGPU_DEVICE_ATTR_RO(smartshift_dgpu_power, ATTR_FLAG_BASIC, diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h index 8156729c370b..3557f4e7fc30 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h @@ -1008,7 +1008,9 @@ struct pptable_funcs { /** * @set_power_limit: Set power limit in watts. */ - int (*set_power_limit)(struct smu_context *smu, uint32_t n); + int (*set_power_limit)(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t limit); /** * @init_max_sustainable_clocks: Populate max sustainable clock speed diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h index cbdae8a2c698..2d422e6a9feb 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h @@ -197,7 +197,9 @@ int smu_v11_0_notify_display_change(struct smu_context *smu); int smu_v11_0_get_current_power_limit(struct smu_context *smu, uint32_t *power_limit); -int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n); +int smu_v11_0_set_power_limit(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t limit); int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu); diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h index dc91eb608791..e5d3b0d1a032 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h @@ -163,7 +163,9 @@ int smu_v13_0_notify_display_change(struct smu_context *smu); int smu_v13_0_get_current_power_limit(struct smu_context *smu, uint32_t *power_limit); -int smu_v13_0_set_power_limit(struct smu_context *smu, uint32_t n); +int smu_v13_0_set_power_limit(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t limit); int smu_v13_0_init_max_sustainable_clocks(struct smu_context *smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 4ea7e90ef60d..b06c59dcc1b4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -455,6 +455,10 @@ static int smu_get_power_num_states(void *handle, bool is_support_sw_smu(struct amdgpu_device *adev) { + /* vega20 is 11.0.2, but it's supported via the powerplay code */ + if (adev->asic_type == CHIP_VEGA20) + return false; + if (adev->ip_versions[MP1_HWIP][0] >= IP_VERSION(11, 0, 0)) return true; @@ -2344,9 +2348,10 @@ static int smu_set_power_limit(void *handle, uint32_t limit) mutex_lock(&smu->mutex); + limit &= (1<<24)-1; if (limit_type != SMU_DEFAULT_PPT_LIMIT) if (smu->ppt_funcs->set_power_limit) { - ret = smu->ppt_funcs->set_power_limit(smu, limit); + ret = smu->ppt_funcs->set_power_limit(smu, limit_type, limit); goto out; } @@ -2362,7 +2367,7 @@ static int smu_set_power_limit(void *handle, uint32_t limit) limit = smu->current_power_limit; if (smu->ppt_funcs->set_power_limit) { - ret = smu->ppt_funcs->set_power_limit(smu, limit); + ret = smu->ppt_funcs->set_power_limit(smu, limit_type, limit); if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE)) smu->user_dpm_profile.power_limit = limit; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 082f01893f3d..fd1d30a93db5 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -436,6 +436,19 @@ static void arcturus_check_bxco_support(struct smu_context *smu) } } +static void arcturus_check_fan_support(struct smu_context *smu) +{ + struct smu_table_context *table_context = &smu->smu_table; + PPTable_t *pptable = table_context->driver_pptable; + + /* No sort of fan control possible if PPTable has it disabled */ + smu->adev->pm.no_fan = + !(pptable->FeaturesToRun[0] & FEATURE_FAN_CONTROL_MASK); + if (smu->adev->pm.no_fan) + dev_info_once(smu->adev->dev, + "PMFW based fan control disabled"); +} + static int arcturus_check_powerplay_table(struct smu_context *smu) { struct smu_table_context *table_context = &smu->smu_table; @@ -443,6 +456,7 @@ static int arcturus_check_powerplay_table(struct smu_context *smu) table_context->power_play_table; arcturus_check_bxco_support(smu); + arcturus_check_fan_support(smu); table_context->thermal_controller_type = powerplay_table->thermal_controller_type; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c index 3d4c65bc29dc..cbc3f99e8573 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c @@ -47,7 +47,6 @@ /* unit: MHz */ #define CYAN_SKILLFISH_SCLK_MIN 1000 #define CYAN_SKILLFISH_SCLK_MAX 2000 -#define CYAN_SKILLFISH_SCLK_DEFAULT 1800 /* unit: mV */ #define CYAN_SKILLFISH_VDDC_MIN 700 @@ -59,6 +58,8 @@ static struct gfx_user_settings { uint32_t vddc; } cyan_skillfish_user_settings; +static uint32_t cyan_skillfish_sclk_default; + #define FEATURE_MASK(feature) (1ULL << feature) #define SMC_DPM_FEATURE ( \ FEATURE_MASK(FEATURE_FCLK_DPM_BIT) | \ @@ -365,13 +366,19 @@ static bool cyan_skillfish_is_dpm_running(struct smu_context *smu) return false; ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2); - if (ret) return false; feature_enabled = (uint64_t)feature_mask[0] | ((uint64_t)feature_mask[1] << 32); + /* + * cyan_skillfish specific, query default sclk inseted of hard code. + */ + if (!cyan_skillfish_sclk_default) + cyan_skillfish_get_smu_metrics_data(smu, METRICS_CURR_GFXCLK, + &cyan_skillfish_sclk_default); + return !!(feature_enabled & SMC_DPM_FEATURE); } @@ -444,14 +451,14 @@ static int cyan_skillfish_od_edit_dpm_table(struct smu_context *smu, return -EINVAL; } - if (input[1] <= CYAN_SKILLFISH_SCLK_MIN || + if (input[1] < CYAN_SKILLFISH_SCLK_MIN || input[1] > CYAN_SKILLFISH_SCLK_MAX) { dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n", CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX); return -EINVAL; } - if (input[2] <= CYAN_SKILLFISH_VDDC_MIN || + if (input[2] < CYAN_SKILLFISH_VDDC_MIN || input[2] > CYAN_SKILLFISH_VDDC_MAX) { dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n", CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX); @@ -468,7 +475,7 @@ static int cyan_skillfish_od_edit_dpm_table(struct smu_context *smu, return -EINVAL; } - cyan_skillfish_user_settings.sclk = CYAN_SKILLFISH_SCLK_DEFAULT; + cyan_skillfish_user_settings.sclk = cyan_skillfish_sclk_default; cyan_skillfish_user_settings.vddc = CYAN_SKILLFISH_VDDC_MAGIC; break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 15e66e1912de..a4108025fe29 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -670,7 +670,7 @@ static int sienna_cichlid_set_default_dpm_table(struct smu_context *smu) struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_11_0_dpm_table *dpm_table; struct amdgpu_device *adev = smu->adev; - int ret = 0; + int i, ret = 0; DpmDescriptor_t *table_member; /* socclk dpm table setup */ @@ -746,78 +746,45 @@ static int sienna_cichlid_set_default_dpm_table(struct smu_context *smu) dpm_table->max = dpm_table->dpm_levels[0].value; } - /* vclk0 dpm table setup */ - dpm_table = &dpm_context->dpm_tables.vclk_table; - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) { - ret = smu_v11_0_set_single_dpm_table(smu, - SMU_VCLK, - dpm_table); - if (ret) - return ret; - dpm_table->is_fine_grained = - !table_member[PPCLK_VCLK_0].SnapToDiscrete; - } else { - dpm_table->count = 1; - dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.vclk / 100; - dpm_table->dpm_levels[0].enabled = true; - dpm_table->min = dpm_table->dpm_levels[0].value; - dpm_table->max = dpm_table->dpm_levels[0].value; - } + /* vclk0/1 dpm table setup */ + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (adev->vcn.harvest_config & (1 << i)) + continue; - /* vclk1 dpm table setup */ - if (adev->vcn.num_vcn_inst > 1) { - dpm_table = &dpm_context->dpm_tables.vclk1_table; + dpm_table = &dpm_context->dpm_tables.vclk_table; if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) { ret = smu_v11_0_set_single_dpm_table(smu, - SMU_VCLK1, + i ? SMU_VCLK1 : SMU_VCLK, dpm_table); if (ret) return ret; dpm_table->is_fine_grained = - !table_member[PPCLK_VCLK_1].SnapToDiscrete; + !table_member[i ? PPCLK_VCLK_1 : PPCLK_VCLK_0].SnapToDiscrete; } else { dpm_table->count = 1; - dpm_table->dpm_levels[0].value = - smu->smu_table.boot_values.vclk / 100; + dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.vclk / 100; dpm_table->dpm_levels[0].enabled = true; dpm_table->min = dpm_table->dpm_levels[0].value; dpm_table->max = dpm_table->dpm_levels[0].value; } } - /* dclk0 dpm table setup */ - dpm_table = &dpm_context->dpm_tables.dclk_table; - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) { - ret = smu_v11_0_set_single_dpm_table(smu, - SMU_DCLK, - dpm_table); - if (ret) - return ret; - dpm_table->is_fine_grained = - !table_member[PPCLK_DCLK_0].SnapToDiscrete; - } else { - dpm_table->count = 1; - dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.dclk / 100; - dpm_table->dpm_levels[0].enabled = true; - dpm_table->min = dpm_table->dpm_levels[0].value; - dpm_table->max = dpm_table->dpm_levels[0].value; - } - - /* dclk1 dpm table setup */ - if (adev->vcn.num_vcn_inst > 1) { - dpm_table = &dpm_context->dpm_tables.dclk1_table; + /* dclk0/1 dpm table setup */ + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (adev->vcn.harvest_config & (1 << i)) + continue; + dpm_table = &dpm_context->dpm_tables.dclk_table; if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) { ret = smu_v11_0_set_single_dpm_table(smu, - SMU_DCLK1, + i ? SMU_DCLK1 : SMU_DCLK, dpm_table); if (ret) return ret; dpm_table->is_fine_grained = - !table_member[PPCLK_DCLK_1].SnapToDiscrete; + !table_member[i ? PPCLK_DCLK_1 : PPCLK_DCLK_0].SnapToDiscrete; } else { dpm_table->count = 1; - dpm_table->dpm_levels[0].value = - smu->smu_table.boot_values.dclk / 100; + dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.dclk / 100; dpm_table->dpm_levels[0].enabled = true; dpm_table->min = dpm_table->dpm_levels[0].value; dpm_table->max = dpm_table->dpm_levels[0].value; @@ -902,32 +869,18 @@ static int sienna_cichlid_set_default_dpm_table(struct smu_context *smu) static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enable) { struct amdgpu_device *adev = smu->adev; - int ret = 0; + int i, ret = 0; - if (enable) { + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (adev->vcn.harvest_config & (1 << i)) + continue; /* vcn dpm on is a prerequisite for vcn power gate messages */ if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) { - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0, NULL); + ret = smu_cmn_send_smc_msg_with_param(smu, enable ? + SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn, + 0x10000 * i, NULL); if (ret) return ret; - if (adev->vcn.num_vcn_inst > 1) { - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, - 0x10000, NULL); - if (ret) - return ret; - } - } - } else { - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_MM_DPM_PG_BIT)) { - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0, NULL); - if (ret) - return ret; - if (adev->vcn.num_vcn_inst > 1) { - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, - 0x10000, NULL); - if (ret) - return ret; - } } } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 3470c33ee09d..28b7c0562b99 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -255,7 +255,7 @@ int smu_v11_0_check_fw_version(struct smu_context *smu) case IP_VERSION(11, 0, 11): smu->smc_driver_if_version = SMU11_DRIVER_IF_VERSION_Navy_Flounder; break; - case CHIP_VANGOGH: + case IP_VERSION(11, 5, 0): smu->smc_driver_if_version = SMU11_DRIVER_IF_VERSION_VANGOGH; break; case IP_VERSION(11, 0, 12): @@ -755,6 +755,7 @@ int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count) */ if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 11) || adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 5, 0) || + adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 12) || adev->ip_versions[MP1_HWIP][0] == IP_VERSION(11, 0, 13)) return 0; @@ -978,10 +979,16 @@ int smu_v11_0_get_current_power_limit(struct smu_context *smu, return ret; } -int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n) +int smu_v11_0_set_power_limit(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t limit) { int power_src; int ret = 0; + uint32_t limit_param; + + if (limit_type != SMU_DEFAULT_PPT_LIMIT) + return -EINVAL; if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) { dev_err(smu->adev->dev, "Setting new power limit is not supported!\n"); @@ -1001,16 +1008,16 @@ int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n) * BIT 16-23: PowerSource * BIT 0-15: PowerLimit */ - n &= 0xFFFF; - n |= 0 << 24; - n |= (power_src) << 16; - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetPptLimit, n, NULL); + limit_param = (limit & 0xFFFF); + limit_param |= 0 << 24; + limit_param |= (power_src) << 16; + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetPptLimit, limit_param, NULL); if (ret) { dev_err(smu->adev->dev, "[%s] Set power limit Failed!\n", __func__); return ret; } - smu->current_power_limit = n; + smu->current_power_limit = limit; return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index f6ef0ce6e9e2..421f38e8dada 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -1386,52 +1386,38 @@ static int vangogh_set_performance_level(struct smu_context *smu, uint32_t soc_mask, mclk_mask, fclk_mask; uint32_t vclk_mask = 0, dclk_mask = 0; + smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; + smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; + switch (level) { case AMD_DPM_FORCED_LEVEL_HIGH: - smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; + smu->gfx_actual_hard_min_freq = smu->gfx_default_soft_max_freq; smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; ret = vangogh_force_dpm_limit_value(smu, true); + if (ret) + return ret; break; case AMD_DPM_FORCED_LEVEL_LOW: smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; - smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; + smu->gfx_actual_soft_max_freq = smu->gfx_default_hard_min_freq; ret = vangogh_force_dpm_limit_value(smu, false); + if (ret) + return ret; break; case AMD_DPM_FORCED_LEVEL_AUTO: smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; - ret = vangogh_unforce_dpm_levels(smu); + if (ret) + return ret; break; case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: - smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; - smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetHardMinGfxClk, - VANGOGH_UMD_PSTATE_STANDARD_GFXCLK, NULL); - if (ret) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetSoftMaxGfxClk, - VANGOGH_UMD_PSTATE_STANDARD_GFXCLK, NULL); - if (ret) - return ret; + smu->gfx_actual_hard_min_freq = VANGOGH_UMD_PSTATE_STANDARD_GFXCLK; + smu->gfx_actual_soft_max_freq = VANGOGH_UMD_PSTATE_STANDARD_GFXCLK; ret = vangogh_get_profiling_clk_mask(smu, level, &vclk_mask, @@ -1446,32 +1432,15 @@ static int vangogh_set_performance_level(struct smu_context *smu, vangogh_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask); vangogh_force_clk_levels(smu, SMU_VCLK, 1 << vclk_mask); vangogh_force_clk_levels(smu, SMU_DCLK, 1 << dclk_mask); - break; case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; - smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; - - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinVcn, - VANGOGH_UMD_PSTATE_PEAK_DCLK, NULL); - if (ret) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxVcn, - VANGOGH_UMD_PSTATE_PEAK_DCLK, NULL); - if (ret) - return ret; + smu->gfx_actual_soft_max_freq = smu->gfx_default_hard_min_freq; break; case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; - ret = vangogh_get_profiling_clk_mask(smu, level, NULL, NULL, @@ -1484,29 +1453,29 @@ static int vangogh_set_performance_level(struct smu_context *smu, vangogh_force_clk_levels(smu, SMU_FCLK, 1 << fclk_mask); break; case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: - smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq; - smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq; - - smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq; - smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq; - - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk, - VANGOGH_UMD_PSTATE_PEAK_GFXCLK, NULL); - if (ret) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk, - VANGOGH_UMD_PSTATE_PEAK_GFXCLK, NULL); - if (ret) - return ret; + smu->gfx_actual_hard_min_freq = VANGOGH_UMD_PSTATE_PEAK_GFXCLK; + smu->gfx_actual_soft_max_freq = VANGOGH_UMD_PSTATE_PEAK_GFXCLK; ret = vangogh_set_peak_clock_by_device(smu); + if (ret) + return ret; break; case AMD_DPM_FORCED_LEVEL_MANUAL: case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT: default: - break; + return 0; } + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk, + smu->gfx_actual_hard_min_freq, NULL); + if (ret) + return ret; + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk, + smu->gfx_actual_soft_max_freq, NULL); + if (ret) + return ret; + return ret; } @@ -2144,11 +2113,12 @@ static int vangogh_get_ppt_limit(struct smu_context *smu, return 0; } -static int vangogh_set_power_limit(struct smu_context *smu, uint32_t ppt_limit) +static int vangogh_set_power_limit(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t ppt_limit) { struct smu_11_5_power_context *power_context = - smu->smu_power.power_context; - uint32_t limit_type = ppt_limit >> 24; + smu->smu_power.power_context; int ret = 0; if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 5019903db492..59a7d276541d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1241,11 +1241,13 @@ static int aldebaran_get_power_limit(struct smu_context *smu, return 0; } -static int aldebaran_set_power_limit(struct smu_context *smu, uint32_t n) +static int aldebaran_set_power_limit(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t limit) { /* Power limit can be set only through primary die */ if (aldebaran_is_primary(smu)) - return smu_v13_0_set_power_limit(smu, n); + return smu_v13_0_set_power_limit(smu, limit_type, limit); return -EINVAL; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 05c5e61f3506..35145db6eedf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -945,22 +945,27 @@ int smu_v13_0_get_current_power_limit(struct smu_context *smu, return ret; } -int smu_v13_0_set_power_limit(struct smu_context *smu, uint32_t n) +int smu_v13_0_set_power_limit(struct smu_context *smu, + enum smu_ppt_limit_type limit_type, + uint32_t limit) { int ret = 0; + if (limit_type != SMU_DEFAULT_PPT_LIMIT) + return -EINVAL; + if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) { dev_err(smu->adev->dev, "Setting new power limit is not supported!\n"); return -EOPNOTSUPP; } - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetPptLimit, n, NULL); + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetPptLimit, limit, NULL); if (ret) { dev_err(smu->adev->dev, "[%s] Set power limit Failed!\n", __func__); return ret; } - smu->current_power_limit = n; + smu->current_power_limit = limit; return 0; } diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-cec.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-cec.c index 70ab4fbdc23e..c8f44bcb298a 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-cec.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-cec.c @@ -265,11 +265,9 @@ static int dw_hdmi_cec_probe(struct platform_device *pdev) /* override the module pointer */ cec->adap->owner = THIS_MODULE; - ret = devm_add_action(&pdev->dev, dw_hdmi_cec_del, cec); - if (ret) { - cec_delete_adapter(cec->adap); + ret = devm_add_action_or_reset(&pdev->dev, dw_hdmi_cec_del, cec); + if (ret) return ret; - } ret = devm_request_threaded_irq(&pdev->dev, cec->irq, dw_hdmi_cec_hardirq, diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 41d48a393e7f..6154bed0af5b 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -615,20 +615,8 @@ static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector) return drm_bridge_get_modes(pdata->next_bridge, connector); } -static enum drm_mode_status -ti_sn_bridge_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - /* maximum supported resolution is 4K at 60 fps */ - if (mode->clock > 594000) - return MODE_CLOCK_HIGH; - - return MODE_OK; -} - static struct drm_connector_helper_funcs ti_sn_bridge_connector_helper_funcs = { .get_modes = ti_sn_bridge_connector_get_modes, - .mode_valid = ti_sn_bridge_connector_mode_valid, }; static const struct drm_connector_funcs ti_sn_bridge_connector_funcs = { @@ -766,6 +754,18 @@ static void ti_sn_bridge_detach(struct drm_bridge *bridge) drm_dp_aux_unregister(&bridge_to_ti_sn65dsi86(bridge)->aux); } +static enum drm_mode_status +ti_sn_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + /* maximum supported resolution is 4K at 60 fps */ + if (mode->clock > 594000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + static void ti_sn_bridge_disable(struct drm_bridge *bridge) { struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); @@ -1127,6 +1127,7 @@ static void ti_sn_bridge_post_disable(struct drm_bridge *bridge) static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .attach = ti_sn_bridge_attach, .detach = ti_sn_bridge_detach, + .mode_valid = ti_sn_bridge_mode_valid, .pre_enable = ti_sn_bridge_pre_enable, .enable = ti_sn_bridge_enable, .disable = ti_sn_bridge_disable, diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 6d0f2c447f3b..4d0d1e8e51fa 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -130,6 +130,20 @@ u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SI } EXPORT_SYMBOL(drm_dp_get_adjust_request_pre_emphasis); +/* DP 2.0 128b/132b */ +u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane) +{ + int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1); + int s = ((lane & 1) ? + DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT : + DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT); + u8 l = dp_link_status(link_status, i); + + return (l >> s) & 0xf; +} +EXPORT_SYMBOL(drm_dp_get_adjust_tx_ffe_preset); + u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], unsigned int lane) { @@ -207,15 +221,33 @@ EXPORT_SYMBOL(drm_dp_lttpr_link_train_channel_eq_delay); u8 drm_dp_link_rate_to_bw_code(int link_rate) { - /* Spec says link_bw = link_rate / 0.27Gbps */ - return link_rate / 27000; + switch (link_rate) { + case 1000000: + return DP_LINK_BW_10; + case 1350000: + return DP_LINK_BW_13_5; + case 2000000: + return DP_LINK_BW_20; + default: + /* Spec says link_bw = link_rate / 0.27Gbps */ + return link_rate / 27000; + } } EXPORT_SYMBOL(drm_dp_link_rate_to_bw_code); int drm_dp_bw_code_to_link_rate(u8 link_bw) { - /* Spec says link_rate = link_bw * 0.27Gbps */ - return link_bw * 27000; + switch (link_bw) { + case DP_LINK_BW_10: + return 1000000; + case DP_LINK_BW_13_5: + return 1350000; + case DP_LINK_BW_20: + return 2000000; + default: + /* Spec says link_rate = link_bw * 0.27Gbps */ + return link_bw * 27000; + } } EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate); @@ -590,7 +622,7 @@ static u8 drm_dp_downstream_port_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) static int drm_dp_read_extended_dpcd_caps(struct drm_dp_aux *aux, u8 dpcd[DP_RECEIVER_CAP_SIZE]) { - u8 dpcd_ext[6]; + u8 dpcd_ext[DP_RECEIVER_CAP_SIZE]; int ret; /* diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 86d13d6bc463..571da0c2f39f 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3355,6 +3355,10 @@ static int drm_dp_destroy_payload_step2(struct drm_dp_mst_topology_mgr *mgr, /** * drm_dp_update_payload_part1() - Execute payload update part 1 * @mgr: manager to use. + * @start_slot: this is the cur slot + * + * NOTE: start_slot is a temporary workaround for non-atomic drivers, + * this will be removed when non-atomic mst helpers are moved out of the helper * * This iterates over all proposed virtual channels, and tries to * allocate space in the link for them. For 0->slots transitions, @@ -3365,12 +3369,12 @@ static int drm_dp_destroy_payload_step2(struct drm_dp_mst_topology_mgr *mgr, * after calling this the driver should generate ACT and payload * packets. */ -int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) +int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr, int start_slot) { struct drm_dp_payload req_payload; struct drm_dp_mst_port *port; int i, j; - int cur_slots = 1; + int cur_slots = start_slot; bool skip; mutex_lock(&mgr->payload_lock); @@ -4334,10 +4338,6 @@ static int drm_dp_init_vcpi(struct drm_dp_mst_topology_mgr *mgr, { int ret; - /* max. time slots - one slot for MTP header */ - if (slots > 63) - return -ENOSPC; - vcpi->pbn = pbn; vcpi->aligned_pbn = slots * mgr->pbn_div; vcpi->num_slots = slots; @@ -4509,6 +4509,27 @@ int drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, } EXPORT_SYMBOL(drm_dp_atomic_release_vcpi_slots); +/** + * drm_dp_mst_update_slots() - updates the slot info depending on the DP ecoding format + * @mst_state: mst_state to update + * @link_encoding_cap: the ecoding format on the link + */ +void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_t link_encoding_cap) +{ + if (link_encoding_cap == DP_CAP_ANSI_128B132B) { + mst_state->total_avail_slots = 64; + mst_state->start_slot = 0; + } else { + mst_state->total_avail_slots = 63; + mst_state->start_slot = 1; + } + + DRM_DEBUG_KMS("%s encoding format on mst_state 0x%p\n", + (link_encoding_cap == DP_CAP_ANSI_128B132B) ? "128b/132b":"8b/10b", + mst_state); +} +EXPORT_SYMBOL(drm_dp_mst_update_slots); + /** * drm_dp_mst_allocate_vcpi() - Allocate a virtual channel * @mgr: manager for this port @@ -4540,7 +4561,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, ret = drm_dp_init_vcpi(mgr, &port->vcpi, pbn, slots); if (ret) { - drm_dbg_kms(mgr->dev, "failed to init vcpi slots=%d max=63 ret=%d\n", + drm_dbg_kms(mgr->dev, "failed to init vcpi slots=%d ret=%d\n", DIV_ROUND_UP(pbn, mgr->pbn_div), ret); drm_dp_mst_topology_put_port(port); goto out; @@ -5228,7 +5249,7 @@ drm_dp_mst_atomic_check_vcpi_alloc_limit(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state) { struct drm_dp_vcpi_allocation *vcpi; - int avail_slots = 63, payload_count = 0; + int avail_slots = mst_state->total_avail_slots, payload_count = 0; list_for_each_entry(vcpi, &mst_state->vcpis, next) { /* Releasing VCPI is always OK-even if the port is gone */ @@ -5257,7 +5278,7 @@ drm_dp_mst_atomic_check_vcpi_alloc_limit(struct drm_dp_mst_topology_mgr *mgr, } } drm_dbg_atomic(mgr->dev, "[MST MGR:%p] mst state %p VCPI avail=%d used=%d\n", - mgr, mst_state, avail_slots, 63 - avail_slots); + mgr, mst_state, avail_slots, mst_state->total_avail_slots - avail_slots); return 0; } @@ -5534,6 +5555,9 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, if (mst_state == NULL) return -ENOMEM; + mst_state->total_avail_slots = 63; + mst_state->start_slot = 1; + mst_state->mgr = mgr; INIT_LIST_HEAD(&mst_state->vcpis); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index cb6361feb843..12893e7be89b 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -1926,13 +1926,15 @@ int drm_add_override_edid_modes(struct drm_connector *connector) } EXPORT_SYMBOL(drm_add_override_edid_modes); -static struct edid *drm_do_get_edid_base_block( +static struct edid *drm_do_get_edid_base_block(struct drm_connector *connector, int (*get_edid_block)(void *data, u8 *buf, unsigned int block, size_t len), - void *data, bool *edid_corrupt, int *null_edid_counter) + void *data) { - int i; + int *null_edid_counter = connector ? &connector->null_edid_counter : NULL; + bool *edid_corrupt = connector ? &connector->edid_corrupt : NULL; void *edid; + int i; edid = kmalloc(EDID_LENGTH, GFP_KERNEL); if (edid == NULL) @@ -1956,9 +1958,8 @@ static struct edid *drm_do_get_edid_base_block( return edid; carp: - kfree(edid); - return ERR_PTR(-EINVAL); - + if (connector) + connector_bad_edid(connector, edid, 1); out: kfree(edid); return NULL; @@ -1997,14 +1998,9 @@ struct edid *drm_do_get_edid(struct drm_connector *connector, if (override) return override; - edid = (u8 *)drm_do_get_edid_base_block(get_edid_block, data, - &connector->edid_corrupt, - &connector->null_edid_counter); - if (IS_ERR_OR_NULL(edid)) { - if (IS_ERR(edid)) - connector_bad_edid(connector, edid, 1); + edid = (u8 *)drm_do_get_edid_base_block(connector, get_edid_block, data); + if (!edid) return NULL; - } /* if there's no extensions or no connector, we're done */ valid_extensions = edid[0x7e]; @@ -2157,14 +2153,13 @@ u32 drm_edid_get_panel_id(struct i2c_adapter *adapter) struct edid *edid; u32 panel_id; - edid = drm_do_get_edid_base_block(drm_do_probe_ddc_edid, adapter, - NULL, NULL); + edid = drm_do_get_edid_base_block(NULL, drm_do_probe_ddc_edid, adapter); /* * There are no manufacturer IDs of 0, so if there is a problem reading * the EDID then we'll just return 0. */ - if (IS_ERR_OR_NULL(edid)) + if (!edid) return 0; panel_id = edid_extract_panel_id(edid); diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index 5231104b1498..69fde60e36b3 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -135,6 +135,56 @@ void drm_fb_swab(void *dst, void *src, struct drm_framebuffer *fb, } EXPORT_SYMBOL(drm_fb_swab); +static void drm_fb_xrgb8888_to_rgb332_line(u8 *dbuf, __le32 *sbuf, unsigned int pixels) +{ + unsigned int x; + u32 pix; + + for (x = 0; x < pixels; x++) { + pix = le32_to_cpu(sbuf[x]); + dbuf[x] = ((pix & 0x00e00000) >> 16) | + ((pix & 0x0000e000) >> 11) | + ((pix & 0x000000c0) >> 6); + } +} + +/** + * drm_fb_xrgb8888_to_rgb332 - Convert XRGB8888 to RGB332 clip buffer + * @dst: RGB332 destination buffer + * @src: XRGB8888 source buffer + * @fb: DRM framebuffer + * @clip: Clip rectangle area to copy + * + * Drivers can use this function for RGB332 devices that don't natively support XRGB8888. + * + * This function does not apply clipping on dst, i.e. the destination is a small buffer + * containing the clip rect only. + */ +void drm_fb_xrgb8888_to_rgb332(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip) +{ + size_t width = drm_rect_width(clip); + size_t src_len = width * sizeof(u32); + unsigned int y; + void *sbuf; + + /* Use a buffer to speed up access on buffers with uncached read mapping (i.e. WC) */ + sbuf = kmalloc(src_len, GFP_KERNEL); + if (!sbuf) + return; + + src += clip_offset(clip, fb->pitches[0], sizeof(u32)); + for (y = 0; y < drm_rect_height(clip); y++) { + memcpy(sbuf, src, src_len); + drm_fb_xrgb8888_to_rgb332_line(dst, sbuf, width); + src += fb->pitches[0]; + dst += width; + } + + kfree(sbuf); +} +EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb332); + static void drm_fb_xrgb8888_to_rgb565_line(u16 *dbuf, u32 *sbuf, unsigned int pixels, bool swab) @@ -250,6 +300,44 @@ static void drm_fb_xrgb8888_to_rgb888_line(u8 *dbuf, u32 *sbuf, } } +/** + * drm_fb_xrgb8888_to_rgb888 - Convert XRGB8888 to RGB888 clip buffer + * @dst: RGB888 destination buffer + * @src: XRGB8888 source buffer + * @fb: DRM framebuffer + * @clip: Clip rectangle area to copy + * + * Drivers can use this function for RGB888 devices that don't natively + * support XRGB8888. + * + * This function does not apply clipping on dst, i.e. the destination + * is a small buffer containing the clip rect only. + */ +void drm_fb_xrgb8888_to_rgb888(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip) +{ + size_t width = drm_rect_width(clip); + size_t src_len = width * sizeof(u32); + unsigned int y; + void *sbuf; + + /* Use a buffer to speed up access on buffers with uncached read mapping (i.e. WC) */ + sbuf = kmalloc(src_len, GFP_KERNEL); + if (!sbuf) + return; + + src += clip_offset(clip, fb->pitches[0], sizeof(u32)); + for (y = 0; y < drm_rect_height(clip); y++) { + memcpy(sbuf, src, src_len); + drm_fb_xrgb8888_to_rgb888_line(dst, sbuf, width); + src += fb->pitches[0]; + dst += width * 3; + } + + kfree(sbuf); +} +EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888); + /** * drm_fb_xrgb8888_to_rgb888_dstclip - Convert XRGB8888 to RGB888 clip buffer * @dst: RGB565 destination buffer (iomem) diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index eda832f9200d..25837b1d6639 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -133,6 +133,9 @@ const struct drm_format_info *__drm_format_info(u32 format) { static const struct drm_format_info formats[] = { { .format = DRM_FORMAT_C8, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, + { .format = DRM_FORMAT_R8, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, + { .format = DRM_FORMAT_R10, .depth = 10, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, + { .format = DRM_FORMAT_R12, .depth = 12, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_RGB332, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_BGR233, .depth = 8, .num_planes = 1, .cpp = { 1, 0, 0 }, .hsub = 1, .vsub = 1 }, { .format = DRM_FORMAT_XRGB4444, .depth = 0, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 }, diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index dee4f24a1808..d72c2fac0ff1 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -489,12 +489,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; - /* need some objects */ - if (cl->object_count == 0) { - DRM_DEBUG_LEASE("no objects in lease\n"); - return -EINVAL; - } - if (cl->flags && (cl->flags & ~(O_CLOEXEC | O_NONBLOCK))) { DRM_DEBUG_LEASE("invalid flags\n"); return -EINVAL; @@ -510,23 +504,26 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, object_count = cl->object_count; - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), - array_size(object_count, sizeof(__u32))); - if (IS_ERR(object_ids)) { - ret = PTR_ERR(object_ids); - goto out_lessor; - } - + /* Handle leased objects, if any */ idr_init(&leases); + if (object_count != 0) { + object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), + array_size(object_count, sizeof(__u32))); + if (IS_ERR(object_ids)) { + ret = PTR_ERR(object_ids); + idr_destroy(&leases); + goto out_lessor; + } - /* fill and validate the object idr */ - ret = fill_object_idr(dev, lessor_priv, &leases, - object_count, object_ids); - kfree(object_ids); - if (ret) { - DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret); - idr_destroy(&leases); - goto out_lessor; + /* fill and validate the object idr */ + ret = fill_object_idr(dev, lessor_priv, &leases, + object_count, object_ids); + kfree(object_ids); + if (ret) { + DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret); + idr_destroy(&leases); + goto out_lessor; + } } /* Allocate a file descriptor for the lease */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index cc5b07f86346..242a5fd8b932 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1733,7 +1733,6 @@ static void etnaviv_gpu_unbind(struct device *dev, struct device *master, DBG("%s", dev_name(gpu->dev)); - flush_workqueue(gpu->wq); destroy_workqueue(gpu->wq); etnaviv_sched_fini(gpu); diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index eb4e08846da4..3f9d4b9a1e3d 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -523,7 +523,13 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) switch (format) { case GUD_DRM_FORMAT_R1: fallthrough; + case DRM_FORMAT_R8: + fallthrough; case GUD_DRM_FORMAT_XRGB1111: + fallthrough; + case DRM_FORMAT_RGB332: + fallthrough; + case DRM_FORMAT_RGB888: if (!xrgb8888_emulation_format) xrgb8888_emulation_format = info; break; diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index 2a388e27d5d7..e351a1f1420d 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -80,10 +80,16 @@ static inline u8 gud_from_fourcc(u32 fourcc) switch (fourcc) { case GUD_DRM_FORMAT_R1: return GUD_PIXEL_FORMAT_R1; + case DRM_FORMAT_R8: + return GUD_PIXEL_FORMAT_R8; case GUD_DRM_FORMAT_XRGB1111: return GUD_PIXEL_FORMAT_XRGB1111; + case DRM_FORMAT_RGB332: + return GUD_PIXEL_FORMAT_RGB332; case DRM_FORMAT_RGB565: return GUD_PIXEL_FORMAT_RGB565; + case DRM_FORMAT_RGB888: + return GUD_PIXEL_FORMAT_RGB888; case DRM_FORMAT_XRGB8888: return GUD_PIXEL_FORMAT_XRGB8888; case DRM_FORMAT_ARGB8888: @@ -98,10 +104,16 @@ static inline u32 gud_to_fourcc(u8 format) switch (format) { case GUD_PIXEL_FORMAT_R1: return GUD_DRM_FORMAT_R1; + case GUD_PIXEL_FORMAT_R8: + return DRM_FORMAT_R8; case GUD_PIXEL_FORMAT_XRGB1111: return GUD_DRM_FORMAT_XRGB1111; + case GUD_PIXEL_FORMAT_RGB332: + return DRM_FORMAT_RGB332; case GUD_PIXEL_FORMAT_RGB565: return DRM_FORMAT_RGB565; + case GUD_PIXEL_FORMAT_RGB888: + return DRM_FORMAT_RGB888; case GUD_PIXEL_FORMAT_XRGB8888: return DRM_FORMAT_XRGB8888; case GUD_PIXEL_FORMAT_ARGB8888: diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index b9b0e435ea0f..daf75c178c2b 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -189,8 +189,14 @@ retry: ret = -ENOMEM; goto end_cpu_access; } + } else if (format->format == DRM_FORMAT_R8) { + drm_fb_xrgb8888_to_gray8(buf, vaddr, fb, rect); + } else if (format->format == DRM_FORMAT_RGB332) { + drm_fb_xrgb8888_to_rgb332(buf, vaddr, fb, rect); } else if (format->format == DRM_FORMAT_RGB565) { drm_fb_xrgb8888_to_rgb565(buf, vaddr, fb, rect, gud_is_big_endian()); + } else if (format->format == DRM_FORMAT_RGB888) { + drm_fb_xrgb8888_to_rgb888(buf, vaddr, fb, rect); } else { len = gud_xrgb8888_to_color(buf, format, vaddr, fb, rect); } diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 107762427648..84b6fc70cbf5 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -132,6 +132,17 @@ config DRM_I915_GVT_KVMGT Choose this option if you want to enable KVMGT support for Intel GVT-g. +config DRM_I915_PXP + bool "Enable Intel PXP support" + depends on DRM_I915 + depends on INTEL_MEI && INTEL_MEI_PXP + default n + help + PXP (Protected Xe Path) is an i915 component, available on graphics + version 12 and newer GPUs, that helps to establish the hardware + protected session and manage the status of the alive software session, + as well as its life cycle. + menu "drm/i915 Debugging" depends on DRM_I915 depends on EXPERT diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 9d371be7dc5c..660bb03de6fc 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -13,13 +13,11 @@ # will most likely get a sudden build breakage... Hopefully we will fix # new warnings before CI updates! subdir-ccflags-y := -Wall -Wextra -subdir-ccflags-y += $(call cc-disable-warning, unused-parameter) -subdir-ccflags-y += $(call cc-disable-warning, type-limits) -subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers) +subdir-ccflags-y += -Wno-unused-parameter +subdir-ccflags-y += -Wno-type-limits +subdir-ccflags-y += -Wno-missing-field-initializers +subdir-ccflags-y += -Wno-sign-compare subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) -# clang warnings -subdir-ccflags-y += $(call cc-disable-warning, sign-compare) -subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides) subdir-ccflags-y += $(call cc-disable-warning, frame-address) subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror @@ -49,13 +47,15 @@ i915-y += i915_drv.o \ intel_dram.o \ intel_memory_region.o \ intel_pch.o \ + intel_pcode.o \ intel_pm.o \ intel_region_ttm.o \ intel_runtime_pm.o \ - intel_sideband.o \ + intel_sbi.o \ intel_step.o \ intel_uncore.o \ intel_wakeref.o \ + vlv_sideband.o \ vlv_suspend.o # core library code @@ -78,9 +78,6 @@ i915-$(CONFIG_PERF_EVENTS) += i915_pmu.o # "Graphics Technology" (aka we talk to the gpu) gt-y += \ - gt/debugfs_engines.o \ - gt/debugfs_gt.o \ - gt/debugfs_gt_pm.o \ gt/gen2_engine_cs.o \ gt/gen6_engine_cs.o \ gt/gen6_ppgtt.o \ @@ -100,8 +97,11 @@ gt-y += \ gt/intel_gt.o \ gt/intel_gt_buffer_pool.o \ gt/intel_gt_clock_utils.o \ + gt/intel_gt_debugfs.o \ + gt/intel_gt_engines_debugfs.o \ gt/intel_gt_irq.o \ gt/intel_gt_pm.o \ + gt/intel_gt_pm_debugfs.o \ gt/intel_gt_pm_irq.o \ gt/intel_gt_requests.o \ gt/intel_gtt.o \ @@ -154,6 +154,7 @@ gem-y += \ gem/i915_gem_throttle.o \ gem/i915_gem_tiling.o \ gem/i915_gem_ttm.o \ + gem/i915_gem_ttm_pm.o \ gem/i915_gem_userptr.o \ gem/i915_gem_wait.o \ gem/i915_gemfs.o @@ -215,6 +216,7 @@ i915-y += \ display/intel_drrs.o \ display/intel_dsb.o \ display/intel_fb.o \ + display/intel_fb_pin.o \ display/intel_fbc.o \ display/intel_fdi.o \ display/intel_fifo_underrun.o \ @@ -224,6 +226,7 @@ i915-y += \ display/intel_hotplug.o \ display/intel_lpe_audio.o \ display/intel_overlay.o \ + display/intel_plane_initial.o \ display/intel_psr.o \ display/intel_quirks.o \ display/intel_sprite.o \ @@ -280,6 +283,16 @@ i915-y += \ i915-y += i915_perf.o +# Protected execution platform (PXP) support +i915-$(CONFIG_DRM_I915_PXP) += \ + pxp/intel_pxp.o \ + pxp/intel_pxp_cmd.o \ + pxp/intel_pxp_debugfs.o \ + pxp/intel_pxp_irq.o \ + pxp/intel_pxp_pm.o \ + pxp/intel_pxp_session.o \ + pxp/intel_pxp_tee.o + # Post-mortem debug and GPU hang state capture i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o i915-$(CONFIG_DRM_I915_SELFTEST) += \ diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index 9577f6843f79..dc41868d01ef 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -18,7 +18,7 @@ #include "intel_hdmi.h" #include "intel_hotplug.h" #include "intel_pps.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" struct dp_link_dpll { int clock; @@ -211,7 +211,7 @@ static void ilk_edp_pll_on(struct intel_dp *intel_dp, struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder); + assert_transcoder_disabled(dev_priv, pipe_config->cpu_transcoder); assert_dp_port_disabled(intel_dp); assert_edp_pll_disabled(dev_priv); @@ -251,7 +251,7 @@ static void ilk_edp_pll_off(struct intel_dp *intel_dp, struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - assert_pipe_disabled(dev_priv, old_crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, old_crtc_state->cpu_transcoder); assert_dp_port_disabled(intel_dp); assert_edp_pll_enabled(dev_priv); @@ -426,7 +426,6 @@ intel_dp_link_down(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); enum port port = encoder->port; - u32 DP = intel_dp->DP; if (drm_WARN_ON(&dev_priv->drm, (intel_de_read(dev_priv, intel_dp->output_reg) & @@ -437,17 +436,17 @@ intel_dp_link_down(struct intel_encoder *encoder, if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) || (HAS_PCH_CPT(dev_priv) && port != PORT_A)) { - DP &= ~DP_LINK_TRAIN_MASK_CPT; - DP |= DP_LINK_TRAIN_PAT_IDLE_CPT; + intel_dp->DP &= ~DP_LINK_TRAIN_MASK_CPT; + intel_dp->DP |= DP_LINK_TRAIN_PAT_IDLE_CPT; } else { - DP &= ~DP_LINK_TRAIN_MASK; - DP |= DP_LINK_TRAIN_PAT_IDLE; + intel_dp->DP &= ~DP_LINK_TRAIN_MASK; + intel_dp->DP |= DP_LINK_TRAIN_PAT_IDLE; } - intel_de_write(dev_priv, intel_dp->output_reg, DP); + intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP); intel_de_posting_read(dev_priv, intel_dp->output_reg); - DP &= ~(DP_PORT_EN | DP_AUDIO_OUTPUT_ENABLE); - intel_de_write(dev_priv, intel_dp->output_reg, DP); + intel_dp->DP &= ~(DP_PORT_EN | DP_AUDIO_OUTPUT_ENABLE); + intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP); intel_de_posting_read(dev_priv, intel_dp->output_reg); /* @@ -464,14 +463,14 @@ intel_dp_link_down(struct intel_encoder *encoder, intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false); /* always enable with pattern 1 (as per spec) */ - DP &= ~(DP_PIPE_SEL_MASK | DP_LINK_TRAIN_MASK); - DP |= DP_PORT_EN | DP_PIPE_SEL(PIPE_A) | + intel_dp->DP &= ~(DP_PIPE_SEL_MASK | DP_LINK_TRAIN_MASK); + intel_dp->DP |= DP_PORT_EN | DP_PIPE_SEL(PIPE_A) | DP_LINK_TRAIN_PAT_1; - intel_de_write(dev_priv, intel_dp->output_reg, DP); + intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP); intel_de_posting_read(dev_priv, intel_dp->output_reg); - DP &= ~DP_PORT_EN; - intel_de_write(dev_priv, intel_dp->output_reg, DP); + intel_dp->DP &= ~DP_PORT_EN; + intel_de_write(dev_priv, intel_dp->output_reg, intel_dp->DP); intel_de_posting_read(dev_priv, intel_dp->output_reg); intel_wait_for_vblank_if_active(dev_priv, PIPE_A); @@ -481,8 +480,6 @@ intel_dp_link_down(struct intel_encoder *encoder, msleep(intel_dp->pps.panel_power_down_delay); - intel_dp->DP = DP; - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { intel_wakeref_t wakeref; @@ -582,19 +579,18 @@ cpt_set_link_train(struct intel_dp *intel_dp, u8 dp_train_pat) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - u32 *DP = &intel_dp->DP; - *DP &= ~DP_LINK_TRAIN_MASK_CPT; + intel_dp->DP &= ~DP_LINK_TRAIN_MASK_CPT; switch (intel_dp_training_pattern_symbol(dp_train_pat)) { case DP_TRAINING_PATTERN_DISABLE: - *DP |= DP_LINK_TRAIN_OFF_CPT; + intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT; break; case DP_TRAINING_PATTERN_1: - *DP |= DP_LINK_TRAIN_PAT_1_CPT; + intel_dp->DP |= DP_LINK_TRAIN_PAT_1_CPT; break; case DP_TRAINING_PATTERN_2: - *DP |= DP_LINK_TRAIN_PAT_2_CPT; + intel_dp->DP |= DP_LINK_TRAIN_PAT_2_CPT; break; default: MISSING_CASE(intel_dp_training_pattern_symbol(dp_train_pat)); @@ -611,19 +607,18 @@ g4x_set_link_train(struct intel_dp *intel_dp, u8 dp_train_pat) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - u32 *DP = &intel_dp->DP; - *DP &= ~DP_LINK_TRAIN_MASK; + intel_dp->DP &= ~DP_LINK_TRAIN_MASK; switch (intel_dp_training_pattern_symbol(dp_train_pat)) { case DP_TRAINING_PATTERN_DISABLE: - *DP |= DP_LINK_TRAIN_OFF; + intel_dp->DP |= DP_LINK_TRAIN_OFF; break; case DP_TRAINING_PATTERN_1: - *DP |= DP_LINK_TRAIN_PAT_1; + intel_dp->DP |= DP_LINK_TRAIN_PAT_1; break; case DP_TRAINING_PATTERN_2: - *DP |= DP_LINK_TRAIN_PAT_2; + intel_dp->DP |= DP_LINK_TRAIN_PAT_2; break; default: MISSING_CASE(intel_dp_training_pattern_symbol(dp_train_pat)); @@ -642,7 +637,7 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp, /* enable with pattern 1 (as per spec) */ intel_dp_program_link_training_pattern(intel_dp, crtc_state, - DP_TRAINING_PATTERN_1); + DP_PHY_DPRX, DP_TRAINING_PATTERN_1); /* * Magic for VLV/CHV. We _must_ first set up the register @@ -813,10 +808,10 @@ static u8 intel_dp_preemph_max_3(struct intel_dp *intel_dp) return DP_TRAIN_PRE_EMPH_LEVEL_3; } -static void vlv_set_signal_levels(struct intel_dp *intel_dp, +static void vlv_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); unsigned long demph_reg_value, preemph_reg_value, uniqtranscale_reg_value; u8 train_set = intel_dp->train_set[0]; @@ -899,10 +894,10 @@ static void vlv_set_signal_levels(struct intel_dp *intel_dp, uniqtranscale_reg_value, 0); } -static void chv_set_signal_levels(struct intel_dp *intel_dp, +static void chv_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); u32 deemph_reg_value, margin_reg_value; bool uniq_trans_scale = false; u8 train_set = intel_dp->train_set[0]; @@ -1020,10 +1015,11 @@ static u32 g4x_signal_levels(u8 train_set) } static void -g4x_set_signal_levels(struct intel_dp *intel_dp, +g4x_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); u8 train_set = intel_dp->train_set[0]; u32 signal_levels; @@ -1067,10 +1063,11 @@ static u32 snb_cpu_edp_signal_levels(u8 train_set) } static void -snb_cpu_edp_set_signal_levels(struct intel_dp *intel_dp, +snb_cpu_edp_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); u8 train_set = intel_dp->train_set[0]; u32 signal_levels; @@ -1118,10 +1115,11 @@ static u32 ivb_cpu_edp_signal_levels(u8 train_set) } static void -ivb_cpu_edp_set_signal_levels(struct intel_dp *intel_dp, +ivb_cpu_edp_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); u8 train_set = intel_dp->train_set[0]; u32 signal_levels; @@ -1364,15 +1362,15 @@ bool g4x_dp_init(struct drm_i915_private *dev_priv, dig_port->dp.set_link_train = g4x_set_link_train; if (IS_CHERRYVIEW(dev_priv)) - dig_port->dp.set_signal_levels = chv_set_signal_levels; + intel_encoder->set_signal_levels = chv_set_signal_levels; else if (IS_VALLEYVIEW(dev_priv)) - dig_port->dp.set_signal_levels = vlv_set_signal_levels; + intel_encoder->set_signal_levels = vlv_set_signal_levels; else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) - dig_port->dp.set_signal_levels = ivb_cpu_edp_set_signal_levels; + intel_encoder->set_signal_levels = ivb_cpu_edp_set_signal_levels; else if (IS_SANDYBRIDGE(dev_priv) && port == PORT_A) - dig_port->dp.set_signal_levels = snb_cpu_edp_set_signal_levels; + intel_encoder->set_signal_levels = snb_cpu_edp_set_signal_levels; else - dig_port->dp.set_signal_levels = g4x_set_signal_levels; + intel_encoder->set_signal_levels = g4x_set_signal_levels; if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv) || (HAS_PCH_SPLIT(dev_priv) && port != PORT_A)) { diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index be352e9f0afc..88c427f3c346 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -14,8 +14,8 @@ #include "intel_fifo_underrun.h" #include "intel_hdmi.h" #include "intel_hotplug.h" -#include "intel_sideband.h" #include "intel_sdvo.h" +#include "vlv_sideband.h" static void intel_hdmi_prepare(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index bd210166b079..168c84a74d30 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -129,44 +129,52 @@ static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder) } } -static bool add_payld_to_queue(struct intel_dsi_host *host, const u8 *data, - u32 len) +static int dsi_send_pkt_payld(struct intel_dsi_host *host, + const struct mipi_dsi_packet *packet) { struct intel_dsi *intel_dsi = host->intel_dsi; - struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev); + struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev); enum transcoder dsi_trans = dsi_port_to_transcoder(host->port); + const u8 *data = packet->payload; + u32 len = packet->payload_length; int i, j; + /* payload queue can accept *256 bytes*, check limit */ + if (len > MAX_PLOAD_CREDIT * 4) { + drm_err(&i915->drm, "payload size exceeds max queue limit\n"); + return -EINVAL; + } + for (i = 0; i < len; i += 4) { u32 tmp = 0; - if (!wait_for_payload_credits(dev_priv, dsi_trans, 1)) - return false; + if (!wait_for_payload_credits(i915, dsi_trans, 1)) + return -EBUSY; for (j = 0; j < min_t(u32, len - i, 4); j++) tmp |= *data++ << 8 * j; - intel_de_write(dev_priv, DSI_CMD_TXPYLD(dsi_trans), tmp); + intel_de_write(i915, DSI_CMD_TXPYLD(dsi_trans), tmp); } - return true; + return 0; } static int dsi_send_pkt_hdr(struct intel_dsi_host *host, - struct mipi_dsi_packet pkt, bool enable_lpdt) + const struct mipi_dsi_packet *packet, + bool enable_lpdt) { struct intel_dsi *intel_dsi = host->intel_dsi; struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev); enum transcoder dsi_trans = dsi_port_to_transcoder(host->port); u32 tmp; - /* check if header credit available */ if (!wait_for_header_credits(dev_priv, dsi_trans, 1)) - return -1; + return -EBUSY; tmp = intel_de_read(dev_priv, DSI_CMD_TXHDR(dsi_trans)); - if (pkt.payload) + if (packet->payload) tmp |= PAYLOAD_PRESENT; else tmp &= ~PAYLOAD_PRESENT; @@ -177,37 +185,15 @@ static int dsi_send_pkt_hdr(struct intel_dsi_host *host, tmp |= LP_DATA_TRANSFER; tmp &= ~(PARAM_WC_MASK | VC_MASK | DT_MASK); - tmp |= ((pkt.header[0] & VC_MASK) << VC_SHIFT); - tmp |= ((pkt.header[0] & DT_MASK) << DT_SHIFT); - tmp |= (pkt.header[1] << PARAM_WC_LOWER_SHIFT); - tmp |= (pkt.header[2] << PARAM_WC_UPPER_SHIFT); + tmp |= ((packet->header[0] & VC_MASK) << VC_SHIFT); + tmp |= ((packet->header[0] & DT_MASK) << DT_SHIFT); + tmp |= (packet->header[1] << PARAM_WC_LOWER_SHIFT); + tmp |= (packet->header[2] << PARAM_WC_UPPER_SHIFT); intel_de_write(dev_priv, DSI_CMD_TXHDR(dsi_trans), tmp); return 0; } -static int dsi_send_pkt_payld(struct intel_dsi_host *host, - struct mipi_dsi_packet pkt) -{ - struct intel_dsi *intel_dsi = host->intel_dsi; - struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev); - - /* payload queue can accept *256 bytes*, check limit */ - if (pkt.payload_length > MAX_PLOAD_CREDIT * 4) { - drm_err(&i915->drm, "payload size exceeds max queue limit\n"); - return -1; - } - - /* load data into command payload queue */ - if (!add_payld_to_queue(host, pkt.payload, - pkt.payload_length)) { - drm_err(&i915->drm, "adding payload to queue failed\n"); - return -1; - } - - return 0; -} - void icl_dsi_frame_update(struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); @@ -247,7 +233,7 @@ static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder) * Program voltage swing and pre-emphasis level values as per * table in BSPEC under DDI buffer programing */ - tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy)); + tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); tmp &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK); tmp |= SCALING_MODE_SEL(0x2); tmp |= TAP2_DISABLE | TAP3_DISABLE; @@ -261,7 +247,7 @@ static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder) tmp |= RTERM_SELECT(0x6); intel_de_write(dev_priv, ICL_PORT_TX_DW5_AUX(phy), tmp); - tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN0(phy)); + tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN(0, phy)); tmp &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | RCOMP_SCALAR_MASK); tmp |= SWING_SEL_UPPER(0x2); @@ -469,7 +455,7 @@ static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder) tmp &= ~FRC_LATENCY_OPTIM_MASK; tmp |= FRC_LATENCY_OPTIM_VAL(0x5); intel_de_write(dev_priv, ICL_PORT_TX_DW2_AUX(phy), tmp); - tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN0(phy)); + tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN(0, phy)); tmp &= ~FRC_LATENCY_OPTIM_MASK; tmp |= FRC_LATENCY_OPTIM_VAL(0x5); intel_de_write(dev_priv, ICL_PORT_TX_DW2_GRP(phy), tmp); @@ -484,7 +470,7 @@ static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder) tmp); tmp = intel_de_read(dev_priv, - ICL_PORT_PCS_DW1_LN0(phy)); + ICL_PORT_PCS_DW1_LN(0, phy)); tmp &= ~LATENCY_OPTIM_MASK; tmp |= LATENCY_OPTIM_VAL(0x1); intel_de_write(dev_priv, ICL_PORT_PCS_DW1_GRP(phy), @@ -503,7 +489,7 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder) /* clear common keeper enable bit */ for_each_dsi_phy(phy, intel_dsi->phys) { - tmp = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN0(phy)); + tmp = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN(0, phy)); tmp &= ~COMMON_KEEPER_EN; intel_de_write(dev_priv, ICL_PORT_PCS_DW1_GRP(phy), tmp); tmp = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_AUX(phy)); @@ -524,7 +510,7 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder) /* Clear training enable to change swing values */ for_each_dsi_phy(phy, intel_dsi->phys) { - tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy)); + tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); tmp &= ~TX_TRAINING_EN; intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), tmp); tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_AUX(phy)); @@ -537,7 +523,7 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder) /* Set training enable to trigger update */ for_each_dsi_phy(phy, intel_dsi->phys) { - tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy)); + tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); tmp |= TX_TRAINING_EN; intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), tmp); tmp = intel_de_read(dev_priv, ICL_PORT_TX_DW5_AUX(phy)); @@ -1672,14 +1658,15 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder, struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi, base); struct intel_connector *intel_connector = intel_dsi->attached_connector; - const struct drm_display_mode *fixed_mode = - intel_connector->panel.fixed_mode; struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; int ret; pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; - intel_panel_fixed_mode(fixed_mode, adjusted_mode); + + ret = intel_panel_compute_config(intel_connector, adjusted_mode); + if (ret) + return ret; ret = intel_panel_fitting(pipe_config, conn_state); if (ret) @@ -1839,13 +1826,13 @@ static ssize_t gen11_dsi_host_transfer(struct mipi_dsi_host *host, /* only long packet contains payload */ if (mipi_dsi_packet_format_is_long(msg->type)) { - ret = dsi_send_pkt_payld(intel_dsi_host, dsi_pkt); + ret = dsi_send_pkt_payld(intel_dsi_host, &dsi_pkt); if (ret < 0) return ret; } /* send packet header */ - ret = dsi_send_pkt_hdr(intel_dsi_host, dsi_pkt, enable_lpdt); + ret = dsi_send_pkt_hdr(intel_dsi_host, &dsi_pkt, enable_lpdt); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 47234d898549..0be8c00e3db9 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -39,8 +39,10 @@ #include "intel_atomic_plane.h" #include "intel_cdclk.h" #include "intel_display_types.h" +#include "intel_fb_pin.h" #include "intel_pm.h" #include "intel_sprite.h" +#include "gt/intel_rps.h" static void intel_plane_state_reset(struct intel_plane_state *plane_state, struct intel_plane *plane) @@ -601,6 +603,213 @@ int intel_atomic_plane_check_clipping(struct intel_plane_state *plane_state, return 0; } +struct wait_rps_boost { + struct wait_queue_entry wait; + + struct drm_crtc *crtc; + struct i915_request *request; +}; + +static int do_rps_boost(struct wait_queue_entry *_wait, + unsigned mode, int sync, void *key) +{ + struct wait_rps_boost *wait = container_of(_wait, typeof(*wait), wait); + struct i915_request *rq = wait->request; + + /* + * If we missed the vblank, but the request is already running it + * is reasonable to assume that it will complete before the next + * vblank without our intervention, so leave RPS alone. + */ + if (!i915_request_started(rq)) + intel_rps_boost(rq); + i915_request_put(rq); + + drm_crtc_vblank_put(wait->crtc); + + list_del(&wait->wait.entry); + kfree(wait); + return 1; +} + +static void add_rps_boost_after_vblank(struct drm_crtc *crtc, + struct dma_fence *fence) +{ + struct wait_rps_boost *wait; + + if (!dma_fence_is_i915(fence)) + return; + + if (DISPLAY_VER(to_i915(crtc->dev)) < 6) + return; + + if (drm_crtc_vblank_get(crtc)) + return; + + wait = kmalloc(sizeof(*wait), GFP_KERNEL); + if (!wait) { + drm_crtc_vblank_put(crtc); + return; + } + + wait->request = to_request(dma_fence_get(fence)); + wait->crtc = crtc; + + wait->wait.func = do_rps_boost; + wait->wait.flags = 0; + + add_wait_queue(drm_crtc_vblank_waitqueue(crtc), &wait->wait); +} + +/** + * intel_prepare_plane_fb - Prepare fb for usage on plane + * @_plane: drm plane to prepare for + * @_new_plane_state: the plane state being prepared + * + * Prepares a framebuffer for usage on a display plane. Generally this + * involves pinning the underlying object and updating the frontbuffer tracking + * bits. Some older platforms need special physical address handling for + * cursor planes. + * + * Returns 0 on success, negative error code on failure. + */ +static int +intel_prepare_plane_fb(struct drm_plane *_plane, + struct drm_plane_state *_new_plane_state) +{ + struct i915_sched_attr attr = { .priority = I915_PRIORITY_DISPLAY }; + struct intel_plane *plane = to_intel_plane(_plane); + struct intel_plane_state *new_plane_state = + to_intel_plane_state(_new_plane_state); + struct intel_atomic_state *state = + to_intel_atomic_state(new_plane_state->uapi.state); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct intel_plane_state *old_plane_state = + intel_atomic_get_old_plane_state(state, plane); + struct drm_i915_gem_object *obj = intel_fb_obj(new_plane_state->hw.fb); + struct drm_i915_gem_object *old_obj = intel_fb_obj(old_plane_state->hw.fb); + int ret; + + if (old_obj) { + const struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, + to_intel_crtc(old_plane_state->hw.crtc)); + + /* Big Hammer, we also need to ensure that any pending + * MI_WAIT_FOR_EVENT inside a user batch buffer on the + * current scanout is retired before unpinning the old + * framebuffer. Note that we rely on userspace rendering + * into the buffer attached to the pipe they are waiting + * on. If not, userspace generates a GPU hang with IPEHR + * point to the MI_WAIT_FOR_EVENT. + * + * This should only fail upon a hung GPU, in which case we + * can safely continue. + */ + if (intel_crtc_needs_modeset(crtc_state)) { + ret = i915_sw_fence_await_reservation(&state->commit_ready, + old_obj->base.resv, NULL, + false, 0, + GFP_KERNEL); + if (ret < 0) + return ret; + } + } + + if (new_plane_state->uapi.fence) { /* explicit fencing */ + i915_gem_fence_wait_priority(new_plane_state->uapi.fence, + &attr); + ret = i915_sw_fence_await_dma_fence(&state->commit_ready, + new_plane_state->uapi.fence, + i915_fence_timeout(dev_priv), + GFP_KERNEL); + if (ret < 0) + return ret; + } + + if (!obj) + return 0; + + + ret = intel_plane_pin_fb(new_plane_state); + if (ret) + return ret; + + i915_gem_object_wait_priority(obj, 0, &attr); + + if (!new_plane_state->uapi.fence) { /* implicit fencing */ + struct dma_fence *fence; + + ret = i915_sw_fence_await_reservation(&state->commit_ready, + obj->base.resv, NULL, + false, + i915_fence_timeout(dev_priv), + GFP_KERNEL); + if (ret < 0) + goto unpin_fb; + + fence = dma_resv_get_excl_unlocked(obj->base.resv); + if (fence) { + add_rps_boost_after_vblank(new_plane_state->hw.crtc, + fence); + dma_fence_put(fence); + } + } else { + add_rps_boost_after_vblank(new_plane_state->hw.crtc, + new_plane_state->uapi.fence); + } + + /* + * We declare pageflips to be interactive and so merit a small bias + * towards upclocking to deliver the frame on time. By only changing + * the RPS thresholds to sample more regularly and aim for higher + * clocks we can hopefully deliver low power workloads (like kodi) + * that are not quite steady state without resorting to forcing + * maximum clocks following a vblank miss (see do_rps_boost()). + */ + if (!state->rps_interactive) { + intel_rps_mark_interactive(&dev_priv->gt.rps, true); + state->rps_interactive = true; + } + + return 0; + +unpin_fb: + intel_plane_unpin_fb(new_plane_state); + + return ret; +} + +/** + * intel_cleanup_plane_fb - Cleans up an fb after plane use + * @plane: drm plane to clean up for + * @_old_plane_state: the state from the previous modeset + * + * Cleans up a framebuffer that has just been removed from a plane. + */ +static void +intel_cleanup_plane_fb(struct drm_plane *plane, + struct drm_plane_state *_old_plane_state) +{ + struct intel_plane_state *old_plane_state = + to_intel_plane_state(_old_plane_state); + struct intel_atomic_state *state = + to_intel_atomic_state(old_plane_state->uapi.state); + struct drm_i915_private *dev_priv = to_i915(plane->dev); + struct drm_i915_gem_object *obj = intel_fb_obj(old_plane_state->hw.fb); + + if (!obj) + return; + + if (state->rps_interactive) { + intel_rps_mark_interactive(&dev_priv->gt.rps, false); + state->rps_interactive = false; + } + + /* Should only be called after a successful intel_prepare_plane_fb()! */ + intel_plane_unpin_fb(old_plane_state); +} + static const struct drm_plane_helper_funcs intel_plane_helper_funcs = { .prepare_fb = intel_prepare_plane_fb, .cleanup_fb = intel_cleanup_plane_fb, diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 4e0f96bf6158..03e8c05a74f6 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -848,10 +848,10 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; - if (dev_priv->display.audio_codec_enable) - dev_priv->display.audio_codec_enable(encoder, - crtc_state, - conn_state); + if (dev_priv->audio_funcs) + dev_priv->audio_funcs->audio_codec_enable(encoder, + crtc_state, + conn_state); mutex_lock(&dev_priv->av_mutex); encoder->audio_connector = connector; @@ -893,10 +893,10 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, enum port port = encoder->port; enum pipe pipe = crtc->pipe; - if (dev_priv->display.audio_codec_disable) - dev_priv->display.audio_codec_disable(encoder, - old_crtc_state, - old_conn_state); + if (dev_priv->audio_funcs) + dev_priv->audio_funcs->audio_codec_disable(encoder, + old_crtc_state, + old_conn_state); mutex_lock(&dev_priv->av_mutex); encoder->audio_connector = NULL; @@ -915,6 +915,21 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, intel_lpe_audio_notify(dev_priv, pipe, port, NULL, 0, false); } +static const struct intel_audio_funcs g4x_audio_funcs = { + .audio_codec_enable = g4x_audio_codec_enable, + .audio_codec_disable = g4x_audio_codec_disable, +}; + +static const struct intel_audio_funcs ilk_audio_funcs = { + .audio_codec_enable = ilk_audio_codec_enable, + .audio_codec_disable = ilk_audio_codec_disable, +}; + +static const struct intel_audio_funcs hsw_audio_funcs = { + .audio_codec_enable = hsw_audio_codec_enable, + .audio_codec_disable = hsw_audio_codec_disable, +}; + /** * intel_init_audio_hooks - Set up chip specific audio hooks * @dev_priv: device private @@ -922,17 +937,13 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, void intel_init_audio_hooks(struct drm_i915_private *dev_priv) { if (IS_G4X(dev_priv)) { - dev_priv->display.audio_codec_enable = g4x_audio_codec_enable; - dev_priv->display.audio_codec_disable = g4x_audio_codec_disable; + dev_priv->audio_funcs = &g4x_audio_funcs; } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - dev_priv->display.audio_codec_enable = ilk_audio_codec_enable; - dev_priv->display.audio_codec_disable = ilk_audio_codec_disable; + dev_priv->audio_funcs = &ilk_audio_funcs; } else if (IS_HASWELL(dev_priv) || DISPLAY_VER(dev_priv) >= 8) { - dev_priv->display.audio_codec_enable = hsw_audio_codec_enable; - dev_priv->display.audio_codec_disable = hsw_audio_codec_disable; + dev_priv->audio_funcs = &hsw_audio_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->display.audio_codec_enable = ilk_audio_codec_enable; - dev_priv->display.audio_codec_disable = ilk_audio_codec_disable; + dev_priv->audio_funcs = &ilk_audio_funcs; } } diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index f9776ca85de3..b99907c656bb 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1930,6 +1930,50 @@ static int _intel_bios_max_tmds_clock(const struct intel_bios_encoder_data *devd } } +static enum port get_edp_port(struct drm_i915_private *i915) +{ + const struct intel_bios_encoder_data *devdata; + enum port port; + + for_each_port(port) { + devdata = i915->vbt.ports[port]; + + if (devdata && intel_bios_encoder_supports_edp(devdata)) + return port; + } + + return PORT_NONE; +} + +/* + * FIXME: The power sequencer and backlight code currently do not support more + * than one set registers, at least not on anything other than VLV/CHV. It will + * clobber the registers. As a temporary workaround, gracefully prevent more + * than one eDP from being registered. + */ +static void sanitize_dual_edp(struct intel_bios_encoder_data *devdata, + enum port port) +{ + struct drm_i915_private *i915 = devdata->i915; + struct child_device_config *child = &devdata->child; + enum port p; + + /* CHV might not clobber PPS registers. */ + if (IS_CHERRYVIEW(i915)) + return; + + p = get_edp_port(i915); + if (p == PORT_NONE) + return; + + drm_dbg_kms(&i915->drm, "both ports %c and %c configured as eDP, " + "disabling port %c eDP\n", port_name(p), port_name(port), + port_name(port)); + + child->device_type &= ~DEVICE_TYPE_DISPLAYPORT_OUTPUT; + child->device_type &= ~DEVICE_TYPE_INTERNAL_CONNECTOR; +} + static bool is_port_valid(struct drm_i915_private *i915, enum port port) { /* @@ -1987,6 +2031,9 @@ static void parse_ddi_port(struct drm_i915_private *i915, supports_typec_usb, supports_tbt, devdata->dsc != NULL); + if (is_edp) + sanitize_dual_edp(devdata, port); + if (is_dvi) sanitize_ddc_pin(devdata, port); diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 4b94256d7319..8d9d888e9316 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -9,8 +9,8 @@ #include "intel_bw.h" #include "intel_cdclk.h" #include "intel_display_types.h" +#include "intel_pcode.h" #include "intel_pm.h" -#include "intel_sideband.h" /* Parameters for Qclk Geyserville (QGV) */ struct intel_qgv_point { diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 9aec17b33819..9e466d829019 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -28,8 +28,9 @@ #include "intel_cdclk.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_pcode.h" #include "intel_psr.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" /** * DOC: CDCLK / RAWCLK @@ -59,6 +60,37 @@ * dividers can be programmed correctly. */ +void intel_cdclk_get_cdclk(struct drm_i915_private *dev_priv, + struct intel_cdclk_config *cdclk_config) +{ + dev_priv->cdclk_funcs->get_cdclk(dev_priv, cdclk_config); +} + +int intel_cdclk_bw_calc_min_cdclk(struct intel_atomic_state *state) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + return dev_priv->cdclk_funcs->bw_calc_min_cdclk(state); +} + +static void intel_cdclk_set_cdclk(struct drm_i915_private *dev_priv, + const struct intel_cdclk_config *cdclk_config, + enum pipe pipe) +{ + dev_priv->cdclk_funcs->set_cdclk(dev_priv, cdclk_config, pipe); +} + +static int intel_cdclk_modeset_calc_cdclk(struct drm_i915_private *dev_priv, + struct intel_cdclk_state *cdclk_config) +{ + return dev_priv->cdclk_funcs->modeset_calc_cdclk(cdclk_config); +} + +static u8 intel_cdclk_calc_voltage_level(struct drm_i915_private *dev_priv, + int cdclk) +{ + return dev_priv->cdclk_funcs->calc_voltage_level(cdclk); +} + static void fixed_133mhz_get_cdclk(struct drm_i915_private *dev_priv, struct intel_cdclk_config *cdclk_config) { @@ -1466,7 +1498,7 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv, * at least what the CDCLK frequency requires. */ cdclk_config->voltage_level = - dev_priv->display.calc_voltage_level(cdclk_config->cdclk); + intel_cdclk_calc_voltage_level(dev_priv, cdclk_config->cdclk); } static void bxt_de_pll_disable(struct drm_i915_private *dev_priv) @@ -1777,7 +1809,7 @@ static void bxt_cdclk_init_hw(struct drm_i915_private *dev_priv) cdclk_config.cdclk = bxt_calc_cdclk(dev_priv, 0); cdclk_config.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_config.cdclk); cdclk_config.voltage_level = - dev_priv->display.calc_voltage_level(cdclk_config.cdclk); + intel_cdclk_calc_voltage_level(dev_priv, cdclk_config.cdclk); bxt_set_cdclk(dev_priv, &cdclk_config, INVALID_PIPE); } @@ -1789,7 +1821,7 @@ static void bxt_cdclk_uninit_hw(struct drm_i915_private *dev_priv) cdclk_config.cdclk = cdclk_config.bypass; cdclk_config.vco = 0; cdclk_config.voltage_level = - dev_priv->display.calc_voltage_level(cdclk_config.cdclk); + intel_cdclk_calc_voltage_level(dev_priv, cdclk_config.cdclk); bxt_set_cdclk(dev_priv, &cdclk_config, INVALID_PIPE); } @@ -1932,7 +1964,7 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, if (!intel_cdclk_changed(&dev_priv->cdclk.hw, cdclk_config)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, !dev_priv->display.set_cdclk)) + if (drm_WARN_ON_ONCE(&dev_priv->drm, !dev_priv->cdclk_funcs->set_cdclk)) return; intel_dump_cdclk_config(cdclk_config, "Changing CDCLK to"); @@ -1956,7 +1988,7 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, &dev_priv->gmbus_mutex); } - dev_priv->display.set_cdclk(dev_priv, cdclk_config, pipe); + intel_cdclk_set_cdclk(dev_priv, cdclk_config, pipe); for_each_intel_dp(&dev_priv->drm, encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -2140,13 +2172,11 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) min_cdclk = max(intel_planes_min_cdclk(crtc_state), min_cdclk); /* - * VDSC engine can process only 1 pixel per Cd clock. - * In case VDSC is used and max slice count == 1, - * max supported pixel clock should be 100% of CD clock. - * Then do min_cdclk and pixel clock comparison to get cdclk. + * When we decide to use only one VDSC engine, since + * each VDSC operates with 1 ppc throughput, pixel clock + * cannot be higher than the VDSC clock (cdclk) */ - if (crtc_state->dsc.compression_enable && - crtc_state->dsc.slice_count == 1) + if (crtc_state->dsc.compression_enable && !crtc_state->dsc.dsc_split) min_cdclk = max(min_cdclk, (int)crtc_state->pixel_rate); /* @@ -2424,7 +2454,7 @@ static int bxt_modeset_calc_cdclk(struct intel_cdclk_state *cdclk_state) cdclk_state->logical.cdclk = cdclk; cdclk_state->logical.voltage_level = max_t(int, min_voltage_level, - dev_priv->display.calc_voltage_level(cdclk)); + intel_cdclk_calc_voltage_level(dev_priv, cdclk)); if (!cdclk_state->active_pipes) { cdclk = bxt_calc_cdclk(dev_priv, cdclk_state->force_min_cdclk); @@ -2433,7 +2463,7 @@ static int bxt_modeset_calc_cdclk(struct intel_cdclk_state *cdclk_state) cdclk_state->actual.vco = vco; cdclk_state->actual.cdclk = cdclk; cdclk_state->actual.voltage_level = - dev_priv->display.calc_voltage_level(cdclk); + intel_cdclk_calc_voltage_level(dev_priv, cdclk); } else { cdclk_state->actual = cdclk_state->logical; } @@ -2525,7 +2555,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) new_cdclk_state->active_pipes = intel_calc_active_pipes(state, old_cdclk_state->active_pipes); - ret = dev_priv->display.modeset_calc_cdclk(new_cdclk_state); + ret = intel_cdclk_modeset_calc_cdclk(dev_priv, new_cdclk_state); if (ret) return ret; @@ -2705,7 +2735,7 @@ void intel_update_max_cdclk(struct drm_i915_private *dev_priv) */ void intel_update_cdclk(struct drm_i915_private *dev_priv) { - dev_priv->display.get_cdclk(dev_priv, &dev_priv->cdclk.hw); + intel_cdclk_get_cdclk(dev_priv, &dev_priv->cdclk.hw); /* * 9:0 CMBUS [sic] CDCLK frequency (cdfreq): @@ -2855,6 +2885,157 @@ u32 intel_read_rawclk(struct drm_i915_private *dev_priv) return freq; } +static struct intel_cdclk_funcs tgl_cdclk_funcs = { + .get_cdclk = bxt_get_cdclk, + .set_cdclk = bxt_set_cdclk, + .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, + .modeset_calc_cdclk = bxt_modeset_calc_cdclk, + .calc_voltage_level = tgl_calc_voltage_level, +}; + +static struct intel_cdclk_funcs ehl_cdclk_funcs = { + .get_cdclk = bxt_get_cdclk, + .set_cdclk = bxt_set_cdclk, + .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, + .modeset_calc_cdclk = bxt_modeset_calc_cdclk, + .calc_voltage_level = ehl_calc_voltage_level, +}; + +static struct intel_cdclk_funcs icl_cdclk_funcs = { + .get_cdclk = bxt_get_cdclk, + .set_cdclk = bxt_set_cdclk, + .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, + .modeset_calc_cdclk = bxt_modeset_calc_cdclk, + .calc_voltage_level = icl_calc_voltage_level, +}; + +static struct intel_cdclk_funcs bxt_cdclk_funcs = { + .get_cdclk = bxt_get_cdclk, + .set_cdclk = bxt_set_cdclk, + .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, + .modeset_calc_cdclk = bxt_modeset_calc_cdclk, + .calc_voltage_level = bxt_calc_voltage_level, +}; + +static struct intel_cdclk_funcs skl_cdclk_funcs = { + .get_cdclk = skl_get_cdclk, + .set_cdclk = skl_set_cdclk, + .bw_calc_min_cdclk = skl_bw_calc_min_cdclk, + .modeset_calc_cdclk = skl_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs bdw_cdclk_funcs = { + .get_cdclk = bdw_get_cdclk, + .set_cdclk = bdw_set_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = bdw_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs chv_cdclk_funcs = { + .get_cdclk = vlv_get_cdclk, + .set_cdclk = chv_set_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = vlv_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs vlv_cdclk_funcs = { + .get_cdclk = vlv_get_cdclk, + .set_cdclk = vlv_set_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = vlv_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs hsw_cdclk_funcs = { + .get_cdclk = hsw_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +/* SNB, IVB, 965G, 945G */ +static struct intel_cdclk_funcs fixed_400mhz_cdclk_funcs = { + .get_cdclk = fixed_400mhz_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs ilk_cdclk_funcs = { + .get_cdclk = fixed_450mhz_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs gm45_cdclk_funcs = { + .get_cdclk = gm45_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +/* G45 uses G33 */ + +static struct intel_cdclk_funcs i965gm_cdclk_funcs = { + .get_cdclk = i965gm_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +/* i965G uses fixed 400 */ + +static struct intel_cdclk_funcs pnv_cdclk_funcs = { + .get_cdclk = pnv_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs g33_cdclk_funcs = { + .get_cdclk = g33_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs i945gm_cdclk_funcs = { + .get_cdclk = i945gm_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +/* i945G uses fixed 400 */ + +static struct intel_cdclk_funcs i915gm_cdclk_funcs = { + .get_cdclk = i915gm_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs i915g_cdclk_funcs = { + .get_cdclk = fixed_333mhz_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs i865g_cdclk_funcs = { + .get_cdclk = fixed_266mhz_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs i85x_cdclk_funcs = { + .get_cdclk = i85x_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs i845g_cdclk_funcs = { + .get_cdclk = fixed_200mhz_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + +static struct intel_cdclk_funcs i830_cdclk_funcs = { + .get_cdclk = fixed_133mhz_get_cdclk, + .bw_calc_min_cdclk = intel_bw_calc_min_cdclk, + .modeset_calc_cdclk = fixed_modeset_calc_cdclk, +}; + /** * intel_init_cdclk_hooks - Initialize CDCLK related modesetting hooks * @dev_priv: i915 device @@ -2862,119 +3043,78 @@ u32 intel_read_rawclk(struct drm_i915_private *dev_priv) void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv) { if (IS_DG2(dev_priv)) { - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = tgl_calc_voltage_level; + dev_priv->cdclk_funcs = &tgl_cdclk_funcs; dev_priv->cdclk.table = dg2_cdclk_table; } else if (IS_ALDERLAKE_P(dev_priv)) { - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = tgl_calc_voltage_level; + dev_priv->cdclk_funcs = &tgl_cdclk_funcs; /* Wa_22011320316:adl-p[a0] */ if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) dev_priv->cdclk.table = adlp_a_step_cdclk_table; else dev_priv->cdclk.table = adlp_cdclk_table; } else if (IS_ROCKETLAKE(dev_priv)) { - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = tgl_calc_voltage_level; + dev_priv->cdclk_funcs = &tgl_cdclk_funcs; dev_priv->cdclk.table = rkl_cdclk_table; } else if (DISPLAY_VER(dev_priv) >= 12) { - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = tgl_calc_voltage_level; + dev_priv->cdclk_funcs = &tgl_cdclk_funcs; dev_priv->cdclk.table = icl_cdclk_table; } else if (IS_JSL_EHL(dev_priv)) { - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = ehl_calc_voltage_level; + dev_priv->cdclk_funcs = &ehl_cdclk_funcs; dev_priv->cdclk.table = icl_cdclk_table; } else if (DISPLAY_VER(dev_priv) >= 11) { - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = icl_calc_voltage_level; + dev_priv->cdclk_funcs = &icl_cdclk_funcs; dev_priv->cdclk.table = icl_cdclk_table; } else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) { - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.set_cdclk = bxt_set_cdclk; - dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk; - dev_priv->display.calc_voltage_level = bxt_calc_voltage_level; + dev_priv->cdclk_funcs = &bxt_cdclk_funcs; if (IS_GEMINILAKE(dev_priv)) dev_priv->cdclk.table = glk_cdclk_table; else dev_priv->cdclk.table = bxt_cdclk_table; } else if (DISPLAY_VER(dev_priv) == 9) { - dev_priv->display.bw_calc_min_cdclk = skl_bw_calc_min_cdclk; - dev_priv->display.set_cdclk = skl_set_cdclk; - dev_priv->display.modeset_calc_cdclk = skl_modeset_calc_cdclk; + dev_priv->cdclk_funcs = &skl_cdclk_funcs; } else if (IS_BROADWELL(dev_priv)) { - dev_priv->display.bw_calc_min_cdclk = intel_bw_calc_min_cdclk; - dev_priv->display.set_cdclk = bdw_set_cdclk; - dev_priv->display.modeset_calc_cdclk = bdw_modeset_calc_cdclk; + dev_priv->cdclk_funcs = &bdw_cdclk_funcs; + } else if (IS_HASWELL(dev_priv)) { + dev_priv->cdclk_funcs = &hsw_cdclk_funcs; } else if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->display.bw_calc_min_cdclk = intel_bw_calc_min_cdclk; - dev_priv->display.set_cdclk = chv_set_cdclk; - dev_priv->display.modeset_calc_cdclk = vlv_modeset_calc_cdclk; + dev_priv->cdclk_funcs = &chv_cdclk_funcs; } else if (IS_VALLEYVIEW(dev_priv)) { - dev_priv->display.bw_calc_min_cdclk = intel_bw_calc_min_cdclk; - dev_priv->display.set_cdclk = vlv_set_cdclk; - dev_priv->display.modeset_calc_cdclk = vlv_modeset_calc_cdclk; - } else { - dev_priv->display.bw_calc_min_cdclk = intel_bw_calc_min_cdclk; - dev_priv->display.modeset_calc_cdclk = fixed_modeset_calc_cdclk; + dev_priv->cdclk_funcs = &vlv_cdclk_funcs; + } else if (IS_SANDYBRIDGE(dev_priv) || IS_IVYBRIDGE(dev_priv)) { + dev_priv->cdclk_funcs = &fixed_400mhz_cdclk_funcs; + } else if (IS_IRONLAKE(dev_priv)) { + dev_priv->cdclk_funcs = &ilk_cdclk_funcs; + } else if (IS_GM45(dev_priv)) { + dev_priv->cdclk_funcs = &gm45_cdclk_funcs; + } else if (IS_G45(dev_priv)) { + dev_priv->cdclk_funcs = &g33_cdclk_funcs; + } else if (IS_I965GM(dev_priv)) { + dev_priv->cdclk_funcs = &i965gm_cdclk_funcs; + } else if (IS_I965G(dev_priv)) { + dev_priv->cdclk_funcs = &fixed_400mhz_cdclk_funcs; + } else if (IS_PINEVIEW(dev_priv)) { + dev_priv->cdclk_funcs = &pnv_cdclk_funcs; + } else if (IS_G33(dev_priv)) { + dev_priv->cdclk_funcs = &g33_cdclk_funcs; + } else if (IS_I945GM(dev_priv)) { + dev_priv->cdclk_funcs = &i945gm_cdclk_funcs; + } else if (IS_I945G(dev_priv)) { + dev_priv->cdclk_funcs = &fixed_400mhz_cdclk_funcs; + } else if (IS_I915GM(dev_priv)) { + dev_priv->cdclk_funcs = &i915gm_cdclk_funcs; + } else if (IS_I915G(dev_priv)) { + dev_priv->cdclk_funcs = &i915g_cdclk_funcs; + } else if (IS_I865G(dev_priv)) { + dev_priv->cdclk_funcs = &i865g_cdclk_funcs; + } else if (IS_I85X(dev_priv)) { + dev_priv->cdclk_funcs = &i85x_cdclk_funcs; + } else if (IS_I845G(dev_priv)) { + dev_priv->cdclk_funcs = &i845g_cdclk_funcs; + } else if (IS_I830(dev_priv)) { + dev_priv->cdclk_funcs = &i830_cdclk_funcs; } - if (DISPLAY_VER(dev_priv) >= 10 || IS_BROXTON(dev_priv)) - dev_priv->display.get_cdclk = bxt_get_cdclk; - else if (DISPLAY_VER(dev_priv) == 9) - dev_priv->display.get_cdclk = skl_get_cdclk; - else if (IS_BROADWELL(dev_priv)) - dev_priv->display.get_cdclk = bdw_get_cdclk; - else if (IS_HASWELL(dev_priv)) - dev_priv->display.get_cdclk = hsw_get_cdclk; - else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - dev_priv->display.get_cdclk = vlv_get_cdclk; - else if (IS_SANDYBRIDGE(dev_priv) || IS_IVYBRIDGE(dev_priv)) - dev_priv->display.get_cdclk = fixed_400mhz_get_cdclk; - else if (IS_IRONLAKE(dev_priv)) - dev_priv->display.get_cdclk = fixed_450mhz_get_cdclk; - else if (IS_GM45(dev_priv)) - dev_priv->display.get_cdclk = gm45_get_cdclk; - else if (IS_G45(dev_priv)) - dev_priv->display.get_cdclk = g33_get_cdclk; - else if (IS_I965GM(dev_priv)) - dev_priv->display.get_cdclk = i965gm_get_cdclk; - else if (IS_I965G(dev_priv)) - dev_priv->display.get_cdclk = fixed_400mhz_get_cdclk; - else if (IS_PINEVIEW(dev_priv)) - dev_priv->display.get_cdclk = pnv_get_cdclk; - else if (IS_G33(dev_priv)) - dev_priv->display.get_cdclk = g33_get_cdclk; - else if (IS_I945GM(dev_priv)) - dev_priv->display.get_cdclk = i945gm_get_cdclk; - else if (IS_I945G(dev_priv)) - dev_priv->display.get_cdclk = fixed_400mhz_get_cdclk; - else if (IS_I915GM(dev_priv)) - dev_priv->display.get_cdclk = i915gm_get_cdclk; - else if (IS_I915G(dev_priv)) - dev_priv->display.get_cdclk = fixed_333mhz_get_cdclk; - else if (IS_I865G(dev_priv)) - dev_priv->display.get_cdclk = fixed_266mhz_get_cdclk; - else if (IS_I85X(dev_priv)) - dev_priv->display.get_cdclk = i85x_get_cdclk; - else if (IS_I845G(dev_priv)) - dev_priv->display.get_cdclk = fixed_200mhz_get_cdclk; - else if (IS_I830(dev_priv)) - dev_priv->display.get_cdclk = fixed_133mhz_get_cdclk; - - if (drm_WARN(&dev_priv->drm, !dev_priv->display.get_cdclk, - "Unknown platform. Assuming 133 MHz CDCLK\n")) - dev_priv->display.get_cdclk = fixed_133mhz_get_cdclk; + if (drm_WARN(&dev_priv->drm, !dev_priv->cdclk_funcs, + "Unknown platform. Assuming i830\n")) + dev_priv->cdclk_funcs = &i830_cdclk_funcs; } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index b34eb00fb327..309b3f394e24 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -68,7 +68,9 @@ void intel_set_cdclk_post_plane_update(struct intel_atomic_state *state); void intel_dump_cdclk_config(const struct intel_cdclk_config *cdclk_config, const char *context); int intel_modeset_calc_cdclk(struct intel_atomic_state *state); - +void intel_cdclk_get_cdclk(struct drm_i915_private *dev_priv, + struct intel_cdclk_config *cdclk_config); +int intel_cdclk_bw_calc_min_cdclk(struct intel_atomic_state *state); struct intel_cdclk_state * intel_atomic_get_cdclk_state(struct intel_atomic_state *state); diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index afcb4bf3826c..5359b7305a78 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -25,6 +25,8 @@ #include "intel_color.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dpll.h" +#include "intel_dsi.h" #define CTM_COEFF_SIGN (1ULL << 63) @@ -1137,14 +1139,14 @@ void intel_color_load_luts(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - dev_priv->display.load_luts(crtc_state); + dev_priv->color_funcs->load_luts(crtc_state); } void intel_color_commit(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - dev_priv->display.color_commit(crtc_state); + dev_priv->color_funcs->color_commit(crtc_state); } static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state) @@ -1200,15 +1202,15 @@ int intel_color_check(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - return dev_priv->display.color_check(crtc_state); + return dev_priv->color_funcs->color_check(crtc_state); } void intel_color_get_config(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - if (dev_priv->display.read_luts) - dev_priv->display.read_luts(crtc_state); + if (dev_priv->color_funcs->read_luts) + dev_priv->color_funcs->read_luts(crtc_state); } static bool need_plane_update(struct intel_plane *plane, @@ -2092,6 +2094,76 @@ static void icl_read_luts(struct intel_crtc_state *crtc_state) } } +static const struct intel_color_funcs chv_color_funcs = { + .color_check = chv_color_check, + .color_commit = i9xx_color_commit, + .load_luts = chv_load_luts, + .read_luts = chv_read_luts, +}; + +static const struct intel_color_funcs i965_color_funcs = { + .color_check = i9xx_color_check, + .color_commit = i9xx_color_commit, + .load_luts = i965_load_luts, + .read_luts = i965_read_luts, +}; + +static const struct intel_color_funcs i9xx_color_funcs = { + .color_check = i9xx_color_check, + .color_commit = i9xx_color_commit, + .load_luts = i9xx_load_luts, + .read_luts = i9xx_read_luts, +}; + +static const struct intel_color_funcs icl_color_funcs = { + .color_check = icl_color_check, + .color_commit = skl_color_commit, + .load_luts = icl_load_luts, + .read_luts = icl_read_luts, +}; + +static const struct intel_color_funcs glk_color_funcs = { + .color_check = glk_color_check, + .color_commit = skl_color_commit, + .load_luts = glk_load_luts, + .read_luts = glk_read_luts, +}; + +static const struct intel_color_funcs skl_color_funcs = { + .color_check = ivb_color_check, + .color_commit = skl_color_commit, + .load_luts = bdw_load_luts, + .read_luts = NULL, +}; + +static const struct intel_color_funcs bdw_color_funcs = { + .color_check = ivb_color_check, + .color_commit = hsw_color_commit, + .load_luts = bdw_load_luts, + .read_luts = NULL, +}; + +static const struct intel_color_funcs hsw_color_funcs = { + .color_check = ivb_color_check, + .color_commit = hsw_color_commit, + .load_luts = ivb_load_luts, + .read_luts = NULL, +}; + +static const struct intel_color_funcs ivb_color_funcs = { + .color_check = ivb_color_check, + .color_commit = ilk_color_commit, + .load_luts = ivb_load_luts, + .read_luts = NULL, +}; + +static const struct intel_color_funcs ilk_color_funcs = { + .color_check = ilk_color_check, + .color_commit = ilk_color_commit, + .load_luts = ilk_load_luts, + .read_luts = ilk_read_luts, +}; + void intel_color_init(struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -2101,52 +2173,28 @@ void intel_color_init(struct intel_crtc *crtc) if (HAS_GMCH(dev_priv)) { if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->display.color_check = chv_color_check; - dev_priv->display.color_commit = i9xx_color_commit; - dev_priv->display.load_luts = chv_load_luts; - dev_priv->display.read_luts = chv_read_luts; + dev_priv->color_funcs = &chv_color_funcs; } else if (DISPLAY_VER(dev_priv) >= 4) { - dev_priv->display.color_check = i9xx_color_check; - dev_priv->display.color_commit = i9xx_color_commit; - dev_priv->display.load_luts = i965_load_luts; - dev_priv->display.read_luts = i965_read_luts; + dev_priv->color_funcs = &i965_color_funcs; } else { - dev_priv->display.color_check = i9xx_color_check; - dev_priv->display.color_commit = i9xx_color_commit; - dev_priv->display.load_luts = i9xx_load_luts; - dev_priv->display.read_luts = i9xx_read_luts; + dev_priv->color_funcs = &i9xx_color_funcs; } } else { if (DISPLAY_VER(dev_priv) >= 11) - dev_priv->display.color_check = icl_color_check; - else if (DISPLAY_VER(dev_priv) >= 10) - dev_priv->display.color_check = glk_color_check; - else if (DISPLAY_VER(dev_priv) >= 7) - dev_priv->display.color_check = ivb_color_check; - else - dev_priv->display.color_check = ilk_color_check; - - if (DISPLAY_VER(dev_priv) >= 9) - dev_priv->display.color_commit = skl_color_commit; - else if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) - dev_priv->display.color_commit = hsw_color_commit; - else - dev_priv->display.color_commit = ilk_color_commit; - - if (DISPLAY_VER(dev_priv) >= 11) { - dev_priv->display.load_luts = icl_load_luts; - dev_priv->display.read_luts = icl_read_luts; - } else if (DISPLAY_VER(dev_priv) == 10) { - dev_priv->display.load_luts = glk_load_luts; - dev_priv->display.read_luts = glk_read_luts; - } else if (DISPLAY_VER(dev_priv) >= 8) { - dev_priv->display.load_luts = bdw_load_luts; - } else if (DISPLAY_VER(dev_priv) >= 7) { - dev_priv->display.load_luts = ivb_load_luts; - } else { - dev_priv->display.load_luts = ilk_load_luts; - dev_priv->display.read_luts = ilk_read_luts; - } + dev_priv->color_funcs = &icl_color_funcs; + else if (DISPLAY_VER(dev_priv) == 10) + dev_priv->color_funcs = &glk_color_funcs; + else if (DISPLAY_VER(dev_priv) == 9) + dev_priv->color_funcs = &skl_color_funcs; + else if (DISPLAY_VER(dev_priv) == 8) + dev_priv->color_funcs = &bdw_color_funcs; + else if (DISPLAY_VER(dev_priv) == 7) { + if (IS_HASWELL(dev_priv)) + dev_priv->color_funcs = &hsw_color_funcs; + else + dev_priv->color_funcs = &ivb_color_funcs; + } else + dev_priv->color_funcs = &ilk_color_funcs; } drm_crtc_enable_color_mgmt(&crtc->base, diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c index bacdf8a16bcb..634e8d449457 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy.c +++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c @@ -220,13 +220,13 @@ static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, return false; if (DISPLAY_VER(dev_priv) >= 12) { - ret &= check_phy_reg(dev_priv, phy, ICL_PORT_TX_DW8_LN0(phy), + ret &= check_phy_reg(dev_priv, phy, ICL_PORT_TX_DW8_LN(0, phy), ICL_PORT_TX_DW8_ODCC_CLK_SEL | ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_MASK, ICL_PORT_TX_DW8_ODCC_CLK_SEL | ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_DIV2); - ret &= check_phy_reg(dev_priv, phy, ICL_PORT_PCS_DW1_LN0(phy), + ret &= check_phy_reg(dev_priv, phy, ICL_PORT_PCS_DW1_LN(0, phy), DCC_MODE_SELECT_MASK, DCC_MODE_SELECT_CONTINUOSLY); } @@ -343,13 +343,13 @@ static void icl_combo_phys_init(struct drm_i915_private *dev_priv) skip_phy_misc: if (DISPLAY_VER(dev_priv) >= 12) { - val = intel_de_read(dev_priv, ICL_PORT_TX_DW8_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_TX_DW8_LN(0, phy)); val &= ~ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_MASK; val |= ICL_PORT_TX_DW8_ODCC_CLK_SEL; val |= ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_DIV2; intel_de_write(dev_priv, ICL_PORT_TX_DW8_GRP(phy), val); - val = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN(0, phy)); val &= ~DCC_MODE_SELECT_MASK; val |= DCC_MODE_SELECT_CONTINUOSLY; intel_de_write(dev_priv, ICL_PORT_PCS_DW1_GRP(phy), val); diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c index 4f49d782eca2..c65f95a9a1ec 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.c +++ b/drivers/gpu/drm/i915/display/intel_connector.c @@ -124,7 +124,7 @@ int intel_connector_register(struct drm_connector *connector) goto err_backlight; } - intel_connector_debugfs_add(connector); + intel_connector_debugfs_add(intel_connector); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 408f82b0dc7d..1c161eeed82f 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -251,7 +251,7 @@ static void hsw_post_disable_crt(struct intel_atomic_state *state, intel_crtc_vblank_off(old_crtc_state); - intel_disable_pipe(old_crtc_state); + intel_disable_transcoder(old_crtc_state); intel_ddi_disable_transcoder_func(old_crtc_state); @@ -314,7 +314,7 @@ static void hsw_enable_crt(struct intel_atomic_state *state, intel_ddi_enable_transcoder_func(encoder, crtc_state); - intel_enable_pipe(crtc_state); + intel_enable_transcoder(crtc_state); lpt_pch_enable(crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index c7618fef0143..11842f212613 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -17,7 +17,7 @@ #include "intel_display_types.h" #include "intel_display.h" #include "intel_fb.h" - +#include "intel_fb_pin.h" #include "intel_frontbuffer.h" #include "intel_pm.h" #include "intel_psr.h" @@ -536,8 +536,10 @@ static void i9xx_update_cursor(struct intel_plane *plane, if (DISPLAY_VER(dev_priv) >= 9) skl_write_cursor_wm(plane, crtc_state); - if (!intel_crtc_needs_modeset(crtc_state)) + if (plane_state) intel_psr2_program_plane_sel_fetch(plane, crtc_state, plane_state, 0); + else + intel_psr2_disable_plane_sel_fetch(plane, crtc_state); if (plane->cursor.base != base || plane->cursor.size != fbc_ctl || @@ -637,8 +639,7 @@ intel_legacy_cursor_update(struct drm_plane *_plane, * FIXME bigjoiner fastpath would be good */ if (!crtc_state->hw.active || intel_crtc_needs_modeset(crtc_state) || - crtc_state->update_pipe || crtc_state->bigjoiner || - crtc_state->enable_psr2_sel_fetch) + crtc_state->update_pipe || crtc_state->bigjoiner) goto slow; /* @@ -696,7 +697,7 @@ intel_legacy_cursor_update(struct drm_plane *_plane, goto out_free; intel_frontbuffer_flush(to_intel_frontbuffer(new_plane_state->hw.fb), - ORIGIN_FLIP); + ORIGIN_CURSOR_UPDATE); intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->hw.fb), to_intel_frontbuffer(new_plane_state->hw.fb), plane->frontbuffer_bit); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 62a86155a841..1dcfe31e6c6f 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -74,24 +74,27 @@ static const u8 index_to_dp_signal_levels[] = { }; static int intel_ddi_hdmi_level(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state) + const struct intel_ddi_buf_trans *trans) { - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - int n_entries, level, default_entry; + int level; - n_entries = intel_ddi_hdmi_num_entries(encoder, crtc_state, &default_entry); - if (n_entries == 0) - return 0; level = intel_bios_hdmi_level_shift(encoder); if (level < 0) - level = default_entry; - - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; + level = trans->hdmi_default_entry; return level; } +static bool has_buf_trans_select(struct drm_i915_private *i915) +{ + return DISPLAY_VER(i915) < 10 && !IS_BROXTON(i915); +} + +static bool has_iboost(struct drm_i915_private *i915) +{ + return DISPLAY_VER(i915) == 9 && !IS_BROXTON(i915); +} + /* * Starting with Haswell, DDI port buffers must be programmed with correct * values in advance. This function programs the correct values for @@ -104,22 +107,22 @@ void hsw_prepare_dp_ddi_buffers(struct intel_encoder *encoder, u32 iboost_bit = 0; int i, n_entries; enum port port = encoder->port; - const struct intel_ddi_buf_trans *ddi_translations; + const struct intel_ddi_buf_trans *trans; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; /* If we're boosting the current, set bit 31 of trans1 */ - if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv) && + if (has_iboost(dev_priv) && intel_bios_encoder_dp_boost_level(encoder->devdata)) iboost_bit = DDI_BUF_BALANCE_LEG_ENABLE; for (i = 0; i < n_entries; i++) { intel_de_write(dev_priv, DDI_BUF_TRANS_LO(port, i), - ddi_translations->entries[i].hsw.trans1 | iboost_bit); + trans->entries[i].hsw.trans1 | iboost_bit); intel_de_write(dev_priv, DDI_BUF_TRANS_HI(port, i), - ddi_translations->entries[i].hsw.trans2); + trans->entries[i].hsw.trans2); } } @@ -129,31 +132,29 @@ void hsw_prepare_dp_ddi_buffers(struct intel_encoder *encoder, * HDMI/DVI use cases. */ static void hsw_prepare_hdmi_ddi_buffers(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + int level = intel_ddi_level(encoder, crtc_state, 0); u32 iboost_bit = 0; int n_entries; enum port port = encoder->port; - const struct intel_ddi_buf_trans *ddi_translations; + const struct intel_ddi_buf_trans *trans; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; /* If we're boosting the current, set bit 31 of trans1 */ - if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv) && + if (has_iboost(dev_priv) && intel_bios_encoder_hdmi_boost_level(encoder->devdata)) iboost_bit = DDI_BUF_BALANCE_LEG_ENABLE; /* Entry 9 is for HDMI: */ intel_de_write(dev_priv, DDI_BUF_TRANS_LO(port, 9), - ddi_translations->entries[level].hsw.trans1 | iboost_bit); + trans->entries[level].hsw.trans1 | iboost_bit); intel_de_write(dev_priv, DDI_BUF_TRANS_HI(port, 9), - ddi_translations->entries[level].hsw.trans2); + trans->entries[level].hsw.trans2); } void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv, @@ -282,13 +283,14 @@ static void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder, struct intel_digital_port *dig_port = enc_to_dig_port(encoder); enum phy phy = intel_port_to_phy(i915, encoder->port); + /* DDI_BUF_CTL_ENABLE will be set by intel_ddi_prepare_link_retrain() later */ intel_dp->DP = dig_port->saved_port_bits | - DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0); - intel_dp->DP |= DDI_PORT_WIDTH(crtc_state->lane_count); + DDI_PORT_WIDTH(crtc_state->lane_count) | + DDI_BUF_TRANS_SELECT(0); if (IS_ALDERLAKE_P(i915) && intel_phy_is_tc(i915, phy)) { intel_dp->DP |= ddi_buf_phy_link_rate(crtc_state->port_clock); - if (dig_port->tc_mode != TC_PORT_TBT_ALT) + if (!intel_tc_port_in_tbt_alt_mode(dig_port)) intel_dp->DP |= DDI_BUF_CTL_TC_PHY_OWNERSHIP; } } @@ -408,6 +410,20 @@ static u32 bdw_trans_port_sync_master_select(enum transcoder master_transcoder) return master_transcoder + 1; } +static void +intel_ddi_config_transcoder_dp2(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + u32 val = 0; + + if (intel_dp_is_uhbr(crtc_state)) + val = TRANS_DP2_128B132B_CHANNEL_CODING; + + intel_de_write(i915, TRANS_DP2_CTL(cpu_transcoder), val); +} + /* * Returns the TRANS_DDI_FUNC_CTL value based on CRTC state. * @@ -489,10 +505,13 @@ intel_ddi_transcoder_func_reg_val_get(struct intel_encoder *encoder, if (crtc_state->hdmi_high_tmds_clock_ratio) temp |= TRANS_DDI_HIGH_TMDS_CHAR_RATE; } else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG)) { - temp |= TRANS_DDI_MODE_SELECT_FDI; + temp |= TRANS_DDI_MODE_SELECT_FDI_OR_128B132B; temp |= (crtc_state->fdi_lanes - 1) << 1; } else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)) { - temp |= TRANS_DDI_MODE_SELECT_DP_MST; + if (intel_dp_is_uhbr(crtc_state)) + temp |= TRANS_DDI_MODE_SELECT_FDI_OR_128B132B; + else + temp |= TRANS_DDI_MODE_SELECT_DP_MST; temp |= DDI_PORT_WIDTH(crtc_state->lane_count); if (DISPLAY_VER(dev_priv) >= 12) { @@ -679,8 +698,13 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) ret = false; break; - case TRANS_DDI_MODE_SELECT_FDI: - ret = type == DRM_MODE_CONNECTOR_VGA; + case TRANS_DDI_MODE_SELECT_FDI_OR_128B132B: + if (HAS_DP20(dev_priv)) + /* 128b/132b */ + ret = false; + else + /* FDI */ + ret = type == DRM_MODE_CONNECTOR_VGA; break; default: @@ -767,8 +791,9 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder, if ((tmp & port_mask) != ddi_select) continue; - if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == - TRANS_DDI_MODE_SELECT_DP_MST) + if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_DP_MST || + (HAS_DP20(dev_priv) && + (tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_FDI_OR_128B132B)) mst_pipe_mask |= BIT(p); *pipe_mask |= BIT(p); @@ -862,8 +887,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder, dig_port = enc_to_dig_port(encoder); - if (!intel_phy_is_tc(dev_priv, phy) || - dig_port->tc_mode != TC_PORT_TBT_ALT) { + if (!intel_tc_port_in_tbt_alt_mode(dig_port)) { drm_WARN_ON(&dev_priv->drm, dig_port->ddi_io_wakeref); dig_port->ddi_io_wakeref = intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); @@ -948,16 +972,14 @@ static void skl_ddi_set_iboost(struct intel_encoder *encoder, iboost = intel_bios_encoder_dp_boost_level(encoder->devdata); if (iboost == 0) { - const struct intel_ddi_buf_trans *ddi_translations; + const struct intel_ddi_buf_trans *trans; int n_entries; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; - iboost = ddi_translations->entries[level].hsw.i_boost; + iboost = trans->entries[level].hsw.i_boost; } /* Make sure that the requested I_boost is valid */ @@ -972,28 +994,6 @@ static void skl_ddi_set_iboost(struct intel_encoder *encoder, _skl_ddi_set_iboost(dev_priv, PORT_E, iboost); } -static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) -{ - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - const struct intel_ddi_buf_trans *ddi_translations; - enum port port = encoder->port; - int n_entries; - - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) - return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; - - bxt_ddi_phy_set_signal_level(dev_priv, port, - ddi_translations->entries[level].bxt.margin, - ddi_translations->entries[level].bxt.scale, - ddi_translations->entries[level].bxt.enable, - ddi_translations->entries[level].bxt.deemphasis); -} - static u8 intel_ddi_dp_voltage_max(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { @@ -1023,33 +1023,43 @@ static u8 intel_ddi_dp_preemph_max(struct intel_dp *intel_dp) return DP_TRAIN_PRE_EMPH_LEVEL_3; } +static u32 icl_combo_phy_loadgen_select(const struct intel_crtc_state *crtc_state, + int lane) +{ + if (crtc_state->port_clock > 600000) + return 0; + + if (crtc_state->lane_count == 4) + return lane >= 1 ? LOADGEN_SELECT : 0; + else + return lane == 1 || lane == 2 ? LOADGEN_SELECT : 0; +} + static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - const struct intel_ddi_buf_trans *ddi_translations; + int level = intel_ddi_level(encoder, crtc_state, 0); + const struct intel_ddi_buf_trans *trans; enum phy phy = intel_port_to_phy(dev_priv, encoder->port); int n_entries, ln; u32 val; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); val = EDP4K2K_MODE_OVRD_EN | EDP4K2K_MODE_OVRD_OPTIMIZED; - intel_dp->hobl_active = is_hobl_buf_trans(ddi_translations); + intel_dp->hobl_active = is_hobl_buf_trans(trans); intel_de_rmw(dev_priv, ICL_PORT_CL_DW10(phy), val, intel_dp->hobl_active ? val : 0); } /* Set PORT_TX_DW5 */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK | TAP2_DISABLE | TAP3_DISABLE); val |= SCALING_MODE_SEL(0x2); @@ -1058,52 +1068,48 @@ static void icl_ddi_combo_vswing_program(struct intel_encoder *encoder, intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), val); /* Program PORT_TX_DW2 */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_TX_DW2_LN(0, phy)); val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | RCOMP_SCALAR_MASK); - val |= SWING_SEL_UPPER(ddi_translations->entries[level].icl.dw2_swing_sel); - val |= SWING_SEL_LOWER(ddi_translations->entries[level].icl.dw2_swing_sel); + val |= SWING_SEL_UPPER(trans->entries[level].icl.dw2_swing_sel); + val |= SWING_SEL_LOWER(trans->entries[level].icl.dw2_swing_sel); /* Program Rcomp scalar for every table entry */ val |= RCOMP_SCALAR(0x98); intel_de_write(dev_priv, ICL_PORT_TX_DW2_GRP(phy), val); /* Program PORT_TX_DW4 */ /* We cannot write to GRP. It would overwrite individual loadgen. */ - for (ln = 0; ln <= 3; ln++) { + for (ln = 0; ln < 4; ln++) { val = intel_de_read(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy)); val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | CURSOR_COEFF_MASK); - val |= POST_CURSOR_1(ddi_translations->entries[level].icl.dw4_post_cursor_1); - val |= POST_CURSOR_2(ddi_translations->entries[level].icl.dw4_post_cursor_2); - val |= CURSOR_COEFF(ddi_translations->entries[level].icl.dw4_cursor_coeff); + val |= POST_CURSOR_1(trans->entries[level].icl.dw4_post_cursor_1); + val |= POST_CURSOR_2(trans->entries[level].icl.dw4_post_cursor_2); + val |= CURSOR_COEFF(trans->entries[level].icl.dw4_cursor_coeff); intel_de_write(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), val); } /* Program PORT_TX_DW7 */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW7_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_TX_DW7_LN(0, phy)); val &= ~N_SCALAR_MASK; - val |= N_SCALAR(ddi_translations->entries[level].icl.dw7_n_scalar); + val |= N_SCALAR(trans->entries[level].icl.dw7_n_scalar); intel_de_write(dev_priv, ICL_PORT_TX_DW7_GRP(phy), val); } -static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) +static void icl_combo_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum phy phy = intel_port_to_phy(dev_priv, encoder->port); - int width, rate, ln; u32 val; - - width = crtc_state->lane_count; - rate = crtc_state->port_clock; + int ln; /* * 1. If port type is eDP or DP, * set PORT_PCS_DW1 cmnkeeper_enable to 1b, * else clear to 0b. */ - val = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_PCS_DW1_LN(0, phy)); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) val &= ~COMMON_KEEPER_EN; else @@ -1112,19 +1118,15 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, /* 2. Program loadgen select */ /* - * Program PORT_TX_DW4_LN depending on Bit rate and used lanes + * Program PORT_TX_DW4 depending on Bit rate and used lanes * <= 6 GHz and 4 lanes (LN0=0, LN1=1, LN2=1, LN3=1) * <= 6 GHz and 1,2 lanes (LN0=0, LN1=1, LN2=1, LN3=0) * > 6 GHz (LN0=0, LN1=0, LN2=0, LN3=0) */ - for (ln = 0; ln <= 3; ln++) { + for (ln = 0; ln < 4; ln++) { val = intel_de_read(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy)); val &= ~LOADGEN_SELECT; - - if ((rate <= 600000 && width == 4 && ln >= 1) || - (rate <= 600000 && width < 4 && (ln == 1 || ln == 2))) { - val |= LOADGEN_SELECT; - } + val |= icl_combo_phy_loadgen_select(crtc_state, ln); intel_de_write(dev_priv, ICL_PORT_TX_DW4_LN(ln, phy), val); } @@ -1134,37 +1136,35 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, intel_de_write(dev_priv, ICL_PORT_CL_DW5(phy), val); /* 4. Clear training enable to change swing values */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); val &= ~TX_TRAINING_EN; intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), val); /* 5. Program swing and de-emphasis */ - icl_ddi_combo_vswing_program(encoder, crtc_state, level); + icl_ddi_combo_vswing_program(encoder, crtc_state); /* 6. Set training enable to trigger update */ - val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN0(phy)); + val = intel_de_read(dev_priv, ICL_PORT_TX_DW5_LN(0, phy)); val |= TX_TRAINING_EN; intel_de_write(dev_priv, ICL_PORT_TX_DW5_GRP(phy), val); } -static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) +static void icl_mg_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port); - const struct intel_ddi_buf_trans *ddi_translations; + int level = intel_ddi_level(encoder, crtc_state, 0); + const struct intel_ddi_buf_trans *trans; int n_entries, ln; u32 val; - if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) + if (intel_tc_port_in_tbt_alt_mode(enc_to_dig_port(encoder))) return; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; /* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */ for (ln = 0; ln < 2; ln++) { @@ -1182,13 +1182,13 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, val = intel_de_read(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port)); val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK; val |= CRI_TXDEEMPH_OVERRIDE_17_12( - ddi_translations->entries[level].mg.cri_txdeemph_override_17_12); + trans->entries[level].mg.cri_txdeemph_override_17_12); intel_de_write(dev_priv, MG_TX1_SWINGCTRL(ln, tc_port), val); val = intel_de_read(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port)); val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK; val |= CRI_TXDEEMPH_OVERRIDE_17_12( - ddi_translations->entries[level].mg.cri_txdeemph_override_17_12); + trans->entries[level].mg.cri_txdeemph_override_17_12); intel_de_write(dev_priv, MG_TX2_SWINGCTRL(ln, tc_port), val); } @@ -1198,9 +1198,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK | CRI_TXDEEMPH_OVERRIDE_5_0_MASK); val |= CRI_TXDEEMPH_OVERRIDE_5_0( - ddi_translations->entries[level].mg.cri_txdeemph_override_5_0) | + trans->entries[level].mg.cri_txdeemph_override_5_0) | CRI_TXDEEMPH_OVERRIDE_11_6( - ddi_translations->entries[level].mg.cri_txdeemph_override_11_6) | + trans->entries[level].mg.cri_txdeemph_override_11_6) | CRI_TXDEEMPH_OVERRIDE_EN; intel_de_write(dev_priv, MG_TX1_DRVCTRL(ln, tc_port), val); @@ -1208,9 +1208,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK | CRI_TXDEEMPH_OVERRIDE_5_0_MASK); val |= CRI_TXDEEMPH_OVERRIDE_5_0( - ddi_translations->entries[level].mg.cri_txdeemph_override_5_0) | + trans->entries[level].mg.cri_txdeemph_override_5_0) | CRI_TXDEEMPH_OVERRIDE_11_6( - ddi_translations->entries[level].mg.cri_txdeemph_override_11_6) | + trans->entries[level].mg.cri_txdeemph_override_11_6) | CRI_TXDEEMPH_OVERRIDE_EN; intel_de_write(dev_priv, MG_TX2_DRVCTRL(ln, tc_port), val); @@ -1270,45 +1270,29 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder, } } -static void icl_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) -{ - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); - - if (intel_phy_is_combo(dev_priv, phy)) - icl_combo_phy_ddi_vswing_sequence(encoder, crtc_state, level); - else - icl_mg_phy_ddi_vswing_sequence(encoder, crtc_state, level); -} - -static void -tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) +static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port); - const struct intel_ddi_buf_trans *ddi_translations; + int level = intel_ddi_level(encoder, crtc_state, 0); + const struct intel_ddi_buf_trans *trans; u32 val, dpcnt_mask, dpcnt_val; int n_entries, ln; - if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) + if (intel_tc_port_in_tbt_alt_mode(enc_to_dig_port(encoder))) return; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level >= n_entries)) - level = n_entries - 1; dpcnt_mask = (DKL_TX_PRESHOOT_COEFF_MASK | DKL_TX_DE_EMPAHSIS_COEFF_MASK | DKL_TX_VSWING_CONTROL_MASK); - dpcnt_val = DKL_TX_VSWING_CONTROL(ddi_translations->entries[level].dkl.dkl_vswing_control); - dpcnt_val |= DKL_TX_DE_EMPHASIS_COEFF(ddi_translations->entries[level].dkl.dkl_de_emphasis_control); - dpcnt_val |= DKL_TX_PRESHOOT_COEFF(ddi_translations->entries[level].dkl.dkl_preshoot_control); + dpcnt_val = DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing); + dpcnt_val |= DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis); + dpcnt_val |= DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot); for (ln = 0; ln < 2; ln++) { intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), @@ -1330,30 +1314,9 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, val = intel_de_read(dev_priv, DKL_TX_DPCNTL2(tc_port)); val &= ~DKL_TX_DP20BITMODE; intel_de_write(dev_priv, DKL_TX_DPCNTL2(tc_port), val); - - if ((intel_crtc_has_dp_encoder(crtc_state) && - crtc_state->port_clock == 162000) || - (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) && - crtc_state->port_clock == 594000)) - val |= DKL_TX_LOADGEN_SHARING_PMD_DISABLE; - else - val &= ~DKL_TX_LOADGEN_SHARING_PMD_DISABLE; } } -static void tgl_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) -{ - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); - - if (intel_phy_is_combo(dev_priv, phy)) - icl_combo_phy_ddi_vswing_sequence(encoder, crtc_state, level); - else - tgl_dkl_phy_ddi_vswing_sequence(encoder, crtc_state, level); -} - static int translate_signal_level(struct intel_dp *intel_dp, u8 signal_levels) { @@ -1373,65 +1336,62 @@ static int translate_signal_level(struct intel_dp *intel_dp, } static int intel_ddi_dp_level(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) + const struct intel_crtc_state *crtc_state, + int lane) { - u8 train_set = intel_dp->train_set[0]; - u8 signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK | - DP_TRAIN_PRE_EMPHASIS_MASK); + u8 train_set = intel_dp->train_set[lane]; - return translate_signal_level(intel_dp, signal_levels); + if (intel_dp_is_uhbr(crtc_state)) { + return train_set & DP_TX_FFE_PRESET_VALUE_MASK; + } else { + u8 signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK | + DP_TRAIN_PRE_EMPHASIS_MASK); + + return translate_signal_level(intel_dp, signal_levels); + } +} + +int intel_ddi_level(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + int lane) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + const struct intel_ddi_buf_trans *trans; + int level, n_entries; + + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&i915->drm, !trans)) + return 0; + + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + level = intel_ddi_hdmi_level(encoder, trans); + else + level = intel_ddi_dp_level(enc_to_intel_dp(encoder), crtc_state, + lane); + + if (drm_WARN_ON_ONCE(&i915->drm, level >= n_entries)) + level = n_entries - 1; + + return level; } static void -dg2_set_signal_levels(struct intel_dp *intel_dp, +hsw_set_signal_levels(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - int level = intel_ddi_dp_level(intel_dp, crtc_state); - - intel_snps_phy_ddi_vswing_sequence(encoder, crtc_state, level); -} - -static void -tgl_set_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - int level = intel_ddi_dp_level(intel_dp, crtc_state); - - tgl_ddi_vswing_sequence(encoder, crtc_state, level); -} - -static void -icl_set_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - int level = intel_ddi_dp_level(intel_dp, crtc_state); - - icl_ddi_vswing_sequence(encoder, crtc_state, level); -} - -static void -bxt_set_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - int level = intel_ddi_dp_level(intel_dp, crtc_state); - - bxt_ddi_vswing_sequence(encoder, crtc_state, level); -} - -static void -hsw_set_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state) -{ - struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - int level = intel_ddi_dp_level(intel_dp, crtc_state); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + int level = intel_ddi_level(encoder, crtc_state, 0); enum port port = encoder->port; u32 signal_levels; + if (has_iboost(dev_priv)) + skl_ddi_set_iboost(encoder, crtc_state, level); + + /* HDMI ignores the rest */ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + return; + signal_levels = DDI_BUF_TRANS_SELECT(level); drm_dbg_kms(&dev_priv->drm, "Using signal levels %08x\n", @@ -1440,9 +1400,6 @@ hsw_set_signal_levels(struct intel_dp *intel_dp, intel_dp->DP &= ~DDI_BUF_EMP_MASK; intel_dp->DP |= signal_levels; - if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv)) - skl_ddi_set_iboost(encoder, crtc_state, level); - intel_de_write(dev_priv, DDI_BUF_CTL(port), intel_dp->DP); intel_de_posting_read(dev_priv, DDI_BUF_CTL(port)); } @@ -2061,7 +2018,7 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port, u8 width; if (!intel_phy_is_tc(dev_priv, phy) || - dig_port->tc_mode == TC_PORT_TBT_ALT) + intel_tc_port_in_tbt_alt_mode(dig_port)) return; if (DISPLAY_VER(dev_priv) >= 12) { @@ -2086,7 +2043,7 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port, switch (pin_assignment) { case 0x0: drm_WARN_ON(&dev_priv->drm, - dig_port->tc_mode != TC_PORT_LEGACY); + !intel_tc_port_in_legacy_mode(dig_port)); if (width == 1) { ln1 |= MG_DP_MODE_CFG_DP_X1_MODE; } else { @@ -2331,14 +2288,18 @@ static void dg2_ddi_pre_enable_dp(struct intel_atomic_state *state, { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST); - int level = intel_ddi_dp_level(intel_dp, crtc_state); intel_dp_set_link_params(intel_dp, crtc_state->port_clock, crtc_state->lane_count); + /* + * We only configure what the register value will be here. Actual + * enabling happens during link training farther down. + */ + intel_ddi_init_dp_buf_reg(encoder, crtc_state); + /* * 1. Enable Power Wells * @@ -2355,8 +2316,7 @@ static void dg2_ddi_pre_enable_dp(struct intel_atomic_state *state, intel_ddi_enable_clock(encoder, crtc_state); /* 4. Enable IO power */ - if (!intel_phy_is_tc(dev_priv, phy) || - dig_port->tc_mode != TC_PORT_TBT_ALT) + if (!intel_tc_port_in_tbt_alt_mode(dig_port)) dig_port->ddi_io_wakeref = intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); @@ -2376,7 +2336,8 @@ static void dg2_ddi_pre_enable_dp(struct intel_atomic_state *state, */ intel_ddi_enable_pipe_clock(encoder, crtc_state); - /* 5.b Not relevant to i915 for now */ + /* 5.b Configure transcoder for DP 2.0 128b/132b */ + intel_ddi_config_transcoder_dp2(encoder, crtc_state); /* * 5.c Configure TRANS_DDI_FUNC_CTL DDI Select, DDI Mode Select & MST @@ -2393,17 +2354,7 @@ static void dg2_ddi_pre_enable_dp(struct intel_atomic_state *state, */ /* 5.e Configure voltage swing and related IO settings */ - intel_snps_phy_ddi_vswing_sequence(encoder, crtc_state, level); - - /* - * 5.f Configure and enable DDI_BUF_CTL - * 5.g Wait for DDI_BUF_CTL DDI Idle Status = 0b (Not Idle), timeout - * after 1200 us. - * - * We only configure what the register value will be here. Actual - * enabling happens during link training farther down. - */ - intel_ddi_init_dp_buf_reg(encoder, crtc_state); + encoder->set_signal_levels(encoder, crtc_state); if (!is_mst) intel_dp_set_power(intel_dp, DP_SET_POWER_D0); @@ -2444,15 +2395,19 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST); - int level = intel_ddi_dp_level(intel_dp, crtc_state); intel_dp_set_link_params(intel_dp, crtc_state->port_clock, crtc_state->lane_count); + /* + * We only configure what the register value will be here. Actual + * enabling happens during link training farther down. + */ + intel_ddi_init_dp_buf_reg(encoder, crtc_state); + /* * 1. Enable Power Wells * @@ -2481,8 +2436,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, intel_ddi_enable_clock(encoder, crtc_state); /* 5. If IO power is controlled through PWR_WELL_CTL, Enable IO Power */ - if (!intel_phy_is_tc(dev_priv, phy) || - dig_port->tc_mode != TC_PORT_TBT_ALT) { + if (!intel_tc_port_in_tbt_alt_mode(dig_port)) { drm_WARN_ON(&dev_priv->drm, dig_port->ddi_io_wakeref); dig_port->ddi_io_wakeref = intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); @@ -2522,7 +2476,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, */ /* 7.e Configure voltage swing and related IO settings */ - tgl_ddi_vswing_sequence(encoder, crtc_state, level); + encoder->set_signal_levels(encoder, crtc_state); /* * 7.f Combo PHY: Configure PORT_CL_DW10 Static Power Down to power up @@ -2535,16 +2489,6 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state, */ intel_ddi_mso_configure(crtc_state); - /* - * 7.g Configure and enable DDI_BUF_CTL - * 7.h Wait for DDI_BUF_CTL DDI Idle Status = 0b (Not Idle), timeout - * after 500 us. - * - * We only configure what the register value will be here. Actual - * enabling happens during link training farther down. - */ - intel_ddi_init_dp_buf_reg(encoder, crtc_state); - if (!is_mst) intel_dp_set_power(intel_dp, DP_SET_POWER_D0); @@ -2587,10 +2531,8 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum port port = encoder->port; - enum phy phy = intel_port_to_phy(dev_priv, port); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST); - int level = intel_ddi_dp_level(intel_dp, crtc_state); if (DISPLAY_VER(dev_priv) < 11) drm_WARN_ON(&dev_priv->drm, @@ -2602,12 +2544,17 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, crtc_state->port_clock, crtc_state->lane_count); + /* + * We only configure what the register value will be here. Actual + * enabling happens during link training farther down. + */ + intel_ddi_init_dp_buf_reg(encoder, crtc_state); + intel_pps_on(intel_dp); intel_ddi_enable_clock(encoder, crtc_state); - if (!intel_phy_is_tc(dev_priv, phy) || - dig_port->tc_mode != TC_PORT_TBT_ALT) { + if (!intel_tc_port_in_tbt_alt_mode(dig_port)) { drm_WARN_ON(&dev_priv->drm, dig_port->ddi_io_wakeref); dig_port->ddi_io_wakeref = intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); @@ -2615,16 +2562,13 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state, icl_program_mg_dp_mode(dig_port, crtc_state); - if (DISPLAY_VER(dev_priv) >= 11) - icl_ddi_vswing_sequence(encoder, crtc_state, level); - else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - bxt_ddi_vswing_sequence(encoder, crtc_state, level); - else + if (has_buf_trans_select(dev_priv)) hsw_prepare_dp_ddi_buffers(encoder, crtc_state); + encoder->set_signal_levels(encoder, crtc_state); + intel_ddi_power_up_lanes(encoder, crtc_state); - intel_ddi_init_dp_buf_reg(encoder, crtc_state); if (!is_mst) intel_dp_set_power(intel_dp, DP_SET_POWER_D0); intel_dp_configure_protocol_converter(intel_dp, crtc_state); @@ -2777,7 +2721,6 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state, struct intel_dp *intel_dp = &dig_port->dp; bool is_mst = intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST); - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); if (!is_mst) intel_dp_set_infoframes(encoder, false, @@ -2820,8 +2763,7 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state, intel_pps_vdd_on(intel_dp); intel_pps_off(intel_dp); - if (!intel_phy_is_tc(dev_priv, phy) || - dig_port->tc_mode != TC_PORT_TBT_ALT) + if (!intel_tc_port_in_tbt_alt_mode(dig_port)) intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain, fetch_and_zero(&dig_port->ddi_io_wakeref)); @@ -2867,7 +2809,7 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state, if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) { intel_crtc_vblank_off(old_crtc_state); - intel_disable_pipe(old_crtc_state); + intel_disable_transcoder(old_crtc_state); intel_vrr_disable(old_crtc_state); @@ -3010,7 +2952,6 @@ static void intel_enable_ddi_dp(struct intel_atomic_state *state, intel_dp_stop_link_train(intel_dp, crtc_state); intel_edp_backlight_on(crtc_state, conn_state); - intel_psr_enable(intel_dp, crtc_state, conn_state); if (!dig_port->lspcon.active || dig_port->dp.has_hdmi_sink) intel_dp_set_infoframes(encoder, true, crtc_state, conn_state); @@ -3051,7 +2992,6 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_digital_port *dig_port = enc_to_dig_port(encoder); struct drm_connector *connector = conn_state->connector; - int level = intel_ddi_hdmi_level(encoder, crtc_state); enum port port = encoder->port; if (!intel_hdmi_handle_sink_scrambling(encoder, connector, @@ -3061,19 +3001,10 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, "[CONNECTOR:%d:%s] Failed to configure sink scrambling/TMDS bit clock ratio\n", connector->base.id, connector->name); - if (IS_DG2(dev_priv)) - intel_snps_phy_ddi_vswing_sequence(encoder, crtc_state, level); - else if (DISPLAY_VER(dev_priv) >= 12) - tgl_ddi_vswing_sequence(encoder, crtc_state, level); - else if (DISPLAY_VER(dev_priv) == 11) - icl_ddi_vswing_sequence(encoder, crtc_state, level); - else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - bxt_ddi_vswing_sequence(encoder, crtc_state, level); - else - hsw_prepare_hdmi_ddi_buffers(encoder, crtc_state, level); + if (has_buf_trans_select(dev_priv)) + hsw_prepare_hdmi_ddi_buffers(encoder, crtc_state); - if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv)) - skl_ddi_set_iboost(encoder, crtc_state, level); + encoder->set_signal_levels(encoder, crtc_state); /* Display WA #1143: skl,kbl,cfl */ if (DISPLAY_VER(dev_priv) == 9 && !IS_BROXTON(dev_priv)) { @@ -3138,7 +3069,7 @@ static void intel_enable_ddi(struct intel_atomic_state *state, intel_vrr_enable(encoder, crtc_state); - intel_enable_pipe(crtc_state); + intel_enable_transcoder(crtc_state); intel_crtc_vblank_on(crtc_state); @@ -3231,7 +3162,6 @@ static void intel_ddi_update_pipe_dp(struct intel_atomic_state *state, intel_ddi_set_dp_msa(crtc_state, conn_state); - intel_psr_update(intel_dp, crtc_state, conn_state); intel_dp_set_infoframes(encoder, true, crtc_state, conn_state); intel_drrs_update(intel_dp, crtc_state); @@ -3298,7 +3228,7 @@ intel_ddi_pre_pll_enable(struct intel_atomic_state *state, intel_ddi_main_link_aux_domain(dig_port)); } - if (is_tc_port && dig_port->tc_mode != TC_PORT_TBT_ALT) + if (is_tc_port && !intel_tc_port_in_tbt_alt_mode(dig_port)) /* * Program the lane count for static/dynamic connections on * Type-C ports. Skip this step for TBT. @@ -3558,9 +3488,6 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, pipe_config->output_types |= BIT(INTEL_OUTPUT_HDMI); pipe_config->lane_count = 4; break; - case TRANS_DDI_MODE_SELECT_FDI: - pipe_config->output_types |= BIT(INTEL_OUTPUT_ANALOG); - break; case TRANS_DDI_MODE_SELECT_DP_SST: if (encoder->type == INTEL_OUTPUT_EDP) pipe_config->output_types |= BIT(INTEL_OUTPUT_EDP); @@ -3589,6 +3516,13 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, pipe_config->infoframes.enable |= intel_hdmi_infoframes_enabled(encoder, pipe_config); break; + case TRANS_DDI_MODE_SELECT_FDI_OR_128B132B: + if (!HAS_DP20(dev_priv)) { + /* FDI */ + pipe_config->output_types |= BIT(INTEL_OUTPUT_ANALOG); + break; + } + fallthrough; /* 128b/132b */ case TRANS_DDI_MODE_SELECT_DP_MST: pipe_config->output_types |= BIT(INTEL_OUTPUT_DP_MST); pipe_config->lane_count = @@ -4000,13 +3934,15 @@ static void intel_ddi_encoder_destroy(struct drm_encoder *encoder) { struct drm_i915_private *i915 = to_i915(encoder->dev); struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder)); + enum phy phy = intel_port_to_phy(i915, dig_port->base.port); intel_dp_encoder_flush_work(encoder); + if (intel_phy_is_tc(i915, phy)) + intel_tc_port_flush_work(dig_port); intel_display_power_flush_work(i915); drm_encoder_cleanup(encoder); - if (dig_port) - kfree(dig_port->hdcp_port_data.streams); + kfree(dig_port->hdcp_port_data.streams); kfree(dig_port); } @@ -4027,7 +3963,6 @@ static const struct drm_encoder_funcs intel_ddi_funcs = { static struct intel_connector * intel_ddi_init_dp_connector(struct intel_digital_port *dig_port) { - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); struct intel_connector *connector; enum port port = dig_port->base.port; @@ -4040,17 +3975,6 @@ intel_ddi_init_dp_connector(struct intel_digital_port *dig_port) dig_port->dp.set_link_train = intel_ddi_set_link_train; dig_port->dp.set_idle_link_train = intel_ddi_set_idle_link_train; - if (IS_DG2(dev_priv)) - dig_port->dp.set_signal_levels = dg2_set_signal_levels; - else if (DISPLAY_VER(dev_priv) >= 12) - dig_port->dp.set_signal_levels = tgl_set_signal_levels; - else if (DISPLAY_VER(dev_priv) >= 11) - dig_port->dp.set_signal_levels = icl_set_signal_levels; - else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - dig_port->dp.set_signal_levels = bxt_set_signal_levels; - else - dig_port->dp.set_signal_levels = hsw_set_signal_levels; - dig_port->dp.voltage_max = intel_ddi_dp_voltage_max; dig_port->dp.preemph_max = intel_ddi_dp_preemph_max; @@ -4426,7 +4350,7 @@ static void intel_ddi_encoder_suspend(struct intel_encoder *encoder) if (!intel_phy_is_tc(i915, phy)) return; - intel_tc_port_disconnect_phy(dig_port); + intel_tc_port_flush_work(dig_port); } static void intel_ddi_encoder_shutdown(struct intel_encoder *encoder) @@ -4441,7 +4365,7 @@ static void intel_ddi_encoder_shutdown(struct intel_encoder *encoder) if (!intel_phy_is_tc(i915, phy)) return; - intel_tc_port_disconnect_phy(dig_port); + intel_tc_port_flush_work(dig_port); } #define port_tc_name(port) ((port) - PORT_TC1 + '1') @@ -4622,6 +4546,24 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) encoder->get_config = hsw_ddi_get_config; } + if (IS_DG2(dev_priv)) { + encoder->set_signal_levels = intel_snps_phy_set_signal_levels; + } else if (DISPLAY_VER(dev_priv) >= 12) { + if (intel_phy_is_combo(dev_priv, phy)) + encoder->set_signal_levels = icl_combo_phy_set_signal_levels; + else + encoder->set_signal_levels = tgl_dkl_phy_set_signal_levels; + } else if (DISPLAY_VER(dev_priv) >= 11) { + if (intel_phy_is_combo(dev_priv, phy)) + encoder->set_signal_levels = icl_combo_phy_set_signal_levels; + else + encoder->set_signal_levels = icl_mg_phy_set_signal_levels; + } else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) { + encoder->set_signal_levels = bxt_ddi_phy_set_signal_levels; + } else { + encoder->set_signal_levels = hsw_set_signal_levels; + } + intel_ddi_buf_trans_init(encoder); if (DISPLAY_VER(dev_priv) >= 13) diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h index 7d448485d887..d6971717ef9c 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.h +++ b/drivers/gpu/drm/i915/display/intel_ddi.h @@ -59,13 +59,12 @@ void intel_ddi_set_vc_payload_alloc(const struct intel_crtc_state *crtc_state, bool state); void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv, struct intel_crtc_state *crtc_state); -u32 bxt_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state); -u32 ddi_signal_levels(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state); int intel_ddi_toggle_hdcp_bits(struct intel_encoder *intel_encoder, enum transcoder cpu_transcoder, bool enable, u32 hdcp_mask); void intel_ddi_sanitize_encoder_pll_mapping(struct intel_encoder *encoder); +int intel_ddi_level(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + int lane); #endif /* __INTEL_DDI_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c index 796dd04eae01..78cd8f77b49d 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.c @@ -8,12 +8,13 @@ #include "intel_ddi_buf_trans.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dp.h" /* HDMI/DVI modes ignore everything but the last 2 items. So we share * them for both DP and FDI transports, allowing those ports to * automatically adapt to HDMI connections as well */ -static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _hsw_trans_dp[] = { { .hsw = { 0x00FFFFFF, 0x0006000E, 0x0 } }, { .hsw = { 0x00D75FFF, 0x0005000A, 0x0 } }, { .hsw = { 0x00C30FFF, 0x00040006, 0x0 } }, @@ -25,12 +26,12 @@ static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_dp[] = { { .hsw = { 0x80D75FFF, 0x000B0000, 0x0 } }, }; -static const struct intel_ddi_buf_trans hsw_ddi_translations_dp = { - .entries = _hsw_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_hsw_ddi_translations_dp), +static const struct intel_ddi_buf_trans hsw_trans_dp = { + .entries = _hsw_trans_dp, + .num_entries = ARRAY_SIZE(_hsw_trans_dp), }; -static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_fdi[] = { +static const union intel_ddi_buf_trans_entry _hsw_trans_fdi[] = { { .hsw = { 0x00FFFFFF, 0x0007000E, 0x0 } }, { .hsw = { 0x00D75FFF, 0x000F000A, 0x0 } }, { .hsw = { 0x00C30FFF, 0x00060006, 0x0 } }, @@ -42,12 +43,12 @@ static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_fdi[] = { { .hsw = { 0x00D75FFF, 0x001E0000, 0x0 } }, }; -static const struct intel_ddi_buf_trans hsw_ddi_translations_fdi = { - .entries = _hsw_ddi_translations_fdi, - .num_entries = ARRAY_SIZE(_hsw_ddi_translations_fdi), +static const struct intel_ddi_buf_trans hsw_trans_fdi = { + .entries = _hsw_trans_fdi, + .num_entries = ARRAY_SIZE(_hsw_trans_fdi), }; -static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _hsw_trans_hdmi[] = { /* Idx NT mV d T mV d db */ { .hsw = { 0x00FFFFFF, 0x0006000E, 0x0 } }, /* 0: 400 400 0 */ { .hsw = { 0x00E79FFF, 0x000E000C, 0x0 } }, /* 1: 400 500 2 */ @@ -63,13 +64,13 @@ static const union intel_ddi_buf_trans_entry _hsw_ddi_translations_hdmi[] = { { .hsw = { 0x80FFFFFF, 0x00030002, 0x0 } }, /* 11: 1000 1000 0 */ }; -static const struct intel_ddi_buf_trans hsw_ddi_translations_hdmi = { - .entries = _hsw_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_hsw_ddi_translations_hdmi), +static const struct intel_ddi_buf_trans hsw_trans_hdmi = { + .entries = _hsw_trans_hdmi, + .num_entries = ARRAY_SIZE(_hsw_trans_hdmi), .hdmi_default_entry = 6, }; -static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_edp[] = { +static const union intel_ddi_buf_trans_entry _bdw_trans_edp[] = { { .hsw = { 0x00FFFFFF, 0x00000012, 0x0 } }, { .hsw = { 0x00EBAFFF, 0x00020011, 0x0 } }, { .hsw = { 0x00C71FFF, 0x0006000F, 0x0 } }, @@ -81,12 +82,12 @@ static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_edp[] = { { .hsw = { 0x00DB6FFF, 0x000A000C, 0x0 } }, }; -static const struct intel_ddi_buf_trans bdw_ddi_translations_edp = { - .entries = _bdw_ddi_translations_edp, - .num_entries = ARRAY_SIZE(_bdw_ddi_translations_edp), +static const struct intel_ddi_buf_trans bdw_trans_edp = { + .entries = _bdw_trans_edp, + .num_entries = ARRAY_SIZE(_bdw_trans_edp), }; -static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _bdw_trans_dp[] = { { .hsw = { 0x00FFFFFF, 0x0007000E, 0x0 } }, { .hsw = { 0x00D75FFF, 0x000E000A, 0x0 } }, { .hsw = { 0x00BEFFFF, 0x00140006, 0x0 } }, @@ -98,12 +99,12 @@ static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_dp[] = { { .hsw = { 0x80D75FFF, 0x001B0002, 0x0 } }, }; -static const struct intel_ddi_buf_trans bdw_ddi_translations_dp = { - .entries = _bdw_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_bdw_ddi_translations_dp), +static const struct intel_ddi_buf_trans bdw_trans_dp = { + .entries = _bdw_trans_dp, + .num_entries = ARRAY_SIZE(_bdw_trans_dp), }; -static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_fdi[] = { +static const union intel_ddi_buf_trans_entry _bdw_trans_fdi[] = { { .hsw = { 0x00FFFFFF, 0x0001000E, 0x0 } }, { .hsw = { 0x00D75FFF, 0x0004000A, 0x0 } }, { .hsw = { 0x00C30FFF, 0x00070006, 0x0 } }, @@ -115,12 +116,12 @@ static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_fdi[] = { { .hsw = { 0x00D75FFF, 0x000C0000, 0x0 } }, }; -static const struct intel_ddi_buf_trans bdw_ddi_translations_fdi = { - .entries = _bdw_ddi_translations_fdi, - .num_entries = ARRAY_SIZE(_bdw_ddi_translations_fdi), +static const struct intel_ddi_buf_trans bdw_trans_fdi = { + .entries = _bdw_trans_fdi, + .num_entries = ARRAY_SIZE(_bdw_trans_fdi), }; -static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _bdw_trans_hdmi[] = { /* Idx NT mV d T mV df db */ { .hsw = { 0x00FFFFFF, 0x0007000E, 0x0 } }, /* 0: 400 400 0 */ { .hsw = { 0x00D75FFF, 0x000E000A, 0x0 } }, /* 1: 400 600 3.5 */ @@ -134,14 +135,14 @@ static const union intel_ddi_buf_trans_entry _bdw_ddi_translations_hdmi[] = { { .hsw = { 0x80FFFFFF, 0x001B0002, 0x0 } }, /* 9: 1000 1000 0 */ }; -static const struct intel_ddi_buf_trans bdw_ddi_translations_hdmi = { - .entries = _bdw_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_bdw_ddi_translations_hdmi), +static const struct intel_ddi_buf_trans bdw_trans_hdmi = { + .entries = _bdw_trans_hdmi, + .num_entries = ARRAY_SIZE(_bdw_trans_hdmi), .hdmi_default_entry = 7, }; /* Skylake H and S */ -static const union intel_ddi_buf_trans_entry _skl_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _skl_trans_dp[] = { { .hsw = { 0x00002016, 0x000000A0, 0x0 } }, { .hsw = { 0x00005012, 0x0000009B, 0x0 } }, { .hsw = { 0x00007011, 0x00000088, 0x0 } }, @@ -153,13 +154,13 @@ static const union intel_ddi_buf_trans_entry _skl_ddi_translations_dp[] = { { .hsw = { 0x80005012, 0x000000C0, 0x1 } }, }; -static const struct intel_ddi_buf_trans skl_ddi_translations_dp = { - .entries = _skl_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_skl_ddi_translations_dp), +static const struct intel_ddi_buf_trans skl_trans_dp = { + .entries = _skl_trans_dp, + .num_entries = ARRAY_SIZE(_skl_trans_dp), }; /* Skylake U */ -static const union intel_ddi_buf_trans_entry _skl_u_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _skl_u_trans_dp[] = { { .hsw = { 0x0000201B, 0x000000A2, 0x0 } }, { .hsw = { 0x00005012, 0x00000088, 0x0 } }, { .hsw = { 0x80007011, 0x000000CD, 0x1 } }, @@ -171,13 +172,13 @@ static const union intel_ddi_buf_trans_entry _skl_u_ddi_translations_dp[] = { { .hsw = { 0x80005012, 0x000000C0, 0x1 } }, }; -static const struct intel_ddi_buf_trans skl_u_ddi_translations_dp = { - .entries = _skl_u_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_skl_u_ddi_translations_dp), +static const struct intel_ddi_buf_trans skl_u_trans_dp = { + .entries = _skl_u_trans_dp, + .num_entries = ARRAY_SIZE(_skl_u_trans_dp), }; /* Skylake Y */ -static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _skl_y_trans_dp[] = { { .hsw = { 0x00000018, 0x000000A2, 0x0 } }, { .hsw = { 0x00005012, 0x00000088, 0x0 } }, { .hsw = { 0x80007011, 0x000000CD, 0x3 } }, @@ -189,13 +190,13 @@ static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_dp[] = { { .hsw = { 0x80005012, 0x000000C0, 0x3 } }, }; -static const struct intel_ddi_buf_trans skl_y_ddi_translations_dp = { - .entries = _skl_y_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_skl_y_ddi_translations_dp), +static const struct intel_ddi_buf_trans skl_y_trans_dp = { + .entries = _skl_y_trans_dp, + .num_entries = ARRAY_SIZE(_skl_y_trans_dp), }; /* Kabylake H and S */ -static const union intel_ddi_buf_trans_entry _kbl_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _kbl_trans_dp[] = { { .hsw = { 0x00002016, 0x000000A0, 0x0 } }, { .hsw = { 0x00005012, 0x0000009B, 0x0 } }, { .hsw = { 0x00007011, 0x00000088, 0x0 } }, @@ -207,13 +208,13 @@ static const union intel_ddi_buf_trans_entry _kbl_ddi_translations_dp[] = { { .hsw = { 0x80005012, 0x000000C0, 0x1 } }, }; -static const struct intel_ddi_buf_trans kbl_ddi_translations_dp = { - .entries = _kbl_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_kbl_ddi_translations_dp), +static const struct intel_ddi_buf_trans kbl_trans_dp = { + .entries = _kbl_trans_dp, + .num_entries = ARRAY_SIZE(_kbl_trans_dp), }; /* Kabylake U */ -static const union intel_ddi_buf_trans_entry _kbl_u_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _kbl_u_trans_dp[] = { { .hsw = { 0x0000201B, 0x000000A1, 0x0 } }, { .hsw = { 0x00005012, 0x00000088, 0x0 } }, { .hsw = { 0x80007011, 0x000000CD, 0x3 } }, @@ -225,13 +226,13 @@ static const union intel_ddi_buf_trans_entry _kbl_u_ddi_translations_dp[] = { { .hsw = { 0x80005012, 0x000000C0, 0x3 } }, }; -static const struct intel_ddi_buf_trans kbl_u_ddi_translations_dp = { - .entries = _kbl_u_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_kbl_u_ddi_translations_dp), +static const struct intel_ddi_buf_trans kbl_u_trans_dp = { + .entries = _kbl_u_trans_dp, + .num_entries = ARRAY_SIZE(_kbl_u_trans_dp), }; /* Kabylake Y */ -static const union intel_ddi_buf_trans_entry _kbl_y_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _kbl_y_trans_dp[] = { { .hsw = { 0x00001017, 0x000000A1, 0x0 } }, { .hsw = { 0x00005012, 0x00000088, 0x0 } }, { .hsw = { 0x80007011, 0x000000CD, 0x3 } }, @@ -243,16 +244,16 @@ static const union intel_ddi_buf_trans_entry _kbl_y_ddi_translations_dp[] = { { .hsw = { 0x80005012, 0x000000C0, 0x3 } }, }; -static const struct intel_ddi_buf_trans kbl_y_ddi_translations_dp = { - .entries = _kbl_y_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_kbl_y_ddi_translations_dp), +static const struct intel_ddi_buf_trans kbl_y_trans_dp = { + .entries = _kbl_y_trans_dp, + .num_entries = ARRAY_SIZE(_kbl_y_trans_dp), }; /* * Skylake/Kabylake H and S * eDP 1.4 low vswing translation parameters */ -static const union intel_ddi_buf_trans_entry _skl_ddi_translations_edp[] = { +static const union intel_ddi_buf_trans_entry _skl_trans_edp[] = { { .hsw = { 0x00000018, 0x000000A8, 0x0 } }, { .hsw = { 0x00004013, 0x000000A9, 0x0 } }, { .hsw = { 0x00007011, 0x000000A2, 0x0 } }, @@ -265,16 +266,16 @@ static const union intel_ddi_buf_trans_entry _skl_ddi_translations_edp[] = { { .hsw = { 0x00000018, 0x000000DF, 0x0 } }, }; -static const struct intel_ddi_buf_trans skl_ddi_translations_edp = { - .entries = _skl_ddi_translations_edp, - .num_entries = ARRAY_SIZE(_skl_ddi_translations_edp), +static const struct intel_ddi_buf_trans skl_trans_edp = { + .entries = _skl_trans_edp, + .num_entries = ARRAY_SIZE(_skl_trans_edp), }; /* * Skylake/Kabylake U * eDP 1.4 low vswing translation parameters */ -static const union intel_ddi_buf_trans_entry _skl_u_ddi_translations_edp[] = { +static const union intel_ddi_buf_trans_entry _skl_u_trans_edp[] = { { .hsw = { 0x00000018, 0x000000A8, 0x0 } }, { .hsw = { 0x00004013, 0x000000A9, 0x0 } }, { .hsw = { 0x00007011, 0x000000A2, 0x0 } }, @@ -287,16 +288,16 @@ static const union intel_ddi_buf_trans_entry _skl_u_ddi_translations_edp[] = { { .hsw = { 0x00000018, 0x000000DF, 0x0 } }, }; -static const struct intel_ddi_buf_trans skl_u_ddi_translations_edp = { - .entries = _skl_u_ddi_translations_edp, - .num_entries = ARRAY_SIZE(_skl_u_ddi_translations_edp), +static const struct intel_ddi_buf_trans skl_u_trans_edp = { + .entries = _skl_u_trans_edp, + .num_entries = ARRAY_SIZE(_skl_u_trans_edp), }; /* * Skylake/Kabylake Y * eDP 1.4 low vswing translation parameters */ -static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_edp[] = { +static const union intel_ddi_buf_trans_entry _skl_y_trans_edp[] = { { .hsw = { 0x00000018, 0x000000A8, 0x0 } }, { .hsw = { 0x00004013, 0x000000AB, 0x0 } }, { .hsw = { 0x00007011, 0x000000A4, 0x0 } }, @@ -309,13 +310,13 @@ static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_edp[] = { { .hsw = { 0x00000018, 0x0000008A, 0x0 } }, }; -static const struct intel_ddi_buf_trans skl_y_ddi_translations_edp = { - .entries = _skl_y_ddi_translations_edp, - .num_entries = ARRAY_SIZE(_skl_y_ddi_translations_edp), +static const struct intel_ddi_buf_trans skl_y_trans_edp = { + .entries = _skl_y_trans_edp, + .num_entries = ARRAY_SIZE(_skl_y_trans_edp), }; /* Skylake/Kabylake U, H and S */ -static const union intel_ddi_buf_trans_entry _skl_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _skl_trans_hdmi[] = { { .hsw = { 0x00000018, 0x000000AC, 0x0 } }, { .hsw = { 0x00005012, 0x0000009D, 0x0 } }, { .hsw = { 0x00007011, 0x00000088, 0x0 } }, @@ -329,14 +330,14 @@ static const union intel_ddi_buf_trans_entry _skl_ddi_translations_hdmi[] = { { .hsw = { 0x80000018, 0x000000C0, 0x1 } }, }; -static const struct intel_ddi_buf_trans skl_ddi_translations_hdmi = { - .entries = _skl_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_skl_ddi_translations_hdmi), +static const struct intel_ddi_buf_trans skl_trans_hdmi = { + .entries = _skl_trans_hdmi, + .num_entries = ARRAY_SIZE(_skl_trans_hdmi), .hdmi_default_entry = 8, }; /* Skylake/Kabylake Y */ -static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _skl_y_trans_hdmi[] = { { .hsw = { 0x00000018, 0x000000A1, 0x0 } }, { .hsw = { 0x00005012, 0x000000DF, 0x0 } }, { .hsw = { 0x80007011, 0x000000CB, 0x3 } }, @@ -350,13 +351,13 @@ static const union intel_ddi_buf_trans_entry _skl_y_ddi_translations_hdmi[] = { { .hsw = { 0x80000018, 0x000000C0, 0x3 } }, }; -static const struct intel_ddi_buf_trans skl_y_ddi_translations_hdmi = { - .entries = _skl_y_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_skl_y_ddi_translations_hdmi), +static const struct intel_ddi_buf_trans skl_y_trans_hdmi = { + .entries = _skl_y_trans_hdmi, + .num_entries = ARRAY_SIZE(_skl_y_trans_hdmi), .hdmi_default_entry = 8, }; -static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _bxt_trans_dp[] = { /* Idx NT mV diff db */ { .bxt = { 52, 0x9A, 0, 128, } }, /* 0: 400 0 */ { .bxt = { 78, 0x9A, 0, 85, } }, /* 1: 400 3.5 */ @@ -370,12 +371,12 @@ static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_dp[] = { { .bxt = { 154, 0x9A, 1, 128, } }, /* 9: 1200 0 */ }; -static const struct intel_ddi_buf_trans bxt_ddi_translations_dp = { - .entries = _bxt_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_bxt_ddi_translations_dp), +static const struct intel_ddi_buf_trans bxt_trans_dp = { + .entries = _bxt_trans_dp, + .num_entries = ARRAY_SIZE(_bxt_trans_dp), }; -static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_edp[] = { +static const union intel_ddi_buf_trans_entry _bxt_trans_edp[] = { /* Idx NT mV diff db */ { .bxt = { 26, 0, 0, 128, } }, /* 0: 200 0 */ { .bxt = { 38, 0, 0, 112, } }, /* 1: 200 1.5 */ @@ -389,15 +390,15 @@ static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_edp[] = { { .bxt = { 48, 0, 0, 128, } }, /* 9: 300 0 */ }; -static const struct intel_ddi_buf_trans bxt_ddi_translations_edp = { - .entries = _bxt_ddi_translations_edp, - .num_entries = ARRAY_SIZE(_bxt_ddi_translations_edp), +static const struct intel_ddi_buf_trans bxt_trans_edp = { + .entries = _bxt_trans_edp, + .num_entries = ARRAY_SIZE(_bxt_trans_edp), }; /* BSpec has 2 recommended values - entries 0 and 8. * Using the entry with higher vswing. */ -static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _bxt_trans_hdmi[] = { /* Idx NT mV diff db */ { .bxt = { 52, 0x9A, 0, 128, } }, /* 0: 400 0 */ { .bxt = { 52, 0x9A, 0, 85, } }, /* 1: 400 3.5 */ @@ -411,14 +412,14 @@ static const union intel_ddi_buf_trans_entry _bxt_ddi_translations_hdmi[] = { { .bxt = { 154, 0x9A, 1, 128, } }, /* 9: 1200 0 */ }; -static const struct intel_ddi_buf_trans bxt_ddi_translations_hdmi = { - .entries = _bxt_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_bxt_ddi_translations_hdmi), - .hdmi_default_entry = ARRAY_SIZE(_bxt_ddi_translations_hdmi) - 1, +static const struct intel_ddi_buf_trans bxt_trans_hdmi = { + .entries = _bxt_trans_hdmi, + .num_entries = ARRAY_SIZE(_bxt_trans_hdmi), + .hdmi_default_entry = ARRAY_SIZE(_bxt_trans_hdmi) - 1, }; -/* icl_combo_phy_ddi_translations */ -static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3[] = { +/* icl_combo_phy_trans */ +static const union intel_ddi_buf_trans_entry _icl_combo_phy_trans_dp_hbr2_edp_hbr3[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -432,12 +433,12 @@ static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3 = { - .entries = _icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, - .num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3), +static const struct intel_ddi_buf_trans icl_combo_phy_trans_dp_hbr2_edp_hbr3 = { + .entries = _icl_combo_phy_trans_dp_hbr2_edp_hbr3, + .num_entries = ARRAY_SIZE(_icl_combo_phy_trans_dp_hbr2_edp_hbr3), }; -static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_edp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _icl_combo_phy_trans_edp_hbr2[] = { /* NT mV Trans mV db */ { .icl = { 0x0, 0x7F, 0x3F, 0x00, 0x00 } }, /* 200 200 0.0 */ { .icl = { 0x8, 0x7F, 0x38, 0x00, 0x07 } }, /* 200 250 1.9 */ @@ -451,12 +452,12 @@ static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_edp { .icl = { 0x9, 0x7F, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ }; -static const struct intel_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2 = { - .entries = _icl_combo_phy_ddi_translations_edp_hbr2, - .num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_edp_hbr2), +static const struct intel_ddi_buf_trans icl_combo_phy_trans_edp_hbr2 = { + .entries = _icl_combo_phy_trans_edp_hbr2, + .num_entries = ARRAY_SIZE(_icl_combo_phy_trans_edp_hbr2), }; -static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _icl_combo_phy_trans_hdmi[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x60, 0x3F, 0x00, 0x00 } }, /* 450 450 0.0 */ { .icl = { 0xB, 0x73, 0x36, 0x00, 0x09 } }, /* 450 650 3.2 */ @@ -467,13 +468,13 @@ static const union intel_ddi_buf_trans_entry _icl_combo_phy_ddi_translations_hdm { .icl = { 0x6, 0x7F, 0x35, 0x00, 0x0A } }, /* 600 850 3.0 */ }; -static const struct intel_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi = { - .entries = _icl_combo_phy_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_hdmi), - .hdmi_default_entry = ARRAY_SIZE(_icl_combo_phy_ddi_translations_hdmi) - 1, +static const struct intel_ddi_buf_trans icl_combo_phy_trans_hdmi = { + .entries = _icl_combo_phy_trans_hdmi, + .num_entries = ARRAY_SIZE(_icl_combo_phy_trans_hdmi), + .hdmi_default_entry = ARRAY_SIZE(_icl_combo_phy_trans_hdmi) - 1, }; -static const union intel_ddi_buf_trans_entry _ehl_combo_phy_ddi_translations_dp[] = { +static const union intel_ddi_buf_trans_entry _ehl_combo_phy_trans_dp[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x33, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x47, 0x36, 0x00, 0x09 } }, /* 350 500 3.1 */ @@ -487,12 +488,12 @@ static const union intel_ddi_buf_trans_entry _ehl_combo_phy_ddi_translations_dp[ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans ehl_combo_phy_ddi_translations_dp = { - .entries = _ehl_combo_phy_ddi_translations_dp, - .num_entries = ARRAY_SIZE(_ehl_combo_phy_ddi_translations_dp), +static const struct intel_ddi_buf_trans ehl_combo_phy_trans_dp = { + .entries = _ehl_combo_phy_trans_dp, + .num_entries = ARRAY_SIZE(_ehl_combo_phy_trans_dp), }; -static const union intel_ddi_buf_trans_entry _ehl_combo_phy_ddi_translations_edp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _ehl_combo_phy_trans_edp_hbr2[] = { /* NT mV Trans mV db */ { .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } }, /* 200 200 0.0 */ { .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } }, /* 200 250 1.9 */ @@ -506,12 +507,12 @@ static const union intel_ddi_buf_trans_entry _ehl_combo_phy_ddi_translations_edp { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ }; -static const struct intel_ddi_buf_trans ehl_combo_phy_ddi_translations_edp_hbr2 = { - .entries = _ehl_combo_phy_ddi_translations_edp_hbr2, - .num_entries = ARRAY_SIZE(_ehl_combo_phy_ddi_translations_edp_hbr2), +static const struct intel_ddi_buf_trans ehl_combo_phy_trans_edp_hbr2 = { + .entries = _ehl_combo_phy_trans_edp_hbr2, + .num_entries = ARRAY_SIZE(_ehl_combo_phy_trans_edp_hbr2), }; -static const union intel_ddi_buf_trans_entry _jsl_combo_phy_ddi_translations_edp_hbr[] = { +static const union intel_ddi_buf_trans_entry _jsl_combo_phy_trans_edp_hbr[] = { /* NT mV Trans mV db */ { .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } }, /* 200 200 0.0 */ { .icl = { 0x8, 0x7F, 0x38, 0x00, 0x07 } }, /* 200 250 1.9 */ @@ -525,12 +526,12 @@ static const union intel_ddi_buf_trans_entry _jsl_combo_phy_ddi_translations_edp { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ }; -static const struct intel_ddi_buf_trans jsl_combo_phy_ddi_translations_edp_hbr = { - .entries = _jsl_combo_phy_ddi_translations_edp_hbr, - .num_entries = ARRAY_SIZE(_jsl_combo_phy_ddi_translations_edp_hbr), +static const struct intel_ddi_buf_trans jsl_combo_phy_trans_edp_hbr = { + .entries = _jsl_combo_phy_trans_edp_hbr, + .num_entries = ARRAY_SIZE(_jsl_combo_phy_trans_edp_hbr), }; -static const union intel_ddi_buf_trans_entry _jsl_combo_phy_ddi_translations_edp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _jsl_combo_phy_trans_edp_hbr2[] = { /* NT mV Trans mV db */ { .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } }, /* 200 200 0.0 */ { .icl = { 0x8, 0x7F, 0x3F, 0x00, 0x00 } }, /* 200 250 1.9 */ @@ -544,12 +545,12 @@ static const union intel_ddi_buf_trans_entry _jsl_combo_phy_ddi_translations_edp { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ }; -static const struct intel_ddi_buf_trans jsl_combo_phy_ddi_translations_edp_hbr2 = { - .entries = _jsl_combo_phy_ddi_translations_edp_hbr2, - .num_entries = ARRAY_SIZE(_jsl_combo_phy_ddi_translations_edp_hbr2), +static const struct intel_ddi_buf_trans jsl_combo_phy_trans_edp_hbr2 = { + .entries = _jsl_combo_phy_trans_edp_hbr2, + .num_entries = ARRAY_SIZE(_jsl_combo_phy_trans_edp_hbr2), }; -static const union intel_ddi_buf_trans_entry _dg1_combo_phy_ddi_translations_dp_rbr_hbr[] = { +static const union intel_ddi_buf_trans_entry _dg1_combo_phy_trans_dp_rbr_hbr[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x32, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x48, 0x35, 0x00, 0x0A } }, /* 350 500 3.1 */ @@ -563,12 +564,12 @@ static const union intel_ddi_buf_trans_entry _dg1_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans dg1_combo_phy_ddi_translations_dp_rbr_hbr = { - .entries = _dg1_combo_phy_ddi_translations_dp_rbr_hbr, - .num_entries = ARRAY_SIZE(_dg1_combo_phy_ddi_translations_dp_rbr_hbr), +static const struct intel_ddi_buf_trans dg1_combo_phy_trans_dp_rbr_hbr = { + .entries = _dg1_combo_phy_trans_dp_rbr_hbr, + .num_entries = ARRAY_SIZE(_dg1_combo_phy_trans_dp_rbr_hbr), }; -static const union intel_ddi_buf_trans_entry _dg1_combo_phy_ddi_translations_dp_hbr2_hbr3[] = { +static const union intel_ddi_buf_trans_entry _dg1_combo_phy_trans_dp_hbr2_hbr3[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x32, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x48, 0x35, 0x00, 0x0A } }, /* 350 500 3.1 */ @@ -582,12 +583,12 @@ static const union intel_ddi_buf_trans_entry _dg1_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans dg1_combo_phy_ddi_translations_dp_hbr2_hbr3 = { - .entries = _dg1_combo_phy_ddi_translations_dp_hbr2_hbr3, - .num_entries = ARRAY_SIZE(_dg1_combo_phy_ddi_translations_dp_hbr2_hbr3), +static const struct intel_ddi_buf_trans dg1_combo_phy_trans_dp_hbr2_hbr3 = { + .entries = _dg1_combo_phy_trans_dp_hbr2_hbr3, + .num_entries = ARRAY_SIZE(_dg1_combo_phy_trans_dp_hbr2_hbr3), }; -static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_rbr_hbr[] = { +static const union intel_ddi_buf_trans_entry _icl_mg_phy_trans_rbr_hbr[] = { /* Voltage swing pre-emphasis */ { .mg = { 0x18, 0x00, 0x00 } }, /* 0 0 */ { .mg = { 0x1D, 0x00, 0x05 } }, /* 0 1 */ @@ -601,12 +602,12 @@ static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_rbr_hb { .mg = { 0x3F, 0x00, 0x00 } }, /* 3 0 */ }; -static const struct intel_ddi_buf_trans icl_mg_phy_ddi_translations_rbr_hbr = { - .entries = _icl_mg_phy_ddi_translations_rbr_hbr, - .num_entries = ARRAY_SIZE(_icl_mg_phy_ddi_translations_rbr_hbr), +static const struct intel_ddi_buf_trans icl_mg_phy_trans_rbr_hbr = { + .entries = _icl_mg_phy_trans_rbr_hbr, + .num_entries = ARRAY_SIZE(_icl_mg_phy_trans_rbr_hbr), }; -static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_hbr2_hbr3[] = { +static const union intel_ddi_buf_trans_entry _icl_mg_phy_trans_hbr2_hbr3[] = { /* Voltage swing pre-emphasis */ { .mg = { 0x18, 0x00, 0x00 } }, /* 0 0 */ { .mg = { 0x1D, 0x00, 0x05 } }, /* 0 1 */ @@ -620,12 +621,12 @@ static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_hbr2_h { .mg = { 0x3F, 0x00, 0x00 } }, /* 3 0 */ }; -static const struct intel_ddi_buf_trans icl_mg_phy_ddi_translations_hbr2_hbr3 = { - .entries = _icl_mg_phy_ddi_translations_hbr2_hbr3, - .num_entries = ARRAY_SIZE(_icl_mg_phy_ddi_translations_hbr2_hbr3), +static const struct intel_ddi_buf_trans icl_mg_phy_trans_hbr2_hbr3 = { + .entries = _icl_mg_phy_trans_hbr2_hbr3, + .num_entries = ARRAY_SIZE(_icl_mg_phy_trans_hbr2_hbr3), }; -static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _icl_mg_phy_trans_hdmi[] = { /* HDMI Preset VS Pre-emph */ { .mg = { 0x1A, 0x0, 0x0 } }, /* 1 400mV 0dB */ { .mg = { 0x20, 0x0, 0x0 } }, /* 2 500mV 0dB */ @@ -639,13 +640,13 @@ static const union intel_ddi_buf_trans_entry _icl_mg_phy_ddi_translations_hdmi[] { .mg = { 0x36, 0x0, 0x9 } }, /* 10 Full -3 dB */ }; -static const struct intel_ddi_buf_trans icl_mg_phy_ddi_translations_hdmi = { - .entries = _icl_mg_phy_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_icl_mg_phy_ddi_translations_hdmi), - .hdmi_default_entry = ARRAY_SIZE(_icl_mg_phy_ddi_translations_hdmi) - 1, +static const struct intel_ddi_buf_trans icl_mg_phy_trans_hdmi = { + .entries = _icl_mg_phy_trans_hdmi, + .num_entries = ARRAY_SIZE(_icl_mg_phy_trans_hdmi), + .hdmi_default_entry = ARRAY_SIZE(_icl_mg_phy_trans_hdmi) - 1, }; -static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_dp_hbr[] = { +static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_trans_dp_hbr[] = { /* VS pre-emp Non-trans mV Pre-emph dB */ { .dkl = { 0x7, 0x0, 0x00 } }, /* 0 0 400mV 0 dB */ { .dkl = { 0x5, 0x0, 0x05 } }, /* 0 1 400mV 3.5 dB */ @@ -659,12 +660,12 @@ static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_dp_hb { .dkl = { 0x0, 0x0, 0x00 } }, /* 3 0 1200mV 0 dB HDMI default */ }; -static const struct intel_ddi_buf_trans tgl_dkl_phy_ddi_translations_dp_hbr = { - .entries = _tgl_dkl_phy_ddi_translations_dp_hbr, - .num_entries = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_dp_hbr), +static const struct intel_ddi_buf_trans tgl_dkl_phy_trans_dp_hbr = { + .entries = _tgl_dkl_phy_trans_dp_hbr, + .num_entries = ARRAY_SIZE(_tgl_dkl_phy_trans_dp_hbr), }; -static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_dp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_trans_dp_hbr2[] = { /* VS pre-emp Non-trans mV Pre-emph dB */ { .dkl = { 0x7, 0x0, 0x00 } }, /* 0 0 400mV 0 dB */ { .dkl = { 0x5, 0x0, 0x05 } }, /* 0 1 400mV 3.5 dB */ @@ -678,12 +679,12 @@ static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_dp_hb { .dkl = { 0x0, 0x0, 0x00 } }, /* 3 0 1200mV 0 dB HDMI default */ }; -static const struct intel_ddi_buf_trans tgl_dkl_phy_ddi_translations_dp_hbr2 = { - .entries = _tgl_dkl_phy_ddi_translations_dp_hbr2, - .num_entries = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_dp_hbr2), +static const struct intel_ddi_buf_trans tgl_dkl_phy_trans_dp_hbr2 = { + .entries = _tgl_dkl_phy_trans_dp_hbr2, + .num_entries = ARRAY_SIZE(_tgl_dkl_phy_trans_dp_hbr2), }; -static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_trans_hdmi[] = { /* HDMI Preset VS Pre-emph */ { .dkl = { 0x7, 0x0, 0x0 } }, /* 1 400mV 0dB */ { .dkl = { 0x6, 0x0, 0x0 } }, /* 2 500mV 0dB */ @@ -697,13 +698,13 @@ static const union intel_ddi_buf_trans_entry _tgl_dkl_phy_ddi_translations_hdmi[ { .dkl = { 0x0, 0x0, 0xA } }, /* 10 Full -3 dB */ }; -static const struct intel_ddi_buf_trans tgl_dkl_phy_ddi_translations_hdmi = { - .entries = _tgl_dkl_phy_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_hdmi), - .hdmi_default_entry = ARRAY_SIZE(_tgl_dkl_phy_ddi_translations_hdmi) - 1, +static const struct intel_ddi_buf_trans tgl_dkl_phy_trans_hdmi = { + .entries = _tgl_dkl_phy_trans_hdmi, + .num_entries = ARRAY_SIZE(_tgl_dkl_phy_trans_hdmi), + .hdmi_default_entry = ARRAY_SIZE(_tgl_dkl_phy_trans_hdmi) - 1, }; -static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_dp_hbr[] = { +static const union intel_ddi_buf_trans_entry _tgl_combo_phy_trans_dp_hbr[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x32, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -717,12 +718,12 @@ static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr = { - .entries = _tgl_combo_phy_ddi_translations_dp_hbr, - .num_entries = ARRAY_SIZE(_tgl_combo_phy_ddi_translations_dp_hbr), +static const struct intel_ddi_buf_trans tgl_combo_phy_trans_dp_hbr = { + .entries = _tgl_combo_phy_trans_dp_hbr, + .num_entries = ARRAY_SIZE(_tgl_combo_phy_trans_dp_hbr), }; -static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_dp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _tgl_combo_phy_trans_dp_hbr2[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -736,12 +737,12 @@ static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans tgl_combo_phy_ddi_translations_dp_hbr2 = { - .entries = _tgl_combo_phy_ddi_translations_dp_hbr2, - .num_entries = ARRAY_SIZE(_tgl_combo_phy_ddi_translations_dp_hbr2), +static const struct intel_ddi_buf_trans tgl_combo_phy_trans_dp_hbr2 = { + .entries = _tgl_combo_phy_trans_dp_hbr2, + .num_entries = ARRAY_SIZE(_tgl_combo_phy_trans_dp_hbr2), }; -static const union intel_ddi_buf_trans_entry _tgl_uy_combo_phy_ddi_translations_dp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _tgl_uy_combo_phy_trans_dp_hbr2[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x36, 0x00, 0x09 } }, /* 350 500 3.1 */ @@ -755,16 +756,16 @@ static const union intel_ddi_buf_trans_entry _tgl_uy_combo_phy_ddi_translations_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans tgl_uy_combo_phy_ddi_translations_dp_hbr2 = { - .entries = _tgl_uy_combo_phy_ddi_translations_dp_hbr2, - .num_entries = ARRAY_SIZE(_tgl_uy_combo_phy_ddi_translations_dp_hbr2), +static const struct intel_ddi_buf_trans tgl_uy_combo_phy_trans_dp_hbr2 = { + .entries = _tgl_uy_combo_phy_trans_dp_hbr2, + .num_entries = ARRAY_SIZE(_tgl_uy_combo_phy_trans_dp_hbr2), }; /* * Cloned the HOBL entry to comply with the voltage and pre-emphasis entries * that DisplayPort specification requires */ -static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_edp_hbr2_hobl[] = { +static const union intel_ddi_buf_trans_entry _tgl_combo_phy_trans_edp_hbr2_hobl[] = { /* VS pre-emp */ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 0 0 */ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 0 1 */ @@ -777,12 +778,12 @@ static const union intel_ddi_buf_trans_entry _tgl_combo_phy_ddi_translations_edp { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 2 1 */ }; -static const struct intel_ddi_buf_trans tgl_combo_phy_ddi_translations_edp_hbr2_hobl = { - .entries = _tgl_combo_phy_ddi_translations_edp_hbr2_hobl, - .num_entries = ARRAY_SIZE(_tgl_combo_phy_ddi_translations_edp_hbr2_hobl), +static const struct intel_ddi_buf_trans tgl_combo_phy_trans_edp_hbr2_hobl = { + .entries = _tgl_combo_phy_trans_edp_hbr2_hobl, + .num_entries = ARRAY_SIZE(_tgl_combo_phy_trans_edp_hbr2_hobl), }; -static const union intel_ddi_buf_trans_entry _rkl_combo_phy_ddi_translations_dp_hbr[] = { +static const union intel_ddi_buf_trans_entry _rkl_combo_phy_trans_dp_hbr[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x2F, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -796,12 +797,12 @@ static const union intel_ddi_buf_trans_entry _rkl_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr = { - .entries = _rkl_combo_phy_ddi_translations_dp_hbr, - .num_entries = ARRAY_SIZE(_rkl_combo_phy_ddi_translations_dp_hbr), +static const struct intel_ddi_buf_trans rkl_combo_phy_trans_dp_hbr = { + .entries = _rkl_combo_phy_trans_dp_hbr, + .num_entries = ARRAY_SIZE(_rkl_combo_phy_trans_dp_hbr), }; -static const union intel_ddi_buf_trans_entry _rkl_combo_phy_ddi_translations_dp_hbr2_hbr3[] = { +static const union intel_ddi_buf_trans_entry _rkl_combo_phy_trans_dp_hbr2_hbr3[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x50, 0x38, 0x00, 0x07 } }, /* 350 500 3.1 */ @@ -815,12 +816,12 @@ static const union intel_ddi_buf_trans_entry _rkl_combo_phy_ddi_translations_dp_ { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans rkl_combo_phy_ddi_translations_dp_hbr2_hbr3 = { - .entries = _rkl_combo_phy_ddi_translations_dp_hbr2_hbr3, - .num_entries = ARRAY_SIZE(_rkl_combo_phy_ddi_translations_dp_hbr2_hbr3), +static const struct intel_ddi_buf_trans rkl_combo_phy_trans_dp_hbr2_hbr3 = { + .entries = _rkl_combo_phy_trans_dp_hbr2_hbr3, + .num_entries = ARRAY_SIZE(_rkl_combo_phy_trans_dp_hbr2_hbr3), }; -static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_dp_hbr2_hbr3[] = { +static const union intel_ddi_buf_trans_entry _adls_combo_phy_trans_dp_hbr2_hbr3[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -834,12 +835,12 @@ static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_dp { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans adls_combo_phy_ddi_translations_dp_hbr2_hbr3 = { - .entries = _adls_combo_phy_ddi_translations_dp_hbr2_hbr3, - .num_entries = ARRAY_SIZE(_adls_combo_phy_ddi_translations_dp_hbr2_hbr3), +static const struct intel_ddi_buf_trans adls_combo_phy_trans_dp_hbr2_hbr3 = { + .entries = _adls_combo_phy_trans_dp_hbr2_hbr3, + .num_entries = ARRAY_SIZE(_adls_combo_phy_trans_dp_hbr2_hbr3), }; -static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_edp_hbr2[] = { +static const union intel_ddi_buf_trans_entry _adls_combo_phy_trans_edp_hbr2[] = { /* NT mV Trans mV db */ { .icl = { 0x9, 0x73, 0x3D, 0x00, 0x02 } }, /* 200 200 0.0 */ { .icl = { 0x9, 0x7A, 0x3C, 0x00, 0x03 } }, /* 200 250 1.9 */ @@ -853,12 +854,12 @@ static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_ed { .icl = { 0x4, 0x6C, 0x3A, 0x00, 0x05 } }, /* 350 350 0.0 */ }; -static const struct intel_ddi_buf_trans adls_combo_phy_ddi_translations_edp_hbr2 = { - .entries = _adls_combo_phy_ddi_translations_edp_hbr2, - .num_entries = ARRAY_SIZE(_adls_combo_phy_ddi_translations_edp_hbr2), +static const struct intel_ddi_buf_trans adls_combo_phy_trans_edp_hbr2 = { + .entries = _adls_combo_phy_trans_edp_hbr2, + .num_entries = ARRAY_SIZE(_adls_combo_phy_trans_edp_hbr2), }; -static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_edp_hbr3[] = { +static const union intel_ddi_buf_trans_entry _adls_combo_phy_trans_edp_hbr3[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -872,12 +873,12 @@ static const union intel_ddi_buf_trans_entry _adls_combo_phy_ddi_translations_ed { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans adls_combo_phy_ddi_translations_edp_hbr3 = { - .entries = _adls_combo_phy_ddi_translations_edp_hbr3, - .num_entries = ARRAY_SIZE(_adls_combo_phy_ddi_translations_edp_hbr3), +static const struct intel_ddi_buf_trans adls_combo_phy_trans_edp_hbr3 = { + .entries = _adls_combo_phy_trans_edp_hbr3, + .num_entries = ARRAY_SIZE(_adls_combo_phy_trans_edp_hbr3), }; -static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_hdmi[] = { +static const union intel_ddi_buf_trans_entry _adlp_combo_phy_trans_hdmi[] = { /* NT mV Trans mV db */ { .icl = { 0x6, 0x60, 0x3F, 0x00, 0x00 } }, /* 400 400 0.0 */ { .icl = { 0x6, 0x68, 0x3F, 0x00, 0x00 } }, /* 500 500 0.0 */ @@ -891,13 +892,13 @@ static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_hd { .icl = { 0xB, 0x7F, 0x33, 0x00, 0x0C } }, /* Full Red -3.0 */ }; -static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_hdmi = { - .entries = _adlp_combo_phy_ddi_translations_hdmi, - .num_entries = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_hdmi), - .hdmi_default_entry = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_hdmi) - 1, +static const struct intel_ddi_buf_trans adlp_combo_phy_trans_hdmi = { + .entries = _adlp_combo_phy_trans_hdmi, + .num_entries = ARRAY_SIZE(_adlp_combo_phy_trans_hdmi), + .hdmi_default_entry = ARRAY_SIZE(_adlp_combo_phy_trans_hdmi) - 1, }; -static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_dp_hbr[] = { +static const union intel_ddi_buf_trans_entry _adlp_combo_phy_trans_dp_hbr[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -911,12 +912,12 @@ static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_dp { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_dp_hbr = { - .entries = _adlp_combo_phy_ddi_translations_dp_hbr, - .num_entries = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_dp_hbr), +static const struct intel_ddi_buf_trans adlp_combo_phy_trans_dp_hbr = { + .entries = _adlp_combo_phy_trans_dp_hbr, + .num_entries = ARRAY_SIZE(_adlp_combo_phy_trans_dp_hbr), }; -static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_dp_hbr2_hbr3[] = { +static const union intel_ddi_buf_trans_entry _adlp_combo_phy_trans_dp_hbr2_hbr3[] = { /* NT mV Trans mV db */ { .icl = { 0xA, 0x35, 0x3F, 0x00, 0x00 } }, /* 350 350 0.0 */ { .icl = { 0xA, 0x4F, 0x37, 0x00, 0x08 } }, /* 350 500 3.1 */ @@ -930,22 +931,22 @@ static const union intel_ddi_buf_trans_entry _adlp_combo_phy_ddi_translations_dp { .icl = { 0x6, 0x7F, 0x3F, 0x00, 0x00 } }, /* 900 900 0.0 */ }; -static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_dp_hbr2_hbr3 = { - .entries = _adlp_combo_phy_ddi_translations_dp_hbr2_hbr3, - .num_entries = ARRAY_SIZE(_adlp_combo_phy_ddi_translations_dp_hbr2_hbr3), +static const struct intel_ddi_buf_trans adlp_combo_phy_trans_dp_hbr2_hbr3 = { + .entries = _adlp_combo_phy_trans_dp_hbr2_hbr3, + .num_entries = ARRAY_SIZE(_adlp_combo_phy_trans_dp_hbr2_hbr3), }; -static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_edp_hbr3 = { - .entries = _icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, - .num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3), +static const struct intel_ddi_buf_trans adlp_combo_phy_trans_edp_hbr3 = { + .entries = _icl_combo_phy_trans_dp_hbr2_edp_hbr3, + .num_entries = ARRAY_SIZE(_icl_combo_phy_trans_dp_hbr2_edp_hbr3), }; -static const struct intel_ddi_buf_trans adlp_combo_phy_ddi_translations_edp_up_to_hbr2 = { - .entries = _icl_combo_phy_ddi_translations_edp_hbr2, - .num_entries = ARRAY_SIZE(_icl_combo_phy_ddi_translations_edp_hbr2), +static const struct intel_ddi_buf_trans adlp_combo_phy_trans_edp_up_to_hbr2 = { + .entries = _icl_combo_phy_trans_edp_hbr2, + .num_entries = ARRAY_SIZE(_icl_combo_phy_trans_edp_hbr2), }; -static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_ddi_translations_dp_hbr[] = { +static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_trans_dp_hbr[] = { /* VS pre-emp Non-trans mV Pre-emph dB */ { .dkl = { 0x7, 0x0, 0x01 } }, /* 0 0 400mV 0 dB */ { .dkl = { 0x5, 0x0, 0x06 } }, /* 0 1 400mV 3.5 dB */ @@ -959,12 +960,12 @@ static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_ddi_translations_dp_h { .dkl = { 0x0, 0x0, 0x00 } }, /* 3 0 1200mV 0 dB */ }; -static const struct intel_ddi_buf_trans adlp_dkl_phy_ddi_translations_dp_hbr = { - .entries = _adlp_dkl_phy_ddi_translations_dp_hbr, - .num_entries = ARRAY_SIZE(_adlp_dkl_phy_ddi_translations_dp_hbr), +static const struct intel_ddi_buf_trans adlp_dkl_phy_trans_dp_hbr = { + .entries = _adlp_dkl_phy_trans_dp_hbr, + .num_entries = ARRAY_SIZE(_adlp_dkl_phy_trans_dp_hbr), }; -static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3[] = { +static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_trans_dp_hbr2_hbr3[] = { /* VS pre-emp Non-trans mV Pre-emph dB */ { .dkl = { 0x7, 0x0, 0x00 } }, /* 0 0 400mV 0 dB */ { .dkl = { 0x5, 0x0, 0x04 } }, /* 0 1 400mV 3.5 dB */ @@ -978,12 +979,12 @@ static const union intel_ddi_buf_trans_entry _adlp_dkl_phy_ddi_translations_dp_h { .dkl = { 0x0, 0x0, 0x00 } }, /* 3 0 1200mV 0 dB */ }; -static const struct intel_ddi_buf_trans adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3 = { - .entries = _adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3, - .num_entries = ARRAY_SIZE(_adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3), +static const struct intel_ddi_buf_trans adlp_dkl_phy_trans_dp_hbr2_hbr3 = { + .entries = _adlp_dkl_phy_trans_dp_hbr2_hbr3, + .num_entries = ARRAY_SIZE(_adlp_dkl_phy_trans_dp_hbr2_hbr3), }; -static const union intel_ddi_buf_trans_entry _dg2_snps_translations[] = { +static const union intel_ddi_buf_trans_entry _dg2_snps_trans[] = { { .snps = { 26, 0, 0 } }, /* VS 0, pre-emph 0 */ { .snps = { 33, 0, 6 } }, /* VS 0, pre-emph 1 */ { .snps = { 38, 0, 12 } }, /* VS 0, pre-emph 2 */ @@ -996,13 +997,13 @@ static const union intel_ddi_buf_trans_entry _dg2_snps_translations[] = { { .snps = { 62, 0, 0 } }, /* VS 3, pre-emph 0 */ }; -static const struct intel_ddi_buf_trans dg2_snps_translations = { - .entries = _dg2_snps_translations, - .num_entries = ARRAY_SIZE(_dg2_snps_translations), - .hdmi_default_entry = ARRAY_SIZE(_dg2_snps_translations) - 1, +static const struct intel_ddi_buf_trans dg2_snps_trans = { + .entries = _dg2_snps_trans, + .num_entries = ARRAY_SIZE(_dg2_snps_trans), + .hdmi_default_entry = ARRAY_SIZE(_dg2_snps_trans) - 1, }; -static const union intel_ddi_buf_trans_entry _dg2_snps_translations_uhbr[] = { +static const union intel_ddi_buf_trans_entry _dg2_snps_trans_uhbr[] = { { .snps = { 62, 0, 0 } }, /* preset 0 */ { .snps = { 56, 0, 6 } }, /* preset 1 */ { .snps = { 51, 0, 11 } }, /* preset 2 */ @@ -1021,21 +1022,21 @@ static const union intel_ddi_buf_trans_entry _dg2_snps_translations_uhbr[] = { { .snps = { 56, 3, 3 } }, /* preset 15 */ }; -static const struct intel_ddi_buf_trans dg2_snps_translations_uhbr = { - .entries = _dg2_snps_translations_uhbr, - .num_entries = ARRAY_SIZE(_dg2_snps_translations_uhbr), +static const struct intel_ddi_buf_trans dg2_snps_trans_uhbr = { + .entries = _dg2_snps_trans_uhbr, + .num_entries = ARRAY_SIZE(_dg2_snps_trans_uhbr), }; bool is_hobl_buf_trans(const struct intel_ddi_buf_trans *table) { - return table == &tgl_combo_phy_ddi_translations_edp_hbr2_hobl; + return table == &tgl_combo_phy_trans_edp_hbr2_hobl; } static const struct intel_ddi_buf_trans * -intel_get_buf_trans(const struct intel_ddi_buf_trans *ddi_translations, int *num_entries) +intel_get_buf_trans(const struct intel_ddi_buf_trans *trans, int *num_entries) { - *num_entries = ddi_translations->num_entries; - return ddi_translations; + *num_entries = trans->num_entries; + return trans; } static const struct intel_ddi_buf_trans * @@ -1044,11 +1045,11 @@ hsw_get_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG)) - return intel_get_buf_trans(&hsw_ddi_translations_fdi, n_entries); + return intel_get_buf_trans(&hsw_trans_fdi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&hsw_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&hsw_trans_hdmi, n_entries); else - return intel_get_buf_trans(&hsw_ddi_translations_dp, n_entries); + return intel_get_buf_trans(&hsw_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1059,14 +1060,14 @@ bdw_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG)) - return intel_get_buf_trans(&bdw_ddi_translations_fdi, n_entries); + return intel_get_buf_trans(&bdw_trans_fdi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&bdw_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&bdw_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return intel_get_buf_trans(&bdw_ddi_translations_edp, n_entries); + return intel_get_buf_trans(&bdw_trans_edp, n_entries); else - return intel_get_buf_trans(&bdw_ddi_translations_dp, n_entries); + return intel_get_buf_trans(&bdw_trans_dp, n_entries); } static int skl_buf_trans_num_entries(enum port port, int n_entries) @@ -1080,12 +1081,12 @@ static int skl_buf_trans_num_entries(enum port port, int n_entries) static const struct intel_ddi_buf_trans * _skl_get_buf_trans_dp(struct intel_encoder *encoder, - const struct intel_ddi_buf_trans *ddi_translations, + const struct intel_ddi_buf_trans *trans, int *n_entries) { - ddi_translations = intel_get_buf_trans(ddi_translations, n_entries); + trans = intel_get_buf_trans(trans, n_entries); *n_entries = skl_buf_trans_num_entries(encoder->port, *n_entries); - return ddi_translations; + return trans; } static const struct intel_ddi_buf_trans * @@ -1096,12 +1097,12 @@ skl_y_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&skl_y_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&skl_y_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return _skl_get_buf_trans_dp(encoder, &skl_y_ddi_translations_edp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_y_trans_edp, n_entries); else - return _skl_get_buf_trans_dp(encoder, &skl_y_ddi_translations_dp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_y_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1112,12 +1113,12 @@ skl_u_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return _skl_get_buf_trans_dp(encoder, &skl_u_ddi_translations_edp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_u_trans_edp, n_entries); else - return _skl_get_buf_trans_dp(encoder, &skl_u_ddi_translations_dp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_u_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1128,12 +1129,12 @@ skl_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return _skl_get_buf_trans_dp(encoder, &skl_ddi_translations_edp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_trans_edp, n_entries); else - return _skl_get_buf_trans_dp(encoder, &skl_ddi_translations_dp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1144,12 +1145,12 @@ kbl_y_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&skl_y_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&skl_y_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return _skl_get_buf_trans_dp(encoder, &skl_y_ddi_translations_edp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_y_trans_edp, n_entries); else - return _skl_get_buf_trans_dp(encoder, &kbl_y_ddi_translations_dp, n_entries); + return _skl_get_buf_trans_dp(encoder, &kbl_y_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1160,12 +1161,12 @@ kbl_u_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return _skl_get_buf_trans_dp(encoder, &skl_u_ddi_translations_edp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_u_trans_edp, n_entries); else - return _skl_get_buf_trans_dp(encoder, &kbl_u_ddi_translations_dp, n_entries); + return _skl_get_buf_trans_dp(encoder, &kbl_u_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1176,12 +1177,12 @@ kbl_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&skl_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&skl_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return _skl_get_buf_trans_dp(encoder, &skl_ddi_translations_edp, n_entries); + return _skl_get_buf_trans_dp(encoder, &skl_trans_edp, n_entries); else - return _skl_get_buf_trans_dp(encoder, &kbl_ddi_translations_dp, n_entries); + return _skl_get_buf_trans_dp(encoder, &kbl_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1192,12 +1193,12 @@ bxt_get_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&bxt_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&bxt_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && i915->vbt.edp.low_vswing) - return intel_get_buf_trans(&bxt_ddi_translations_edp, n_entries); + return intel_get_buf_trans(&bxt_trans_edp, n_entries); else - return intel_get_buf_trans(&bxt_ddi_translations_dp, n_entries); + return intel_get_buf_trans(&bxt_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1205,7 +1206,7 @@ icl_get_combo_buf_trans_dp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, + return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); } @@ -1217,10 +1218,10 @@ icl_get_combo_buf_trans_edp(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); if (crtc_state->port_clock > 540000) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, + return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); } else if (dev_priv->vbt.edp.low_vswing) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2, + return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } @@ -1233,7 +1234,7 @@ icl_get_combo_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) return icl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else @@ -1246,10 +1247,10 @@ icl_get_mg_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) { - return intel_get_buf_trans(&icl_mg_phy_ddi_translations_hbr2_hbr3, + return intel_get_buf_trans(&icl_mg_phy_trans_hbr2_hbr3, n_entries); } else { - return intel_get_buf_trans(&icl_mg_phy_ddi_translations_rbr_hbr, + return intel_get_buf_trans(&icl_mg_phy_trans_rbr_hbr, n_entries); } } @@ -1260,7 +1261,7 @@ icl_get_mg_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_mg_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_mg_phy_trans_hdmi, n_entries); else return icl_get_mg_buf_trans_dp(encoder, crtc_state, n_entries); } @@ -1271,9 +1272,9 @@ ehl_get_combo_buf_trans_edp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) - return intel_get_buf_trans(&ehl_combo_phy_ddi_translations_edp_hbr2, n_entries); + return intel_get_buf_trans(&ehl_combo_phy_trans_edp_hbr2, n_entries); else - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } static const struct intel_ddi_buf_trans * @@ -1284,12 +1285,12 @@ ehl_get_combo_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && dev_priv->vbt.edp.low_vswing) return ehl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else - return intel_get_buf_trans(&ehl_combo_phy_ddi_translations_dp, n_entries); + return intel_get_buf_trans(&ehl_combo_phy_trans_dp, n_entries); } static const struct intel_ddi_buf_trans * @@ -1298,9 +1299,9 @@ jsl_get_combo_buf_trans_edp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) - return intel_get_buf_trans(&jsl_combo_phy_ddi_translations_edp_hbr2, n_entries); + return intel_get_buf_trans(&jsl_combo_phy_trans_edp_hbr2, n_entries); else - return intel_get_buf_trans(&jsl_combo_phy_ddi_translations_edp_hbr, n_entries); + return intel_get_buf_trans(&jsl_combo_phy_trans_edp_hbr, n_entries); } static const struct intel_ddi_buf_trans * @@ -1311,12 +1312,12 @@ jsl_get_combo_buf_trans(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && dev_priv->vbt.edp.low_vswing) return jsl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); } static const struct intel_ddi_buf_trans * @@ -1328,14 +1329,14 @@ tgl_get_combo_buf_trans_dp(struct intel_encoder *encoder, if (crtc_state->port_clock > 270000) { if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) { - return intel_get_buf_trans(&tgl_uy_combo_phy_ddi_translations_dp_hbr2, + return intel_get_buf_trans(&tgl_uy_combo_phy_trans_dp_hbr2, n_entries); } else { - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_dp_hbr2, + return intel_get_buf_trans(&tgl_combo_phy_trans_dp_hbr2, n_entries); } } else { - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_dp_hbr, + return intel_get_buf_trans(&tgl_combo_phy_trans_dp_hbr, n_entries); } } @@ -1349,13 +1350,13 @@ tgl_get_combo_buf_trans_edp(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); if (crtc_state->port_clock > 540000) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, + return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); } else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) { - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl, + return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); } else if (dev_priv->vbt.edp.low_vswing) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2, + return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } @@ -1368,7 +1369,7 @@ tgl_get_combo_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) return tgl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else @@ -1381,10 +1382,10 @@ dg1_get_combo_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) - return intel_get_buf_trans(&dg1_combo_phy_ddi_translations_dp_hbr2_hbr3, + return intel_get_buf_trans(&dg1_combo_phy_trans_dp_hbr2_hbr3, n_entries); else - return intel_get_buf_trans(&dg1_combo_phy_ddi_translations_dp_rbr_hbr, + return intel_get_buf_trans(&dg1_combo_phy_trans_dp_rbr_hbr, n_entries); } @@ -1397,13 +1398,13 @@ dg1_get_combo_buf_trans_edp(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); if (crtc_state->port_clock > 540000) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, + return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl, + return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); else if (dev_priv->vbt.edp.low_vswing) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2, + return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); else return dg1_get_combo_buf_trans_dp(encoder, crtc_state, n_entries); @@ -1415,7 +1416,7 @@ dg1_get_combo_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) return dg1_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else @@ -1428,9 +1429,9 @@ rkl_get_combo_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) - return intel_get_buf_trans(&rkl_combo_phy_ddi_translations_dp_hbr2_hbr3, n_entries); + return intel_get_buf_trans(&rkl_combo_phy_trans_dp_hbr2_hbr3, n_entries); else - return intel_get_buf_trans(&rkl_combo_phy_ddi_translations_dp_hbr, n_entries); + return intel_get_buf_trans(&rkl_combo_phy_trans_dp_hbr, n_entries); } static const struct intel_ddi_buf_trans * @@ -1442,13 +1443,13 @@ rkl_get_combo_buf_trans_edp(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); if (crtc_state->port_clock > 540000) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_dp_hbr2_edp_hbr3, + return intel_get_buf_trans(&icl_combo_phy_trans_dp_hbr2_edp_hbr3, n_entries); } else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) { - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl, + return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); } else if (dev_priv->vbt.edp.low_vswing) { - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_edp_hbr2, + return intel_get_buf_trans(&icl_combo_phy_trans_edp_hbr2, n_entries); } @@ -1461,7 +1462,7 @@ rkl_get_combo_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) return rkl_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else @@ -1474,9 +1475,9 @@ adls_get_combo_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) - return intel_get_buf_trans(&adls_combo_phy_ddi_translations_dp_hbr2_hbr3, n_entries); + return intel_get_buf_trans(&adls_combo_phy_trans_dp_hbr2_hbr3, n_entries); else - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_dp_hbr, n_entries); + return intel_get_buf_trans(&tgl_combo_phy_trans_dp_hbr, n_entries); } static const struct intel_ddi_buf_trans * @@ -1488,11 +1489,11 @@ adls_get_combo_buf_trans_edp(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); if (crtc_state->port_clock > 540000) - return intel_get_buf_trans(&adls_combo_phy_ddi_translations_edp_hbr3, n_entries); + return intel_get_buf_trans(&adls_combo_phy_trans_edp_hbr3, n_entries); else if (i915->vbt.edp.hobl && !intel_dp->hobl_failed) - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl, n_entries); + return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); else if (i915->vbt.edp.low_vswing) - return intel_get_buf_trans(&adls_combo_phy_ddi_translations_edp_hbr2, n_entries); + return intel_get_buf_trans(&adls_combo_phy_trans_edp_hbr2, n_entries); else return adls_get_combo_buf_trans_dp(encoder, crtc_state, n_entries); } @@ -1503,7 +1504,7 @@ adls_get_combo_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&icl_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&icl_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) return adls_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else @@ -1516,9 +1517,9 @@ adlp_get_combo_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) - return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_dp_hbr2_hbr3, n_entries); + return intel_get_buf_trans(&adlp_combo_phy_trans_dp_hbr2_hbr3, n_entries); else - return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_dp_hbr, n_entries); + return intel_get_buf_trans(&adlp_combo_phy_trans_dp_hbr, n_entries); } static const struct intel_ddi_buf_trans * @@ -1530,13 +1531,13 @@ adlp_get_combo_buf_trans_edp(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); if (crtc_state->port_clock > 540000) { - return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_edp_hbr3, + return intel_get_buf_trans(&adlp_combo_phy_trans_edp_hbr3, n_entries); } else if (dev_priv->vbt.edp.hobl && !intel_dp->hobl_failed) { - return intel_get_buf_trans(&tgl_combo_phy_ddi_translations_edp_hbr2_hobl, + return intel_get_buf_trans(&tgl_combo_phy_trans_edp_hbr2_hobl, n_entries); } else if (dev_priv->vbt.edp.low_vswing) { - return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_edp_up_to_hbr2, + return intel_get_buf_trans(&adlp_combo_phy_trans_edp_up_to_hbr2, n_entries); } @@ -1549,7 +1550,7 @@ adlp_get_combo_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&adlp_combo_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&adlp_combo_phy_trans_hdmi, n_entries); else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) return adlp_get_combo_buf_trans_edp(encoder, crtc_state, n_entries); else @@ -1562,10 +1563,10 @@ tgl_get_dkl_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) { - return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_dp_hbr2, + return intel_get_buf_trans(&tgl_dkl_phy_trans_dp_hbr2, n_entries); } else { - return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_dp_hbr, + return intel_get_buf_trans(&tgl_dkl_phy_trans_dp_hbr, n_entries); } } @@ -1576,7 +1577,7 @@ tgl_get_dkl_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&tgl_dkl_phy_trans_hdmi, n_entries); else return tgl_get_dkl_buf_trans_dp(encoder, crtc_state, n_entries); } @@ -1587,10 +1588,10 @@ adlp_get_dkl_buf_trans_dp(struct intel_encoder *encoder, int *n_entries) { if (crtc_state->port_clock > 270000) { - return intel_get_buf_trans(&adlp_dkl_phy_ddi_translations_dp_hbr2_hbr3, + return intel_get_buf_trans(&adlp_dkl_phy_trans_dp_hbr2_hbr3, n_entries); } else { - return intel_get_buf_trans(&adlp_dkl_phy_ddi_translations_dp_hbr, + return intel_get_buf_trans(&adlp_dkl_phy_trans_dp_hbr, n_entries); } } @@ -1601,7 +1602,7 @@ adlp_get_dkl_buf_trans(struct intel_encoder *encoder, int *n_entries) { if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) - return intel_get_buf_trans(&tgl_dkl_phy_ddi_translations_hdmi, n_entries); + return intel_get_buf_trans(&tgl_dkl_phy_trans_hdmi, n_entries); else return adlp_get_dkl_buf_trans_dp(encoder, crtc_state, n_entries); } @@ -1611,30 +1612,11 @@ dg2_get_snps_buf_trans(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries) { - if (crtc_state->port_clock > 1000000) - return intel_get_buf_trans(&dg2_snps_translations_uhbr, n_entries); + if (intel_crtc_has_dp_encoder(crtc_state) && + intel_dp_is_uhbr(crtc_state)) + return intel_get_buf_trans(&dg2_snps_trans_uhbr, n_entries); else - return intel_get_buf_trans(&dg2_snps_translations, n_entries); -} - -int intel_ddi_hdmi_num_entries(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int *default_entry) -{ - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - const struct intel_ddi_buf_trans *ddi_translations; - int n_entries; - - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - - if (drm_WARN_ON(&dev_priv->drm, !ddi_translations)) { - *default_entry = 0; - return 0; - } - - *default_entry = ddi_translations->hdmi_default_entry; - - return n_entries; + return intel_get_buf_trans(&dg2_snps_trans, n_entries); } void intel_ddi_buf_trans_init(struct intel_encoder *encoder) diff --git a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h index 94d338287f61..2133984a572b 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h +++ b/drivers/gpu/drm/i915/display/intel_ddi_buf_trans.h @@ -34,21 +34,21 @@ struct icl_ddi_buf_trans { }; struct icl_mg_phy_ddi_buf_trans { - u32 cri_txdeemph_override_11_6; - u32 cri_txdeemph_override_5_0; - u32 cri_txdeemph_override_17_12; + u8 cri_txdeemph_override_11_6; + u8 cri_txdeemph_override_5_0; + u8 cri_txdeemph_override_17_12; }; struct tgl_dkl_phy_ddi_buf_trans { - u32 dkl_vswing_control; - u32 dkl_preshoot_control; - u32 dkl_de_emphasis_control; + u8 vswing; + u8 preshoot; + u8 de_emphasis; }; struct dg2_snps_phy_buf_trans { - u8 snps_vswing; - u8 snps_pre_cursor; - u8 snps_post_cursor; + u8 vswing; + u8 pre_cursor; + u8 post_cursor; }; union intel_ddi_buf_trans_entry { @@ -68,10 +68,6 @@ struct intel_ddi_buf_trans { bool is_hobl_buf_trans(const struct intel_ddi_buf_trans *table); -int intel_ddi_hdmi_num_entries(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int *default_entry); - void intel_ddi_buf_trans_init(struct intel_encoder *encoder); #endif diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index ad622d0f569b..ff598b6cd953 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -68,9 +68,10 @@ #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_object.h" -#include "gt/intel_rps.h" #include "gt/gen8_ppgtt.h" +#include "pxp/intel_pxp.h" + #include "g4x_dp.h" #include "g4x_hdmi.h" #include "i915_drv.h" @@ -87,26 +88,29 @@ #include "intel_dp_link_training.h" #include "intel_dpt.h" #include "intel_fbc.h" -#include "intel_fdi.h" #include "intel_fbdev.h" +#include "intel_fdi.h" #include "intel_fifo_underrun.h" #include "intel_frontbuffer.h" #include "intel_hdcp.h" #include "intel_hotplug.h" #include "intel_overlay.h" #include "intel_panel.h" +#include "intel_pcode.h" #include "intel_pipe_crc.h" +#include "intel_plane_initial.h" #include "intel_pm.h" #include "intel_pps.h" #include "intel_psr.h" #include "intel_quirks.h" -#include "intel_sideband.h" +#include "intel_sbi.h" #include "intel_sprite.h" #include "intel_tc.h" #include "intel_vga.h" #include "i9xx_plane.h" #include "skl_scaler.h" #include "skl_universal_plane.h" +#include "vlv_sideband.h" static void i9xx_crtc_clock_get(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config); @@ -120,12 +124,107 @@ static void intel_cpu_transcoder_set_m_n(const struct intel_crtc_state *crtc_sta const struct intel_link_m_n *m2_n2); static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state); static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state); -static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state); +static void hsw_set_transconf(const struct intel_crtc_state *crtc_state); static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state); static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state); static void intel_modeset_setup_hw_state(struct drm_device *dev, struct drm_modeset_acquire_ctx *ctx); +/** + * intel_update_watermarks - update FIFO watermark values based on current modes + * @dev_priv: i915 device + * + * Calculate watermark values for the various WM regs based on current mode + * and plane configuration. + * + * There are several cases to deal with here: + * - normal (i.e. non-self-refresh) + * - self-refresh (SR) mode + * - lines are large relative to FIFO size (buffer can hold up to 2) + * - lines are small relative to FIFO size (buffer can hold more than 2 + * lines), so need to account for TLB latency + * + * The normal calculation is: + * watermark = dotclock * bytes per pixel * latency + * where latency is platform & configuration dependent (we assume pessimal + * values here). + * + * The SR calculation is: + * watermark = (trunc(latency/line time)+1) * surface width * + * bytes per pixel + * where + * line time = htotal / dotclock + * surface width = hdisplay for normal plane and 64 for cursor + * and latency is assumed to be high, as above. + * + * The final value programmed to the register should always be rounded up, + * and include an extra 2 entries to account for clock crossings. + * + * We don't use the sprite, so we can ignore that. And on Crestline we have + * to set the non-SR watermarks to 8. + */ +static void intel_update_watermarks(struct drm_i915_private *dev_priv) +{ + if (dev_priv->wm_disp->update_wm) + dev_priv->wm_disp->update_wm(dev_priv); +} + +static int intel_compute_pipe_wm(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + if (dev_priv->wm_disp->compute_pipe_wm) + return dev_priv->wm_disp->compute_pipe_wm(state, crtc); + return 0; +} + +static int intel_compute_intermediate_wm(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + if (!dev_priv->wm_disp->compute_intermediate_wm) + return 0; + if (drm_WARN_ON(&dev_priv->drm, + !dev_priv->wm_disp->compute_pipe_wm)) + return 0; + return dev_priv->wm_disp->compute_intermediate_wm(state, crtc); +} + +static bool intel_initial_watermarks(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + if (dev_priv->wm_disp->initial_watermarks) { + dev_priv->wm_disp->initial_watermarks(state, crtc); + return true; + } + return false; +} + +static void intel_atomic_update_watermarks(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + if (dev_priv->wm_disp->atomic_update_watermarks) + dev_priv->wm_disp->atomic_update_watermarks(state, crtc); +} + +static void intel_optimize_watermarks(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + if (dev_priv->wm_disp->optimize_watermarks) + dev_priv->wm_disp->optimize_watermarks(state, crtc); +} + +static int intel_compute_global_watermarks(struct intel_atomic_state *state) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + if (dev_priv->wm_disp->compute_global_watermarks) + return dev_priv->wm_disp->compute_global_watermarks(state); + return 0; +} + /* returns HPLL frequency in kHz */ int vlv_get_hpll_vco(struct drm_i915_private *dev_priv) { @@ -183,6 +282,12 @@ static void intel_update_czclk(struct drm_i915_private *dev_priv) dev_priv->czclk_freq); } +static bool is_hdr_mode(const struct intel_crtc_state *crtc_state) +{ + return (crtc_state->active_planes & + ~(icl_hdr_plane_mask() | BIT(PLANE_CURSOR))) == 0; +} + /* WA Display #0827: Gen9:all */ static void skl_wa_827(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable) @@ -208,6 +313,15 @@ icl_wa_scalerclkgating(struct drm_i915_private *dev_priv, enum pipe pipe, intel_de_read(dev_priv, CLKGATE_DIS_PSL(pipe)) & ~DPFR_GATING_DIS); } +/* Wa_1604331009:icl,jsl,ehl */ +static void +icl_wa_cursorclkgating(struct drm_i915_private *dev_priv, enum pipe pipe, + bool enable) +{ + intel_de_rmw(dev_priv, CLKGATE_DIS_PSL(pipe), CURSOR_GATING_DIS, + enable ? CURSOR_GATING_DIS : 0); +} + static bool is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state) { @@ -288,168 +402,8 @@ intel_wait_for_pipe_off(const struct intel_crtc_state *old_crtc_state) } } -/* Only for pre-ILK configs */ -void assert_pll(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state) -{ - u32 val; - bool cur_state; - - val = intel_de_read(dev_priv, DPLL(pipe)); - cur_state = !!(val & DPLL_VCO_ENABLE); - I915_STATE_WARN(cur_state != state, - "PLL state assertion failure (expected %s, current %s)\n", - onoff(state), onoff(cur_state)); -} - -/* XXX: the dsi pll is shared between MIPI DSI ports */ -void assert_dsi_pll(struct drm_i915_private *dev_priv, bool state) -{ - u32 val; - bool cur_state; - - vlv_cck_get(dev_priv); - val = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL); - vlv_cck_put(dev_priv); - - cur_state = val & DSI_PLL_VCO_EN; - I915_STATE_WARN(cur_state != state, - "DSI PLL state assertion failure (expected %s, current %s)\n", - onoff(state), onoff(cur_state)); -} - -static void assert_fdi_tx(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state) -{ - bool cur_state; - - if (HAS_DDI(dev_priv)) { - /* - * DDI does not have a specific FDI_TX register. - * - * FDI is never fed from EDP transcoder - * so pipe->transcoder cast is fine here. - */ - enum transcoder cpu_transcoder = (enum transcoder)pipe; - u32 val = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(cpu_transcoder)); - cur_state = !!(val & TRANS_DDI_FUNC_ENABLE); - } else { - u32 val = intel_de_read(dev_priv, FDI_TX_CTL(pipe)); - cur_state = !!(val & FDI_TX_ENABLE); - } - I915_STATE_WARN(cur_state != state, - "FDI TX state assertion failure (expected %s, current %s)\n", - onoff(state), onoff(cur_state)); -} -#define assert_fdi_tx_enabled(d, p) assert_fdi_tx(d, p, true) -#define assert_fdi_tx_disabled(d, p) assert_fdi_tx(d, p, false) - -static void assert_fdi_rx(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state) -{ - u32 val; - bool cur_state; - - val = intel_de_read(dev_priv, FDI_RX_CTL(pipe)); - cur_state = !!(val & FDI_RX_ENABLE); - I915_STATE_WARN(cur_state != state, - "FDI RX state assertion failure (expected %s, current %s)\n", - onoff(state), onoff(cur_state)); -} -#define assert_fdi_rx_enabled(d, p) assert_fdi_rx(d, p, true) -#define assert_fdi_rx_disabled(d, p) assert_fdi_rx(d, p, false) - -static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe) -{ - u32 val; - - /* ILK FDI PLL is always enabled */ - if (IS_IRONLAKE(dev_priv)) - return; - - /* On Haswell, DDI ports are responsible for the FDI PLL setup */ - if (HAS_DDI(dev_priv)) - return; - - val = intel_de_read(dev_priv, FDI_TX_CTL(pipe)); - I915_STATE_WARN(!(val & FDI_TX_PLL_ENABLE), "FDI TX PLL assertion failure, should be active but is disabled\n"); -} - -void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state) -{ - u32 val; - bool cur_state; - - val = intel_de_read(dev_priv, FDI_RX_CTL(pipe)); - cur_state = !!(val & FDI_RX_PLL_ENABLE); - I915_STATE_WARN(cur_state != state, - "FDI RX PLL assertion failure (expected %s, current %s)\n", - onoff(state), onoff(cur_state)); -} - -void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe) -{ - i915_reg_t pp_reg; - u32 val; - enum pipe panel_pipe = INVALID_PIPE; - bool locked = true; - - if (drm_WARN_ON(&dev_priv->drm, HAS_DDI(dev_priv))) - return; - - if (HAS_PCH_SPLIT(dev_priv)) { - u32 port_sel; - - pp_reg = PP_CONTROL(0); - port_sel = intel_de_read(dev_priv, PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK; - - switch (port_sel) { - case PANEL_PORT_SELECT_LVDS: - intel_lvds_port_enabled(dev_priv, PCH_LVDS, &panel_pipe); - break; - case PANEL_PORT_SELECT_DPA: - g4x_dp_port_enabled(dev_priv, DP_A, PORT_A, &panel_pipe); - break; - case PANEL_PORT_SELECT_DPC: - g4x_dp_port_enabled(dev_priv, PCH_DP_C, PORT_C, &panel_pipe); - break; - case PANEL_PORT_SELECT_DPD: - g4x_dp_port_enabled(dev_priv, PCH_DP_D, PORT_D, &panel_pipe); - break; - default: - MISSING_CASE(port_sel); - break; - } - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - /* presumably write lock depends on pipe, not port select */ - pp_reg = PP_CONTROL(pipe); - panel_pipe = pipe; - } else { - u32 port_sel; - - pp_reg = PP_CONTROL(0); - port_sel = intel_de_read(dev_priv, PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK; - - drm_WARN_ON(&dev_priv->drm, - port_sel != PANEL_PORT_SELECT_LVDS); - intel_lvds_port_enabled(dev_priv, LVDS, &panel_pipe); - } - - val = intel_de_read(dev_priv, pp_reg); - if (!(val & PANEL_POWER_ON) || - ((val & PANEL_UNLOCK_MASK) == PANEL_UNLOCK_REGS)) - locked = false; - - I915_STATE_WARN(panel_pipe == pipe && locked, - "panel assertion failure, pipe %c regs locked\n", - pipe_name(pipe)); -} - -void assert_pipe(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder, bool state) +void assert_transcoder(struct drm_i915_private *dev_priv, + enum transcoder cpu_transcoder, bool state) { bool cur_state; enum intel_display_power_domain power_domain; @@ -766,7 +720,7 @@ enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc) return crtc->pipe; } -void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state) +void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state) { struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -827,7 +781,7 @@ void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state) intel_wait_for_pipe_scanline_moving(crtc); } -void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state) +void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state) { struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -893,13 +847,16 @@ unsigned int intel_remapped_info_size(const struct intel_remapped_info *rem_info unsigned int size = 0; int i; - for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) + for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { + if (rem_info->plane_alignment) + size = ALIGN(size, rem_info->plane_alignment); size += rem_info->plane[i].dst_stride * rem_info->plane[i].height; + } return size; } -static bool intel_plane_uses_fence(const struct intel_plane_state *plane_state) +bool intel_plane_uses_fence(const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); @@ -909,198 +866,6 @@ static bool intel_plane_uses_fence(const struct intel_plane_state *plane_state) plane_state->view.gtt.type == I915_GGTT_VIEW_NORMAL); } -static struct i915_vma * -intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, - const struct i915_ggtt_view *view, - bool uses_fence, - unsigned long *out_flags, - struct i915_address_space *vm) -{ - struct drm_device *dev = fb->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct drm_i915_gem_object *obj = intel_fb_obj(fb); - struct i915_vma *vma; - u32 alignment; - int ret; - - if (WARN_ON(!i915_gem_object_is_framebuffer(obj))) - return ERR_PTR(-EINVAL); - - alignment = 4096 * 512; - - atomic_inc(&dev_priv->gpu_error.pending_fb_pin); - - ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE); - if (ret) { - vma = ERR_PTR(ret); - goto err; - } - - vma = i915_vma_instance(obj, vm, view); - if (IS_ERR(vma)) - goto err; - - if (i915_vma_misplaced(vma, 0, alignment, 0)) { - ret = i915_vma_unbind(vma); - if (ret) { - vma = ERR_PTR(ret); - goto err; - } - } - - ret = i915_vma_pin(vma, 0, alignment, PIN_GLOBAL); - if (ret) { - vma = ERR_PTR(ret); - goto err; - } - - vma->display_alignment = max_t(u64, vma->display_alignment, alignment); - - i915_gem_object_flush_if_display(obj); - - i915_vma_get(vma); -err: - atomic_dec(&dev_priv->gpu_error.pending_fb_pin); - - return vma; -} - -struct i915_vma * -intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, - bool phys_cursor, - const struct i915_ggtt_view *view, - bool uses_fence, - unsigned long *out_flags) -{ - struct drm_device *dev = fb->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct drm_i915_gem_object *obj = intel_fb_obj(fb); - intel_wakeref_t wakeref; - struct i915_gem_ww_ctx ww; - struct i915_vma *vma; - unsigned int pinctl; - u32 alignment; - int ret; - - if (drm_WARN_ON(dev, !i915_gem_object_is_framebuffer(obj))) - return ERR_PTR(-EINVAL); - - if (phys_cursor) - alignment = intel_cursor_alignment(dev_priv); - else - alignment = intel_surf_alignment(fb, 0); - if (drm_WARN_ON(dev, alignment && !is_power_of_2(alignment))) - return ERR_PTR(-EINVAL); - - /* Note that the w/a also requires 64 PTE of padding following the - * bo. We currently fill all unused PTE with the shadow page and so - * we should always have valid PTE following the scanout preventing - * the VT-d warning. - */ - if (intel_scanout_needs_vtd_wa(dev_priv) && alignment < 256 * 1024) - alignment = 256 * 1024; - - /* - * Global gtt pte registers are special registers which actually forward - * writes to a chunk of system memory. Which means that there is no risk - * that the register values disappear as soon as we call - * intel_runtime_pm_put(), so it is correct to wrap only the - * pin/unpin/fence and not more. - */ - wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); - - atomic_inc(&dev_priv->gpu_error.pending_fb_pin); - - /* - * Valleyview is definitely limited to scanning out the first - * 512MiB. Lets presume this behaviour was inherited from the - * g4x display engine and that all earlier gen are similarly - * limited. Testing suggests that it is a little more - * complicated than this. For example, Cherryview appears quite - * happy to scanout from anywhere within its global aperture. - */ - pinctl = 0; - if (HAS_GMCH(dev_priv)) - pinctl |= PIN_MAPPABLE; - - i915_gem_ww_ctx_init(&ww, true); -retry: - ret = i915_gem_object_lock(obj, &ww); - if (!ret && phys_cursor) - ret = i915_gem_object_attach_phys(obj, alignment); - else if (!ret && HAS_LMEM(dev_priv)) - ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM); - /* TODO: Do we need to sync when migration becomes async? */ - if (!ret) - ret = i915_gem_object_pin_pages(obj); - if (ret) - goto err; - - if (!ret) { - vma = i915_gem_object_pin_to_display_plane(obj, &ww, alignment, - view, pinctl); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err_unpin; - } - } - - if (uses_fence && i915_vma_is_map_and_fenceable(vma)) { - /* - * Install a fence for tiled scan-out. Pre-i965 always needs a - * fence, whereas 965+ only requires a fence if using - * framebuffer compression. For simplicity, we always, when - * possible, install a fence as the cost is not that onerous. - * - * If we fail to fence the tiled scanout, then either the - * modeset will reject the change (which is highly unlikely as - * the affected systems, all but one, do not have unmappable - * space) or we will not be able to enable full powersaving - * techniques (also likely not to apply due to various limits - * FBC and the like impose on the size of the buffer, which - * presumably we violated anyway with this unmappable buffer). - * Anyway, it is presumably better to stumble onwards with - * something and try to run the system in a "less than optimal" - * mode that matches the user configuration. - */ - ret = i915_vma_pin_fence(vma); - if (ret != 0 && DISPLAY_VER(dev_priv) < 4) { - i915_vma_unpin(vma); - goto err_unpin; - } - ret = 0; - - if (vma->fence) - *out_flags |= PLANE_HAS_FENCE; - } - - i915_vma_get(vma); - -err_unpin: - i915_gem_object_unpin_pages(obj); -err: - if (ret == -EDEADLK) { - ret = i915_gem_ww_ctx_backoff(&ww); - if (!ret) - goto retry; - } - i915_gem_ww_ctx_fini(&ww); - if (ret) - vma = ERR_PTR(ret); - - atomic_dec(&dev_priv->gpu_error.pending_fb_pin); - intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); - return vma; -} - -void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags) -{ - if (flags & PLANE_HAS_FENCE) - i915_vma_unpin_fence(vma); - i915_vma_unpin(vma); - i915_vma_put(vma); -} - /* * Convert the x/y offsets into a linear offset. * Only valid with 0/180 degree rotation, which is fine since linear @@ -1286,123 +1051,6 @@ u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, DRM_MODE_ROTATE_0); } -static struct i915_vma * -initial_plane_vma(struct drm_i915_private *i915, - struct intel_initial_plane_config *plane_config) -{ - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - u32 base, size; - - if (plane_config->size == 0) - return NULL; - - base = round_down(plane_config->base, - I915_GTT_MIN_ALIGNMENT); - size = round_up(plane_config->base + plane_config->size, - I915_GTT_MIN_ALIGNMENT); - size -= base; - - /* - * If the FB is too big, just don't use it since fbdev is not very - * important and we should probably use that space with FBC or other - * features. - */ - if (IS_ENABLED(CONFIG_FRAMEBUFFER_CONSOLE) && - size * 2 > i915->stolen_usable_size) - return NULL; - - obj = i915_gem_object_create_stolen_for_preallocated(i915, base, size); - if (IS_ERR(obj)) - return NULL; - - /* - * Mark it WT ahead of time to avoid changing the - * cache_level during fbdev initialization. The - * unbind there would get stuck waiting for rcu. - */ - i915_gem_object_set_cache_coherency(obj, HAS_WT(i915) ? - I915_CACHE_WT : I915_CACHE_NONE); - - switch (plane_config->tiling) { - case I915_TILING_NONE: - break; - case I915_TILING_X: - case I915_TILING_Y: - obj->tiling_and_stride = - plane_config->fb->base.pitches[0] | - plane_config->tiling; - break; - default: - MISSING_CASE(plane_config->tiling); - goto err_obj; - } - - vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); - if (IS_ERR(vma)) - goto err_obj; - - if (i915_ggtt_pin(vma, NULL, 0, PIN_MAPPABLE | PIN_OFFSET_FIXED | base)) - goto err_obj; - - if (i915_gem_object_is_tiled(obj) && - !i915_vma_is_map_and_fenceable(vma)) - goto err_obj; - - return vma; - -err_obj: - i915_gem_object_put(obj); - return NULL; -} - -static bool -intel_alloc_initial_plane_obj(struct intel_crtc *crtc, - struct intel_initial_plane_config *plane_config) -{ - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct drm_mode_fb_cmd2 mode_cmd = { 0 }; - struct drm_framebuffer *fb = &plane_config->fb->base; - struct i915_vma *vma; - - switch (fb->modifier) { - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - case I915_FORMAT_MOD_Y_TILED: - break; - default: - drm_dbg(&dev_priv->drm, - "Unsupported modifier for initial FB: 0x%llx\n", - fb->modifier); - return false; - } - - vma = initial_plane_vma(dev_priv, plane_config); - if (!vma) - return false; - - mode_cmd.pixel_format = fb->format->format; - mode_cmd.width = fb->width; - mode_cmd.height = fb->height; - mode_cmd.pitches[0] = fb->pitches[0]; - mode_cmd.modifier[0] = fb->modifier; - mode_cmd.flags = DRM_MODE_FB_MODIFIERS; - - if (intel_framebuffer_init(to_intel_framebuffer(fb), - vma->obj, &mode_cmd)) { - drm_dbg_kms(&dev_priv->drm, "intel fb init failed\n"); - goto err_vma; - } - - plane_config->vma = vma; - return true; - -err_vma: - i915_vma_put(vma); - return false; -} - static void intel_set_plane_visible(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state, @@ -1438,8 +1086,8 @@ static void fixup_plane_bitmasks(struct intel_crtc_state *crtc_state) } } -static void intel_plane_disable_noatomic(struct intel_crtc *crtc, - struct intel_plane *plane) +void intel_plane_disable_noatomic(struct intel_crtc *crtc, + struct intel_plane *plane) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_crtc_state *crtc_state = @@ -1484,125 +1132,6 @@ static void intel_plane_disable_noatomic(struct intel_crtc *crtc, intel_wait_for_vblank(dev_priv, crtc->pipe); } -static bool -intel_reuse_initial_plane_obj(struct drm_i915_private *i915, - const struct intel_initial_plane_config *plane_config, - struct drm_framebuffer **fb, - struct i915_vma **vma) -{ - struct intel_crtc *crtc; - - for_each_intel_crtc(&i915->drm, crtc) { - struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - struct intel_plane *plane = - to_intel_plane(crtc->base.primary); - struct intel_plane_state *plane_state = - to_intel_plane_state(plane->base.state); - - if (!crtc_state->uapi.active) - continue; - - if (!plane_state->ggtt_vma) - continue; - - if (intel_plane_ggtt_offset(plane_state) == plane_config->base) { - *fb = plane_state->hw.fb; - *vma = plane_state->ggtt_vma; - return true; - } - } - - return false; -} - -static void -intel_find_initial_plane_obj(struct intel_crtc *crtc, - struct intel_initial_plane_config *plane_config) -{ - struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - struct intel_plane *plane = - to_intel_plane(crtc->base.primary); - struct intel_plane_state *plane_state = - to_intel_plane_state(plane->base.state); - struct drm_framebuffer *fb; - struct i915_vma *vma; - - /* - * TODO: - * Disable planes if get_initial_plane_config() failed. - * Make sure things work if the surface base is not page aligned. - */ - if (!plane_config->fb) - return; - - if (intel_alloc_initial_plane_obj(crtc, plane_config)) { - fb = &plane_config->fb->base; - vma = plane_config->vma; - goto valid_fb; - } - - /* - * Failed to alloc the obj, check to see if we should share - * an fb with another CRTC instead - */ - if (intel_reuse_initial_plane_obj(dev_priv, plane_config, &fb, &vma)) - goto valid_fb; - - /* - * We've failed to reconstruct the BIOS FB. Current display state - * indicates that the primary plane is visible, but has a NULL FB, - * which will lead to problems later if we don't fix it up. The - * simplest solution is to just disable the primary plane now and - * pretend the BIOS never had it enabled. - */ - intel_plane_disable_noatomic(crtc, plane); - if (crtc_state->bigjoiner) { - struct intel_crtc *slave = - crtc_state->bigjoiner_linked_crtc; - intel_plane_disable_noatomic(slave, to_intel_plane(slave->base.primary)); - } - - return; - -valid_fb: - plane_state->uapi.rotation = plane_config->rotation; - intel_fb_fill_view(to_intel_framebuffer(fb), - plane_state->uapi.rotation, &plane_state->view); - - __i915_vma_pin(vma); - plane_state->ggtt_vma = i915_vma_get(vma); - if (intel_plane_uses_fence(plane_state) && - i915_vma_pin_fence(vma) == 0 && vma->fence) - plane_state->flags |= PLANE_HAS_FENCE; - - plane_state->uapi.src_x = 0; - plane_state->uapi.src_y = 0; - plane_state->uapi.src_w = fb->width << 16; - plane_state->uapi.src_h = fb->height << 16; - - plane_state->uapi.crtc_x = 0; - plane_state->uapi.crtc_y = 0; - plane_state->uapi.crtc_w = fb->width; - plane_state->uapi.crtc_h = fb->height; - - if (plane_config->tiling) - dev_priv->preserve_bios_swizzle = true; - - plane_state->uapi.fb = fb; - drm_framebuffer_get(fb); - - plane_state->uapi.crtc = &crtc->base; - intel_plane_copy_uapi_to_hw_state(plane_state, plane_state, crtc); - - intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_DIRTYFB); - - atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits); -} - unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state) { @@ -2061,7 +1590,7 @@ static void ilk_pch_enable(const struct intel_atomic_state *state, assert_pch_transcoder_disabled(dev_priv, pipe); /* For PCH output, training FDI link */ - dev_priv->display.fdi_link_train(crtc, crtc_state); + intel_fdi_link_train(crtc, crtc_state); /* We need to program the right clock selection before writing the pixel * mutliplier into the DPLL. */ @@ -2089,7 +1618,7 @@ static void ilk_pch_enable(const struct intel_atomic_state *state, intel_enable_shared_dpll(crtc_state); /* set transcoder timing, panel must allow it */ - assert_panel_unlocked(dev_priv, pipe); + assert_pps_unlocked(dev_priv, pipe); ilk_pch_transcoder_set_timings(crtc_state, pipe); intel_fdi_normal_train(crtc); @@ -2347,6 +1876,46 @@ static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state) return false; } +static bool needs_cursorclk_wa(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); + + /* Wa_1604331009:icl,jsl,ehl */ + if (is_hdr_mode(crtc_state) && + crtc_state->active_planes & BIT(PLANE_CURSOR) && + DISPLAY_VER(dev_priv) == 11) + return true; + + return false; +} + +static void intel_async_flip_vtd_wa(struct drm_i915_private *i915, + enum pipe pipe, bool enable) +{ + if (DISPLAY_VER(i915) == 9) { + /* + * "Plane N strech max must be programmed to 11b (x1) + * when Async flips are enabled on that plane." + */ + intel_de_rmw(i915, CHICKEN_PIPESL_1(pipe), + SKL_PLANE1_STRETCH_MAX_MASK, + enable ? SKL_PLANE1_STRETCH_MAX_X1 : SKL_PLANE1_STRETCH_MAX_X8); + } else { + /* Also needed on HSW/BDW albeit undocumented */ + intel_de_rmw(i915, CHICKEN_PIPESL_1(pipe), + HSW_PRI_STRETCH_MAX_MASK, + enable ? HSW_PRI_STRETCH_MAX_X1 : HSW_PRI_STRETCH_MAX_X8); + } +} + +static bool needs_async_flip_vtd_wa(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + + return crtc_state->uapi.async_flip && intel_vtd_active() && + (DISPLAY_VER(i915) == 9 || IS_BROADWELL(i915) || IS_HASWELL(i915)); +} + static bool planes_enabling(const struct intel_crtc_state *old_crtc_state, const struct intel_crtc_state *new_crtc_state) { @@ -2374,7 +1943,7 @@ static void intel_post_plane_update(struct intel_atomic_state *state, intel_frontbuffer_flip(dev_priv, new_crtc_state->fb_bits); if (new_crtc_state->update_wm_post && new_crtc_state->hw.active) - intel_update_watermarks(crtc); + intel_update_watermarks(dev_priv); if (hsw_post_update_enable_ips(old_crtc_state, new_crtc_state)) hsw_enable_ips(new_crtc_state); @@ -2382,6 +1951,10 @@ static void intel_post_plane_update(struct intel_atomic_state *state, intel_fbc_post_update(state, crtc); intel_drrs_page_flip(state, crtc); + if (needs_async_flip_vtd_wa(old_crtc_state) && + !needs_async_flip_vtd_wa(new_crtc_state)) + intel_async_flip_vtd_wa(dev_priv, pipe, false); + if (needs_nv12_wa(old_crtc_state) && !needs_nv12_wa(new_crtc_state)) skl_wa_827(dev_priv, pipe, false); @@ -2389,6 +1962,11 @@ static void intel_post_plane_update(struct intel_atomic_state *state, if (needs_scalerclk_wa(old_crtc_state) && !needs_scalerclk_wa(new_crtc_state)) icl_wa_scalerclkgating(dev_priv, pipe, false); + + if (needs_cursorclk_wa(old_crtc_state) && + !needs_cursorclk_wa(new_crtc_state)) + icl_wa_cursorclkgating(dev_priv, pipe, false); + } static void intel_crtc_enable_flip_done(struct intel_atomic_state *state, @@ -2475,6 +2053,10 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, if (intel_fbc_pre_update(state, crtc)) intel_wait_for_vblank(dev_priv, pipe); + if (!needs_async_flip_vtd_wa(old_crtc_state) && + needs_async_flip_vtd_wa(new_crtc_state)) + intel_async_flip_vtd_wa(dev_priv, pipe, true); + /* Display WA 827 */ if (!needs_nv12_wa(old_crtc_state) && needs_nv12_wa(new_crtc_state)) @@ -2485,6 +2067,11 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, needs_scalerclk_wa(new_crtc_state)) icl_wa_scalerclkgating(dev_priv, pipe, true); + /* Wa_1604331009:icl,jsl,ehl */ + if (!needs_cursorclk_wa(old_crtc_state) && + needs_cursorclk_wa(new_crtc_state)) + icl_wa_cursorclkgating(dev_priv, pipe, true); + /* * Vblank time updates from the shadow to live plane control register * are blocked if the memory self-refresh mode is active at that @@ -2528,10 +2115,9 @@ static void intel_pre_plane_update(struct intel_atomic_state *state, * we'll continue to update watermarks the old way, if flags tell * us to. */ - if (dev_priv->display.initial_watermarks) - dev_priv->display.initial_watermarks(state, crtc); - else if (new_crtc_state->update_wm_pre) - intel_update_watermarks(crtc); + if (!intel_initial_watermarks(state, crtc)) + if (new_crtc_state->update_wm_pre) + intel_update_watermarks(dev_priv); } /* @@ -2903,9 +2489,8 @@ static void ilk_crtc_enable(struct intel_atomic_state *state, /* update DSPCNTR to configure gamma for pipe bottom color */ intel_disable_primary_plane(new_crtc_state); - if (dev_priv->display.initial_watermarks) - dev_priv->display.initial_watermarks(state, crtc); - intel_enable_pipe(new_crtc_state); + intel_initial_watermarks(state, crtc); + intel_enable_transcoder(new_crtc_state); if (new_crtc_state->has_pch_encoder) ilk_pch_enable(state, new_crtc_state); @@ -3081,10 +2666,9 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, &new_crtc_state->fdi_m_n, NULL); hsw_set_frame_start_delay(new_crtc_state); - } - if (!transcoder_is_dsi(cpu_transcoder)) - hsw_set_pipeconf(new_crtc_state); + hsw_set_transconf(new_crtc_state); + } crtc->active = true; @@ -3114,8 +2698,7 @@ static void hsw_crtc_enable(struct intel_atomic_state *state, if (DISPLAY_VER(dev_priv) >= 11) icl_set_pipe_chicken(new_crtc_state); - if (dev_priv->display.initial_watermarks) - dev_priv->display.initial_watermarks(state, crtc); + intel_initial_watermarks(state, crtc); if (DISPLAY_VER(dev_priv) >= 11) { const struct intel_dbuf_state *dbuf_state = @@ -3179,7 +2762,7 @@ static void ilk_crtc_disable(struct intel_atomic_state *state, intel_crtc_vblank_off(old_crtc_state); - intel_disable_pipe(old_crtc_state); + intel_disable_transcoder(old_crtc_state); ilk_pfit_disable(old_crtc_state); @@ -3241,7 +2824,7 @@ static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) */ drm_WARN_ON(&dev_priv->drm, intel_de_read(dev_priv, PFIT_CONTROL) & PFIT_ENABLE); - assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, crtc_state->cpu_transcoder); intel_de_write(dev_priv, PFIT_PGM_RATIOS, crtc_state->gmch_pfit.pgm_ratios); @@ -3361,11 +2944,7 @@ enum intel_display_power_domain intel_port_to_power_domain(enum port port) enum intel_display_power_domain intel_aux_power_domain(struct intel_digital_port *dig_port) { - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - - if (intel_phy_is_tc(dev_priv, phy) && - dig_port->tc_mode == TC_PORT_TBT_ALT) { + if (intel_tc_port_in_tbt_alt_mode(dig_port)) { switch (dig_port->aux_ch) { case AUX_CH_C: return POWER_DOMAIN_AUX_C_TBT; @@ -3426,16 +3005,16 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; struct drm_encoder *encoder; enum pipe pipe = crtc->pipe; u64 mask; - enum transcoder transcoder = crtc_state->cpu_transcoder; if (!crtc_state->hw.active) return 0; mask = BIT_ULL(POWER_DOMAIN_PIPE(pipe)); - mask |= BIT_ULL(POWER_DOMAIN_TRANSCODER(transcoder)); + mask |= BIT_ULL(POWER_DOMAIN_TRANSCODER(cpu_transcoder)); if (crtc_state->pch_pfit.enabled || crtc_state->pch_pfit.force_thru) mask |= BIT_ULL(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe)); @@ -3454,7 +3033,7 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state) mask |= BIT_ULL(POWER_DOMAIN_DISPLAY_CORE); if (crtc_state->dsc.compression_enable) - mask |= BIT_ULL(intel_dsc_power_domain(crtc_state)); + mask |= BIT_ULL(intel_dsc_power_domain(crtc, cpu_transcoder)); return mask; } @@ -3532,8 +3111,8 @@ static void valleyview_crtc_enable(struct intel_atomic_state *state, /* update DSPCNTR to configure gamma for pipe bottom color */ intel_disable_primary_plane(new_crtc_state); - dev_priv->display.initial_watermarks(state, crtc); - intel_enable_pipe(new_crtc_state); + intel_initial_watermarks(state, crtc); + intel_enable_transcoder(new_crtc_state); intel_crtc_vblank_on(new_crtc_state); @@ -3575,11 +3154,9 @@ static void i9xx_crtc_enable(struct intel_atomic_state *state, /* update DSPCNTR to configure gamma for pipe bottom color */ intel_disable_primary_plane(new_crtc_state); - if (dev_priv->display.initial_watermarks) - dev_priv->display.initial_watermarks(state, crtc); - else - intel_update_watermarks(crtc); - intel_enable_pipe(new_crtc_state); + if (!intel_initial_watermarks(state, crtc)) + intel_update_watermarks(dev_priv); + intel_enable_transcoder(new_crtc_state); intel_crtc_vblank_on(new_crtc_state); @@ -3598,7 +3175,7 @@ static void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state) if (!old_crtc_state->gmch_pfit.control) return; - assert_pipe_disabled(dev_priv, old_crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, old_crtc_state->cpu_transcoder); drm_dbg_kms(&dev_priv->drm, "disabling pfit, current: 0x%08x\n", intel_de_read(dev_priv, PFIT_CONTROL)); @@ -3624,7 +3201,7 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, intel_crtc_vblank_off(old_crtc_state); - intel_disable_pipe(old_crtc_state); + intel_disable_transcoder(old_crtc_state); i9xx_pfit_disable(old_crtc_state); @@ -3644,8 +3221,8 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, if (DISPLAY_VER(dev_priv) != 2) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); - if (!dev_priv->display.initial_watermarks) - intel_update_watermarks(crtc); + if (!dev_priv->wm_disp->initial_watermarks) + intel_update_watermarks(dev_priv); /* clock the pipe down to 640x480@60 to potentially save power */ if (IS_I830(dev_priv)) @@ -3698,7 +3275,7 @@ static void intel_crtc_disable_noatomic(struct intel_crtc *crtc, drm_WARN_ON(&dev_priv->drm, IS_ERR(temp_crtc_state) || ret); - dev_priv->display.crtc_disable(to_intel_atomic_state(state), crtc); + dev_priv->display->crtc_disable(to_intel_atomic_state(state), crtc); drm_atomic_state_put(state); @@ -3721,7 +3298,7 @@ static void intel_crtc_disable_noatomic(struct intel_crtc *crtc, encoder->base.crtc = NULL; intel_fbc_disable(crtc); - intel_update_watermarks(crtc); + intel_update_watermarks(dev_priv); intel_disable_shared_dpll(crtc_state); intel_display_power_put_all_in_set(dev_priv, &crtc->enabled_power_domains); @@ -4082,13 +3659,6 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc, } } - /* Cantiga+ cannot handle modes with a hsync front porch of 0. - * WaPruneModeWithIncorrectHsyncOffset:ctg,elk,ilk,snb,ivb,vlv,hsw. - */ - if ((DISPLAY_VER(dev_priv) > 4 || IS_G4X(dev_priv)) && - pipe_mode->crtc_hsync_start == pipe_mode->crtc_hdisplay) - return -EINVAL; - intel_crtc_compute_pixel_rate(pipe_config); if (pipe_config->has_pch_encoder) @@ -5194,7 +4764,7 @@ static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state) intel_de_posting_read(dev_priv, PIPECONF(pipe)); } -static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state) +static void hsw_set_transconf(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); @@ -5258,9 +4828,7 @@ static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state) val |= PIPEMISC_YUV420_ENABLE | PIPEMISC_YUV420_MODE_FULL_BLEND; - if (DISPLAY_VER(dev_priv) >= 11 && - (crtc_state->active_planes & ~(icl_hdr_plane_mask() | - BIT(PLANE_CURSOR))) == 0) + if (DISPLAY_VER(dev_priv) >= 11 && is_hdr_mode(crtc_state)) val |= PIPEMISC_HDR_MODE_PRECISION; if (DISPLAY_VER(dev_priv) >= 12) @@ -5599,59 +5167,64 @@ out: return ret; } -static bool hsw_get_transcoder_state(struct intel_crtc *crtc, - struct intel_crtc_state *pipe_config, - struct intel_display_power_domain_set *power_domain_set) +static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv, + enum transcoder cpu_transcoder) +{ + enum intel_display_power_domain power_domain; + intel_wakeref_t wakeref; + u32 tmp = 0; + + power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); + + with_intel_display_power_if_enabled(dev_priv, power_domain, wakeref) + tmp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); + + return tmp & TRANS_DDI_FUNC_ENABLE; +} + +static u8 hsw_panel_transcoders(struct drm_i915_private *i915) +{ + u8 panel_transcoder_mask = BIT(TRANSCODER_EDP); + + if (DISPLAY_VER(i915) >= 11) + panel_transcoder_mask |= BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1); + + return panel_transcoder_mask; +} + +static u8 hsw_enabled_transcoders(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); - unsigned long panel_transcoder_mask = BIT(TRANSCODER_EDP); - unsigned long enabled_panel_transcoders = 0; - enum transcoder panel_transcoder; - u32 tmp; - - if (DISPLAY_VER(dev_priv) >= 11) - panel_transcoder_mask |= - BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1); - - /* - * The pipe->transcoder mapping is fixed with the exception of the eDP - * and DSI transcoders handled below. - */ - pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; + u8 panel_transcoder_mask = hsw_panel_transcoders(dev_priv); + enum transcoder cpu_transcoder; + u8 enabled_transcoders = 0; /* * XXX: Do intel_display_power_get_if_enabled before reading this (for * consistency and less surprising code; it's in always on power). */ - for_each_cpu_transcoder_masked(dev_priv, panel_transcoder, + for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, panel_transcoder_mask) { - bool force_thru = false; + enum intel_display_power_domain power_domain; + intel_wakeref_t wakeref; enum pipe trans_pipe; + u32 tmp = 0; + + power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); + with_intel_display_power_if_enabled(dev_priv, power_domain, wakeref) + tmp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)); - tmp = intel_de_read(dev_priv, - TRANS_DDI_FUNC_CTL(panel_transcoder)); if (!(tmp & TRANS_DDI_FUNC_ENABLE)) continue; - /* - * Log all enabled ones, only use the first one. - * - * FIXME: This won't work for two separate DSI displays. - */ - enabled_panel_transcoders |= BIT(panel_transcoder); - if (enabled_panel_transcoders != BIT(panel_transcoder)) - continue; - switch (tmp & TRANS_DDI_EDP_INPUT_MASK) { default: drm_WARN(dev, 1, "unknown pipe linked to transcoder %s\n", - transcoder_name(panel_transcoder)); + transcoder_name(cpu_transcoder)); fallthrough; case TRANS_DDI_EDP_INPUT_A_ONOFF: - force_thru = true; - fallthrough; case TRANS_DDI_EDP_INPUT_A_ON: trans_pipe = PIPE_A; break; @@ -5666,22 +5239,83 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, break; } - if (trans_pipe == crtc->pipe) { - pipe_config->cpu_transcoder = panel_transcoder; - pipe_config->pch_pfit.force_thru = force_thru; - } + if (trans_pipe == crtc->pipe) + enabled_transcoders |= BIT(cpu_transcoder); } + cpu_transcoder = (enum transcoder) crtc->pipe; + if (transcoder_ddi_func_is_enabled(dev_priv, cpu_transcoder)) + enabled_transcoders |= BIT(cpu_transcoder); + + return enabled_transcoders; +} + +static bool has_edp_transcoders(u8 enabled_transcoders) +{ + return enabled_transcoders & BIT(TRANSCODER_EDP); +} + +static bool has_dsi_transcoders(u8 enabled_transcoders) +{ + return enabled_transcoders & (BIT(TRANSCODER_DSI_0) | + BIT(TRANSCODER_DSI_1)); +} + +static bool has_pipe_transcoders(u8 enabled_transcoders) +{ + return enabled_transcoders & ~(BIT(TRANSCODER_EDP) | + BIT(TRANSCODER_DSI_0) | + BIT(TRANSCODER_DSI_1)); +} + +static void assert_enabled_transcoders(struct drm_i915_private *i915, + u8 enabled_transcoders) +{ + /* Only one type of transcoder please */ + drm_WARN_ON(&i915->drm, + has_edp_transcoders(enabled_transcoders) + + has_dsi_transcoders(enabled_transcoders) + + has_pipe_transcoders(enabled_transcoders) > 1); + + /* Only DSI transcoders can be ganged */ + drm_WARN_ON(&i915->drm, + !has_dsi_transcoders(enabled_transcoders) && + !is_power_of_2(enabled_transcoders)); +} + +static bool hsw_get_transcoder_state(struct intel_crtc *crtc, + struct intel_crtc_state *pipe_config, + struct intel_display_power_domain_set *power_domain_set) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + unsigned long enabled_transcoders; + u32 tmp; + + enabled_transcoders = hsw_enabled_transcoders(crtc); + if (!enabled_transcoders) + return false; + + assert_enabled_transcoders(dev_priv, enabled_transcoders); + /* - * Valid combos: none, eDP, DSI0, DSI1, DSI0+DSI1 + * With the exception of DSI we should only ever have + * a single enabled transcoder. With DSI let's just + * pick the first one. */ - drm_WARN_ON(dev, (enabled_panel_transcoders & BIT(TRANSCODER_EDP)) && - enabled_panel_transcoders != BIT(TRANSCODER_EDP)); + pipe_config->cpu_transcoder = ffs(enabled_transcoders) - 1; if (!intel_display_power_get_in_set_if_enabled(dev_priv, power_domain_set, POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder))) return false; + if (hsw_panel_transcoders(dev_priv) & BIT(pipe_config->cpu_transcoder)) { + tmp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(pipe_config->cpu_transcoder)); + + if ((tmp & TRANS_DDI_EDP_INPUT_MASK) == TRANS_DDI_EDP_INPUT_A_ONOFF) + pipe_config->pch_pfit.force_thru = true; + } + tmp = intel_de_read(dev_priv, PIPECONF(pipe_config->cpu_transcoder)); return tmp & PIPECONF_ENABLE; @@ -5903,7 +5537,7 @@ static bool intel_crtc_get_pipe_config(struct intel_crtc_state *crtc_state) struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *i915 = to_i915(crtc->base.dev); - if (!i915->display.get_pipe_config(crtc, crtc_state)) + if (!i915->display->get_pipe_config(crtc, crtc_state)) return false; crtc_state->hw.active = true; @@ -6352,27 +5986,27 @@ static bool needs_scaling(const struct intel_plane_state *state) } int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *crtc_state, + struct intel_crtc_state *new_crtc_state, const struct intel_plane_state *old_plane_state, - struct intel_plane_state *plane_state) + struct intel_plane_state *new_plane_state) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); + struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - bool mode_changed = intel_crtc_needs_modeset(crtc_state); + bool mode_changed = intel_crtc_needs_modeset(new_crtc_state); bool was_crtc_enabled = old_crtc_state->hw.active; - bool is_crtc_enabled = crtc_state->hw.active; + bool is_crtc_enabled = new_crtc_state->hw.active; bool turn_off, turn_on, visible, was_visible; int ret; if (DISPLAY_VER(dev_priv) >= 9 && plane->id != PLANE_CURSOR) { - ret = skl_update_scaler_plane(crtc_state, plane_state); + ret = skl_update_scaler_plane(new_crtc_state, new_plane_state); if (ret) return ret; } was_visible = old_plane_state->uapi.visible; - visible = plane_state->uapi.visible; + visible = new_plane_state->uapi.visible; if (!was_crtc_enabled && drm_WARN_ON(&dev_priv->drm, was_visible)) was_visible = false; @@ -6388,7 +6022,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat * only combine the results from all planes in the current place? */ if (!is_crtc_enabled) { - intel_plane_set_invisible(crtc_state, plane_state); + intel_plane_set_invisible(new_crtc_state, new_plane_state); visible = false; } @@ -6407,28 +6041,28 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat if (turn_on) { if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) - crtc_state->update_wm_pre = true; + new_crtc_state->update_wm_pre = true; /* must disable cxsr around plane enable/disable */ if (plane->id != PLANE_CURSOR) - crtc_state->disable_cxsr = true; + new_crtc_state->disable_cxsr = true; } else if (turn_off) { if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) - crtc_state->update_wm_post = true; + new_crtc_state->update_wm_post = true; /* must disable cxsr around plane enable/disable */ if (plane->id != PLANE_CURSOR) - crtc_state->disable_cxsr = true; - } else if (intel_wm_need_update(old_plane_state, plane_state)) { + new_crtc_state->disable_cxsr = true; + } else if (intel_wm_need_update(old_plane_state, new_plane_state)) { if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) { /* FIXME bollocks */ - crtc_state->update_wm_pre = true; - crtc_state->update_wm_post = true; + new_crtc_state->update_wm_pre = true; + new_crtc_state->update_wm_post = true; } } if (visible || was_visible) - crtc_state->fb_bits |= plane->frontbuffer_bit; + new_crtc_state->fb_bits |= plane->frontbuffer_bit; /* * ILK/SNB DVSACNTR/Sprite Enable @@ -6467,8 +6101,8 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat (IS_IRONLAKE(dev_priv) || IS_SANDYBRIDGE(dev_priv) || IS_IVYBRIDGE(dev_priv)) && (turn_on || (!needs_scaling(old_plane_state) && - needs_scaling(plane_state)))) - crtc_state->disable_lp_wm = true; + needs_scaling(new_plane_state)))) + new_crtc_state->disable_lp_wm = true; return 0; } @@ -6730,10 +6364,10 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, crtc_state->update_wm_post = true; if (mode_changed && crtc_state->hw.enable && - dev_priv->display.crtc_compute_clock && + dev_priv->dpll_funcs && !crtc_state->bigjoiner_slave && !drm_WARN_ON(&dev_priv->drm, crtc_state->shared_dpll)) { - ret = dev_priv->display.crtc_compute_clock(crtc_state); + ret = dev_priv->dpll_funcs->crtc_compute_clock(crtc_state); if (ret) return ret; } @@ -6752,32 +6386,23 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, return ret; } - if (dev_priv->display.compute_pipe_wm) { - ret = dev_priv->display.compute_pipe_wm(state, crtc); - if (ret) { - drm_dbg_kms(&dev_priv->drm, - "Target pipe watermarks are invalid\n"); - return ret; - } - + ret = intel_compute_pipe_wm(state, crtc); + if (ret) { + drm_dbg_kms(&dev_priv->drm, + "Target pipe watermarks are invalid\n"); + return ret; } - if (dev_priv->display.compute_intermediate_wm) { - if (drm_WARN_ON(&dev_priv->drm, - !dev_priv->display.compute_pipe_wm)) - return 0; - - /* - * Calculate 'intermediate' watermarks that satisfy both the - * old state and the new state. We can program these - * immediately. - */ - ret = dev_priv->display.compute_intermediate_wm(state, crtc); - if (ret) { - drm_dbg_kms(&dev_priv->drm, - "No valid intermediate pipe watermarks are possible\n"); - return ret; - } + /* + * Calculate 'intermediate' watermarks that satisfy both the + * old state and the new state. We can program these + * immediately. + */ + ret = intel_compute_intermediate_wm(state, crtc); + if (ret) { + drm_dbg_kms(&dev_priv->drm, + "No valid intermediate pipe watermarks are possible\n"); + return ret; } if (DISPLAY_VER(dev_priv) >= 9) { @@ -6806,11 +6431,9 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, } - if (!mode_changed) { - ret = intel_psr2_sel_fetch_update(state, crtc); - if (ret) - return ret; - } + ret = intel_psr2_sel_fetch_update(state, crtc); + if (ret) + return ret; return 0; } @@ -7520,11 +7143,10 @@ encoder_retry: ret = encoder->compute_config(encoder, pipe_config, connector_state); + if (ret == -EDEADLK) + return ret; if (ret < 0) { - if (ret != -EDEADLK) - drm_dbg_kms(&i915->drm, - "Encoder config failure: %d\n", - ret); + drm_dbg_kms(&i915->drm, "Encoder config failure: %d\n", ret); return ret; } } @@ -7538,12 +7160,7 @@ encoder_retry: ret = intel_crtc_compute_config(to_intel_crtc(crtc), pipe_config); if (ret == -EDEADLK) return ret; - if (ret < 0) { - drm_dbg_kms(&i915->drm, "CRTC fixup failed\n"); - return ret; - } - - if (ret == I915_DISPLAY_CONFIG_RETRY) { + if (ret == -EAGAIN) { if (drm_WARN(&i915->drm, !retry, "loop in pipe configuration computation\n")) return -EINVAL; @@ -7552,6 +7169,10 @@ encoder_retry: retry = false; goto encoder_retry; } + if (ret < 0) { + drm_dbg_kms(&i915->drm, "CRTC config failure: %d\n", ret); + return ret; + } /* Dithering seems to not pass-through bits correctly when it should, so * only enable it on 6bpc panels and when its not a compliance @@ -8087,10 +7708,12 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, if (bp_gamma) PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, hw.gamma_lut, bp_gamma); - PIPE_CONF_CHECK_BOOL(has_psr); - PIPE_CONF_CHECK_BOOL(has_psr2); - PIPE_CONF_CHECK_BOOL(enable_psr2_sel_fetch); - PIPE_CONF_CHECK_I(dc3co_exitline); + if (current_config->active_planes) { + PIPE_CONF_CHECK_BOOL(has_psr); + PIPE_CONF_CHECK_BOOL(has_psr2); + PIPE_CONF_CHECK_BOOL(enable_psr2_sel_fetch); + PIPE_CONF_CHECK_I(dc3co_exitline); + } } PIPE_CONF_CHECK_BOOL(double_wide); @@ -8147,7 +7770,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(min_voltage_level); } - if (fastset && (current_config->has_psr || pipe_config->has_psr)) + if (current_config->has_psr || pipe_config->has_psr) PIPE_CONF_CHECK_X_WITH_MASK(infoframes.enable, ~intel_hdmi_infoframe_enable(DP_SDP_VSC)); else @@ -8769,7 +8392,7 @@ static void intel_modeset_clear_plls(struct intel_atomic_state *state) struct intel_crtc *crtc; int i; - if (!dev_priv->display.crtc_compute_clock) + if (!dev_priv->dpll_funcs) return; for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { @@ -8870,23 +8493,6 @@ static int intel_modeset_checks(struct intel_atomic_state *state) return 0; } -/* - * Handle calculation of various watermark data at the end of the atomic check - * phase. The code here should be run after the per-crtc and per-plane 'check' - * handlers to ensure that all derived state has been updated. - */ -static int calc_watermark_data(struct intel_atomic_state *state) -{ - struct drm_device *dev = state->base.dev; - struct drm_i915_private *dev_priv = to_i915(dev); - - /* Is there platform-specific watermark information to calculate? */ - if (dev_priv->display.compute_global_watermarks) - return dev_priv->display.compute_global_watermarks(state); - - return 0; -} - static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *new_crtc_state) { @@ -8994,13 +8600,28 @@ static int intel_bigjoiner_add_affected_planes(struct intel_atomic_state *state) return 0; } +static bool bo_has_valid_encryption(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + + return intel_pxp_key_check(&i915->gt.pxp, obj, false) == 0; +} + +static bool pxp_is_borked(struct drm_i915_gem_object *obj) +{ + return i915_gem_object_is_protected(obj) && !bo_has_valid_encryption(obj); +} + static int intel_atomic_check_planes(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_crtc_state *old_crtc_state, *new_crtc_state; struct intel_plane_state *plane_state; struct intel_plane *plane; + struct intel_plane_state *new_plane_state; + struct intel_plane_state *old_plane_state; struct intel_crtc *crtc; + const struct drm_framebuffer *fb; int i, ret; ret = icl_add_linked_planes(state); @@ -9048,6 +8669,19 @@ static int intel_atomic_check_planes(struct intel_atomic_state *state) return ret; } + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + new_plane_state = intel_atomic_get_new_plane_state(state, plane); + old_plane_state = intel_atomic_get_old_plane_state(state, plane); + fb = new_plane_state->hw.fb; + if (fb) { + new_plane_state->decrypt = bo_has_valid_encryption(intel_fb_obj(fb)); + new_plane_state->force_black = pxp_is_borked(intel_fb_obj(fb)); + } else { + new_plane_state->decrypt = old_plane_state->decrypt; + new_plane_state->force_black = old_plane_state->force_black; + } + } + return 0; } @@ -9082,7 +8716,7 @@ static int intel_atomic_check_cdclk(struct intel_atomic_state *state, old_cdclk_state->force_min_cdclk != new_cdclk_state->force_min_cdclk) *need_cdclk_calc = true; - ret = dev_priv->display.bw_calc_min_cdclk(state); + ret = intel_cdclk_bw_calc_min_cdclk(state); if (ret) return ret; @@ -9334,6 +8968,10 @@ static int intel_atomic_check_async(struct intel_atomic_state *state) drm_dbg_kms(&i915->drm, "Color range cannot be changed in async flip\n"); return -EINVAL; } + + /* plane decryption is allow to change only in synchronous flips */ + if (old_plane_state->decrypt != new_plane_state->decrypt) + return -EINVAL; } return 0; @@ -9533,7 +9171,7 @@ static int intel_atomic_check(struct drm_device *dev, goto fail; intel_fbc_choose_crtc(dev_priv, state); - ret = calc_watermark_data(state); + ret = intel_compute_global_watermarks(state); if (ret) goto fail; @@ -9703,12 +9341,11 @@ static void commit_pipe_pre_planes(struct intel_atomic_state *state, if (new_crtc_state->update_pipe) intel_pipe_fastset(old_crtc_state, new_crtc_state); - - intel_psr2_program_trans_man_trk_ctl(new_crtc_state); } - if (dev_priv->display.atomic_update_watermarks) - dev_priv->display.atomic_update_watermarks(state, crtc); + intel_psr2_program_trans_man_trk_ctl(new_crtc_state); + + intel_atomic_update_watermarks(state, crtc); } static void commit_pipe_post_planes(struct intel_atomic_state *state, @@ -9740,7 +9377,7 @@ static void intel_enable_crtc(struct intel_atomic_state *state, intel_crtc_update_active_timings(new_crtc_state); - dev_priv->display.crtc_enable(state, crtc); + dev_priv->display->crtc_enable(state, crtc); if (new_crtc_state->bigjoiner_slave) return; @@ -9828,16 +9465,15 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state, */ intel_crtc_disable_pipe_crc(crtc); - dev_priv->display.crtc_disable(state, crtc); + dev_priv->display->crtc_disable(state, crtc); crtc->active = false; intel_fbc_disable(crtc); intel_disable_shared_dpll(old_crtc_state); /* FIXME unify this for all platforms */ if (!new_crtc_state->hw.active && - !HAS_GMCH(dev_priv) && - dev_priv->display.initial_watermarks) - dev_priv->display.initial_watermarks(state, crtc); + !HAS_GMCH(dev_priv)) + intel_initial_watermarks(state, crtc); } static void intel_commit_modeset_disables(struct intel_atomic_state *state) @@ -10201,6 +9837,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) intel_encoders_update_prepare(state); intel_dbuf_pre_plane_update(state); + intel_psr_pre_plane_update(state); for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { if (new_crtc_state->uapi.async_flip) @@ -10208,7 +9845,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) } /* Now enable the clocks, plane, pipe, and connectors that we set up. */ - dev_priv->display.commit_modeset_enables(state); + dev_priv->display->commit_modeset_enables(state); if (state->modeset) { intel_encoders_update_complete(state); @@ -10259,11 +9896,11 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) if (DISPLAY_VER(dev_priv) == 2 && planes_enabling(old_crtc_state, new_crtc_state)) intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true); - if (dev_priv->display.optimize_watermarks) - dev_priv->display.optimize_watermarks(state, crtc); + intel_optimize_watermarks(state, crtc); } intel_dbuf_post_plane_update(state); + intel_psr_post_plane_update(state); for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { intel_post_plane_update(state, crtc); @@ -10452,280 +10089,6 @@ static int intel_atomic_commit(struct drm_device *dev, return 0; } -struct wait_rps_boost { - struct wait_queue_entry wait; - - struct drm_crtc *crtc; - struct i915_request *request; -}; - -static int do_rps_boost(struct wait_queue_entry *_wait, - unsigned mode, int sync, void *key) -{ - struct wait_rps_boost *wait = container_of(_wait, typeof(*wait), wait); - struct i915_request *rq = wait->request; - - /* - * If we missed the vblank, but the request is already running it - * is reasonable to assume that it will complete before the next - * vblank without our intervention, so leave RPS alone. - */ - if (!i915_request_started(rq)) - intel_rps_boost(rq); - i915_request_put(rq); - - drm_crtc_vblank_put(wait->crtc); - - list_del(&wait->wait.entry); - kfree(wait); - return 1; -} - -static void add_rps_boost_after_vblank(struct drm_crtc *crtc, - struct dma_fence *fence) -{ - struct wait_rps_boost *wait; - - if (!dma_fence_is_i915(fence)) - return; - - if (DISPLAY_VER(to_i915(crtc->dev)) < 6) - return; - - if (drm_crtc_vblank_get(crtc)) - return; - - wait = kmalloc(sizeof(*wait), GFP_KERNEL); - if (!wait) { - drm_crtc_vblank_put(crtc); - return; - } - - wait->request = to_request(dma_fence_get(fence)); - wait->crtc = crtc; - - wait->wait.func = do_rps_boost; - wait->wait.flags = 0; - - add_wait_queue(drm_crtc_vblank_waitqueue(crtc), &wait->wait); -} - -int intel_plane_pin_fb(struct intel_plane_state *plane_state) -{ - struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - struct drm_framebuffer *fb = plane_state->hw.fb; - struct i915_vma *vma; - bool phys_cursor = - plane->id == PLANE_CURSOR && - INTEL_INFO(dev_priv)->display.cursor_needs_physical; - - if (!intel_fb_uses_dpt(fb)) { - vma = intel_pin_and_fence_fb_obj(fb, phys_cursor, - &plane_state->view.gtt, - intel_plane_uses_fence(plane_state), - &plane_state->flags); - if (IS_ERR(vma)) - return PTR_ERR(vma); - - plane_state->ggtt_vma = vma; - } else { - struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); - - vma = intel_dpt_pin(intel_fb->dpt_vm); - if (IS_ERR(vma)) - return PTR_ERR(vma); - - plane_state->ggtt_vma = vma; - - vma = intel_pin_fb_obj_dpt(fb, &plane_state->view.gtt, false, - &plane_state->flags, intel_fb->dpt_vm); - if (IS_ERR(vma)) { - intel_dpt_unpin(intel_fb->dpt_vm); - plane_state->ggtt_vma = NULL; - return PTR_ERR(vma); - } - - plane_state->dpt_vma = vma; - - WARN_ON(plane_state->ggtt_vma == plane_state->dpt_vma); - } - - return 0; -} - -void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state) -{ - struct drm_framebuffer *fb = old_plane_state->hw.fb; - struct i915_vma *vma; - - if (!intel_fb_uses_dpt(fb)) { - vma = fetch_and_zero(&old_plane_state->ggtt_vma); - if (vma) - intel_unpin_fb_vma(vma, old_plane_state->flags); - } else { - struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); - - vma = fetch_and_zero(&old_plane_state->dpt_vma); - if (vma) - intel_unpin_fb_vma(vma, old_plane_state->flags); - - vma = fetch_and_zero(&old_plane_state->ggtt_vma); - if (vma) - intel_dpt_unpin(intel_fb->dpt_vm); - } -} - -/** - * intel_prepare_plane_fb - Prepare fb for usage on plane - * @_plane: drm plane to prepare for - * @_new_plane_state: the plane state being prepared - * - * Prepares a framebuffer for usage on a display plane. Generally this - * involves pinning the underlying object and updating the frontbuffer tracking - * bits. Some older platforms need special physical address handling for - * cursor planes. - * - * Returns 0 on success, negative error code on failure. - */ -int -intel_prepare_plane_fb(struct drm_plane *_plane, - struct drm_plane_state *_new_plane_state) -{ - struct i915_sched_attr attr = { .priority = I915_PRIORITY_DISPLAY }; - struct intel_plane *plane = to_intel_plane(_plane); - struct intel_plane_state *new_plane_state = - to_intel_plane_state(_new_plane_state); - struct intel_atomic_state *state = - to_intel_atomic_state(new_plane_state->uapi.state); - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - const struct intel_plane_state *old_plane_state = - intel_atomic_get_old_plane_state(state, plane); - struct drm_i915_gem_object *obj = intel_fb_obj(new_plane_state->hw.fb); - struct drm_i915_gem_object *old_obj = intel_fb_obj(old_plane_state->hw.fb); - int ret; - - if (old_obj) { - const struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, - to_intel_crtc(old_plane_state->hw.crtc)); - - /* Big Hammer, we also need to ensure that any pending - * MI_WAIT_FOR_EVENT inside a user batch buffer on the - * current scanout is retired before unpinning the old - * framebuffer. Note that we rely on userspace rendering - * into the buffer attached to the pipe they are waiting - * on. If not, userspace generates a GPU hang with IPEHR - * point to the MI_WAIT_FOR_EVENT. - * - * This should only fail upon a hung GPU, in which case we - * can safely continue. - */ - if (intel_crtc_needs_modeset(crtc_state)) { - ret = i915_sw_fence_await_reservation(&state->commit_ready, - old_obj->base.resv, NULL, - false, 0, - GFP_KERNEL); - if (ret < 0) - return ret; - } - } - - if (new_plane_state->uapi.fence) { /* explicit fencing */ - i915_gem_fence_wait_priority(new_plane_state->uapi.fence, - &attr); - ret = i915_sw_fence_await_dma_fence(&state->commit_ready, - new_plane_state->uapi.fence, - i915_fence_timeout(dev_priv), - GFP_KERNEL); - if (ret < 0) - return ret; - } - - if (!obj) - return 0; - - - ret = intel_plane_pin_fb(new_plane_state); - if (ret) - return ret; - - i915_gem_object_wait_priority(obj, 0, &attr); - i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB); - - if (!new_plane_state->uapi.fence) { /* implicit fencing */ - struct dma_fence *fence; - - ret = i915_sw_fence_await_reservation(&state->commit_ready, - obj->base.resv, NULL, - false, - i915_fence_timeout(dev_priv), - GFP_KERNEL); - if (ret < 0) - goto unpin_fb; - - fence = dma_resv_get_excl_unlocked(obj->base.resv); - if (fence) { - add_rps_boost_after_vblank(new_plane_state->hw.crtc, - fence); - dma_fence_put(fence); - } - } else { - add_rps_boost_after_vblank(new_plane_state->hw.crtc, - new_plane_state->uapi.fence); - } - - /* - * We declare pageflips to be interactive and so merit a small bias - * towards upclocking to deliver the frame on time. By only changing - * the RPS thresholds to sample more regularly and aim for higher - * clocks we can hopefully deliver low power workloads (like kodi) - * that are not quite steady state without resorting to forcing - * maximum clocks following a vblank miss (see do_rps_boost()). - */ - if (!state->rps_interactive) { - intel_rps_mark_interactive(&dev_priv->gt.rps, true); - state->rps_interactive = true; - } - - return 0; - -unpin_fb: - intel_plane_unpin_fb(new_plane_state); - - return ret; -} - -/** - * intel_cleanup_plane_fb - Cleans up an fb after plane use - * @plane: drm plane to clean up for - * @_old_plane_state: the state from the previous modeset - * - * Cleans up a framebuffer that has just been removed from a plane. - */ -void -intel_cleanup_plane_fb(struct drm_plane *plane, - struct drm_plane_state *_old_plane_state) -{ - struct intel_plane_state *old_plane_state = - to_intel_plane_state(_old_plane_state); - struct intel_atomic_state *state = - to_intel_atomic_state(old_plane_state->uapi.state); - struct drm_i915_private *dev_priv = to_i915(plane->dev); - struct drm_i915_gem_object *obj = intel_fb_obj(old_plane_state->hw.fb); - - if (!obj) - return; - - if (state->rps_interactive) { - intel_rps_mark_interactive(&dev_priv->gt.rps, false); - state->rps_interactive = false; - } - - /* Should only be called after a successful intel_prepare_plane_fb()! */ - intel_plane_unpin_fb(old_plane_state); -} - /** * intel_plane_destroy - destroy a plane * @plane: plane to destroy @@ -11161,6 +10524,14 @@ intel_mode_valid(struct drm_device *dev, return MODE_V_ILLEGAL; } + /* + * Cantiga+ cannot handle modes with a hsync front porch of 0. + * WaPruneModeWithIncorrectHsyncOffset:ctg,elk,ilk,snb,ivb,vlv,hsw. + */ + if ((DISPLAY_VER(dev_priv) > 4 || IS_G4X(dev_priv)) && + mode->hsync_start == mode->hdisplay) + return MODE_H_ILLEGAL; + return MODE_OK; } @@ -11212,6 +10583,46 @@ static const struct drm_mode_config_funcs intel_mode_funcs = { .atomic_state_free = intel_atomic_state_free, }; +static const struct drm_i915_display_funcs skl_display_funcs = { + .get_pipe_config = hsw_get_pipe_config, + .crtc_enable = hsw_crtc_enable, + .crtc_disable = hsw_crtc_disable, + .commit_modeset_enables = skl_commit_modeset_enables, + .get_initial_plane_config = skl_get_initial_plane_config, +}; + +static const struct drm_i915_display_funcs ddi_display_funcs = { + .get_pipe_config = hsw_get_pipe_config, + .crtc_enable = hsw_crtc_enable, + .crtc_disable = hsw_crtc_disable, + .commit_modeset_enables = intel_commit_modeset_enables, + .get_initial_plane_config = i9xx_get_initial_plane_config, +}; + +static const struct drm_i915_display_funcs pch_split_display_funcs = { + .get_pipe_config = ilk_get_pipe_config, + .crtc_enable = ilk_crtc_enable, + .crtc_disable = ilk_crtc_disable, + .commit_modeset_enables = intel_commit_modeset_enables, + .get_initial_plane_config = i9xx_get_initial_plane_config, +}; + +static const struct drm_i915_display_funcs vlv_display_funcs = { + .get_pipe_config = i9xx_get_pipe_config, + .crtc_enable = valleyview_crtc_enable, + .crtc_disable = i9xx_crtc_disable, + .commit_modeset_enables = intel_commit_modeset_enables, + .get_initial_plane_config = i9xx_get_initial_plane_config, +}; + +static const struct drm_i915_display_funcs i9xx_display_funcs = { + .get_pipe_config = i9xx_get_pipe_config, + .crtc_enable = i9xx_crtc_enable, + .crtc_disable = i9xx_crtc_disable, + .commit_modeset_enables = intel_commit_modeset_enables, + .get_initial_plane_config = i9xx_get_initial_plane_config, +}; + /** * intel_init_display_hooks - initialize the display modesetting hooks * @dev_priv: device private @@ -11227,38 +10638,19 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) intel_dpll_init_clock_hook(dev_priv); if (DISPLAY_VER(dev_priv) >= 9) { - dev_priv->display.get_pipe_config = hsw_get_pipe_config; - dev_priv->display.crtc_enable = hsw_crtc_enable; - dev_priv->display.crtc_disable = hsw_crtc_disable; + dev_priv->display = &skl_display_funcs; } else if (HAS_DDI(dev_priv)) { - dev_priv->display.get_pipe_config = hsw_get_pipe_config; - dev_priv->display.crtc_enable = hsw_crtc_enable; - dev_priv->display.crtc_disable = hsw_crtc_disable; + dev_priv->display = &ddi_display_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->display.get_pipe_config = ilk_get_pipe_config; - dev_priv->display.crtc_enable = ilk_crtc_enable; - dev_priv->display.crtc_disable = ilk_crtc_disable; + dev_priv->display = &pch_split_display_funcs; } else if (IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv)) { - dev_priv->display.get_pipe_config = i9xx_get_pipe_config; - dev_priv->display.crtc_enable = valleyview_crtc_enable; - dev_priv->display.crtc_disable = i9xx_crtc_disable; + dev_priv->display = &vlv_display_funcs; } else { - dev_priv->display.get_pipe_config = i9xx_get_pipe_config; - dev_priv->display.crtc_enable = i9xx_crtc_enable; - dev_priv->display.crtc_disable = i9xx_crtc_disable; + dev_priv->display = &i9xx_display_funcs; } intel_fdi_init_hook(dev_priv); - - if (DISPLAY_VER(dev_priv) >= 9) { - dev_priv->display.commit_modeset_enables = skl_commit_modeset_enables; - dev_priv->display.get_initial_plane_config = skl_get_initial_plane_config; - } else { - dev_priv->display.commit_modeset_enables = intel_commit_modeset_enables; - dev_priv->display.get_initial_plane_config = i9xx_get_initial_plane_config; - } - } void intel_modeset_init_hw(struct drm_i915_private *i915) @@ -11328,7 +10720,7 @@ static void sanitize_watermarks(struct drm_i915_private *dev_priv) int i; /* Only supported on platforms that use atomic watermark design */ - if (!dev_priv->display.optimize_watermarks) + if (!dev_priv->wm_disp->optimize_watermarks) return; state = drm_atomic_state_alloc(&dev_priv->drm); @@ -11361,7 +10753,7 @@ retry: /* Write calculated watermark values back */ for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) { crtc_state->wm.need_postvbl_update = true; - dev_priv->display.optimize_watermarks(intel_state, crtc); + intel_optimize_watermarks(intel_state, crtc); to_intel_crtc_state(crtc->base.state)->wm = crtc_state->wm; } @@ -11526,22 +10918,6 @@ static void intel_mode_config_cleanup(struct drm_i915_private *i915) drm_mode_config_cleanup(&i915->drm); } -static void plane_config_fini(struct intel_initial_plane_config *plane_config) -{ - if (plane_config->fb) { - struct drm_framebuffer *fb = &plane_config->fb->base; - - /* We may only have the stub and not a full framebuffer */ - if (drm_framebuffer_read_refcount(fb)) - drm_framebuffer_put(fb); - else - kfree(fb); - } - - if (plane_config->vma) - i915_vma_put(plane_config->vma); -} - /* part #1: call before irq install */ int intel_modeset_init_noirq(struct drm_i915_private *i915) { @@ -11674,27 +11050,9 @@ int intel_modeset_init_nogem(struct drm_i915_private *i915) drm_modeset_unlock_all(dev); for_each_intel_crtc(dev, crtc) { - struct intel_initial_plane_config plane_config = {}; - if (!to_intel_crtc_state(crtc->base.state)->uapi.active) continue; - - /* - * Note that reserving the BIOS fb up front prevents us - * from stuffing other stolen allocations like the ring - * on top. This prevents some ugliness at boot time, and - * can even allow for smooth boot transitions if the BIOS - * fb is large enough for the active pipe configuration. - */ - i915->display.get_initial_plane_config(crtc, &plane_config); - - /* - * If the fb is shared between multiple heads, we'll - * just get the first one. - */ - intel_find_initial_plane_obj(crtc, &plane_config); - - plane_config_fini(&plane_config); + intel_crtc_initial_plane_config(crtc); } /* @@ -11976,13 +11334,8 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc, intel_plane_disable_noatomic(crtc, plane); } - /* - * Disable any background color set by the BIOS, but enable the - * gamma and CSC to match how we program our planes. - */ - if (DISPLAY_VER(dev_priv) >= 9) - intel_de_write(dev_priv, SKL_BOTTOM_COLOR(crtc->pipe), - SKL_BOTTOM_COLOR_GAMMA_ENABLE | SKL_BOTTOM_COLOR_CSC_ENABLE); + /* Disable any background color/etc. set by the BIOS */ + intel_color_commit(crtc_state); } /* Adjust the state of the output pipe according to whether we diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index 4719ffc97fce..0c76bf57f86b 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -270,6 +270,7 @@ enum tc_port { }; enum tc_port_mode { + TC_PORT_DISCONNECTED, TC_PORT_TBT_ALT, TC_PORT_DP_ALT, TC_PORT_LEGACY, @@ -531,8 +532,8 @@ enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port); bool is_trans_port_sync_mode(const struct intel_crtc_state *state); void intel_plane_destroy(struct drm_plane *plane); -void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state); -void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state); +void intel_enable_transcoder(const struct intel_crtc_state *new_crtc_state); +void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state); void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe); void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe); enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc); @@ -575,19 +576,9 @@ int intel_get_load_detect_pipe(struct drm_connector *connector, void intel_release_load_detect_pipe(struct drm_connector *connector, struct intel_load_detect_pipe *old, struct drm_modeset_acquire_ctx *ctx); -struct i915_vma * -intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, bool phys_cursor, - const struct i915_ggtt_view *view, - bool uses_fence, - unsigned long *out_flags); -void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags); struct drm_framebuffer * intel_framebuffer_create(struct drm_i915_gem_object *obj, struct drm_mode_fb_cmd2 *mode_cmd); -int intel_prepare_plane_fb(struct drm_plane *plane, - struct drm_plane_state *new_state); -void intel_cleanup_plane_fb(struct drm_plane *plane, - struct drm_plane_state *old_state); void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv, enum pipe pipe); @@ -618,15 +609,16 @@ void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state); int bdw_get_pipemisc_bpp(struct intel_crtc *crtc); unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state); +bool intel_plane_uses_fence(const struct intel_plane_state *plane_state); bool intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info, u64 modifier); -int intel_plane_pin_fb(struct intel_plane_state *plane_state); -void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state); struct intel_encoder * intel_get_crtc_new_encoder(const struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state); +void intel_plane_disable_noatomic(struct intel_crtc *crtc, + struct intel_plane *plane); void intel_display_driver_register(struct drm_i915_private *i915); void intel_display_driver_unregister(struct drm_i915_private *i915); @@ -644,23 +636,10 @@ void intel_init_pch_refclk(struct drm_i915_private *dev_priv); int intel_modeset_all_pipes(struct intel_atomic_state *state); /* modesetting asserts */ -void assert_panel_unlocked(struct drm_i915_private *dev_priv, - enum pipe pipe); -void assert_pll(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state); -#define assert_pll_enabled(d, p) assert_pll(d, p, true) -#define assert_pll_disabled(d, p) assert_pll(d, p, false) -void assert_dsi_pll(struct drm_i915_private *dev_priv, bool state); -#define assert_dsi_pll_enabled(d) assert_dsi_pll(d, true) -#define assert_dsi_pll_disabled(d) assert_dsi_pll(d, false) -void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state); -#define assert_fdi_rx_pll_enabled(d, p) assert_fdi_rx_pll(d, p, true) -#define assert_fdi_rx_pll_disabled(d, p) assert_fdi_rx_pll(d, p, false) -void assert_pipe(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder, bool state); -#define assert_pipe_enabled(d, t) assert_pipe(d, t, true) -#define assert_pipe_disabled(d, t) assert_pipe(d, t, false) +void assert_transcoder(struct drm_i915_private *dev_priv, + enum transcoder cpu_transcoder, bool state); +#define assert_transcoder_enabled(d, t) assert_transcoder(d, t, true) +#define assert_transcoder_disabled(d, t) assert_transcoder(d, t, false) /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and * WARN_ON()) for hw state sanity checks to check for unexpected conditions diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 68f4ba8c46e7..e04767695530 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -7,19 +7,19 @@ #include #include "i915_debugfs.h" +#include "intel_de.h" #include "intel_display_debugfs.h" #include "intel_display_power.h" -#include "intel_de.h" #include "intel_display_types.h" #include "intel_dmc.h" #include "intel_dp.h" +#include "intel_dp_mst.h" #include "intel_drrs.h" #include "intel_fbc.h" #include "intel_hdcp.h" #include "intel_hdmi.h" #include "intel_pm.h" #include "intel_psr.h" -#include "intel_sideband.h" #include "intel_sprite.h" static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node) @@ -1379,7 +1379,7 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused) continue; dig_port = enc_to_dig_port(intel_encoder); - if (!dig_port->dp.can_mst) + if (!intel_dp_mst_source_support(&dig_port->dp)) continue; seq_printf(m, "MST Source Port [ENCODER:%d:%s]\n", @@ -2442,17 +2442,16 @@ static const struct file_operations i915_dsc_bpp_fops = { * * Cleanup will be done by drm_connector_unregister() through a call to * drm_debugfs_connector_remove(). - * - * Returns 0 on success, negative error codes on error. */ -int intel_connector_debugfs_add(struct drm_connector *connector) +void intel_connector_debugfs_add(struct intel_connector *intel_connector) { + struct drm_connector *connector = &intel_connector->base; struct dentry *root = connector->debugfs_entry; struct drm_i915_private *dev_priv = to_i915(connector->dev); /* The connector must have been registered beforehands. */ if (!root) - return -ENODEV; + return; if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { debugfs_create_file("i915_panel_timings", S_IRUGO, root, @@ -2485,33 +2484,23 @@ int intel_connector_debugfs_add(struct drm_connector *connector) connector, &i915_dsc_bpp_fops); } - /* Legacy panels doesn't lpsp on any platform */ - if ((DISPLAY_VER(dev_priv) >= 9 || IS_HASWELL(dev_priv) || - IS_BROADWELL(dev_priv)) && - (connector->connector_type == DRM_MODE_CONNECTOR_DSI || - connector->connector_type == DRM_MODE_CONNECTOR_eDP || - connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || - connector->connector_type == DRM_MODE_CONNECTOR_HDMIA || - connector->connector_type == DRM_MODE_CONNECTOR_HDMIB)) + if (connector->connector_type == DRM_MODE_CONNECTOR_DSI || + connector->connector_type == DRM_MODE_CONNECTOR_eDP || + connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector->connector_type == DRM_MODE_CONNECTOR_HDMIA || + connector->connector_type == DRM_MODE_CONNECTOR_HDMIB) debugfs_create_file("i915_lpsp_capability", 0444, root, connector, &i915_lpsp_capability_fops); - - return 0; } /** * intel_crtc_debugfs_add - add i915 specific crtc debugfs files * @crtc: pointer to a drm_crtc * - * Returns 0 on success, negative error codes on error. - * * Failure to add debugfs entries should generally be ignored. */ -int intel_crtc_debugfs_add(struct drm_crtc *crtc) +void intel_crtc_debugfs_add(struct drm_crtc *crtc) { - if (!crtc->debugfs_entry) - return -ENODEV; - - crtc_updates_add(crtc); - return 0; + if (crtc->debugfs_entry) + crtc_updates_add(crtc); } diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.h b/drivers/gpu/drm/i915/display/intel_display_debugfs.h index 557901f3eb90..d3a79c07c384 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.h +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.h @@ -6,18 +6,18 @@ #ifndef __INTEL_DISPLAY_DEBUGFS_H__ #define __INTEL_DISPLAY_DEBUGFS_H__ -struct drm_connector; struct drm_crtc; struct drm_i915_private; +struct intel_connector; #ifdef CONFIG_DEBUG_FS void intel_display_debugfs_register(struct drm_i915_private *i915); -int intel_connector_debugfs_add(struct drm_connector *connector); -int intel_crtc_debugfs_add(struct drm_crtc *crtc); +void intel_connector_debugfs_add(struct intel_connector *connector); +void intel_crtc_debugfs_add(struct drm_crtc *crtc); #else static inline void intel_display_debugfs_register(struct drm_i915_private *i915) {} -static inline int intel_connector_debugfs_add(struct drm_connector *connector) { return 0; } -static inline int intel_crtc_debugfs_add(struct drm_crtc *crtc) { return 0; } +static inline void intel_connector_debugfs_add(struct intel_connector *connector) {} +static inline void intel_crtc_debugfs_add(struct drm_crtc *crtc) {} #endif #endif /* __INTEL_DISPLAY_DEBUGFS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index cce1a926fcc1..1672604f9ef7 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -3,24 +3,25 @@ * Copyright © 2019 Intel Corporation */ -#include "display/intel_crt.h" - #include "i915_drv.h" #include "i915_irq.h" #include "intel_cdclk.h" #include "intel_combo_phy.h" -#include "intel_display_power.h" +#include "intel_crt.h" #include "intel_de.h" +#include "intel_display_power.h" #include "intel_display_types.h" #include "intel_dmc.h" #include "intel_dpio_phy.h" +#include "intel_dpll.h" #include "intel_hotplug.h" +#include "intel_pcode.h" #include "intel_pm.h" #include "intel_pps.h" -#include "intel_sideband.h" #include "intel_snps_phy.h" #include "intel_tc.h" #include "intel_vga.h" +#include "vlv_sideband.h" bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv, enum i915_power_well_id power_well_id); @@ -560,7 +561,7 @@ static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv, if (drm_WARN_ON(&dev_priv->drm, !dig_port)) return; - if (DISPLAY_VER(dev_priv) == 11 && dig_port->tc_legacy_port) + if (DISPLAY_VER(dev_priv) == 11 && intel_tc_cold_requires_aux_pw(dig_port)) return; drm_WARN_ON(&dev_priv->drm, !intel_tc_port_ref_held(dig_port)); @@ -629,7 +630,7 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, * exit sequence. */ timeout_expected = is_tbt || intel_tc_cold_requires_aux_pw(dig_port); - if (DISPLAY_VER(dev_priv) == 11 && dig_port->tc_legacy_port) + if (DISPLAY_VER(dev_priv) == 11 && intel_tc_cold_requires_aux_pw(dig_port)) icl_tc_cold_exit(dev_priv); hsw_wait_for_power_well_enable(dev_priv, power_well, timeout_expected); @@ -1195,7 +1196,7 @@ static void gen9_disable_dc_states(struct drm_i915_private *dev_priv) if (!HAS_DISPLAY(dev_priv)) return; - dev_priv->display.get_cdclk(dev_priv, &cdclk_config); + intel_cdclk_get_cdclk(dev_priv, &cdclk_config); /* Can't read out voltage_level so can't use intel_cdclk_changed() */ drm_WARN_ON(&dev_priv->drm, intel_cdclk_needs_modeset(&dev_priv->cdclk.hw, diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h index 978531841fa3..0612e4b6e3c8 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.h +++ b/drivers/gpu/drm/i915/display/intel_display_power.h @@ -410,6 +410,10 @@ void gen9_dbuf_slices_update(struct drm_i915_private *dev_priv, for ((wf) = intel_display_power_get((i915), (domain)); (wf); \ intel_display_power_put_async((i915), (domain), (wf)), (wf) = 0) +#define with_intel_display_power_if_enabled(i915, domain, wf) \ + for ((wf) = intel_display_power_get_if_enabled((i915), (domain)); (wf); \ + intel_display_power_put_async((i915), (domain), (wf)), (wf) = 0) + void chv_phy_powergate_lanes(struct intel_encoder *encoder, bool override, unsigned int mask); bool chv_phy_powergate_ch(struct drm_i915_private *dev_priv, enum dpio_phy phy, diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index e9e806d90eec..39e11eaec1a3 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -103,8 +103,6 @@ struct intel_fb_view { * in the rotated and remapped GTT view all no-CCS formats (up to 2 * color planes) are supported. * - * TODO: add support for CCS formats in the remapped GTT view. - * * The view information shared by all FB color planes in the FB, * like dst x/y and src/dst width, is stored separately in * intel_plane_state. @@ -271,6 +269,9 @@ struct intel_encoder { const struct intel_ddi_buf_trans *(*get_buf_trans)(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, int *n_entries); + void (*set_signal_levels)(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); + enum hpd_pin hpd_pin; enum intel_display_power_domain power_domain; /* for communication with audio component; protected by av_mutex */ @@ -625,6 +626,12 @@ struct intel_plane_state { struct intel_fb_view view; + /* Plane pxp decryption state */ + bool decrypt; + + /* Plane state to display black pixels when pxp is borked */ + bool force_black; + /* plane control register */ u32 ctl; @@ -1056,12 +1063,14 @@ struct intel_crtc_state { struct intel_link_m_n dp_m2_n2; bool has_drrs; + /* PSR is supported but might not be enabled due the lack of enabled planes */ bool has_psr; bool has_psr2; bool enable_psr2_sel_fetch; bool req_psr2_sdp_prior_scanline; u32 dc3co_exitline; u16 su_y_granularity; + struct drm_dp_vsc_sdp psr_vsc; /* * Frequence the dpll for the port should run at. Differs from the @@ -1525,7 +1534,6 @@ struct intel_psr { u32 dc3co_exitline; u32 dc3co_exit_delay; struct delayed_work dc3co_work; - struct drm_dp_vsc_sdp vsc; }; struct intel_dp { @@ -1572,7 +1580,6 @@ struct intel_dp { struct intel_pps pps; - bool can_mst; /* this port supports mst */ bool is_mst; int active_mst_links; @@ -1602,8 +1609,6 @@ struct intel_dp { u8 dp_train_pat); void (*set_idle_link_train)(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); - void (*set_signal_levels)(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state); u8 (*preemph_max)(struct intel_dp *intel_dp); u8 (*voltage_max)(struct intel_dp *intel_dp, @@ -1663,8 +1668,11 @@ struct intel_digital_port { enum intel_display_power_domain ddi_io_power_domain; intel_wakeref_t ddi_io_wakeref; intel_wakeref_t aux_wakeref; + struct mutex tc_lock; /* protects the TypeC port mode */ intel_wakeref_t tc_lock_wakeref; + enum intel_display_power_domain tc_lock_power_domain; + struct delayed_work tc_disconnect_phy_work; int tc_link_refcount; bool tc_legacy_port:1; char tc_port_name[8]; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index b3c8e1c450ef..2dc9d632969d 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -45,8 +45,8 @@ #define GEN12_DMC_MAX_FW_SIZE ICL_DMC_MAX_FW_SIZE -#define ADLP_DMC_PATH DMC_PATH(adlp, 2, 10) -#define ADLP_DMC_VERSION_REQUIRED DMC_VERSION(2, 10) +#define ADLP_DMC_PATH DMC_PATH(adlp, 2, 12) +#define ADLP_DMC_VERSION_REQUIRED DMC_VERSION(2, 12) MODULE_FIRMWARE(ADLP_DMC_PATH); #define ADLS_DMC_PATH DMC_PATH(adls, 2, 01) @@ -255,20 +255,10 @@ intel_get_stepping_info(struct drm_i915_private *i915, static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) { - u32 val, mask; - - mask = DC_STATE_DEBUG_MASK_MEMORY_UP; - - if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - mask |= DC_STATE_DEBUG_MASK_CORES; - /* The below bit doesn't need to be cleared ever afterwards */ - val = intel_de_read(dev_priv, DC_STATE_DEBUG); - if ((val & mask) != mask) { - val |= mask; - intel_de_write(dev_priv, DC_STATE_DEBUG, val); - intel_de_posting_read(dev_priv, DC_STATE_DEBUG); - } + intel_de_rmw(dev_priv, DC_STATE_DEBUG, 0, + DC_STATE_DEBUG_MASK_CORES | DC_STATE_DEBUG_MASK_MEMORY_UP); + intel_de_posting_read(dev_priv, DC_STATE_DEBUG); } /** diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index b9036b80493f..23de500d56b5 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -66,7 +66,6 @@ #include "intel_panel.h" #include "intel_pps.h" #include "intel_psr.h" -#include "intel_sideband.h" #include "intel_tc.h" #include "intel_vdsc.h" #include "intel_vrr.h" @@ -115,6 +114,12 @@ bool intel_dp_is_edp(struct intel_dp *intel_dp) static void intel_dp_unset_edid(struct intel_dp *intel_dp); static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc); +/* Is link rate UHBR and thus 128b/132b? */ +bool intel_dp_is_uhbr(const struct intel_crtc_state *crtc_state) +{ + return crtc_state->port_clock >= 1000000; +} + /* update sink rates from dpcd */ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) { @@ -134,6 +139,9 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) return; } + /* + * Sink rates for 8b/10b. + */ max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]); max_lttpr_rate = drm_dp_lttpr_max_link_rate(intel_dp->lttpr_common_caps); if (max_lttpr_rate) @@ -157,6 +165,21 @@ static void intel_dp_set_sink_rates(struct intel_dp *intel_dp) drm_dp_dpcd_readb(&intel_dp->aux, DP_128B132B_SUPPORTED_LINK_RATES, &uhbr_rates); + if (drm_dp_lttpr_count(intel_dp->lttpr_common_caps)) { + /* We have a repeater */ + if (intel_dp->lttpr_common_caps[0] >= 0x20 && + intel_dp->lttpr_common_caps[DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] & + DP_PHY_REPEATER_128B132B_SUPPORTED) { + /* Repeater supports 128b/132b, valid UHBR rates */ + uhbr_rates &= intel_dp->lttpr_common_caps[DP_PHY_REPEATER_128B132B_RATES - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + } else { + /* Does not support 128b/132b */ + uhbr_rates = 0; + } + } + if (uhbr_rates & DP_UHBR10) intel_dp->sink_rates[i++] = 1000000; if (uhbr_rates & DP_UHBR13_5) @@ -805,6 +828,17 @@ intel_dp_mode_valid_downstream(struct intel_connector *connector, return MODE_OK; } +static bool intel_dp_need_bigjoiner(struct intel_dp *intel_dp, + int hdisplay, int clock) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + if (!intel_dp_can_bigjoiner(intel_dp)) + return false; + + return clock > i915->max_dotclk_freq || hdisplay > 5120; +} + static enum drm_mode_status intel_dp_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) @@ -828,11 +862,9 @@ intel_dp_mode_valid(struct drm_connector *connector, return MODE_H_ILLEGAL; if (intel_dp_is_edp(intel_dp) && fixed_mode) { - if (mode->hdisplay != fixed_mode->hdisplay) - return MODE_PANEL; - - if (mode->vdisplay != fixed_mode->vdisplay) - return MODE_PANEL; + status = intel_panel_mode_valid(intel_connector, mode); + if (status != MODE_OK) + return status; target_clock = fixed_mode->clock; } @@ -840,8 +872,7 @@ intel_dp_mode_valid(struct drm_connector *connector, if (mode->clock < 10000) return MODE_CLOCK_LOW; - if ((target_clock > max_dotclk || mode->hdisplay > 5120) && - intel_dp_can_bigjoiner(intel_dp)) { + if (intel_dp_need_bigjoiner(intel_dp, mode->hdisplay, target_clock)) { bigjoiner = true; max_dotclk *= 2; } @@ -913,18 +944,14 @@ intel_dp_mode_valid(struct drm_connector *connector, return intel_mode_valid_max_plane_size(dev_priv, mode, bigjoiner); } -bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp) +bool intel_dp_source_supports_tps3(struct drm_i915_private *i915) { - int max_rate = intel_dp->source_rates[intel_dp->num_source_rates - 1]; - - return max_rate >= 540000; + return DISPLAY_VER(i915) >= 9 || IS_BROADWELL(i915) || IS_HASWELL(i915); } -bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp) +bool intel_dp_source_supports_tps4(struct drm_i915_private *i915) { - int max_rate = intel_dp->source_rates[intel_dp->num_source_rates - 1]; - - return max_rate >= 810000; + return DISPLAY_VER(i915) >= 10; } static void snprintf_int_array(char *str, size_t len, @@ -1457,9 +1484,8 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, limits.max_lane_count, limits.max_rate, limits.max_bpp, adjusted_mode->crtc_clock); - if ((adjusted_mode->crtc_clock > i915->max_dotclk_freq || - adjusted_mode->crtc_hdisplay > 5120) && - intel_dp_can_bigjoiner(intel_dp)) + if (intel_dp_need_bigjoiner(intel_dp, adjusted_mode->crtc_hdisplay, + adjusted_mode->crtc_clock)) pipe_config->bigjoiner = true; /* @@ -1659,7 +1685,7 @@ void intel_dp_compute_psr_vsc_sdp(struct intel_dp *intel_dp, { vsc->sdp_type = DP_SDP_VSC; - if (intel_dp->psr.psr2_enabled) { + if (crtc_state->has_psr2) { if (intel_dp->psr.colorimetry_support && intel_dp_needs_vsc_sdp(crtc_state, conn_state)) { /* [PSR2, +Colorimetry] */ @@ -1744,8 +1770,9 @@ intel_dp_compute_config(struct intel_encoder *encoder, pipe_config->has_audio = intel_conn_state->force_audio == HDMI_AUDIO_ON; if (intel_dp_is_edp(intel_dp) && intel_connector->panel.fixed_mode) { - intel_panel_fixed_mode(intel_connector->panel.fixed_mode, - adjusted_mode); + ret = intel_panel_compute_config(intel_connector, adjusted_mode); + if (ret) + return ret; ret = intel_panel_fitting(pipe_config, conn_state); if (ret) @@ -1813,7 +1840,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, g4x_dp_set_clock(encoder, pipe_config); intel_vrr_compute_config(pipe_config, conn_state); - intel_psr_compute_config(intel_dp, pipe_config); + intel_psr_compute_config(intel_dp, pipe_config, conn_state); intel_drrs_compute_config(intel_dp, pipe_config, output_bpp, constant_n); intel_dp_compute_vsc_sdp(intel_dp, pipe_config, conn_state); @@ -1825,6 +1852,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, void intel_dp_set_link_params(struct intel_dp *intel_dp, int link_rate, int lane_count) { + memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); intel_dp->link_trained = false; intel_dp->link_rate = link_rate; intel_dp->lane_count = lane_count; @@ -2641,7 +2669,7 @@ intel_dp_can_mst(struct intel_dp *intel_dp) struct drm_i915_private *i915 = dp_to_i915(intel_dp); return i915->params.enable_dp_mst && - intel_dp->can_mst && + intel_dp_mst_source_support(intel_dp) && drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd); } @@ -2656,10 +2684,10 @@ intel_dp_configure_mst(struct intel_dp *intel_dp) drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n", encoder->base.base.id, encoder->base.name, - yesno(intel_dp->can_mst), yesno(sink_can_mst), + yesno(intel_dp_mst_source_support(intel_dp)), yesno(sink_can_mst), yesno(i915->params.enable_dp_mst)); - if (!intel_dp->can_mst) + if (!intel_dp_mst_source_support(intel_dp)) return; intel_dp->is_mst = sink_can_mst && @@ -2876,7 +2904,7 @@ static void intel_write_dp_sdp(struct intel_encoder *encoder, void intel_write_dp_vsc_sdp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, - struct drm_dp_vsc_sdp *vsc) + const struct drm_dp_vsc_sdp *vsc) { struct intel_digital_port *dig_port = enc_to_dig_port(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); @@ -5059,7 +5087,7 @@ void intel_dp_mst_suspend(struct drm_i915_private *dev_priv) intel_dp = enc_to_intel_dp(encoder); - if (!intel_dp->can_mst) + if (!intel_dp_mst_source_support(intel_dp)) continue; if (intel_dp->is_mst) @@ -5083,7 +5111,7 @@ void intel_dp_mst_resume(struct drm_i915_private *dev_priv) intel_dp = enc_to_intel_dp(encoder); - if (!intel_dp->can_mst) + if (!intel_dp_mst_source_support(intel_dp)) continue; ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr, diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index a28fff286c21..ce229026dc91 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -58,6 +58,7 @@ int intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state); bool intel_dp_is_edp(struct intel_dp *intel_dp); +bool intel_dp_is_uhbr(const struct intel_crtc_state *crtc_state); bool intel_dp_is_port_edp(struct drm_i915_private *dev_priv, enum port port); enum irqreturn intel_dp_hpd_pulse(struct intel_digital_port *dig_port, bool long_hpd); @@ -72,8 +73,8 @@ int intel_dp_rate_select(struct intel_dp *intel_dp, int rate); void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock, u8 *link_bw, u8 *rate_select); -bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp); -bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp); +bool intel_dp_source_supports_tps3(struct drm_i915_private *i915); +bool intel_dp_source_supports_tps4(struct drm_i915_private *i915); bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp); int intel_dp_link_required(int pixel_clock, int bpp); @@ -87,7 +88,7 @@ void intel_dp_compute_psr_vsc_sdp(struct intel_dp *intel_dp, struct drm_dp_vsc_sdp *vsc); void intel_write_dp_vsc_sdp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, - struct drm_dp_vsc_sdp *vsc); + const struct drm_dp_vsc_sdp *vsc); void intel_dp_set_infoframes(struct intel_encoder *encoder, bool enable, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c index f483f479dd0b..5fbb767fcd63 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c @@ -150,9 +150,6 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, u32 unused) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *i915 = - to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(i915, dig_port->base.port); u32 ret; /* @@ -170,8 +167,7 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) | DP_AUX_CH_CTL_SYNC_PULSE_SKL(32); - if (intel_phy_is_tc(i915, phy) && - dig_port->tc_mode == TC_PORT_TBT_ALT) + if (intel_tc_port_in_tbt_alt_mode(dig_port)) ret |= DP_AUX_CH_CTL_TBT_IO; return ret; diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 508a514c5e37..85676c953e0a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -25,15 +25,6 @@ #include "intel_dp.h" #include "intel_dp_link_training.h" -static void -intel_dp_dump_link_status(struct drm_device *drm, - const u8 link_status[DP_LINK_STATUS_SIZE]) -{ - drm_dbg_kms(drm, - "ln0_1:0x%x ln2_3:0x%x align:0x%x sink:0x%x adj_req0_1:0x%x adj_req2_3:0x%x\n", - link_status[0], link_status[1], link_status[2], - link_status[3], link_status[4], link_status[5]); -} static void intel_dp_reset_lttpr_common_caps(struct intel_dp *intel_dp) { @@ -66,6 +57,7 @@ static u8 *intel_dp_lttpr_phy_caps(struct intel_dp *intel_dp, static void intel_dp_read_lttpr_phy_caps(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy) { + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; u8 *phy_caps = intel_dp_lttpr_phy_caps(intel_dp, dp_phy); char phy_name[10]; @@ -73,21 +65,22 @@ static void intel_dp_read_lttpr_phy_caps(struct intel_dp *intel_dp, if (drm_dp_read_lttpr_phy_caps(&intel_dp->aux, dp_phy, phy_caps) < 0) { drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "failed to read the PHY caps for %s\n", - phy_name); + "[ENCODER:%d:%s][%s] failed to read the PHY caps\n", + encoder->base.base.id, encoder->base.name, phy_name); return; } drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "%s PHY capabilities: %*ph\n", - phy_name, + "[ENCODER:%d:%s][%s] PHY capabilities: %*ph\n", + encoder->base.base.id, encoder->base.name, phy_name, (int)sizeof(intel_dp->lttpr_phy_caps[0]), phy_caps); } static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp) { - struct drm_i915_private *i915 = dp_to_i915(intel_dp); + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); if (intel_dp_is_edp(intel_dp)) return false; @@ -104,7 +97,8 @@ static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp) goto reset_caps; drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "LTTPR common capabilities: %*ph\n", + "[ENCODER:%d:%s] LTTPR common capabilities: %*ph\n", + encoder->base.base.id, encoder->base.name, (int)sizeof(intel_dp->lttpr_common_caps), intel_dp->lttpr_common_caps); @@ -130,6 +124,8 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) static int intel_dp_init_lttpr(struct intel_dp *intel_dp) { + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); int lttpr_count; int i; @@ -161,8 +157,9 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp) return 0; if (!intel_dp_set_lttpr_transparent_mode(intel_dp, false)) { - drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "Switching to LTTPR non-transparent LT mode failed, fall-back to transparent mode\n"); + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s] Switching to LTTPR non-transparent LT mode failed, fall-back to transparent mode\n", + encoder->base.base.id, encoder->base.name); intel_dp_set_lttpr_transparent_mode(intel_dp, true); intel_dp_reset_lttpr_count(intel_dp); @@ -301,21 +298,54 @@ static u8 intel_dp_phy_preemph_max(struct intel_dp *intel_dp, return preemph_max; } -void -intel_dp_get_adjust_train(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - enum drm_dp_phy dp_phy, - const u8 link_status[DP_LINK_STATUS_SIZE]) +static bool has_per_lane_signal_levels(struct intel_dp *intel_dp, + enum drm_dp_phy dp_phy) +{ + return !intel_dp_phy_is_downstream_of_source(intel_dp, dp_phy); +} + +/* 128b/132b */ +static u8 intel_dp_get_lane_adjust_tx_ffe_preset(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy, + const u8 link_status[DP_LINK_STATUS_SIZE], + int lane) +{ + u8 tx_ffe = 0; + + if (has_per_lane_signal_levels(intel_dp, dp_phy)) { + lane = min(lane, crtc_state->lane_count - 1); + tx_ffe = drm_dp_get_adjust_tx_ffe_preset(link_status, lane); + } else { + for (lane = 0; lane < crtc_state->lane_count; lane++) + tx_ffe = max(tx_ffe, drm_dp_get_adjust_tx_ffe_preset(link_status, lane)); + } + + return tx_ffe; +} + +/* 8b/10b */ +static u8 intel_dp_get_lane_adjust_vswing_preemph(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy, + const u8 link_status[DP_LINK_STATUS_SIZE], + int lane) { u8 v = 0; u8 p = 0; - int lane; u8 voltage_max; u8 preemph_max; - for (lane = 0; lane < crtc_state->lane_count; lane++) { - v = max(v, drm_dp_get_adjust_request_voltage(link_status, lane)); - p = max(p, drm_dp_get_adjust_request_pre_emphasis(link_status, lane)); + if (has_per_lane_signal_levels(intel_dp, dp_phy)) { + lane = min(lane, crtc_state->lane_count - 1); + + v = drm_dp_get_adjust_request_voltage(link_status, lane); + p = drm_dp_get_adjust_request_pre_emphasis(link_status, lane); + } else { + for (lane = 0; lane < crtc_state->lane_count; lane++) { + v = max(v, drm_dp_get_adjust_request_voltage(link_status, lane)); + p = max(p, drm_dp_get_adjust_request_pre_emphasis(link_status, lane)); + } } preemph_max = intel_dp_phy_preemph_max(intel_dp, dp_phy); @@ -328,8 +358,79 @@ intel_dp_get_adjust_train(struct intel_dp *intel_dp, if (v >= voltage_max) v = voltage_max | DP_TRAIN_MAX_SWING_REACHED; + return v | p; +} + +static u8 intel_dp_get_lane_adjust_train(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy, + const u8 link_status[DP_LINK_STATUS_SIZE], + int lane) +{ + if (intel_dp_is_uhbr(crtc_state)) + return intel_dp_get_lane_adjust_tx_ffe_preset(intel_dp, crtc_state, + dp_phy, link_status, lane); + else + return intel_dp_get_lane_adjust_vswing_preemph(intel_dp, crtc_state, + dp_phy, link_status, lane); +} + +#define TRAIN_REQ_FMT "%d/%d/%d/%d" +#define _TRAIN_REQ_VSWING_ARGS(link_status, lane) \ + (drm_dp_get_adjust_request_voltage((link_status), (lane)) >> DP_TRAIN_VOLTAGE_SWING_SHIFT) +#define TRAIN_REQ_VSWING_ARGS(link_status) \ + _TRAIN_REQ_VSWING_ARGS(link_status, 0), \ + _TRAIN_REQ_VSWING_ARGS(link_status, 1), \ + _TRAIN_REQ_VSWING_ARGS(link_status, 2), \ + _TRAIN_REQ_VSWING_ARGS(link_status, 3) +#define _TRAIN_REQ_PREEMPH_ARGS(link_status, lane) \ + (drm_dp_get_adjust_request_pre_emphasis((link_status), (lane)) >> DP_TRAIN_PRE_EMPHASIS_SHIFT) +#define TRAIN_REQ_PREEMPH_ARGS(link_status) \ + _TRAIN_REQ_PREEMPH_ARGS(link_status, 0), \ + _TRAIN_REQ_PREEMPH_ARGS(link_status, 1), \ + _TRAIN_REQ_PREEMPH_ARGS(link_status, 2), \ + _TRAIN_REQ_PREEMPH_ARGS(link_status, 3) +#define _TRAIN_REQ_TX_FFE_ARGS(link_status, lane) \ + drm_dp_get_adjust_tx_ffe_preset((link_status), (lane)) +#define TRAIN_REQ_TX_FFE_ARGS(link_status) \ + _TRAIN_REQ_TX_FFE_ARGS(link_status, 0), \ + _TRAIN_REQ_TX_FFE_ARGS(link_status, 1), \ + _TRAIN_REQ_TX_FFE_ARGS(link_status, 2), \ + _TRAIN_REQ_TX_FFE_ARGS(link_status, 3) + +void +intel_dp_get_adjust_train(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy, + const u8 link_status[DP_LINK_STATUS_SIZE]) +{ + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + char phy_name[10]; + int lane; + + if (intel_dp_is_uhbr(crtc_state)) { + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] 128b/132b, lanes: %d, " + "TX FFE request: " TRAIN_REQ_FMT "\n", + encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + crtc_state->lane_count, + TRAIN_REQ_TX_FFE_ARGS(link_status)); + } else { + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] 8b/10b, lanes: %d, " + "vswing request: " TRAIN_REQ_FMT ", " + "pre-emphasis request: " TRAIN_REQ_FMT "\n", + encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + crtc_state->lane_count, + TRAIN_REQ_VSWING_ARGS(link_status), + TRAIN_REQ_PREEMPH_ARGS(link_status)); + } + for (lane = 0; lane < 4; lane++) - intel_dp->train_set[lane] = v | p; + intel_dp->train_set[lane] = + intel_dp_get_lane_adjust_train(intel_dp, crtc_state, + dp_phy, link_status, lane); } static int intel_dp_training_pattern_set_reg(struct intel_dp *intel_dp, @@ -351,7 +452,7 @@ intel_dp_set_link_train(struct intel_dp *intel_dp, int len; intel_dp_program_link_training_pattern(intel_dp, crtc_state, - dp_train_pat); + dp_phy, dp_train_pat); buf[0] = dp_train_pat; /* DP_TRAINING_LANEx_SET follow DP_TRAINING_PATTERN_SET */ @@ -379,40 +480,77 @@ static char dp_training_pattern_name(u8 train_pat) void intel_dp_program_link_training_pattern(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy, u8 dp_train_pat) { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); u8 train_pat = intel_dp_training_pattern_symbol(dp_train_pat); + char phy_name[10]; if (train_pat != DP_TRAINING_PATTERN_DISABLE) - drm_dbg_kms(&dev_priv->drm, - "[ENCODER:%d:%s] Using DP training pattern TPS%c\n", + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s][%s] Using DP training pattern TPS%c\n", encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), dp_training_pattern_name(train_pat)); intel_dp->set_link_train(intel_dp, crtc_state, dp_train_pat); } +#define TRAIN_SET_FMT "%d%s/%d%s/%d%s/%d%s" +#define _TRAIN_SET_VSWING_ARGS(train_set) \ + ((train_set) & DP_TRAIN_VOLTAGE_SWING_MASK) >> DP_TRAIN_VOLTAGE_SWING_SHIFT, \ + (train_set) & DP_TRAIN_MAX_SWING_REACHED ? "(max)" : "" +#define TRAIN_SET_VSWING_ARGS(train_set) \ + _TRAIN_SET_VSWING_ARGS((train_set)[0]), \ + _TRAIN_SET_VSWING_ARGS((train_set)[1]), \ + _TRAIN_SET_VSWING_ARGS((train_set)[2]), \ + _TRAIN_SET_VSWING_ARGS((train_set)[3]) +#define _TRAIN_SET_PREEMPH_ARGS(train_set) \ + ((train_set) & DP_TRAIN_PRE_EMPHASIS_MASK) >> DP_TRAIN_PRE_EMPHASIS_SHIFT, \ + (train_set) & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ? "(max)" : "" +#define TRAIN_SET_PREEMPH_ARGS(train_set) \ + _TRAIN_SET_PREEMPH_ARGS((train_set)[0]), \ + _TRAIN_SET_PREEMPH_ARGS((train_set)[1]), \ + _TRAIN_SET_PREEMPH_ARGS((train_set)[2]), \ + _TRAIN_SET_PREEMPH_ARGS((train_set)[3]) +#define _TRAIN_SET_TX_FFE_ARGS(train_set) \ + ((train_set) & DP_TX_FFE_PRESET_VALUE_MASK), "" +#define TRAIN_SET_TX_FFE_ARGS(train_set) \ + _TRAIN_SET_TX_FFE_ARGS((train_set)[0]), \ + _TRAIN_SET_TX_FFE_ARGS((train_set)[1]), \ + _TRAIN_SET_TX_FFE_ARGS((train_set)[2]), \ + _TRAIN_SET_TX_FFE_ARGS((train_set)[3]) + void intel_dp_set_signal_levels(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, enum drm_dp_phy dp_phy) { - struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - u8 train_set = intel_dp->train_set[0]; + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); char phy_name[10]; - drm_dbg_kms(&dev_priv->drm, "Using vswing level %d%s, pre-emphasis level %d%s, at %s\n", - train_set & DP_TRAIN_VOLTAGE_SWING_MASK, - train_set & DP_TRAIN_MAX_SWING_REACHED ? " (max)" : "", - (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) >> - DP_TRAIN_PRE_EMPHASIS_SHIFT, - train_set & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ? - " (max)" : "", - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name))); + if (intel_dp_is_uhbr(crtc_state)) { + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] 128b/132b, lanes: %d, " + "TX FFE presets: " TRAIN_SET_FMT "\n", + encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + crtc_state->lane_count, + TRAIN_SET_TX_FFE_ARGS(intel_dp->train_set)); + } else { + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] 8b/10b, lanes: %d, " + "vswing levels: " TRAIN_SET_FMT ", " + "pre-emphasis levels: " TRAIN_SET_FMT "\n", + encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + crtc_state->lane_count, + TRAIN_SET_VSWING_ARGS(intel_dp->train_set), + TRAIN_SET_PREEMPH_ARGS(intel_dp->train_set)); + } if (intel_dp_phy_is_downstream_of_source(intel_dp, dp_phy)) - intel_dp->set_signal_levels(intel_dp, crtc_state); + encoder->set_signal_levels(encoder, crtc_state); } static bool @@ -444,15 +582,55 @@ intel_dp_update_link_train(struct intel_dp *intel_dp, return ret == crtc_state->lane_count; } +/* 128b/132b */ +static bool intel_dp_lane_max_tx_ffe_reached(u8 train_set_lane) +{ + return (train_set_lane & DP_TX_FFE_PRESET_VALUE_MASK) == + DP_TX_FFE_PRESET_VALUE_MASK; +} + +/* + * 8b/10b + * + * FIXME: The DP spec is very confusing here, also the Link CTS spec seems to + * have self contradicting tests around this area. + * + * In lieu of better ideas let's just stop when we've reached the max supported + * vswing with its max pre-emphasis, which is either 2+1 or 3+0 depending on + * whether vswing level 3 is supported or not. + */ +static bool intel_dp_lane_max_vswing_reached(u8 train_set_lane) +{ + u8 v = (train_set_lane & DP_TRAIN_VOLTAGE_SWING_MASK) >> + DP_TRAIN_VOLTAGE_SWING_SHIFT; + u8 p = (train_set_lane & DP_TRAIN_PRE_EMPHASIS_MASK) >> + DP_TRAIN_PRE_EMPHASIS_SHIFT; + + if ((train_set_lane & DP_TRAIN_MAX_SWING_REACHED) == 0) + return false; + + if (v + p != 3) + return false; + + return true; +} + static bool intel_dp_link_max_vswing_reached(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { int lane; - for (lane = 0; lane < crtc_state->lane_count; lane++) - if ((intel_dp->train_set[lane] & - DP_TRAIN_MAX_SWING_REACHED) == 0) - return false; + for (lane = 0; lane < crtc_state->lane_count; lane++) { + u8 train_set_lane = intel_dp->train_set[lane]; + + if (intel_dp_is_uhbr(crtc_state)) { + if (!intel_dp_lane_max_tx_ffe_reached(train_set_lane)) + return false; + } else { + if (!intel_dp_lane_max_vswing_reached(train_set_lane)) + return false; + } + } return true; } @@ -465,7 +643,8 @@ static bool intel_dp_prepare_link_train(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { - struct drm_i915_private *i915 = dp_to_i915(intel_dp); + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); u8 link_config[2]; u8 link_bw, rate_select; @@ -477,10 +656,12 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp, if (link_bw) drm_dbg_kms(&i915->drm, - "Using LINK_BW_SET value %02x\n", link_bw); + "[ENCODER:%d:%s] Using LINK_BW_SET value %02x\n", + encoder->base.base.id, encoder->base.name, link_bw); else drm_dbg_kms(&i915->drm, - "Using LINK_RATE_SET value %02x\n", rate_select); + "[ENCODER:%d:%s] Using LINK_RATE_SET value %02x\n", + encoder->base.base.id, encoder->base.name, rate_select); /* Write the link configuration data */ link_config[0] = link_bw; @@ -495,11 +676,10 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp, &rate_select, 1); link_config[0] = crtc_state->vrr.enable ? DP_MSA_TIMING_PAR_IGNORE_EN : 0; - link_config[1] = DP_SET_ANSI_8B10B; + link_config[1] = intel_dp_is_uhbr(crtc_state) ? + DP_SET_ANSI_128B132B : DP_SET_ANSI_8B10B; drm_dp_dpcd_write(&intel_dp->aux, DP_DOWNSPREAD_CTRL, link_config, 2); - intel_dp->DP |= DP_PORT_EN; - return true; } @@ -512,6 +692,48 @@ static void intel_dp_link_training_clock_recovery_delay(struct intel_dp *intel_d drm_dp_lttpr_link_train_clock_recovery_delay(); } +static bool intel_dp_adjust_request_changed(const struct intel_crtc_state *crtc_state, + const u8 old_link_status[DP_LINK_STATUS_SIZE], + const u8 new_link_status[DP_LINK_STATUS_SIZE]) +{ + int lane; + + for (lane = 0; lane < crtc_state->lane_count; lane++) { + u8 old, new; + + if (intel_dp_is_uhbr(crtc_state)) { + old = drm_dp_get_adjust_tx_ffe_preset(old_link_status, lane); + new = drm_dp_get_adjust_tx_ffe_preset(new_link_status, lane); + } else { + old = drm_dp_get_adjust_request_voltage(old_link_status, lane) | + drm_dp_get_adjust_request_pre_emphasis(old_link_status, lane); + new = drm_dp_get_adjust_request_voltage(new_link_status, lane) | + drm_dp_get_adjust_request_pre_emphasis(new_link_status, lane); + } + + if (old != new) + return true; + } + + return false; +} + +static void +intel_dp_dump_link_status(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy, + const u8 link_status[DP_LINK_STATUS_SIZE]) +{ + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + char phy_name[10]; + + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s][%s] ln0_1:0x%x ln2_3:0x%x align:0x%x sink:0x%x adj_req0_1:0x%x adj_req2_3:0x%x\n", + encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + link_status[0], link_status[1], link_status[2], + link_status[3], link_status[4], link_status[5]); +} + /* * Perform the link training clock recovery phase on the given DP PHY using * training pattern 1. @@ -521,16 +743,22 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, enum drm_dp_phy dp_phy) { - struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 voltage; + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + u8 old_link_status[DP_LINK_STATUS_SIZE] = {}; int voltage_tries, cr_tries, max_cr_tries; + u8 link_status[DP_LINK_STATUS_SIZE]; bool max_vswing_reached = false; + char phy_name[10]; + + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); /* clock recovery */ if (!intel_dp_reset_link_train(intel_dp, crtc_state, dp_phy, DP_TRAINING_PATTERN_1 | DP_LINK_SCRAMBLING_DISABLE)) { - drm_err(&i915->drm, "failed to enable link training\n"); + drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to enable link training\n", + encoder->base.base.id, encoder->base.name, phy_name); return false; } @@ -549,105 +777,118 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, voltage_tries = 1; for (cr_tries = 0; cr_tries < max_cr_tries; ++cr_tries) { - u8 link_status[DP_LINK_STATUS_SIZE]; - intel_dp_link_training_clock_recovery_delay(intel_dp, dp_phy); if (drm_dp_dpcd_read_phy_link_status(&intel_dp->aux, dp_phy, link_status) < 0) { - drm_err(&i915->drm, "failed to get link status\n"); + drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to get link status\n", + encoder->base.base.id, encoder->base.name, phy_name); return false; } if (drm_dp_clock_recovery_ok(link_status, crtc_state->lane_count)) { - drm_dbg_kms(&i915->drm, "clock recovery OK\n"); + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s][%s] Clock recovery OK\n", + encoder->base.base.id, encoder->base.name, phy_name); return true; } if (voltage_tries == 5) { + intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_dbg_kms(&i915->drm, - "Same voltage tried 5 times\n"); + "[ENCODER:%d:%s][%s] Same voltage tried 5 times\n", + encoder->base.base.id, encoder->base.name, phy_name); return false; } if (max_vswing_reached) { - drm_dbg_kms(&i915->drm, "Max Voltage Swing reached\n"); + intel_dp_dump_link_status(intel_dp, dp_phy, link_status); + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s][%s] Max Voltage Swing reached\n", + encoder->base.base.id, encoder->base.name, phy_name); return false; } - voltage = intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK; - /* Update training set as requested by target */ intel_dp_get_adjust_train(intel_dp, crtc_state, dp_phy, link_status); if (!intel_dp_update_link_train(intel_dp, crtc_state, dp_phy)) { drm_err(&i915->drm, - "failed to update link training\n"); + "[ENCODER:%d:%s][%s] Failed to update link training\n", + encoder->base.base.id, encoder->base.name, phy_name); return false; } - if ((intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK) == - voltage) + if (!intel_dp_adjust_request_changed(crtc_state, old_link_status, link_status)) ++voltage_tries; else voltage_tries = 1; + memcpy(old_link_status, link_status, sizeof(link_status)); + if (intel_dp_link_max_vswing_reached(intel_dp, crtc_state)) max_vswing_reached = true; - } + + intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_err(&i915->drm, - "Failed clock recovery %d times, giving up!\n", max_cr_tries); + "[ENCODER:%d:%s][%s] Failed clock recovery %d times, giving up!\n", + encoder->base.base.id, encoder->base.name, phy_name, max_cr_tries); + return false; } /* - * Pick training pattern for channel equalization. Training pattern 4 for HBR3 - * or for 1.4 devices that support it, training Pattern 3 for HBR2 - * or 1.2 devices that support it, Training Pattern 2 otherwise. + * Pick Training Pattern Sequence (TPS) for channel equalization. 128b/132b TPS2 + * for UHBR+, TPS4 for HBR3 or for 1.4 devices that support it, TPS3 for HBR2 or + * 1.2 devices that support it, TPS2 otherwise. */ static u32 intel_dp_training_pattern(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, enum drm_dp_phy dp_phy) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); bool source_tps3, sink_tps3, source_tps4, sink_tps4; + /* UHBR+ use separate 128b/132b TPS2 */ + if (intel_dp_is_uhbr(crtc_state)) + return DP_TRAINING_PATTERN_2; + /* - * Intel platforms that support HBR3 also support TPS4. It is mandatory - * for all downstream devices that support HBR3. There are no known eDP - * panels that support TPS4 as of Feb 2018 as per VESA eDP_v1.4b_E1 - * specification. + * TPS4 support is mandatory for all downstream devices that + * support HBR3. There are no known eDP panels that support + * TPS4 as of Feb 2018 as per VESA eDP_v1.4b_E1 specification. * LTTPRs must support TPS4. */ - source_tps4 = intel_dp_source_supports_hbr3(intel_dp); + source_tps4 = intel_dp_source_supports_tps4(i915); sink_tps4 = dp_phy != DP_PHY_DPRX || drm_dp_tps4_supported(intel_dp->dpcd); if (source_tps4 && sink_tps4) { return DP_TRAINING_PATTERN_4; } else if (crtc_state->port_clock == 810000) { if (!source_tps4) - drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "8.1 Gbps link rate without source HBR3/TPS4 support\n"); + drm_dbg_kms(&i915->drm, + "8.1 Gbps link rate without source TPS4 support\n"); if (!sink_tps4) - drm_dbg_kms(&dp_to_i915(intel_dp)->drm, + drm_dbg_kms(&i915->drm, "8.1 Gbps link rate without sink TPS4 support\n"); } + /* - * Intel platforms that support HBR2 also support TPS3. TPS3 support is - * also mandatory for downstream devices that support HBR2. However, not - * all sinks follow the spec. + * TPS3 support is mandatory for downstream devices that + * support HBR2. However, not all sinks follow the spec. */ - source_tps3 = intel_dp_source_supports_hbr2(intel_dp); + source_tps3 = intel_dp_source_supports_tps3(i915); sink_tps3 = dp_phy != DP_PHY_DPRX || drm_dp_tps3_supported(intel_dp->dpcd); if (source_tps3 && sink_tps3) { return DP_TRAINING_PATTERN_3; } else if (crtc_state->port_clock >= 540000) { if (!source_tps3) - drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - ">=5.4/6.48 Gbps link rate without source HBR2/TPS3 support\n"); + drm_dbg_kms(&i915->drm, + ">=5.4/6.48 Gbps link rate without source TPS3 support\n"); if (!sink_tps3) - drm_dbg_kms(&dp_to_i915(intel_dp)->drm, + drm_dbg_kms(&i915->drm, ">=5.4/6.48 Gbps link rate without sink TPS3 support\n"); } @@ -677,11 +918,15 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, enum drm_dp_phy dp_phy) { - struct drm_i915_private *i915 = dp_to_i915(intel_dp); + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + struct drm_i915_private *i915 = to_i915(encoder->base.dev); int tries; u32 training_pattern; u8 link_status[DP_LINK_STATUS_SIZE]; bool channel_eq = false; + char phy_name[10]; + + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); training_pattern = intel_dp_training_pattern(intel_dp, crtc_state, dp_phy); /* Scrambling is disabled for TPS2/3 and enabled for TPS4 */ @@ -691,7 +936,10 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, /* channel equalization */ if (!intel_dp_set_link_train(intel_dp, crtc_state, dp_phy, training_pattern)) { - drm_err(&i915->drm, "failed to start channel equalization\n"); + drm_err(&i915->drm, + "[ENCODER:%d:%s][%s] Failed to start channel equalization\n", + encoder->base.base.id, encoder->base.name, + phy_name); return false; } @@ -701,25 +949,28 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, if (drm_dp_dpcd_read_phy_link_status(&intel_dp->aux, dp_phy, link_status) < 0) { drm_err(&i915->drm, - "failed to get link status\n"); + "[ENCODER:%d:%s][%s] Failed to get link status\n", + encoder->base.base.id, encoder->base.name, phy_name); break; } /* Make sure clock is still ok */ if (!drm_dp_clock_recovery_ok(link_status, crtc_state->lane_count)) { - intel_dp_dump_link_status(&i915->drm, link_status); + intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_dbg_kms(&i915->drm, - "Clock recovery check failed, cannot " - "continue channel equalization\n"); + "[ENCODER:%d:%s][%s] Clock recovery check failed, cannot " + "continue channel equalization\n", + encoder->base.base.id, encoder->base.name, phy_name); break; } if (drm_dp_channel_eq_ok(link_status, crtc_state->lane_count)) { channel_eq = true; - drm_dbg_kms(&i915->drm, "Channel EQ done. DP Training " - "successful\n"); + drm_dbg_kms(&i915->drm, + "[ENCODER:%d:%s][%s] Channel EQ done. DP Training successful\n", + encoder->base.base.id, encoder->base.name, phy_name); break; } @@ -728,16 +979,18 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, link_status); if (!intel_dp_update_link_train(intel_dp, crtc_state, dp_phy)) { drm_err(&i915->drm, - "failed to update link training\n"); + "[ENCODER:%d:%s][%s] Failed to update link training\n", + encoder->base.base.id, encoder->base.name, phy_name); break; } } /* Try 5 times, else fail and try at lower BW */ if (tries == 5) { - intel_dp_dump_link_status(&i915->drm, link_status); + intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_dbg_kms(&i915->drm, - "Channel equalization failed 5 times\n"); + "[ENCODER:%d:%s][%s] Channel equalization failed 5 times\n", + encoder->base.base.id, encoder->base.name, phy_name); } return channel_eq; @@ -774,7 +1027,7 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp, intel_dp->link_trained = true; intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX); - intel_dp_program_link_training_pattern(intel_dp, crtc_state, + intel_dp_program_link_training_pattern(intel_dp, crtc_state, DP_PHY_DPRX, DP_TRAINING_PATTERN_DISABLE); } @@ -783,7 +1036,8 @@ intel_dp_link_train_phy(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, enum drm_dp_phy dp_phy) { - struct intel_connector *intel_connector = intel_dp->attached_connector; + struct intel_connector *connector = intel_dp->attached_connector; + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; char phy_name[10]; bool ret = false; @@ -797,12 +1051,12 @@ intel_dp_link_train_phy(struct intel_dp *intel_dp, out: drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "[CONNECTOR:%d:%s] Link Training %s at link rate = %d, lane count = %d, at %s\n", - intel_connector->base.base.id, - intel_connector->base.name, + "[CONNECTOR:%d:%s][ENCODER:%d:%s][%s] Link Training %s at link rate = %d, lane count = %d\n", + connector->base.base.id, connector->base.name, + encoder->base.base.id, encoder->base.name, + intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), ret ? "passed" : "failed", - crtc_state->port_clock, crtc_state->lane_count, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name))); + crtc_state->port_clock, crtc_state->lane_count); return ret; } @@ -811,10 +1065,13 @@ static void intel_dp_schedule_fallback_link_training(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { struct intel_connector *intel_connector = intel_dp->attached_connector; + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; if (intel_dp->hobl_active) { drm_dbg_kms(&dp_to_i915(intel_dp)->drm, - "Link Training failed with HOBL active, not enabling it from now on"); + "[ENCODER:%d:%s] Link Training failed with HOBL active, " + "not enabling it from now on", + encoder->base.base.id, encoder->base.name); intel_dp->hobl_failed = true; } else if (intel_dp_get_link_train_fallback_values(intel_dp, crtc_state->port_clock, diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h index 9d24d594368c..6a3a7b37349a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h @@ -19,6 +19,7 @@ void intel_dp_get_adjust_train(struct intel_dp *intel_dp, const u8 link_status[DP_LINK_STATUS_SIZE]); void intel_dp_program_link_training_pattern(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, + enum drm_dp_phy dp_phy, u8 dp_train_pat); void intel_dp_set_signal_levels(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index d104441344c0..89d701e8ae9d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -378,7 +378,7 @@ static void intel_mst_disable_dp(struct intel_atomic_state *state, drm_dp_mst_reset_vcpi_slots(&intel_dp->mst_mgr, connector->port); - ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr); + ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr, 1); if (ret) { drm_dbg_kms(&i915->drm, "failed to update payload %d\n", ret); } @@ -405,7 +405,7 @@ static void intel_mst_post_disable_dp(struct intel_atomic_state *state, intel_crtc_vblank_off(old_crtc_state); - intel_disable_pipe(old_crtc_state); + intel_disable_transcoder(old_crtc_state); drm_dp_update_payload_part2(&intel_dp->mst_mgr); @@ -518,7 +518,7 @@ static void intel_mst_pre_enable_dp(struct intel_atomic_state *state, intel_dp->active_mst_links++; - ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr); + ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr, 1); /* * Before Gen 12 this is not done as part of @@ -550,6 +550,17 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, clear_act_sent(encoder, pipe_config); + if (intel_dp_is_uhbr(pipe_config)) { + const struct drm_display_mode *adjusted_mode = + &pipe_config->hw.adjusted_mode; + u64 crtc_clock_hz = KHz(adjusted_mode->crtc_clock); + + intel_de_write(dev_priv, TRANS_DP2_VFREQHIGH(pipe_config->cpu_transcoder), + TRANS_DP2_VFREQ_PIXEL_CLOCK(crtc_clock_hz >> 24)); + intel_de_write(dev_priv, TRANS_DP2_VFREQLOW(pipe_config->cpu_transcoder), + TRANS_DP2_VFREQ_PIXEL_CLOCK(crtc_clock_hz & 0xffffff)); + } + intel_ddi_enable_transcoder_func(encoder, pipe_config); intel_de_rmw(dev_priv, TRANS_DDI_FUNC_CTL(trans), 0, @@ -566,7 +577,7 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, intel_de_rmw(dev_priv, CHICKEN_TRANS(trans), 0, FECSTALL_DIS_DPTSTREAM_DPTTG); - intel_enable_pipe(pipe_config); + intel_enable_transcoder(pipe_config); intel_crtc_vblank_on(pipe_config); @@ -966,24 +977,31 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id) dig_port->max_lanes, max_source_rate, conn_base_id); - if (ret) + if (ret) { + intel_dp->mst_mgr.cbs = NULL; return ret; - - intel_dp->can_mst = true; + } return 0; } +bool intel_dp_mst_source_support(struct intel_dp *intel_dp) +{ + return intel_dp->mst_mgr.cbs; +} + void intel_dp_mst_encoder_cleanup(struct intel_digital_port *dig_port) { struct intel_dp *intel_dp = &dig_port->dp; - if (!intel_dp->can_mst) + if (!intel_dp_mst_source_support(intel_dp)) return; drm_dp_mst_topology_mgr_destroy(&intel_dp->mst_mgr); /* encoders will get killed by normal cleanup */ + + intel_dp->mst_mgr.cbs = NULL; } bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.h b/drivers/gpu/drm/i915/display/intel_dp_mst.h index 6afda4e86b3c..f7301de6cdfb 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.h +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.h @@ -8,13 +8,15 @@ #include -struct intel_digital_port; struct intel_crtc_state; +struct intel_digital_port; +struct intel_dp; int intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_id); void intel_dp_mst_encoder_cleanup(struct intel_digital_port *dig_port); int intel_dp_mst_encoder_active_links(struct intel_digital_port *dig_port); bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state); bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state); +bool intel_dp_mst_source_support(struct intel_dp *intel_dp); #endif /* __INTEL_DP_MST_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.c b/drivers/gpu/drm/i915/display/intel_dpio_phy.c index 48507ed79950..44edeb2e55c0 100644 --- a/drivers/gpu/drm/i915/display/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.c @@ -21,12 +21,13 @@ * DEALINGS IN THE SOFTWARE. */ -#include "display/intel_dp.h" - +#include "intel_ddi.h" +#include "intel_ddi_buf_trans.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dp.h" #include "intel_dpio_phy.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" /** * DOC: DPIO @@ -266,15 +267,22 @@ void bxt_port_to_phy_channel(struct drm_i915_private *dev_priv, enum port port, *ch = DPIO_CH0; } -void bxt_ddi_phy_set_signal_level(struct drm_i915_private *dev_priv, - enum port port, u32 margin, u32 scale, - u32 enable, u32 deemphasis) +void bxt_ddi_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { - u32 val; - enum dpio_phy phy; + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + int level = intel_ddi_level(encoder, crtc_state, 0); + const struct intel_ddi_buf_trans *trans; enum dpio_channel ch; + enum dpio_phy phy; + int n_entries; + u32 val; - bxt_port_to_phy_channel(dev_priv, port, &phy, &ch); + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) + return; + + bxt_port_to_phy_channel(dev_priv, encoder->port, &phy, &ch); /* * While we write to the group register to program all lanes at once we @@ -286,12 +294,13 @@ void bxt_ddi_phy_set_signal_level(struct drm_i915_private *dev_priv, val = intel_de_read(dev_priv, BXT_PORT_TX_DW2_LN0(phy, ch)); val &= ~(MARGIN_000 | UNIQ_TRANS_SCALE); - val |= margin << MARGIN_000_SHIFT | scale << UNIQ_TRANS_SCALE_SHIFT; + val |= trans->entries[level].bxt.margin << MARGIN_000_SHIFT | + trans->entries[level].bxt.scale << UNIQ_TRANS_SCALE_SHIFT; intel_de_write(dev_priv, BXT_PORT_TX_DW2_GRP(phy, ch), val); val = intel_de_read(dev_priv, BXT_PORT_TX_DW3_LN0(phy, ch)); val &= ~SCALE_DCOMP_METHOD; - if (enable) + if (trans->entries[level].bxt.enable) val |= SCALE_DCOMP_METHOD; if ((val & UNIQUE_TRANGE_EN_METHOD) && !(val & SCALE_DCOMP_METHOD)) @@ -302,7 +311,7 @@ void bxt_ddi_phy_set_signal_level(struct drm_i915_private *dev_priv, val = intel_de_read(dev_priv, BXT_PORT_TX_DW4_LN0(phy, ch)); val &= ~DE_EMPHASIS; - val |= deemphasis << DEEMPH_SHIFT; + val |= trans->entries[level].bxt.deemphasis << DEEMPH_SHIFT; intel_de_write(dev_priv, BXT_PORT_TX_DW4_GRP(phy, ch), val); val = intel_de_read(dev_priv, BXT_PORT_PCS_DW10_LN01(phy, ch)); diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.h b/drivers/gpu/drm/i915/display/intel_dpio_phy.h index 6473440e7457..9c3d008e8e1a 100644 --- a/drivers/gpu/drm/i915/display/intel_dpio_phy.h +++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.h @@ -17,9 +17,8 @@ struct intel_encoder; void bxt_port_to_phy_channel(struct drm_i915_private *dev_priv, enum port port, enum dpio_phy *phy, enum dpio_channel *ch); -void bxt_ddi_phy_set_signal_level(struct drm_i915_private *dev_priv, - enum port port, u32 margin, u32 scale, - u32 enable, u32 deemphasis); +void bxt_ddi_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy); void bxt_ddi_phy_uninit(struct drm_i915_private *dev_priv, enum dpio_phy phy); bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_dpll.c b/drivers/gpu/drm/i915/display/intel_dpll.c index 210f91f4a576..04a7af8340ca 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll.c +++ b/drivers/gpu/drm/i915/display/intel_dpll.c @@ -2,16 +2,19 @@ /* * Copyright © 2020 Intel Corporation */ + #include + #include "intel_crtc.h" #include "intel_de.h" -#include "intel_display_types.h" #include "intel_display.h" +#include "intel_display_types.h" #include "intel_dpll.h" #include "intel_lvds.h" #include "intel_panel.h" -#include "intel_sideband.h" -#include "display/intel_snps_phy.h" +#include "intel_pps.h" +#include "intel_snps_phy.h" +#include "vlv_sideband.h" struct intel_limit { struct { @@ -937,16 +940,18 @@ static int hsw_crtc_compute_clock(struct intel_crtc_state *crtc_state) struct intel_encoder *encoder = intel_get_crtc_new_encoder(state, crtc_state); - if (IS_DG2(dev_priv)) { + if (IS_DG2(dev_priv)) return intel_mpllb_calc_state(crtc_state, encoder); - } else if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) || - DISPLAY_VER(dev_priv) >= 11) { - if (!intel_reserve_shared_dplls(state, crtc, encoder)) { - drm_dbg_kms(&dev_priv->drm, - "failed to find PLL for pipe %c\n", - pipe_name(crtc->pipe)); - return -EINVAL; - } + + if (DISPLAY_VER(dev_priv) < 11 && + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) + return 0; + + if (!intel_reserve_shared_dplls(state, crtc, encoder)) { + drm_dbg_kms(&dev_priv->drm, + "failed to find PLL for pipe %c\n", + pipe_name(crtc->pipe)); + return -EINVAL; } return 0; @@ -1363,25 +1368,57 @@ static int i8xx_crtc_compute_clock(struct intel_crtc_state *crtc_state) return 0; } +static const struct intel_dpll_funcs hsw_dpll_funcs = { + .crtc_compute_clock = hsw_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs ilk_dpll_funcs = { + .crtc_compute_clock = ilk_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs chv_dpll_funcs = { + .crtc_compute_clock = chv_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs vlv_dpll_funcs = { + .crtc_compute_clock = vlv_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs g4x_dpll_funcs = { + .crtc_compute_clock = g4x_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs pnv_dpll_funcs = { + .crtc_compute_clock = pnv_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs i9xx_dpll_funcs = { + .crtc_compute_clock = i9xx_crtc_compute_clock, +}; + +static const struct intel_dpll_funcs i8xx_dpll_funcs = { + .crtc_compute_clock = i8xx_crtc_compute_clock, +}; + void intel_dpll_init_clock_hook(struct drm_i915_private *dev_priv) { if (DISPLAY_VER(dev_priv) >= 9 || HAS_DDI(dev_priv)) - dev_priv->display.crtc_compute_clock = hsw_crtc_compute_clock; + dev_priv->dpll_funcs = &hsw_dpll_funcs; else if (HAS_PCH_SPLIT(dev_priv)) - dev_priv->display.crtc_compute_clock = ilk_crtc_compute_clock; + dev_priv->dpll_funcs = &ilk_dpll_funcs; else if (IS_CHERRYVIEW(dev_priv)) - dev_priv->display.crtc_compute_clock = chv_crtc_compute_clock; + dev_priv->dpll_funcs = &chv_dpll_funcs; else if (IS_VALLEYVIEW(dev_priv)) - dev_priv->display.crtc_compute_clock = vlv_crtc_compute_clock; + dev_priv->dpll_funcs = &vlv_dpll_funcs; else if (IS_G4X(dev_priv)) - dev_priv->display.crtc_compute_clock = g4x_crtc_compute_clock; + dev_priv->dpll_funcs = &g4x_dpll_funcs; else if (IS_PINEVIEW(dev_priv)) - dev_priv->display.crtc_compute_clock = pnv_crtc_compute_clock; + dev_priv->dpll_funcs = &pnv_dpll_funcs; else if (DISPLAY_VER(dev_priv) != 2) - dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock; + dev_priv->dpll_funcs = &i9xx_dpll_funcs; else - dev_priv->display.crtc_compute_clock = i8xx_crtc_compute_clock; + dev_priv->dpll_funcs = &i8xx_dpll_funcs; } static bool i9xx_has_pps(struct drm_i915_private *dev_priv) @@ -1400,11 +1437,11 @@ void i9xx_enable_pll(const struct intel_crtc_state *crtc_state) enum pipe pipe = crtc->pipe; int i; - assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, crtc_state->cpu_transcoder); /* PLL is protected by panel, make sure we can write it */ if (i9xx_has_pps(dev_priv)) - assert_panel_unlocked(dev_priv, pipe); + assert_pps_unlocked(dev_priv, pipe); intel_de_write(dev_priv, FP0(pipe), crtc_state->dpll_hw_state.fp0); intel_de_write(dev_priv, FP1(pipe), crtc_state->dpll_hw_state.fp1); @@ -1580,10 +1617,10 @@ void vlv_enable_pll(const struct intel_crtc_state *crtc_state) struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, crtc_state->cpu_transcoder); /* PLL is protected by panel, make sure we can write it */ - assert_panel_unlocked(dev_priv, pipe); + assert_pps_unlocked(dev_priv, pipe); /* Enable Refclk */ intel_de_write(dev_priv, DPLL(pipe), @@ -1732,10 +1769,10 @@ void chv_enable_pll(const struct intel_crtc_state *crtc_state) struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; - assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, crtc_state->cpu_transcoder); /* PLL is protected by panel, make sure we can write it */ - assert_panel_unlocked(dev_priv, pipe); + assert_pps_unlocked(dev_priv, pipe); /* Enable Refclk and SSC */ intel_de_write(dev_priv, DPLL(pipe), @@ -1816,7 +1853,7 @@ void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) u32 val; /* Make sure the pipe isn't still relying on us */ - assert_pipe_disabled(dev_priv, (enum transcoder)pipe); + assert_transcoder_disabled(dev_priv, (enum transcoder)pipe); val = DPLL_INTEGRATED_REF_CLK_VLV | DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS; @@ -1833,7 +1870,7 @@ void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) u32 val; /* Make sure the pipe isn't still relying on us */ - assert_pipe_disabled(dev_priv, (enum transcoder)pipe); + assert_transcoder_disabled(dev_priv, (enum transcoder)pipe); val = DPLL_SSC_REF_CLK_CHV | DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS; @@ -1864,7 +1901,7 @@ void i9xx_disable_pll(const struct intel_crtc_state *crtc_state) return; /* Make sure the pipe isn't still relying on us */ - assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder); + assert_transcoder_disabled(dev_priv, crtc_state->cpu_transcoder); intel_de_write(dev_priv, DPLL(pipe), DPLL_VGA_MODE_DIS); intel_de_posting_read(dev_priv, DPLL(pipe)); @@ -1886,3 +1923,25 @@ void vlv_force_pll_off(struct drm_i915_private *dev_priv, enum pipe pipe) else vlv_disable_pll(dev_priv, pipe); } + +/* Only for pre-ILK configs */ +static void assert_pll(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state) +{ + bool cur_state; + + cur_state = intel_de_read(dev_priv, DPLL(pipe)) & DPLL_VCO_ENABLE; + I915_STATE_WARN(cur_state != state, + "PLL state assertion failure (expected %s, current %s)\n", + onoff(state), onoff(cur_state)); +} + +void assert_pll_enabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_pll(i915, pipe, true); +} + +void assert_pll_disabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_pll(i915, pipe, false); +} diff --git a/drivers/gpu/drm/i915/display/intel_dpll.h b/drivers/gpu/drm/i915/display/intel_dpll.h index db396b3e1141..1af0ac43cca4 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll.h +++ b/drivers/gpu/drm/i915/display/intel_dpll.h @@ -36,4 +36,7 @@ bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state, struct dpll *best_clock); int chv_calc_dpll_params(int refclk, struct dpll *pll_clock); +void assert_pll_enabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_pll_disabled(struct drm_i915_private *i915, enum pipe pipe); + #endif diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 055992d099c7..0a7e04db04be 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -26,6 +26,7 @@ #include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_dpll_mgr.h" +#include "intel_tc.h" /** * DOC: Display PLLs @@ -3101,8 +3102,8 @@ static void icl_update_active_dpll(struct intel_atomic_state *state, enc_to_dig_port(encoder); if (primary_port && - (primary_port->tc_mode == TC_PORT_DP_ALT || - primary_port->tc_mode == TC_PORT_LEGACY)) + (intel_tc_port_in_dp_alt_mode(primary_port) || + intel_tc_port_in_legacy_mode(primary_port))) port_dpll_id = ICL_PORT_DPLL_MG_PHY; icl_set_active_port_dpll(crtc_state, port_dpll_id); diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c index de62bd77b15e..8f7b1f7534a4 100644 --- a/drivers/gpu/drm/i915/display/intel_dpt.c +++ b/drivers/gpu/drm/i915/display/intel_dpt.c @@ -121,32 +121,42 @@ struct i915_vma *intel_dpt_pin(struct i915_address_space *vm) intel_wakeref_t wakeref; struct i915_vma *vma; void __iomem *iomem; + struct i915_gem_ww_ctx ww; + int err; wakeref = intel_runtime_pm_get(&i915->runtime_pm); atomic_inc(&i915->gpu_error.pending_fb_pin); - vma = i915_gem_object_ggtt_pin(dpt->obj, NULL, 0, 4096, - HAS_LMEM(i915) ? 0 : PIN_MAPPABLE); - if (IS_ERR(vma)) - goto err; + for_i915_gem_ww(&ww, err, true) { + err = i915_gem_object_lock(dpt->obj, &ww); + if (err) + continue; - iomem = i915_vma_pin_iomap(vma); - i915_vma_unpin(vma); - if (IS_ERR(iomem)) { - vma = ERR_CAST(iomem); - goto err; + vma = i915_gem_object_ggtt_pin_ww(dpt->obj, &ww, NULL, 0, 4096, + HAS_LMEM(i915) ? 0 : PIN_MAPPABLE); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + continue; + } + + iomem = i915_vma_pin_iomap(vma); + i915_vma_unpin(vma); + + if (IS_ERR(iomem)) { + err = PTR_ERR(iomem); + continue; + } + + dpt->vma = vma; + dpt->iomem = iomem; + + i915_vma_get(vma); } - dpt->vma = vma; - dpt->iomem = iomem; - - i915_vma_get(vma); - -err: atomic_dec(&i915->gpu_error.pending_fb_pin); intel_runtime_pm_put(&i915->runtime_pm, wakeref); - return vma; + return err ? ERR_PTR(err) : vma; } void intel_dpt_unpin(struct i915_address_space *vm) diff --git a/drivers/gpu/drm/i915/display/intel_dsi.c b/drivers/gpu/drm/i915/display/intel_dsi.c index f453ceb8d149..6b0301ba046e 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.c +++ b/drivers/gpu/drm/i915/display/intel_dsi.c @@ -5,6 +5,7 @@ #include #include "intel_dsi.h" +#include "intel_panel.h" int intel_dsi_bitrate(const struct intel_dsi *intel_dsi) { @@ -60,20 +61,19 @@ enum drm_mode_status intel_dsi_mode_valid(struct drm_connector *connector, struct intel_connector *intel_connector = to_intel_connector(connector); const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + enum drm_mode_status status; drm_dbg_kms(&dev_priv->drm, "\n"); if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; - if (fixed_mode) { - if (mode->hdisplay > fixed_mode->hdisplay) - return MODE_PANEL; - if (mode->vdisplay > fixed_mode->vdisplay) - return MODE_PANEL; - if (fixed_mode->clock > max_dotclk) - return MODE_CLOCK_HIGH; - } + status = intel_panel_mode_valid(intel_connector, mode); + if (status != MODE_OK) + return status; + + if (fixed_mode->clock > max_dotclk) + return MODE_CLOCK_HIGH; return intel_mode_valid_max_plane_size(dev_priv, mode, false); } diff --git a/drivers/gpu/drm/i915/display/intel_dsi.h b/drivers/gpu/drm/i915/display/intel_dsi.h index 50d6da0b2419..fbc40ffdc02e 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.h +++ b/drivers/gpu/drm/i915/display/intel_dsi.h @@ -207,6 +207,9 @@ u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, struct intel_crtc_state *config); void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); +void assert_dsi_pll_enabled(struct drm_i915_private *i915); +void assert_dsi_pll_disabled(struct drm_i915_private *i915); + /* intel_dsi_vbt.c */ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id); void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on); diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index c2a2cd1f84dc..f241bedb8597 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -31,7 +31,6 @@ #include #include -#include #include #include @@ -42,7 +41,7 @@ #include "i915_drv.h" #include "intel_display_types.h" #include "intel_dsi.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" #define MIPI_TRANSFER_MODE_SHIFT 0 #define MIPI_VIRTUAL_CHANNEL_SHIFT 1 diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index 86c903e9df60..2eeb209afc64 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -223,9 +223,10 @@ static enum drm_mode_status intel_dvo_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { - struct intel_dvo *intel_dvo = intel_attached_dvo(to_intel_connector(connector)); + struct intel_connector *intel_connector = to_intel_connector(connector); + struct intel_dvo *intel_dvo = intel_attached_dvo(intel_connector); const struct drm_display_mode *fixed_mode = - to_intel_connector(connector)->panel.fixed_mode; + intel_connector->panel.fixed_mode; int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; int target_clock = mode->clock; @@ -235,10 +236,11 @@ intel_dvo_mode_valid(struct drm_connector *connector, /* XXX: Validate clock range */ if (fixed_mode) { - if (mode->hdisplay > fixed_mode->hdisplay) - return MODE_PANEL; - if (mode->vdisplay > fixed_mode->vdisplay) - return MODE_PANEL; + enum drm_mode_status status; + + status = intel_panel_mode_valid(intel_connector, mode); + if (status != MODE_OK) + return status; target_clock = fixed_mode->clock; } @@ -254,6 +256,7 @@ static int intel_dvo_compute_config(struct intel_encoder *encoder, struct drm_connector_state *conn_state) { struct intel_dvo *intel_dvo = enc_to_dvo(encoder); + struct intel_connector *connector = to_intel_connector(conn_state->connector); const struct drm_display_mode *fixed_mode = intel_dvo->attached_connector->panel.fixed_mode; struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; @@ -264,8 +267,13 @@ static int intel_dvo_compute_config(struct intel_encoder *encoder, * with the panel scaling set up to source from the H/VDisplay * of the original mode. */ - if (fixed_mode) - intel_panel_fixed_mode(fixed_mode, adjusted_mode); + if (fixed_mode) { + int ret; + + ret = intel_panel_compute_config(connector, adjusted_mode); + if (ret) + return ret; + } if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) return -EINVAL; diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index e4b8602ec0cd..fa1f375e696b 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -63,10 +63,36 @@ int skl_ccs_to_main_plane(const struct drm_framebuffer *fb, int ccs_plane) return ccs_plane - fb->format->num_planes / 2; } -static int gen12_ccs_aux_stride(struct drm_framebuffer *fb, int ccs_plane) +static unsigned int gen12_aligned_scanout_stride(const struct intel_framebuffer *fb, + int color_plane) { - return DIV_ROUND_UP(fb->pitches[skl_ccs_to_main_plane(fb, ccs_plane)], - 512) * 64; + struct drm_i915_private *i915 = to_i915(fb->base.dev); + unsigned int stride = fb->base.pitches[color_plane]; + + if (IS_ALDERLAKE_P(i915)) + return roundup_pow_of_two(max(stride, + 8u * intel_tile_width_bytes(&fb->base, color_plane))); + + return stride; +} + +static unsigned int gen12_ccs_aux_stride(struct intel_framebuffer *fb, int ccs_plane) +{ + struct drm_i915_private *i915 = to_i915(fb->base.dev); + int main_plane = skl_ccs_to_main_plane(&fb->base, ccs_plane); + unsigned int main_stride = fb->base.pitches[main_plane]; + unsigned int main_tile_width = intel_tile_width_bytes(&fb->base, main_plane); + + /* + * On ADL-P the AUX stride must align with a power-of-two aligned main + * surface stride. The stride of the allocated main surface object can + * be less than this POT stride, which is then autopadded to the POT + * size. + */ + if (IS_ALDERLAKE_P(i915)) + main_stride = gen12_aligned_scanout_stride(fb, main_plane); + + return DIV_ROUND_UP(main_stride, 4 * main_tile_width) * 64; } int skl_main_to_aux_plane(const struct drm_framebuffer *fb, int main_plane) @@ -143,14 +169,14 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) unsigned int intel_tile_height(const struct drm_framebuffer *fb, int color_plane) { - if (is_gen12_ccs_plane(fb, color_plane)) - return 1; - return intel_tile_size(to_i915(fb->dev)) / intel_tile_width_bytes(fb, color_plane); } -/* Return the tile dimensions in pixel units */ +/* + * Return the tile dimensions in pixel units, based on the (2 or 4 kbyte) GTT + * page tile size. + */ static void intel_tile_dims(const struct drm_framebuffer *fb, int color_plane, unsigned int *tile_width, unsigned int *tile_height) @@ -162,6 +188,21 @@ static void intel_tile_dims(const struct drm_framebuffer *fb, int color_plane, *tile_height = intel_tile_height(fb, color_plane); } +/* + * Return the tile dimensions in pixel units, based on the tile block size. + * The block covers the full GTT page sized tile on all tiled surfaces and + * it's a 64 byte portion of the tile on TGL+ CCS surfaces. + */ +static void intel_tile_block_dims(const struct drm_framebuffer *fb, int color_plane, + unsigned int *tile_width, + unsigned int *tile_height) +{ + intel_tile_dims(fb, color_plane, tile_width, tile_height); + + if (is_gen12_ccs_plane(fb, color_plane)) + *tile_height = 1; +} + unsigned int intel_tile_row_size(const struct drm_framebuffer *fb, int color_plane) { unsigned int tile_width, tile_height; @@ -316,15 +357,29 @@ void intel_fb_plane_get_subsampling(int *hsub, int *vsub, static void intel_fb_plane_dims(const struct intel_framebuffer *fb, int color_plane, int *w, int *h) { + struct drm_i915_private *i915 = to_i915(fb->base.dev); int main_plane = is_ccs_plane(&fb->base, color_plane) ? skl_ccs_to_main_plane(&fb->base, color_plane) : 0; + unsigned int main_width = fb->base.width; + unsigned int main_height = fb->base.height; int main_hsub, main_vsub; int hsub, vsub; + /* + * On ADL-P the CCS AUX surface layout always aligns with the + * power-of-two aligned main surface stride. The main surface + * stride in the allocated FB object may not be power-of-two + * sized, in which case it is auto-padded to the POT size. + */ + if (IS_ALDERLAKE_P(i915) && is_ccs_plane(&fb->base, color_plane)) + main_width = gen12_aligned_scanout_stride(fb, 0) / + fb->base.format->cpp[0]; + intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, &fb->base, main_plane); intel_fb_plane_get_subsampling(&hsub, &vsub, &fb->base, color_plane); - *w = fb->base.width / main_hsub / hsub; - *h = fb->base.height / main_vsub / vsub; + + *w = main_width / main_hsub / hsub; + *h = main_height / main_vsub / vsub; } static u32 intel_adjust_tile_offset(int *x, int *y, @@ -506,17 +561,8 @@ static int intel_fb_offset_to_xy(int *x, int *y, unsigned int height; u32 alignment; - /* - * All DPT color planes must be 512*4k aligned (the amount mapped by a - * single DPT page). For ADL_P CCS FBs this only works by requiring - * the allocated offsets to be 2MB aligned. Once supoort to remap - * such FBs is added we can remove this requirement, as then all the - * planes can be remapped to an aligned offset. - */ - if (IS_ALDERLAKE_P(i915) && is_ccs_modifier(fb->modifier)) - alignment = 512 * 4096; - else if (DISPLAY_VER(i915) >= 12 && - is_semiplanar_uv_plane(fb, color_plane)) + if (DISPLAY_VER(i915) >= 12 && + is_semiplanar_uv_plane(fb, color_plane)) alignment = intel_tile_row_size(fb, color_plane); else if (fb->modifier != DRM_FORMAT_MOD_LINEAR) alignment = intel_tile_size(i915); @@ -567,7 +613,12 @@ static int intel_fb_check_ccs_xy(const struct drm_framebuffer *fb, int ccs_plane if (!is_ccs_plane(fb, ccs_plane) || is_gen12_ccs_cc_plane(fb, ccs_plane)) return 0; - intel_tile_dims(fb, ccs_plane, &tile_width, &tile_height); + /* + * While all the tile dimensions are based on a 2k or 4k GTT page size + * here the main and CCS coordinates must match only within a (64 byte + * on TGL+) block inside the tile. + */ + intel_tile_block_dims(fb, ccs_plane, &tile_width, &tile_height); intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane); tile_width *= hsub; @@ -642,8 +693,7 @@ bool intel_fb_needs_pot_stride_remap(const struct intel_framebuffer *fb) { struct drm_i915_private *i915 = to_i915(fb->base.dev); - return IS_ALDERLAKE_P(i915) && fb->base.modifier != DRM_FORMAT_MOD_LINEAR && - !is_ccs_modifier(fb->base.modifier); + return IS_ALDERLAKE_P(i915) && fb->base.modifier != DRM_FORMAT_MOD_LINEAR; } static int intel_fb_pitch(const struct intel_framebuffer *fb, int color_plane, unsigned int rotation) @@ -763,14 +813,16 @@ static unsigned int plane_view_dst_stride_tiles(const struct intel_framebuffer *fb, int color_plane, unsigned int pitch_tiles) { - if (intel_fb_needs_pot_stride_remap(fb)) + if (intel_fb_needs_pot_stride_remap(fb)) { + unsigned int min_stride = is_ccs_plane(&fb->base, color_plane) ? 2 : 8; /* * ADL_P, the only platform needing a POT stride has a minimum - * of 8 stride tiles. + * of 8 main surface and 2 CCS AUX stride tiles. */ - return roundup_pow_of_two(max(pitch_tiles, 8u)); - else + return roundup_pow_of_two(max(pitch_tiles, min_stride)); + } else { return pitch_tiles; + } } static unsigned int @@ -806,7 +858,7 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p unsigned int tile_height = dims->tile_height; unsigned int tile_size = intel_tile_size(i915); struct drm_rect r; - u32 size; + u32 size = 0; assign_chk_ovf(i915, remap_info->offset, obj_offset); assign_chk_ovf(i915, remap_info->src_stride, plane_view_src_stride_tiles(fb, color_plane, dims)); @@ -831,7 +883,7 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p color_plane_info->stride = remap_info->dst_stride * tile_height; - size = remap_info->dst_stride * remap_info->width; + size += remap_info->dst_stride * remap_info->width; /* rotate the tile dimensions to match the GTT view */ swap(tile_width, tile_height); @@ -840,6 +892,14 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p check_array_bounds(i915, view->gtt.remapped.plane, color_plane); + if (view->gtt.remapped.plane_alignment) { + unsigned int aligned_offset = ALIGN(gtt_offset, + view->gtt.remapped.plane_alignment); + + size += aligned_offset - gtt_offset; + gtt_offset = aligned_offset; + } + assign_chk_ovf(i915, remap_info->dst_stride, plane_view_dst_stride_tiles(fb, color_plane, remap_info->width)); @@ -849,7 +909,7 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p color_plane_info->stride = remap_info->dst_stride * tile_width * fb->base.format->cpp[color_plane]; - size = remap_info->dst_stride * remap_info->height; + size += remap_info->dst_stride * remap_info->height; } /* @@ -896,10 +956,14 @@ calc_plane_normal_size(const struct intel_framebuffer *fb, int color_plane, return tiles; } -static void intel_fb_view_init(struct intel_fb_view *view, enum i915_ggtt_view_type view_type) +static void intel_fb_view_init(struct drm_i915_private *i915, struct intel_fb_view *view, + enum i915_ggtt_view_type view_type) { memset(view, 0, sizeof(*view)); view->gtt.type = view_type; + + if (view_type == I915_GGTT_VIEW_REMAPPED && IS_ALDERLAKE_P(i915)) + view->gtt.remapped.plane_alignment = SZ_2M / PAGE_SIZE; } bool intel_fb_supports_90_270_rotation(const struct intel_framebuffer *fb) @@ -920,16 +984,16 @@ int intel_fill_fb_info(struct drm_i915_private *i915, struct intel_framebuffer * int i, num_planes = fb->base.format->num_planes; unsigned int tile_size = intel_tile_size(i915); - intel_fb_view_init(&fb->normal_view, I915_GGTT_VIEW_NORMAL); + intel_fb_view_init(i915, &fb->normal_view, I915_GGTT_VIEW_NORMAL); drm_WARN_ON(&i915->drm, intel_fb_supports_90_270_rotation(fb) && intel_fb_needs_pot_stride_remap(fb)); if (intel_fb_supports_90_270_rotation(fb)) - intel_fb_view_init(&fb->rotated_view, I915_GGTT_VIEW_ROTATED); + intel_fb_view_init(i915, &fb->rotated_view, I915_GGTT_VIEW_ROTATED); if (intel_fb_needs_pot_stride_remap(fb)) - intel_fb_view_init(&fb->remapped_view, I915_GGTT_VIEW_REMAPPED); + intel_fb_view_init(i915, &fb->remapped_view, I915_GGTT_VIEW_REMAPPED); for (i = 0; i < num_planes; i++) { struct fb_plane_view_dims view_dims; @@ -1007,7 +1071,7 @@ static void intel_plane_remap_gtt(struct intel_plane_state *plane_state) unsigned int src_w, src_h; u32 gtt_offset = 0; - intel_fb_view_init(&plane_state->view, + intel_fb_view_init(i915, &plane_state->view, drm_rotation_90_or_270(rotation) ? I915_GGTT_VIEW_ROTATED : I915_GGTT_VIEW_REMAPPED); @@ -1112,6 +1176,20 @@ intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane) tile_width = intel_tile_width_bytes(fb, color_plane); if (is_ccs_modifier(fb->modifier)) { + /* + * On ADL-P the stride must be either 8 tiles or a stride + * that is aligned to 16 tiles, required by the 16 tiles = + * 64 kbyte CCS AUX PTE granularity, allowing CCS FBs to be + * remapped. + */ + if (IS_ALDERLAKE_P(dev_priv)) + tile_width *= fb->pitches[0] <= tile_width * 8 ? 8 : 16; + /* + * On TGL the surface stride must be 4 tile aligned, mapped by + * one 64 byte cacheline on the CCS AUX surface. + */ + else if (DISPLAY_VER(dev_priv) >= 12) + tile_width *= 4; /* * Display WA #0531: skl,bxt,kbl,glk * @@ -1121,14 +1199,8 @@ intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane) * require the entire fb to accommodate that to avoid * potential runtime errors at plane configuration time. */ - if ((DISPLAY_VER(dev_priv) == 9 || IS_GEMINILAKE(dev_priv)) && - color_plane == 0 && fb->width > 3840) - tile_width *= 4; - /* - * The main surface pitch must be padded to a multiple of four - * tile widths. - */ - else if (DISPLAY_VER(dev_priv) >= 12) + else if ((DISPLAY_VER(dev_priv) == 9 || IS_GEMINILAKE(dev_priv)) && + color_plane == 0 && fb->width > 3840) tile_width *= 4; } return tile_width; @@ -1359,7 +1431,7 @@ int intel_framebuffer_init(struct intel_framebuffer *intel_fb, } if (is_gen12_ccs_plane(fb, i) && !is_gen12_ccs_cc_plane(fb, i)) { - int ccs_aux_stride = gen12_ccs_aux_stride(fb, i); + int ccs_aux_stride = gen12_ccs_aux_stride(intel_fb, i); if (fb->pitches[i] != ccs_aux_stride) { drm_dbg_kms(&dev_priv->drm, @@ -1370,17 +1442,6 @@ int intel_framebuffer_init(struct intel_framebuffer *intel_fb, } } - /* TODO: Add POT stride remapping support for CCS formats as well. */ - if (IS_ALDERLAKE_P(dev_priv) && - mode_cmd->modifier[i] != DRM_FORMAT_MOD_LINEAR && - !intel_fb_needs_pot_stride_remap(intel_fb) && - !is_power_of_2(mode_cmd->pitches[i])) { - drm_dbg_kms(&dev_priv->drm, - "plane %d pitch (%d) must be power of two for tiled buffers\n", - i, mode_cmd->pitches[i]); - goto err; - } - fb->obj[i] = &obj->base; } diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c new file mode 100644 index 000000000000..3f77f3013584 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +/** + * DOC: display pinning helpers + */ + +#include "intel_display_types.h" +#include "intel_fb_pin.h" +#include "intel_fb.h" + +#include "intel_dpt.h" + +#include "gem/i915_gem_object.h" + +static struct i915_vma * +intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, + const struct i915_ggtt_view *view, + bool uses_fence, + unsigned long *out_flags, + struct i915_address_space *vm) +{ + struct drm_device *dev = fb->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_gem_object *obj = intel_fb_obj(fb); + struct i915_vma *vma; + u32 alignment; + int ret; + + if (WARN_ON(!i915_gem_object_is_framebuffer(obj))) + return ERR_PTR(-EINVAL); + + alignment = 4096 * 512; + + atomic_inc(&dev_priv->gpu_error.pending_fb_pin); + + ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE); + if (ret) { + vma = ERR_PTR(ret); + goto err; + } + + vma = i915_vma_instance(obj, vm, view); + if (IS_ERR(vma)) + goto err; + + if (i915_vma_misplaced(vma, 0, alignment, 0)) { + ret = i915_vma_unbind(vma); + if (ret) { + vma = ERR_PTR(ret); + goto err; + } + } + + ret = i915_vma_pin(vma, 0, alignment, PIN_GLOBAL); + if (ret) { + vma = ERR_PTR(ret); + goto err; + } + + vma->display_alignment = max_t(u64, vma->display_alignment, alignment); + + i915_gem_object_flush_if_display(obj); + + i915_vma_get(vma); +err: + atomic_dec(&dev_priv->gpu_error.pending_fb_pin); + + return vma; +} + +struct i915_vma * +intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, + bool phys_cursor, + const struct i915_ggtt_view *view, + bool uses_fence, + unsigned long *out_flags) +{ + struct drm_device *dev = fb->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_gem_object *obj = intel_fb_obj(fb); + intel_wakeref_t wakeref; + struct i915_gem_ww_ctx ww; + struct i915_vma *vma; + unsigned int pinctl; + u32 alignment; + int ret; + + if (drm_WARN_ON(dev, !i915_gem_object_is_framebuffer(obj))) + return ERR_PTR(-EINVAL); + + if (phys_cursor) + alignment = intel_cursor_alignment(dev_priv); + else + alignment = intel_surf_alignment(fb, 0); + if (drm_WARN_ON(dev, alignment && !is_power_of_2(alignment))) + return ERR_PTR(-EINVAL); + + /* Note that the w/a also requires 64 PTE of padding following the + * bo. We currently fill all unused PTE with the shadow page and so + * we should always have valid PTE following the scanout preventing + * the VT-d warning. + */ + if (intel_scanout_needs_vtd_wa(dev_priv) && alignment < 256 * 1024) + alignment = 256 * 1024; + + /* + * Global gtt pte registers are special registers which actually forward + * writes to a chunk of system memory. Which means that there is no risk + * that the register values disappear as soon as we call + * intel_runtime_pm_put(), so it is correct to wrap only the + * pin/unpin/fence and not more. + */ + wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); + + atomic_inc(&dev_priv->gpu_error.pending_fb_pin); + + /* + * Valleyview is definitely limited to scanning out the first + * 512MiB. Lets presume this behaviour was inherited from the + * g4x display engine and that all earlier gen are similarly + * limited. Testing suggests that it is a little more + * complicated than this. For example, Cherryview appears quite + * happy to scanout from anywhere within its global aperture. + */ + pinctl = 0; + if (HAS_GMCH(dev_priv)) + pinctl |= PIN_MAPPABLE; + + i915_gem_ww_ctx_init(&ww, true); +retry: + ret = i915_gem_object_lock(obj, &ww); + if (!ret && phys_cursor) + ret = i915_gem_object_attach_phys(obj, alignment); + else if (!ret && HAS_LMEM(dev_priv)) + ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM); + /* TODO: Do we need to sync when migration becomes async? */ + if (!ret) + ret = i915_gem_object_pin_pages(obj); + if (ret) + goto err; + + if (!ret) { + vma = i915_gem_object_pin_to_display_plane(obj, &ww, alignment, + view, pinctl); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unpin; + } + } + + if (uses_fence && i915_vma_is_map_and_fenceable(vma)) { + /* + * Install a fence for tiled scan-out. Pre-i965 always needs a + * fence, whereas 965+ only requires a fence if using + * framebuffer compression. For simplicity, we always, when + * possible, install a fence as the cost is not that onerous. + * + * If we fail to fence the tiled scanout, then either the + * modeset will reject the change (which is highly unlikely as + * the affected systems, all but one, do not have unmappable + * space) or we will not be able to enable full powersaving + * techniques (also likely not to apply due to various limits + * FBC and the like impose on the size of the buffer, which + * presumably we violated anyway with this unmappable buffer). + * Anyway, it is presumably better to stumble onwards with + * something and try to run the system in a "less than optimal" + * mode that matches the user configuration. + */ + ret = i915_vma_pin_fence(vma); + if (ret != 0 && DISPLAY_VER(dev_priv) < 4) { + i915_vma_unpin(vma); + goto err_unpin; + } + ret = 0; + + if (vma->fence) + *out_flags |= PLANE_HAS_FENCE; + } + + i915_vma_get(vma); + +err_unpin: + i915_gem_object_unpin_pages(obj); +err: + if (ret == -EDEADLK) { + ret = i915_gem_ww_ctx_backoff(&ww); + if (!ret) + goto retry; + } + i915_gem_ww_ctx_fini(&ww); + if (ret) + vma = ERR_PTR(ret); + + atomic_dec(&dev_priv->gpu_error.pending_fb_pin); + intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); + return vma; +} + +void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags) +{ + if (flags & PLANE_HAS_FENCE) + i915_vma_unpin_fence(vma); + i915_vma_unpin(vma); + i915_vma_put(vma); +} + +int intel_plane_pin_fb(struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + struct drm_framebuffer *fb = plane_state->hw.fb; + struct i915_vma *vma; + bool phys_cursor = + plane->id == PLANE_CURSOR && + INTEL_INFO(dev_priv)->display.cursor_needs_physical; + + if (!intel_fb_uses_dpt(fb)) { + vma = intel_pin_and_fence_fb_obj(fb, phys_cursor, + &plane_state->view.gtt, + intel_plane_uses_fence(plane_state), + &plane_state->flags); + if (IS_ERR(vma)) + return PTR_ERR(vma); + + plane_state->ggtt_vma = vma; + } else { + struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); + + vma = intel_dpt_pin(intel_fb->dpt_vm); + if (IS_ERR(vma)) + return PTR_ERR(vma); + + plane_state->ggtt_vma = vma; + + vma = intel_pin_fb_obj_dpt(fb, &plane_state->view.gtt, false, + &plane_state->flags, intel_fb->dpt_vm); + if (IS_ERR(vma)) { + intel_dpt_unpin(intel_fb->dpt_vm); + plane_state->ggtt_vma = NULL; + return PTR_ERR(vma); + } + + plane_state->dpt_vma = vma; + + WARN_ON(plane_state->ggtt_vma == plane_state->dpt_vma); + } + + return 0; +} + +void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state) +{ + struct drm_framebuffer *fb = old_plane_state->hw.fb; + struct i915_vma *vma; + + if (!intel_fb_uses_dpt(fb)) { + vma = fetch_and_zero(&old_plane_state->ggtt_vma); + if (vma) + intel_unpin_fb_vma(vma, old_plane_state->flags); + } else { + struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); + + vma = fetch_and_zero(&old_plane_state->dpt_vma); + if (vma) + intel_unpin_fb_vma(vma, old_plane_state->flags); + + vma = fetch_and_zero(&old_plane_state->ggtt_vma); + if (vma) + intel_dpt_unpin(intel_fb->dpt_vm); + } +} diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.h b/drivers/gpu/drm/i915/display/intel_fb_pin.h new file mode 100644 index 000000000000..e4fcd0218d9d --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __INTEL_FB_PIN_H__ +#define __INTEL_FB_PIN_H__ + +#include + +struct drm_framebuffer; +struct i915_vma; +struct intel_plane_state; +struct i915_ggtt_view; + +struct i915_vma * +intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, + bool phys_cursor, + const struct i915_ggtt_view *view, + bool uses_fence, + unsigned long *out_flags); + +void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags); + +int intel_plane_pin_fb(struct intel_plane_state *plane_state); +void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state); + +#endif diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index b1c1a23c36be..1f66de77a6b1 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -62,19 +62,84 @@ static void intel_fbc_get_plane_source_size(const struct intel_fbc_state_cache * *height = cache->plane.src_h; } -static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv, - const struct intel_fbc_state_cache *cache) +/* plane stride in pixels */ +static unsigned int intel_fbc_plane_stride(const struct intel_plane_state *plane_state) { - int lines; + const struct drm_framebuffer *fb = plane_state->hw.fb; + unsigned int stride; + + stride = plane_state->view.color_plane[0].stride; + if (!drm_rotation_90_or_270(plane_state->hw.rotation)) + stride /= fb->format->cpp[0]; + + return stride; +} + +/* plane stride based cfb stride in bytes, assuming 1:1 compression limit */ +static unsigned int _intel_fbc_cfb_stride(const struct intel_fbc_state_cache *cache) +{ + unsigned int cpp = 4; /* FBC always 4 bytes per pixel */ + + return cache->fb.stride * cpp; +} + +/* minimum acceptable cfb stride in bytes, assuming 1:1 compression limit */ +static unsigned int skl_fbc_min_cfb_stride(struct drm_i915_private *i915, + const struct intel_fbc_state_cache *cache) +{ + unsigned int limit = 4; /* 1:4 compression limit is the worst case */ + unsigned int cpp = 4; /* FBC always 4 bytes per pixel */ + unsigned int height = 4; /* FBC segment is 4 lines */ + unsigned int stride; + + /* minimum segment stride we can use */ + stride = cache->plane.src_w * cpp * height / limit; + + /* + * Wa_16011863758: icl+ + * Avoid some hardware segment address miscalculation. + */ + if (DISPLAY_VER(i915) >= 11) + stride += 64; + + /* + * At least some of the platforms require each 4 line segment to + * be 512 byte aligned. Just do it always for simplicity. + */ + stride = ALIGN(stride, 512); + + /* convert back to single line equivalent with 1:1 compression limit */ + return stride * limit / height; +} + +/* properly aligned cfb stride in bytes, assuming 1:1 compression limit */ +static unsigned int intel_fbc_cfb_stride(struct drm_i915_private *i915, + const struct intel_fbc_state_cache *cache) +{ + unsigned int stride = _intel_fbc_cfb_stride(cache); + + /* + * At least some of the platforms require each 4 line segment to + * be 512 byte aligned. Aligning each line to 512 bytes guarantees + * that regardless of the compression limit we choose later. + */ + if (DISPLAY_VER(i915) >= 9) + return max(ALIGN(stride, 512), skl_fbc_min_cfb_stride(i915, cache)); + else + return stride; +} + +static unsigned int intel_fbc_cfb_size(struct drm_i915_private *dev_priv, + const struct intel_fbc_state_cache *cache) +{ + int lines = cache->plane.src_h; - intel_fbc_get_plane_source_size(cache, NULL, &lines); if (DISPLAY_VER(dev_priv) == 7) lines = min(lines, 2048); else if (DISPLAY_VER(dev_priv) >= 8) lines = min(lines, 2560); - /* Hardware needs the full buffer stride, not just the active area. */ - return lines * cache->fb.stride; + return lines * intel_fbc_cfb_stride(dev_priv, cache); } static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv) @@ -99,15 +164,13 @@ static void i8xx_fbc_deactivate(struct drm_i915_private *dev_priv) static void i8xx_fbc_activate(struct drm_i915_private *dev_priv) { - struct intel_fbc_reg_params *params = &dev_priv->fbc.params; + struct intel_fbc *fbc = &dev_priv->fbc; + const struct intel_fbc_reg_params *params = &fbc->params; int cfb_pitch; int i; u32 fbc_ctl; - /* Note: fbc.limit == 1 for i8xx */ - cfb_pitch = params->cfb_size / FBC_LL_SIZE; - if (params->fb.stride < cfb_pitch) - cfb_pitch = params->fb.stride; + cfb_pitch = params->cfb_stride / fbc->limit; /* FBC_CTL wants 32B or 64B units */ if (DISPLAY_VER(dev_priv) == 2) @@ -150,15 +213,9 @@ static bool i8xx_fbc_is_active(struct drm_i915_private *dev_priv) static u32 g4x_dpfc_ctl_limit(struct drm_i915_private *i915) { - const struct intel_fbc_reg_params *params = &i915->fbc.params; - int limit = i915->fbc.limit; - - if (params->fb.format->cpp[0] == 2) - limit <<= 1; - - switch (limit) { + switch (i915->fbc.limit) { default: - MISSING_CASE(limit); + MISSING_CASE(i915->fbc.limit); fallthrough; case 1: return DPFC_CTL_LIMIT_1X; @@ -301,16 +358,25 @@ static bool ilk_fbc_is_active(struct drm_i915_private *dev_priv) static void gen7_fbc_activate(struct drm_i915_private *dev_priv) { - struct intel_fbc_reg_params *params = &dev_priv->fbc.params; + struct intel_fbc *fbc = &dev_priv->fbc; + const struct intel_fbc_reg_params *params = &fbc->params; u32 dpfc_ctl; - /* Display WA #0529: skl, kbl, bxt. */ - if (DISPLAY_VER(dev_priv) == 9) { + if (DISPLAY_VER(dev_priv) >= 10) { u32 val = 0; + if (params->override_cfb_stride) + val |= FBC_STRIDE_OVERRIDE | + FBC_STRIDE(params->override_cfb_stride / fbc->limit); + + intel_de_write(dev_priv, GLK_FBC_STRIDE, val); + } else if (DISPLAY_VER(dev_priv) == 9) { + u32 val = 0; + + /* Display WA #0529: skl, kbl, bxt. */ if (params->override_cfb_stride) val |= CHICKEN_FBC_STRIDE_OVERRIDE | - CHICKEN_FBC_STRIDE(params->override_cfb_stride); + CHICKEN_FBC_STRIDE(params->override_cfb_stride / fbc->limit); intel_de_rmw(dev_priv, CHICKEN_MISC_4, CHICKEN_FBC_STRIDE_OVERRIDE | @@ -443,30 +509,32 @@ static u64 intel_fbc_stolen_end(struct drm_i915_private *dev_priv) return min(end, intel_fbc_cfb_base_max(dev_priv)); } -static int intel_fbc_max_limit(struct drm_i915_private *dev_priv, int fb_cpp) +static int intel_fbc_min_limit(int fb_cpp) { - /* - * FIXME: FBC1 can have arbitrary cfb stride, - * so we could support different compression ratios. - */ - if (DISPLAY_VER(dev_priv) < 5 && !IS_G4X(dev_priv)) - return 1; + return fb_cpp == 2 ? 2 : 1; +} +static int intel_fbc_max_limit(struct drm_i915_private *dev_priv) +{ /* WaFbcOnly1to1Ratio:ctg */ if (IS_G4X(dev_priv)) return 1; - /* FBC2 can only do 1:1, 1:2, 1:4 */ - return fb_cpp == 2 ? 2 : 4; + /* + * FBC2 can only do 1:1, 1:2, 1:4, we limit + * FBC1 to the same out of convenience. + */ + return 4; } static int find_compression_limit(struct drm_i915_private *dev_priv, - unsigned int size, - unsigned int fb_cpp) + unsigned int size, int min_limit) { struct intel_fbc *fbc = &dev_priv->fbc; u64 end = intel_fbc_stolen_end(dev_priv); - int ret, limit = 1; + int ret, limit = min_limit; + + size /= limit; /* Try to over-allocate to reduce reallocations and fragmentation. */ ret = i915_gem_stolen_insert_node_in_range(dev_priv, &fbc->compressed_fb, @@ -474,7 +542,7 @@ static int find_compression_limit(struct drm_i915_private *dev_priv, if (ret == 0) return limit; - for (; limit <= intel_fbc_max_limit(dev_priv, fb_cpp); limit <<= 1) { + for (; limit <= intel_fbc_max_limit(dev_priv); limit <<= 1) { ret = i915_gem_stolen_insert_node_in_range(dev_priv, &fbc->compressed_fb, size >>= 1, 4096, 0, end); if (ret == 0) @@ -485,7 +553,7 @@ static int find_compression_limit(struct drm_i915_private *dev_priv, } static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, - unsigned int size, unsigned int fb_cpp) + unsigned int size, int min_limit) { struct intel_fbc *fbc = &dev_priv->fbc; int ret; @@ -502,13 +570,12 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, goto err; } - ret = find_compression_limit(dev_priv, size, fb_cpp); + ret = find_compression_limit(dev_priv, size, min_limit); if (!ret) goto err_llb; - else if (ret > 1) { + else if (ret > min_limit) drm_info_once(&dev_priv->drm, "Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); - } fbc->limit = ret; @@ -679,6 +746,7 @@ static bool tiling_is_valid(struct drm_i915_private *dev_priv, switch (modifier) { case DRM_FORMAT_MOD_LINEAR: case I915_FORMAT_MOD_Y_TILED: + case I915_FORMAT_MOD_Yf_TILED: return DISPLAY_VER(dev_priv) >= 9; case I915_FORMAT_MOD_X_TILED: return true; @@ -719,11 +787,7 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc, cache->fb.format = fb->format; cache->fb.modifier = fb->modifier; - - /* FIXME is this correct? */ - cache->fb.stride = plane_state->view.color_plane[0].stride; - if (drm_rotation_90_or_270(plane_state->hw.rotation)) - cache->fb.stride *= fb->format->cpp[0]; + cache->fb.stride = intel_fbc_plane_stride(plane_state); /* FBC1 compression interval: arbitrary choice of 1 second */ cache->interval = drm_mode_vrefresh(&crtc_state->hw.adjusted_mode); @@ -746,27 +810,29 @@ static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv) { struct intel_fbc *fbc = &dev_priv->fbc; - return intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) > + return intel_fbc_cfb_size(dev_priv, &fbc->state_cache) > fbc->compressed_fb.size * fbc->limit; } -static u16 intel_fbc_override_cfb_stride(struct drm_i915_private *dev_priv) +static u16 intel_fbc_override_cfb_stride(struct drm_i915_private *dev_priv, + const struct intel_fbc_state_cache *cache) { - struct intel_fbc *fbc = &dev_priv->fbc; - struct intel_fbc_state_cache *cache = &fbc->state_cache; + unsigned int stride = _intel_fbc_cfb_stride(cache); + unsigned int stride_aligned = intel_fbc_cfb_stride(dev_priv, cache); - if ((DISPLAY_VER(dev_priv) == 9) && - cache->fb.modifier != I915_FORMAT_MOD_X_TILED) - return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->limit) * 8; - else - return 0; -} + /* + * Override stride in 64 byte units per 4 line segment. + * + * Gen9 hw miscalculates cfb stride for linear as + * PLANE_STRIDE*512 instead of PLANE_STRIDE*64, so + * we always need to use the override there. + */ + if (stride != stride_aligned || + (DISPLAY_VER(dev_priv) == 9 && + cache->fb.modifier == DRM_FORMAT_MOD_LINEAR)) + return stride_aligned * 4 / 64; -static bool intel_fbc_override_cfb_stride_changed(struct drm_i915_private *dev_priv) -{ - struct intel_fbc *fbc = &dev_priv->fbc; - - return fbc->params.override_cfb_stride != intel_fbc_override_cfb_stride(dev_priv); + return 0; } static bool intel_fbc_can_enable(struct drm_i915_private *dev_priv) @@ -861,7 +927,8 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) return false; } - if (!stride_is_valid(dev_priv, cache->fb.modifier, cache->fb.stride)) { + if (!stride_is_valid(dev_priv, cache->fb.modifier, + cache->fb.stride * cache->fb.format->cpp[0])) { fbc->no_fbc_reason = "framebuffer stride not supported"; return false; } @@ -949,9 +1016,9 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc, params->fb.modifier = cache->fb.modifier; params->fb.stride = cache->fb.stride; - params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache); - - params->override_cfb_stride = cache->override_cfb_stride; + params->cfb_stride = intel_fbc_cfb_stride(dev_priv, cache); + params->cfb_size = intel_fbc_cfb_size(dev_priv, cache); + params->override_cfb_stride = intel_fbc_override_cfb_stride(dev_priv, cache); params->plane_visible = cache->plane.visible; } @@ -982,10 +1049,13 @@ static bool intel_fbc_can_flip_nuke(const struct intel_crtc_state *crtc_state) if (params->fb.stride != cache->fb.stride) return false; - if (params->cfb_size != intel_fbc_calculate_cfb_size(dev_priv, cache)) + if (params->cfb_stride != intel_fbc_cfb_stride(dev_priv, cache)) return false; - if (params->override_cfb_stride != cache->override_cfb_stride) + if (params->cfb_size != intel_fbc_cfb_size(dev_priv, cache)) + return false; + + if (params->override_cfb_stride != intel_fbc_override_cfb_stride(dev_priv, cache)) return false; return true; @@ -1130,7 +1200,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv, if (!HAS_FBC(dev_priv)) return; - if (origin == ORIGIN_FLIP) + if (origin == ORIGIN_FLIP || origin == ORIGIN_CURSOR_UPDATE) return; mutex_lock(&fbc->lock); @@ -1155,7 +1225,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv, fbc->busy_bits &= ~frontbuffer_bits; - if (origin == ORIGIN_FLIP) + if (origin == ORIGIN_FLIP || origin == ORIGIN_CURSOR_UPDATE) goto out; if (!fbc->busy_bits && fbc->crtc && @@ -1250,16 +1320,22 @@ static void intel_fbc_enable(struct intel_atomic_state *state, intel_atomic_get_new_plane_state(state, plane); struct intel_fbc *fbc = &dev_priv->fbc; struct intel_fbc_state_cache *cache = &fbc->state_cache; + int min_limit; if (!plane->has_fbc || !plane_state) return; + min_limit = intel_fbc_min_limit(plane_state->hw.fb ? + plane_state->hw.fb->format->cpp[0] : 0); + mutex_lock(&fbc->lock); if (fbc->crtc) { - if (fbc->crtc != crtc || - (!intel_fbc_cfb_size_changed(dev_priv) && - !intel_fbc_override_cfb_stride_changed(dev_priv))) + if (fbc->crtc != crtc) + goto out; + + if (fbc->limit >= min_limit && + !intel_fbc_cfb_size_changed(dev_priv)) goto out; __intel_fbc_disable(dev_priv); @@ -1274,15 +1350,12 @@ static void intel_fbc_enable(struct intel_atomic_state *state, goto out; if (intel_fbc_alloc_cfb(dev_priv, - intel_fbc_calculate_cfb_size(dev_priv, cache), - plane_state->hw.fb->format->cpp[0])) { + intel_fbc_cfb_size(dev_priv, cache), min_limit)) { cache->plane.visible = false; fbc->no_fbc_reason = "not enough stolen memory"; goto out; } - cache->override_cfb_stride = intel_fbc_override_cfb_stride(dev_priv); - drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n", pipe_name(crtc->pipe)); fbc->no_fbc_reason = "FBC enabled but not active yet\n"; diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 60d3ded27047..adc3a81be9f7 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -46,6 +46,7 @@ #include "i915_drv.h" #include "intel_display_types.h" #include "intel_fb.h" +#include "intel_fb_pin.h" #include "intel_fbdev.h" #include "intel_frontbuffer.h" @@ -230,8 +231,6 @@ static int intelfb_create(struct drm_fb_helper *helper, goto out_unlock; } - intel_frontbuffer_flush(to_frontbuffer(ifbdev), ORIGIN_DIRTYFB); - info = drm_fb_helper_alloc_fbi(helper); if (IS_ERR(info)) { drm_err(&dev_priv->drm, "Failed to allocate fb_info\n"); diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c index fc09b781f15f..dd2cf0c59921 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.c +++ b/drivers/gpu/drm/i915/display/intel_fdi.c @@ -8,7 +8,106 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_fdi.h" -#include "intel_sideband.h" +#include "intel_sbi.h" + +static void assert_fdi_tx(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state) +{ + bool cur_state; + + if (HAS_DDI(dev_priv)) { + /* + * DDI does not have a specific FDI_TX register. + * + * FDI is never fed from EDP transcoder + * so pipe->transcoder cast is fine here. + */ + enum transcoder cpu_transcoder = (enum transcoder)pipe; + cur_state = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder)) & TRANS_DDI_FUNC_ENABLE; + } else { + cur_state = intel_de_read(dev_priv, FDI_TX_CTL(pipe)) & FDI_TX_ENABLE; + } + I915_STATE_WARN(cur_state != state, + "FDI TX state assertion failure (expected %s, current %s)\n", + onoff(state), onoff(cur_state)); +} + +void assert_fdi_tx_enabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_fdi_tx(i915, pipe, true); +} + +void assert_fdi_tx_disabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_fdi_tx(i915, pipe, false); +} + +static void assert_fdi_rx(struct drm_i915_private *dev_priv, + enum pipe pipe, bool state) +{ + bool cur_state; + + cur_state = intel_de_read(dev_priv, FDI_RX_CTL(pipe)) & FDI_RX_ENABLE; + I915_STATE_WARN(cur_state != state, + "FDI RX state assertion failure (expected %s, current %s)\n", + onoff(state), onoff(cur_state)); +} + +void assert_fdi_rx_enabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_fdi_rx(i915, pipe, true); +} + +void assert_fdi_rx_disabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_fdi_rx(i915, pipe, false); +} + +void assert_fdi_tx_pll_enabled(struct drm_i915_private *i915, + enum pipe pipe) +{ + bool cur_state; + + /* ILK FDI PLL is always enabled */ + if (IS_IRONLAKE(i915)) + return; + + /* On Haswell, DDI ports are responsible for the FDI PLL setup */ + if (HAS_DDI(i915)) + return; + + cur_state = intel_de_read(i915, FDI_TX_CTL(pipe)) & FDI_TX_PLL_ENABLE; + I915_STATE_WARN(!cur_state, "FDI TX PLL assertion failure, should be active but is disabled\n"); +} + +static void assert_fdi_rx_pll(struct drm_i915_private *i915, + enum pipe pipe, bool state) +{ + bool cur_state; + + cur_state = intel_de_read(i915, FDI_RX_CTL(pipe)) & FDI_RX_PLL_ENABLE; + I915_STATE_WARN(cur_state != state, + "FDI RX PLL assertion failure (expected %s, current %s)\n", + onoff(state), onoff(cur_state)); +} + +void assert_fdi_rx_pll_enabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_fdi_rx_pll(i915, pipe, true); +} + +void assert_fdi_rx_pll_disabled(struct drm_i915_private *i915, enum pipe pipe) +{ + assert_fdi_rx_pll(i915, pipe, false); +} + +void intel_fdi_link_train(struct intel_crtc *crtc, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + + dev_priv->fdi_funcs->fdi_link_train(crtc, crtc_state); +} /* units of 100MHz */ static int pipe_required_fdi_lanes(struct intel_crtc_state *crtc_state) @@ -168,7 +267,7 @@ retry: } if (needs_recompute) - return I915_DISPLAY_CONFIG_RETRY; + return -EAGAIN; return ret; } @@ -281,7 +380,7 @@ static void ilk_fdi_link_train(struct intel_crtc *crtc, intel_de_read(dev_priv, PIPE_DATA_M1(pipe)) & TU_SIZE_MASK); /* FDI needs bits from pipe first */ - assert_pipe_enabled(dev_priv, crtc_state->cpu_transcoder); + assert_transcoder_enabled(dev_priv, crtc_state->cpu_transcoder); /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit for train result */ @@ -1005,15 +1104,27 @@ void lpt_fdi_program_mphy(struct drm_i915_private *dev_priv) intel_sbi_write(dev_priv, 0x21EC, tmp, SBI_MPHY); } +static const struct intel_fdi_funcs ilk_funcs = { + .fdi_link_train = ilk_fdi_link_train, +}; + +static const struct intel_fdi_funcs gen6_funcs = { + .fdi_link_train = gen6_fdi_link_train, +}; + +static const struct intel_fdi_funcs ivb_funcs = { + .fdi_link_train = ivb_manual_fdi_link_train, +}; + void intel_fdi_init_hook(struct drm_i915_private *dev_priv) { if (IS_IRONLAKE(dev_priv)) { - dev_priv->display.fdi_link_train = ilk_fdi_link_train; + dev_priv->fdi_funcs = &ilk_funcs; } else if (IS_SANDYBRIDGE(dev_priv)) { - dev_priv->display.fdi_link_train = gen6_fdi_link_train; + dev_priv->fdi_funcs = &gen6_funcs; } else if (IS_IVYBRIDGE(dev_priv)) { /* FIXME: detect B0+ stepping and use auto training */ - dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train; + dev_priv->fdi_funcs = &ivb_funcs; } } diff --git a/drivers/gpu/drm/i915/display/intel_fdi.h b/drivers/gpu/drm/i915/display/intel_fdi.h index 60acf2133145..640d6585c137 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.h +++ b/drivers/gpu/drm/i915/display/intel_fdi.h @@ -6,12 +6,12 @@ #ifndef _INTEL_FDI_H_ #define _INTEL_FDI_H_ +enum pipe; struct drm_i915_private; struct intel_crtc; struct intel_crtc_state; struct intel_encoder; -#define I915_DISPLAY_CONFIG_RETRY 1 int intel_fdi_link_freq(struct drm_i915_private *i915, const struct intel_crtc_state *pipe_config); int ilk_fdi_compute_config(struct intel_crtc *intel_crtc, @@ -26,4 +26,15 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, void intel_fdi_pll_freq_update(struct drm_i915_private *i915); void lpt_fdi_program_mphy(struct drm_i915_private *i915); +void intel_fdi_link_train(struct intel_crtc *crtc, + const struct intel_crtc_state *crtc_state); + +void assert_fdi_tx_enabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_tx_disabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_rx_enabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_rx_disabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_tx_pll_enabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_rx_pll_enabled(struct drm_i915_private *i915, enum pipe pipe); +void assert_fdi_rx_pll_disabled(struct drm_i915_private *i915, enum pipe pipe); + #endif diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.h b/drivers/gpu/drm/i915/display/intel_frontbuffer.h index 4b977c1e4d52..a88441edc8f9 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.h +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.h @@ -37,6 +37,7 @@ enum fb_op_origin { ORIGIN_CS, ORIGIN_FLIP, ORIGIN_DIRTYFB, + ORIGIN_CURSOR_UPDATE, }; struct intel_frontbuffer { diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 9b9fd9d13043..4509fe7438e8 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -17,12 +17,12 @@ #include "i915_drv.h" #include "i915_reg.h" -#include "intel_display_power.h" +#include "intel_connector.h" #include "intel_de.h" +#include "intel_display_power.h" #include "intel_display_types.h" #include "intel_hdcp.h" -#include "intel_sideband.h" -#include "intel_connector.h" +#include "intel_pcode.h" #define KEY_LOAD_TRIES 5 #define HDCP2_LC_RETRY_CNT 3 diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 1bc33766ed39..d2e61f6c6e08 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -53,21 +53,20 @@ #include "intel_panel.h" #include "intel_snps_phy.h" -static struct drm_device *intel_hdmi_to_dev(struct intel_hdmi *intel_hdmi) +static struct drm_i915_private *intel_hdmi_to_i915(struct intel_hdmi *intel_hdmi) { - return hdmi_to_dig_port(intel_hdmi)->base.base.dev; + return to_i915(hdmi_to_dig_port(intel_hdmi)->base.base.dev); } static void assert_hdmi_port_disabled(struct intel_hdmi *intel_hdmi) { - struct drm_device *dev = intel_hdmi_to_dev(intel_hdmi); - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = intel_hdmi_to_i915(intel_hdmi); u32 enabled_bits; enabled_bits = HAS_DDI(dev_priv) ? DDI_BUF_CTL_ENABLE : SDVO_ENABLE; - drm_WARN(dev, + drm_WARN(&dev_priv->drm, intel_de_read(dev_priv, intel_hdmi->hdmi_reg) & enabled_bits, "HDMI port enabled, expecting disabled\n"); } @@ -1246,7 +1245,7 @@ static void hsw_set_infoframes(struct intel_encoder *encoder, void intel_dp_dual_mode_set_tmds_output(struct intel_hdmi *hdmi, bool enable) { - struct drm_i915_private *dev_priv = to_i915(intel_hdmi_to_dev(hdmi)); + struct drm_i915_private *dev_priv = intel_hdmi_to_i915(hdmi); struct i2c_adapter *adapter = intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus); @@ -1703,7 +1702,7 @@ int intel_hdmi_hdcp2_read_msg(struct intel_digital_port *dig_port, drm_dbg_kms(&i915->drm, "msg_sz(%zd) is more than exp size(%zu)\n", ret, size); - return -1; + return -EINVAL; } offset = HDCP_2_2_HDMI_REG_RD_MSG_OFFSET; @@ -1830,7 +1829,7 @@ hdmi_port_clock_valid(struct intel_hdmi *hdmi, int clock, bool respect_downstream_limits, bool has_hdmi_sink) { - struct drm_i915_private *dev_priv = to_i915(intel_hdmi_to_dev(hdmi)); + struct drm_i915_private *dev_priv = intel_hdmi_to_i915(hdmi); if (clock < 25000) return MODE_CLOCK_LOW; @@ -1946,8 +1945,7 @@ intel_hdmi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector)); - struct drm_device *dev = intel_hdmi_to_dev(hdmi); - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = intel_hdmi_to_i915(hdmi); enum drm_mode_status status; int clock = mode->clock; int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c index 47c85ac97c87..955f6d07b0e1 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.c +++ b/drivers/gpu/drm/i915/display/intel_hotplug.c @@ -215,8 +215,8 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv) static void intel_hpd_irq_setup(struct drm_i915_private *i915) { - if (i915->display_irqs_enabled && i915->display.hpd_irq_setup) - i915->display.hpd_irq_setup(i915); + if (i915->display_irqs_enabled && i915->hotplug_funcs) + i915->hotplug_funcs->hpd_irq_setup(i915); } static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index e9fb402708a7..9fced37bed70 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -44,6 +44,8 @@ #include "intel_connector.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dpll.h" +#include "intel_fdi.h" #include "intel_gmbus.h" #include "intel_lvds.h" #include "intel_panel.h" @@ -389,13 +391,15 @@ intel_lvds_mode_valid(struct drm_connector *connector, struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; int max_pixclk = to_i915(connector->dev)->max_dotclk_freq; + enum drm_mode_status status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; - if (mode->hdisplay > fixed_mode->hdisplay) - return MODE_PANEL; - if (mode->vdisplay > fixed_mode->vdisplay) - return MODE_PANEL; + + status = intel_panel_mode_valid(intel_connector, mode); + if (status != MODE_OK) + return status; + if (fixed_mode->clock > max_pixclk) return MODE_CLOCK_HIGH; @@ -442,8 +446,9 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder, * with the panel scaling set up to source from the H/VDisplay * of the original mode. */ - intel_panel_fixed_mode(intel_connector->panel.fixed_mode, - adjusted_mode); + ret = intel_panel_compute_config(intel_connector, adjusted_mode); + if (ret) + return ret; if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) return -EINVAL; diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 4804b6b86798..a0c8e43db5eb 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -45,12 +45,34 @@ bool intel_panel_use_ssc(struct drm_i915_private *i915) && !(i915->quirks & QUIRK_LVDS_SSC_DISABLE); } -void intel_panel_fixed_mode(const struct drm_display_mode *fixed_mode, - struct drm_display_mode *adjusted_mode) +int intel_panel_compute_config(struct intel_connector *connector, + struct drm_display_mode *adjusted_mode) { + const struct drm_display_mode *fixed_mode = connector->panel.fixed_mode; + + if (!fixed_mode) + return 0; + + /* + * We don't want to lie too much to the user about the refresh + * rate they're going to get. But we have to allow a bit of latitude + * for Xorg since it likes to automagically cook up modes with slightly + * off refresh rates. + */ + if (abs(drm_mode_vrefresh(adjusted_mode) - drm_mode_vrefresh(fixed_mode)) > 1) { + drm_dbg_kms(connector->base.dev, + "[CONNECTOR:%d:%s] Requested mode vrefresh (%d Hz) does not match fixed mode vrefresh (%d Hz)\n", + connector->base.base.id, connector->base.name, + drm_mode_vrefresh(adjusted_mode), drm_mode_vrefresh(fixed_mode)); + + return -EINVAL; + } + drm_mode_copy(adjusted_mode, fixed_mode); drm_mode_set_crtcinfo(adjusted_mode, 0); + + return 0; } static bool is_downclock_mode(const struct drm_display_mode *downclock_mode, @@ -482,6 +504,27 @@ intel_panel_detect(struct drm_connector *connector, bool force) return connector_status_connected; } +enum drm_mode_status +intel_panel_mode_valid(struct intel_connector *connector, + const struct drm_display_mode *mode) +{ + const struct drm_display_mode *fixed_mode = connector->panel.fixed_mode; + + if (!fixed_mode) + return MODE_OK; + + if (mode->hdisplay != fixed_mode->hdisplay) + return MODE_PANEL; + + if (mode->vdisplay != fixed_mode->vdisplay) + return MODE_PANEL; + + if (drm_mode_vrefresh(mode) != drm_mode_vrefresh(fixed_mode)) + return MODE_PANEL; + + return MODE_OK; +} + int intel_panel_init(struct intel_panel *panel, struct drm_display_mode *fixed_mode, struct drm_display_mode *downclock_mode) diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h index f6af1a98290c..d50b3f7e9e58 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.h +++ b/drivers/gpu/drm/i915/display/intel_panel.h @@ -26,8 +26,13 @@ intel_panel_detect(struct drm_connector *connector, bool force); bool intel_panel_use_ssc(struct drm_i915_private *i915); void intel_panel_fixed_mode(const struct drm_display_mode *fixed_mode, struct drm_display_mode *adjusted_mode); +enum drm_mode_status +intel_panel_mode_valid(struct intel_connector *connector, + const struct drm_display_mode *mode); int intel_panel_fitting(struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state); +int intel_panel_compute_config(struct intel_connector *connector, + struct drm_display_mode *adjusted_mode); struct drm_display_mode * intel_panel_edid_downclock_mode(struct intel_connector *connector, const struct drm_display_mode *fixed_mode); diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c new file mode 100644 index 000000000000..dcd698a02da2 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include "intel_display_types.h" +#include "intel_plane_initial.h" +#include "intel_atomic_plane.h" +#include "intel_display.h" +#include "intel_fb.h" + +static bool +intel_reuse_initial_plane_obj(struct drm_i915_private *i915, + const struct intel_initial_plane_config *plane_config, + struct drm_framebuffer **fb, + struct i915_vma **vma) +{ + struct intel_crtc *crtc; + + for_each_intel_crtc(&i915->drm, crtc) { + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct intel_plane *plane = + to_intel_plane(crtc->base.primary); + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + + if (!crtc_state->uapi.active) + continue; + + if (!plane_state->ggtt_vma) + continue; + + if (intel_plane_ggtt_offset(plane_state) == plane_config->base) { + *fb = plane_state->hw.fb; + *vma = plane_state->ggtt_vma; + return true; + } + } + + return false; +} + +static struct i915_vma * +initial_plane_vma(struct drm_i915_private *i915, + struct intel_initial_plane_config *plane_config) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + u32 base, size; + + if (plane_config->size == 0) + return NULL; + + base = round_down(plane_config->base, + I915_GTT_MIN_ALIGNMENT); + size = round_up(plane_config->base + plane_config->size, + I915_GTT_MIN_ALIGNMENT); + size -= base; + + /* + * If the FB is too big, just don't use it since fbdev is not very + * important and we should probably use that space with FBC or other + * features. + */ + if (IS_ENABLED(CONFIG_FRAMEBUFFER_CONSOLE) && + size * 2 > i915->stolen_usable_size) + return NULL; + + obj = i915_gem_object_create_stolen_for_preallocated(i915, base, size); + if (IS_ERR(obj)) + return NULL; + + /* + * Mark it WT ahead of time to avoid changing the + * cache_level during fbdev initialization. The + * unbind there would get stuck waiting for rcu. + */ + i915_gem_object_set_cache_coherency(obj, HAS_WT(i915) ? + I915_CACHE_WT : I915_CACHE_NONE); + + switch (plane_config->tiling) { + case I915_TILING_NONE: + break; + case I915_TILING_X: + case I915_TILING_Y: + obj->tiling_and_stride = + plane_config->fb->base.pitches[0] | + plane_config->tiling; + break; + default: + MISSING_CASE(plane_config->tiling); + goto err_obj; + } + + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); + if (IS_ERR(vma)) + goto err_obj; + + if (i915_ggtt_pin(vma, NULL, 0, PIN_MAPPABLE | PIN_OFFSET_FIXED | base)) + goto err_obj; + + if (i915_gem_object_is_tiled(obj) && + !i915_vma_is_map_and_fenceable(vma)) + goto err_obj; + + return vma; + +err_obj: + i915_gem_object_put(obj); + return NULL; +} + +static bool +intel_alloc_initial_plane_obj(struct intel_crtc *crtc, + struct intel_initial_plane_config *plane_config) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_mode_fb_cmd2 mode_cmd = { 0 }; + struct drm_framebuffer *fb = &plane_config->fb->base; + struct i915_vma *vma; + + switch (fb->modifier) { + case DRM_FORMAT_MOD_LINEAR: + case I915_FORMAT_MOD_X_TILED: + case I915_FORMAT_MOD_Y_TILED: + break; + default: + drm_dbg(&dev_priv->drm, + "Unsupported modifier for initial FB: 0x%llx\n", + fb->modifier); + return false; + } + + vma = initial_plane_vma(dev_priv, plane_config); + if (!vma) + return false; + + mode_cmd.pixel_format = fb->format->format; + mode_cmd.width = fb->width; + mode_cmd.height = fb->height; + mode_cmd.pitches[0] = fb->pitches[0]; + mode_cmd.modifier[0] = fb->modifier; + mode_cmd.flags = DRM_MODE_FB_MODIFIERS; + + if (intel_framebuffer_init(to_intel_framebuffer(fb), + vma->obj, &mode_cmd)) { + drm_dbg_kms(&dev_priv->drm, "intel fb init failed\n"); + goto err_vma; + } + + plane_config->vma = vma; + return true; + +err_vma: + i915_vma_put(vma); + return false; +} + +static void +intel_find_initial_plane_obj(struct intel_crtc *crtc, + struct intel_initial_plane_config *plane_config) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct intel_plane *plane = + to_intel_plane(crtc->base.primary); + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + struct drm_framebuffer *fb; + struct i915_vma *vma; + + /* + * TODO: + * Disable planes if get_initial_plane_config() failed. + * Make sure things work if the surface base is not page aligned. + */ + if (!plane_config->fb) + return; + + if (intel_alloc_initial_plane_obj(crtc, plane_config)) { + fb = &plane_config->fb->base; + vma = plane_config->vma; + goto valid_fb; + } + + /* + * Failed to alloc the obj, check to see if we should share + * an fb with another CRTC instead + */ + if (intel_reuse_initial_plane_obj(dev_priv, plane_config, &fb, &vma)) + goto valid_fb; + + /* + * We've failed to reconstruct the BIOS FB. Current display state + * indicates that the primary plane is visible, but has a NULL FB, + * which will lead to problems later if we don't fix it up. The + * simplest solution is to just disable the primary plane now and + * pretend the BIOS never had it enabled. + */ + intel_plane_disable_noatomic(crtc, plane); + if (crtc_state->bigjoiner) { + struct intel_crtc *slave = + crtc_state->bigjoiner_linked_crtc; + intel_plane_disable_noatomic(slave, to_intel_plane(slave->base.primary)); + } + + return; + +valid_fb: + plane_state->uapi.rotation = plane_config->rotation; + intel_fb_fill_view(to_intel_framebuffer(fb), + plane_state->uapi.rotation, &plane_state->view); + + __i915_vma_pin(vma); + plane_state->ggtt_vma = i915_vma_get(vma); + if (intel_plane_uses_fence(plane_state) && + i915_vma_pin_fence(vma) == 0 && vma->fence) + plane_state->flags |= PLANE_HAS_FENCE; + + plane_state->uapi.src_x = 0; + plane_state->uapi.src_y = 0; + plane_state->uapi.src_w = fb->width << 16; + plane_state->uapi.src_h = fb->height << 16; + + plane_state->uapi.crtc_x = 0; + plane_state->uapi.crtc_y = 0; + plane_state->uapi.crtc_w = fb->width; + plane_state->uapi.crtc_h = fb->height; + + if (plane_config->tiling) + dev_priv->preserve_bios_swizzle = true; + + plane_state->uapi.fb = fb; + drm_framebuffer_get(fb); + + plane_state->uapi.crtc = &crtc->base; + intel_plane_copy_uapi_to_hw_state(plane_state, plane_state, crtc); + + atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits); +} + +static void plane_config_fini(struct intel_initial_plane_config *plane_config) +{ + if (plane_config->fb) { + struct drm_framebuffer *fb = &plane_config->fb->base; + + /* We may only have the stub and not a full framebuffer */ + if (drm_framebuffer_read_refcount(fb)) + drm_framebuffer_put(fb); + else + kfree(fb); + } + + if (plane_config->vma) + i915_vma_put(plane_config->vma); +} + +void intel_crtc_initial_plane_config(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_initial_plane_config plane_config = {}; + + /* + * Note that reserving the BIOS fb up front prevents us + * from stuffing other stolen allocations like the ring + * on top. This prevents some ugliness at boot time, and + * can even allow for smooth boot transitions if the BIOS + * fb is large enough for the active pipe configuration. + */ + dev_priv->display->get_initial_plane_config(crtc, &plane_config); + + /* + * If the fb is shared between multiple heads, we'll + * just get the first one. + */ + intel_find_initial_plane_obj(crtc, &plane_config); + + plane_config_fini(&plane_config); +} diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.h b/drivers/gpu/drm/i915/display/intel_plane_initial.h new file mode 100644 index 000000000000..c7e35ab3182b --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_plane_initial.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __INTEL_PLANE_INITIAL_H__ +#define __INTEL_PLANE_INITIAL_H__ + +struct intel_crtc; + +void intel_crtc_initial_plane_config(struct intel_crtc *crtc); + +#endif diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c index a36ec4a818ff..e9c679bb1b2e 100644 --- a/drivers/gpu/drm/i915/display/intel_pps.c +++ b/drivers/gpu/drm/i915/display/intel_pps.c @@ -9,6 +9,7 @@ #include "intel_display_types.h" #include "intel_dp.h" #include "intel_dpll.h" +#include "intel_lvds.h" #include "intel_pps.h" static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv, @@ -1408,3 +1409,61 @@ void intel_pps_setup(struct drm_i915_private *i915) else i915->pps_mmio_base = PPS_BASE; } + +void assert_pps_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe) +{ + i915_reg_t pp_reg; + u32 val; + enum pipe panel_pipe = INVALID_PIPE; + bool locked = true; + + if (drm_WARN_ON(&dev_priv->drm, HAS_DDI(dev_priv))) + return; + + if (HAS_PCH_SPLIT(dev_priv)) { + u32 port_sel; + + pp_reg = PP_CONTROL(0); + port_sel = intel_de_read(dev_priv, PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK; + + switch (port_sel) { + case PANEL_PORT_SELECT_LVDS: + intel_lvds_port_enabled(dev_priv, PCH_LVDS, &panel_pipe); + break; + case PANEL_PORT_SELECT_DPA: + g4x_dp_port_enabled(dev_priv, DP_A, PORT_A, &panel_pipe); + break; + case PANEL_PORT_SELECT_DPC: + g4x_dp_port_enabled(dev_priv, PCH_DP_C, PORT_C, &panel_pipe); + break; + case PANEL_PORT_SELECT_DPD: + g4x_dp_port_enabled(dev_priv, PCH_DP_D, PORT_D, &panel_pipe); + break; + default: + MISSING_CASE(port_sel); + break; + } + } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { + /* presumably write lock depends on pipe, not port select */ + pp_reg = PP_CONTROL(pipe); + panel_pipe = pipe; + } else { + u32 port_sel; + + pp_reg = PP_CONTROL(0); + port_sel = intel_de_read(dev_priv, PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK; + + drm_WARN_ON(&dev_priv->drm, + port_sel != PANEL_PORT_SELECT_LVDS); + intel_lvds_port_enabled(dev_priv, LVDS, &panel_pipe); + } + + val = intel_de_read(dev_priv, pp_reg); + if (!(val & PANEL_POWER_ON) || + ((val & PANEL_UNLOCK_MASK) == PANEL_UNLOCK_REGS)) + locked = false; + + I915_STATE_WARN(panel_pipe == pipe && locked, + "panel assertion failure, pipe %c regs locked\n", + pipe_name(pipe)); +} diff --git a/drivers/gpu/drm/i915/display/intel_pps.h b/drivers/gpu/drm/i915/display/intel_pps.h index fbbcca782e7b..fbb47f6f453e 100644 --- a/drivers/gpu/drm/i915/display/intel_pps.h +++ b/drivers/gpu/drm/i915/display/intel_pps.h @@ -10,6 +10,7 @@ #include "intel_wakeref.h" +enum pipe; struct drm_i915_private; struct intel_connector; struct intel_crtc_state; @@ -49,4 +50,6 @@ void vlv_pps_init(struct intel_encoder *encoder, void intel_pps_unlock_regs_wa(struct drm_i915_private *i915); void intel_pps_setup(struct drm_i915_private *i915); +void assert_pps_unlocked(struct drm_i915_private *i915, enum pipe pipe); + #endif /* __INTEL_PPS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 3f6fb7d67f84..7a205fd5023b 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -22,6 +22,7 @@ */ #include +#include #include "display/intel_dp.h" @@ -425,7 +426,7 @@ static u32 intel_psr1_get_tp_time(struct intel_dp *intel_dp) val |= EDP_PSR_TP2_TP3_TIME_2500us; check_tp3_sel: - if (intel_dp_source_supports_hbr2(intel_dp) && + if (intel_dp_source_supports_tps3(dev_priv) && drm_dp_tps3_supported(intel_dp->dpcd)) val |= EDP_PSR_TP1_TP3_SEL; else @@ -510,7 +511,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) if (DISPLAY_VER(dev_priv) >= 10 && DISPLAY_VER(dev_priv) <= 12) val |= EDP_Y_COORDINATE_ENABLE; - val |= EDP_PSR2_FRAME_BEFORE_SU(intel_dp->psr.sink_sync_latency + 1); + val |= EDP_PSR2_FRAME_BEFORE_SU(max_t(u8, intel_dp->psr.sink_sync_latency + 1, 2)); val |= intel_psr2_get_tp_time(intel_dp); /* Wa_22012278275:adl-p */ @@ -560,15 +561,16 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) val |= EDP_PSR2_SU_SDP_SCANLINE; if (intel_dp->psr.psr2_sel_fetch_enabled) { + u32 tmp; + /* Wa_1408330847 */ if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) intel_de_rmw(dev_priv, CHICKEN_PAR1_1, DIS_RAM_BYPASS_PSR2_MAN_TRACK, DIS_RAM_BYPASS_PSR2_MAN_TRACK); - intel_de_write(dev_priv, - PSR2_MAN_TRK_CTL(intel_dp->psr.transcoder), - PSR2_MAN_TRK_CTL_ENABLE); + tmp = intel_de_read(dev_priv, PSR2_MAN_TRK_CTL(intel_dp->psr.transcoder)); + drm_WARN_ON(&dev_priv->drm, !(tmp & PSR2_MAN_TRK_CTL_ENABLE)); } else if (HAS_PSR2_SEL_FETCH(dev_priv)) { intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(intel_dp->psr.transcoder), 0); @@ -718,11 +720,7 @@ tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp, static bool intel_psr2_sel_fetch_config_valid(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state) { - struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state); struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - struct intel_plane_state *plane_state; - struct intel_plane *plane; - int i; if (!dev_priv->params.enable_psr2_sel_fetch && intel_dp->psr.debug != I915_PSR_DEBUG_ENABLE_SEL_FETCH) { @@ -737,14 +735,6 @@ static bool intel_psr2_sel_fetch_config_valid(struct intel_dp *intel_dp, return false; } - for_each_new_intel_plane_in_state(state, plane, plane_state, i) { - if (plane_state->uapi.rotation != DRM_MODE_ROTATE_0) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 sel fetch not enabled, plane rotated\n"); - return false; - } - } - /* Wa_14010254185 Wa_14010103792 */ if (IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) { drm_dbg_kms(&dev_priv->drm, @@ -840,12 +830,8 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } - /* - * We are missing the implementation of some workarounds to enabled PSR2 - * in Alderlake_P, until ready PSR2 should be kept disabled. - */ - if (IS_ALDERLAKE_P(dev_priv)) { - drm_dbg_kms(&dev_priv->drm, "PSR2 is missing the implementation of workarounds\n"); + if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { + drm_dbg_kms(&dev_priv->drm, "PSR2 not completely functional in this stepping\n"); return false; } @@ -948,7 +934,8 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, } void intel_psr_compute_config(struct intel_dp *intel_dp, - struct intel_crtc_state *crtc_state) + struct intel_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); const struct drm_display_mode *adjusted_mode = @@ -1000,7 +987,10 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, crtc_state->has_psr = true; crtc_state->has_psr2 = intel_psr2_config_valid(intel_dp, crtc_state); + crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_VSC); + intel_dp_compute_psr_vsc_sdp(intel_dp, crtc_state, conn_state, + &crtc_state->psr_vsc); } void intel_psr_get_config(struct intel_encoder *encoder, @@ -1086,6 +1076,16 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp) intel_de_write(dev_priv, reg, chicken); } + /* + * Wa_16014451276:adlp + * All supported adlp panels have 1-based X granularity, this may + * cause issues if non-supported panels are used. + */ + if (IS_ALDERLAKE_P(dev_priv) && + intel_dp->psr.psr2_enabled) + intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder), 0, + ADLP_1_BASED_X_GRANULARITY); + /* * Per Spec: Avoid continuous PSR exit by masking MEMUP and HPD also * mask LPSP to avoid dependency on other drivers that might block @@ -1131,6 +1131,11 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp) TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder), TRANS_SET_CONTEXT_LATENCY_MASK, TRANS_SET_CONTEXT_LATENCY_VALUE(1)); + + /* Wa_16012604467:adlp */ + if (IS_ALDERLAKE_P(dev_priv) && intel_dp->psr.psr2_enabled) + intel_de_rmw(dev_priv, CLKGATE_DIS_MISC, 0, + CLKGATE_DIS_MISC_DMASC_GATING_DIS); } static bool psr_interrupt_error_check(struct intel_dp *intel_dp) @@ -1165,8 +1170,7 @@ static bool psr_interrupt_error_check(struct intel_dp *intel_dp) } static void intel_psr_enable_locked(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state) + const struct intel_crtc_state *crtc_state) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -1193,9 +1197,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp, drm_dbg_kms(&dev_priv->drm, "Enabling PSR%s\n", intel_dp->psr.psr2_enabled ? "2" : "1"); - intel_dp_compute_psr_vsc_sdp(intel_dp, crtc_state, conn_state, - &intel_dp->psr.vsc); - intel_write_dp_vsc_sdp(encoder, crtc_state, &intel_dp->psr.vsc); + intel_write_dp_vsc_sdp(encoder, crtc_state, &crtc_state->psr_vsc); intel_snps_phy_update_psr_power_state(dev_priv, phy, true); intel_psr_enable_sink(intel_dp); intel_psr_enable_source(intel_dp); @@ -1205,33 +1207,6 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp, intel_psr_activate(intel_dp); } -/** - * intel_psr_enable - Enable PSR - * @intel_dp: Intel DP - * @crtc_state: new CRTC state - * @conn_state: new CONNECTOR state - * - * This function can only be called after the pipe is fully trained and enabled. - */ -void intel_psr_enable(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state) -{ - struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - - if (!CAN_PSR(intel_dp)) - return; - - if (!crtc_state->has_psr) - return; - - drm_WARN_ON(&dev_priv->drm, dev_priv->drrs.dp); - - mutex_lock(&intel_dp->psr.lock); - intel_psr_enable_locked(intel_dp, crtc_state, conn_state); - mutex_unlock(&intel_dp->psr.lock); -} - static void intel_psr_exit(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -1320,6 +1295,11 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp) TRANS_SET_CONTEXT_LATENCY(intel_dp->psr.transcoder), TRANS_SET_CONTEXT_LATENCY_MASK, 0); + /* Wa_16012604467:adlp */ + if (IS_ALDERLAKE_P(dev_priv) && intel_dp->psr.psr2_enabled) + intel_de_rmw(dev_priv, CLKGATE_DIS_MISC, + CLKGATE_DIS_MISC_DMASC_GATING_DIS, 0); + intel_snps_phy_update_psr_power_state(dev_priv, phy, false); /* Disable PSR on Sink */ @@ -1413,10 +1393,22 @@ unlock: mutex_unlock(&psr->lock); } +static inline u32 man_trk_ctl_single_full_frame_bit_get(struct drm_i915_private *dev_priv) +{ + return IS_ALDERLAKE_P(dev_priv) ? + ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME : + PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME; +} + static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + if (intel_dp->psr.psr2_sel_fetch_enabled) + intel_de_rmw(dev_priv, + PSR2_MAN_TRK_CTL(intel_dp->psr.transcoder), 0, + man_trk_ctl_single_full_frame_bit_get(dev_priv)); + /* * Display WA #0884: skl+ * This documented WA for bxt can be safely applied @@ -1425,10 +1417,26 @@ static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp) * Workaround tells us to write 0 to CUR_SURFLIVE_A, * but it makes more sense write to the current active * pipe. + * + * This workaround do not exist for platforms with display 10 or newer + * but testing proved that it works for up display 13, for newer + * than that testing will be needed. */ intel_de_write(dev_priv, CURSURFLIVE(intel_dp->psr.pipe), 0); } +void intel_psr2_disable_plane_sel_fetch(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + + if (!crtc_state->enable_psr2_sel_fetch) + return; + + intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_CTL(pipe, plane->id), 0); +} + void intel_psr2_program_plane_sel_fetch(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state, @@ -1443,11 +1451,11 @@ void intel_psr2_program_plane_sel_fetch(struct intel_plane *plane, if (!crtc_state->enable_psr2_sel_fetch) return; - val = plane_state ? plane_state->ctl : 0; - val &= plane->id == PLANE_CURSOR ? val : PLANE_SEL_FETCH_CTL_ENABLE; - intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_CTL(pipe, plane->id), val); - if (!val || plane->id == PLANE_CURSOR) + if (plane->id == PLANE_CURSOR) { + intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_CTL(pipe, plane->id), + plane_state->ctl); return; + } clip = &plane_state->psr2_sel_fetch_area; @@ -1466,14 +1474,16 @@ void intel_psr2_program_plane_sel_fetch(struct intel_plane *plane, val = (drm_rect_height(clip) - 1) << 16; val |= (drm_rect_width(&plane_state->uapi.src) >> 16) - 1; intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_SIZE(pipe, plane->id), val); + + intel_de_write_fw(dev_priv, PLANE_SEL_FETCH_CTL(pipe, plane->id), + PLANE_SEL_FETCH_CTL_ENABLE); } void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - if (!HAS_PSR2_SEL_FETCH(dev_priv) || - !crtc_state->enable_psr2_sel_fetch) + if (!crtc_state->enable_psr2_sel_fetch) return; intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(crtc_state->cpu_transcoder), @@ -1488,11 +1498,11 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, u32 val = PSR2_MAN_TRK_CTL_ENABLE; if (full_update) { - if (IS_ALDERLAKE_P(dev_priv)) - val |= ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME; - else - val |= PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME; - + /* + * Not applying Wa_14014971508:adlp as we do not support the + * feature that requires this workaround. + */ + val |= man_trk_ctl_single_full_frame_bit_get(dev_priv); goto exit; } @@ -1501,7 +1511,7 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, if (IS_ALDERLAKE_P(dev_priv)) { val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1); - val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2); + val |= ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 - 1); } else { drm_WARN_ON(crtc_state->uapi.crtc->dev, clip->y1 % 4 || clip->y2 % 4); @@ -1543,6 +1553,45 @@ static void intel_psr2_sel_fetch_pipe_alignment(const struct intel_crtc_state *c drm_warn(&dev_priv->drm, "Missing PSR2 sel fetch alignment with DSC\n"); } +/* + * TODO: Not clear how to handle planes with negative position, + * also planes are not updated if they have a negative X + * position so for now doing a full update in this cases + * + * TODO: We are missing multi-planar formats handling, until it is + * implemented it will send full frame updates. + * + * Plane scaling and rotation is not supported by selective fetch and both + * properties can change without a modeset, so need to be check at every + * atomic commmit. + */ +static bool psr2_sel_fetch_plane_state_supported(const struct intel_plane_state *plane_state) +{ + if (plane_state->uapi.dst.y1 < 0 || + plane_state->uapi.dst.x1 < 0 || + plane_state->scaler_id >= 0 || + plane_state->hw.fb->format->num_planes > 1 || + plane_state->uapi.rotation != DRM_MODE_ROTATE_0) + return false; + + return true; +} + +/* + * Check for pipe properties that is not supported by selective fetch. + * + * TODO: pipe scaling causes a modeset but skl_update_scaler_crtc() is executed + * after intel_psr_compute_config(), so for now keeping PSR2 selective fetch + * enabled and going to the full update path. + */ +static bool psr2_sel_fetch_pipe_state_supported(const struct intel_crtc_state *crtc_state) +{ + if (crtc_state->scaler_state.scaler_id >= 0) + return false; + + return true; +} + int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, struct intel_crtc *crtc) { @@ -1556,9 +1605,10 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, if (!crtc_state->enable_psr2_sel_fetch) return 0; - ret = drm_atomic_add_affected_planes(&state->base, &crtc->base); - if (ret) - return ret; + if (!psr2_sel_fetch_pipe_state_supported(crtc_state)) { + full_update = true; + goto skip_sel_fetch_set_loop; + } /* * Calculate minimal selective fetch area of each plane and calculate @@ -1569,8 +1619,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { struct drm_rect src, damaged_area = { .y1 = -1 }; - struct drm_mode_rect *damaged_clips; - u32 num_clips, j; + struct drm_atomic_helper_damage_iter iter; + struct drm_rect clip; if (new_plane_state->uapi.crtc != crtc_state->uapi.crtc) continue; @@ -1579,19 +1629,11 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, !old_plane_state->uapi.visible) continue; - /* - * TODO: Not clear how to handle planes with negative position, - * also planes are not updated if they have a negative X - * position so for now doing a full update in this cases - */ - if (new_plane_state->uapi.dst.y1 < 0 || - new_plane_state->uapi.dst.x1 < 0) { + if (!psr2_sel_fetch_plane_state_supported(new_plane_state)) { full_update = true; break; } - num_clips = drm_plane_get_damage_clips_count(&new_plane_state->uapi); - /* * If visibility or plane moved, mark the whole plane area as * damaged as it needs to be complete redraw in the new and old @@ -1612,14 +1654,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, clip_area_update(&pipe_clip, &damaged_area); } continue; - } else if (new_plane_state->uapi.alpha != old_plane_state->uapi.alpha || - (!num_clips && - new_plane_state->uapi.fb != old_plane_state->uapi.fb)) { - /* - * If the plane don't have damaged areas but the - * framebuffer changed or alpha changed, mark the whole - * plane area as damaged. - */ + } else if (new_plane_state->uapi.alpha != old_plane_state->uapi.alpha) { + /* If alpha changed mark the whole plane area as damaged */ damaged_area.y1 = new_plane_state->uapi.dst.y1; damaged_area.y2 = new_plane_state->uapi.dst.y2; clip_area_update(&pipe_clip, &damaged_area); @@ -1627,15 +1663,11 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, } drm_rect_fp_to_int(&src, &new_plane_state->uapi.src); - damaged_clips = drm_plane_get_damage_clips(&new_plane_state->uapi); - for (j = 0; j < num_clips; j++) { - struct drm_rect clip; - - clip.x1 = damaged_clips[j].x1; - clip.y1 = damaged_clips[j].y1; - clip.x2 = damaged_clips[j].x2; - clip.y2 = damaged_clips[j].y2; + drm_atomic_helper_damage_iter_init(&iter, + &old_plane_state->uapi, + &new_plane_state->uapi); + drm_atomic_for_each_plane_damage(&iter, &clip) { if (drm_rect_intersect(&clip, &src)) clip_area_update(&damaged_area, &clip); } @@ -1651,6 +1683,10 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, if (full_update) goto skip_sel_fetch_set_loop; + ret = drm_atomic_add_affected_planes(&state->base, &crtc->base); + if (ret) + return ret; + intel_psr2_sel_fetch_pipe_alignment(crtc_state, &pipe_clip); /* @@ -1669,6 +1705,11 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, if (!drm_rect_intersect(&inter, &new_plane_state->uapi.dst)) continue; + if (!psr2_sel_fetch_plane_state_supported(new_plane_state)) { + full_update = true; + break; + } + sel_fetch_area = &new_plane_state->psr2_sel_fetch_area; sel_fetch_area->y1 = inter.y1 - new_plane_state->uapi.dst.y1; sel_fetch_area->y2 = inter.y2 - new_plane_state->uapi.dst.y1; @@ -1680,48 +1721,92 @@ skip_sel_fetch_set_loop: return 0; } -/** - * intel_psr_update - Update PSR state - * @intel_dp: Intel DP - * @crtc_state: new CRTC state - * @conn_state: new CONNECTOR state - * - * This functions will update PSR states, disabling, enabling or switching PSR - * version when executing fastsets. For full modeset, intel_psr_disable() and - * intel_psr_enable() should be called instead. - */ -void intel_psr_update(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state) +static void _intel_psr_pre_plane_update(const struct intel_atomic_state *state, + const struct intel_crtc_state *crtc_state) { - struct intel_psr *psr = &intel_dp->psr; - bool enable, psr2_enable; + struct intel_encoder *encoder; - if (!CAN_PSR(intel_dp)) + for_each_intel_encoder_mask_with_psr(state->base.dev, encoder, + crtc_state->uapi.encoder_mask) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + struct intel_psr *psr = &intel_dp->psr; + bool needs_to_disable = false; + + mutex_lock(&psr->lock); + + /* + * Reasons to disable: + * - PSR disabled in new state + * - All planes will go inactive + * - Changing between PSR versions + */ + needs_to_disable |= !crtc_state->has_psr; + needs_to_disable |= !crtc_state->active_planes; + needs_to_disable |= crtc_state->has_psr2 != psr->psr2_enabled; + + if (psr->enabled && needs_to_disable) + intel_psr_disable_locked(intel_dp); + + mutex_unlock(&psr->lock); + } +} + +void intel_psr_pre_plane_update(const struct intel_atomic_state *state) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_crtc_state *crtc_state; + struct intel_crtc *crtc; + int i; + + if (!HAS_PSR(dev_priv)) return; - mutex_lock(&intel_dp->psr.lock); + for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) + _intel_psr_pre_plane_update(state, crtc_state); +} - enable = crtc_state->has_psr; - psr2_enable = crtc_state->has_psr2; +static void _intel_psr_post_plane_update(const struct intel_atomic_state *state, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_encoder *encoder; + + if (!crtc_state->has_psr) + return; + + for_each_intel_encoder_mask_with_psr(state->base.dev, encoder, + crtc_state->uapi.encoder_mask) { + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + struct intel_psr *psr = &intel_dp->psr; + + mutex_lock(&psr->lock); + + drm_WARN_ON(&dev_priv->drm, psr->enabled && !crtc_state->active_planes); + + /* Only enable if there is active planes */ + if (!psr->enabled && crtc_state->active_planes) + intel_psr_enable_locked(intel_dp, crtc_state); - if (enable == psr->enabled && psr2_enable == psr->psr2_enabled && - crtc_state->enable_psr2_sel_fetch == psr->psr2_sel_fetch_enabled) { /* Force a PSR exit when enabling CRC to avoid CRC timeouts */ if (crtc_state->crc_enabled && psr->enabled) psr_force_hw_tracking_exit(intel_dp); - goto unlock; + mutex_unlock(&psr->lock); } +} - if (psr->enabled) - intel_psr_disable_locked(intel_dp); +void intel_psr_post_plane_update(const struct intel_atomic_state *state) +{ + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct intel_crtc_state *crtc_state; + struct intel_crtc *crtc; + int i; - if (enable) - intel_psr_enable_locked(intel_dp, crtc_state, conn_state); + if (!HAS_PSR(dev_priv)) + return; -unlock: - mutex_unlock(&intel_dp->psr.lock); + for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) + _intel_psr_post_plane_update(state, crtc_state); } /** @@ -2001,20 +2086,16 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv, /* * When we will be completely rely on PSR2 S/W tracking in future, * intel_psr_flush() will invalidate and flush the PSR for ORIGIN_FLIP - * event also therefore tgl_dc3co_flush() require to be changed + * event also therefore tgl_dc3co_flush_locked() require to be changed * accordingly in future. */ static void -tgl_dc3co_flush(struct intel_dp *intel_dp, unsigned int frontbuffer_bits, - enum fb_op_origin origin) +tgl_dc3co_flush_locked(struct intel_dp *intel_dp, unsigned int frontbuffer_bits, + enum fb_op_origin origin) { - mutex_lock(&intel_dp->psr.lock); - - if (!intel_dp->psr.dc3co_exitline) - goto unlock; - - if (!intel_dp->psr.psr2_enabled || !intel_dp->psr.active) - goto unlock; + if (!intel_dp->psr.dc3co_exitline || !intel_dp->psr.psr2_enabled || + !intel_dp->psr.active) + return; /* * At every frontbuffer flush flip event modified delay of delayed work, @@ -2022,14 +2103,11 @@ tgl_dc3co_flush(struct intel_dp *intel_dp, unsigned int frontbuffer_bits, */ if (!(frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(intel_dp->psr.pipe))) - goto unlock; + return; tgl_psr2_enable_dc3co(intel_dp); mod_delayed_work(system_wq, &intel_dp->psr.dc3co_work, intel_dp->psr.dc3co_exit_delay); - -unlock: - mutex_unlock(&intel_dp->psr.lock); } /** @@ -2054,11 +2132,6 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, unsigned int pipe_frontbuffer_bits = frontbuffer_bits; struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - if (origin == ORIGIN_FLIP) { - tgl_dc3co_flush(intel_dp, frontbuffer_bits, origin); - continue; - } - mutex_lock(&intel_dp->psr.lock); if (!intel_dp->psr.enabled) { mutex_unlock(&intel_dp->psr.lock); @@ -2079,6 +2152,14 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, continue; } + if (origin == ORIGIN_FLIP || + (origin == ORIGIN_CURSOR_UPDATE && + !intel_dp->psr.psr2_sel_fetch_enabled)) { + tgl_dc3co_flush_locked(intel_dp, frontbuffer_bits, origin); + mutex_unlock(&intel_dp->psr.lock); + continue; + } + /* By definition flush = invalidate + flush */ if (pipe_frontbuffer_bits) psr_force_hw_tracking_exit(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index 641521b101c8..facffbacd357 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -20,14 +20,10 @@ struct intel_plane; struct intel_encoder; void intel_psr_init_dpcd(struct intel_dp *intel_dp); -void intel_psr_enable(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state); +void intel_psr_pre_plane_update(const struct intel_atomic_state *state); +void intel_psr_post_plane_update(const struct intel_atomic_state *state); void intel_psr_disable(struct intel_dp *intel_dp, const struct intel_crtc_state *old_crtc_state); -void intel_psr_update(struct intel_dp *intel_dp, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state); int intel_psr_debug_set(struct intel_dp *intel_dp, u64 value); void intel_psr_invalidate(struct drm_i915_private *dev_priv, unsigned frontbuffer_bits, @@ -37,7 +33,8 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, enum fb_op_origin origin); void intel_psr_init(struct intel_dp *intel_dp); void intel_psr_compute_config(struct intel_dp *intel_dp, - struct intel_crtc_state *crtc_state); + struct intel_crtc_state *crtc_state, + struct drm_connector_state *conn_state); void intel_psr_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config); void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir); @@ -51,6 +48,8 @@ void intel_psr2_program_plane_sel_fetch(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state, int color_plane); +void intel_psr2_disable_plane_sel_fetch(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); void intel_psr_pause(struct intel_dp *intel_dp); void intel_psr_resume(struct intel_dp *intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 6cb27599ea03..2dc6c3742ba2 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1335,6 +1335,13 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder, adjusted_mode); pipe_config->sdvo_tv_clock = true; } else if (IS_LVDS(intel_sdvo_connector)) { + int ret; + + ret = intel_panel_compute_config(&intel_sdvo_connector->base, + adjusted_mode); + if (ret) + return ret; + if (!intel_sdvo_set_output_timings_from_mode(intel_sdvo, intel_sdvo_connector->base.panel.fixed_mode)) return -EINVAL; @@ -1873,7 +1880,6 @@ intel_sdvo_mode_valid(struct drm_connector *connector, if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; - if (clock > max_dotclk) return MODE_CLOCK_HIGH; @@ -1890,14 +1896,11 @@ intel_sdvo_mode_valid(struct drm_connector *connector, return MODE_CLOCK_HIGH; if (IS_LVDS(intel_sdvo_connector)) { - const struct drm_display_mode *fixed_mode = - intel_sdvo_connector->base.panel.fixed_mode; + enum drm_mode_status status; - if (mode->hdisplay > fixed_mode->hdisplay) - return MODE_PANEL; - - if (mode->vdisplay > fixed_mode->vdisplay) - return MODE_PANEL; + status = intel_panel_mode_valid(&intel_sdvo_connector->base, mode); + if (status != MODE_OK) + return status; } return MODE_OK; diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index 2405f70d82de..5e20f340730f 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -5,6 +5,7 @@ #include +#include "intel_ddi.h" #include "intel_ddi_buf_trans.h" #include "intel_de.h" #include "intel_display_types.h" @@ -51,27 +52,25 @@ void intel_snps_phy_update_psr_power_state(struct drm_i915_private *dev_priv, SNPS_PHY_TX_REQ_LN_DIS_PWR_STATE_PSR, val); } -void intel_snps_phy_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level) +void intel_snps_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - const struct intel_ddi_buf_trans *ddi_translations; + const struct intel_ddi_buf_trans *trans; enum phy phy = intel_port_to_phy(dev_priv, encoder->port); + int level = intel_ddi_level(encoder, crtc_state, 0); int n_entries, ln; - ddi_translations = encoder->get_buf_trans(encoder, crtc_state, &n_entries); - if (drm_WARN_ON_ONCE(&dev_priv->drm, !ddi_translations)) + trans = encoder->get_buf_trans(encoder, crtc_state, &n_entries); + if (drm_WARN_ON_ONCE(&dev_priv->drm, !trans)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, level < 0 || level >= n_entries)) - level = n_entries - 1; for (ln = 0; ln < 4; ln++) { u32 val = 0; - val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, ddi_translations->entries[level].snps.snps_vswing); - val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_PRE, ddi_translations->entries[level].snps.snps_pre_cursor); - val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, ddi_translations->entries[level].snps.snps_post_cursor); + val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_MAIN, trans->entries[level].snps.vswing); + val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_PRE, trans->entries[level].snps.pre_cursor); + val |= REG_FIELD_PREP(SNPS_PHY_TX_EQ_POST, trans->entries[level].snps.post_cursor); intel_de_write(dev_priv, SNPS_PHY_TX_EQ(ln, phy), val); } diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.h b/drivers/gpu/drm/i915/display/intel_snps_phy.h index a68547a6fee5..11dcd6deb070 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.h +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.h @@ -29,8 +29,7 @@ int intel_mpllb_calc_port_clock(struct intel_encoder *encoder, const struct intel_mpllb_state *pll_state); int intel_snps_phy_check_hdmi_link_rate(int clock); -void intel_snps_phy_ddi_vswing_sequence(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - int level); +void intel_snps_phy_set_signal_levels(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); #endif /* __INTEL_SNPS_PHY_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 3ffece568ed9..40faa18947c9 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -12,44 +12,81 @@ static const char *tc_port_mode_name(enum tc_port_mode mode) { static const char * const names[] = { + [TC_PORT_DISCONNECTED] = "disconnected", [TC_PORT_TBT_ALT] = "tbt-alt", [TC_PORT_DP_ALT] = "dp-alt", [TC_PORT_LEGACY] = "legacy", }; if (WARN_ON(mode >= ARRAY_SIZE(names))) - mode = TC_PORT_TBT_ALT; + mode = TC_PORT_DISCONNECTED; return names[mode]; } -static enum intel_display_power_domain -tc_cold_get_power_domain(struct intel_digital_port *dig_port) +static bool intel_tc_port_in_mode(struct intel_digital_port *dig_port, + enum tc_port_mode mode) { - if (intel_tc_cold_requires_aux_pw(dig_port)) - return intel_legacy_aux_to_power_domain(dig_port->aux_ch); - else + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + enum phy phy = intel_port_to_phy(i915, dig_port->base.port); + + return intel_phy_is_tc(i915, phy) && dig_port->tc_mode == mode; +} + +bool intel_tc_port_in_tbt_alt_mode(struct intel_digital_port *dig_port) +{ + return intel_tc_port_in_mode(dig_port, TC_PORT_TBT_ALT); +} + +bool intel_tc_port_in_dp_alt_mode(struct intel_digital_port *dig_port) +{ + return intel_tc_port_in_mode(dig_port, TC_PORT_DP_ALT); +} + +bool intel_tc_port_in_legacy_mode(struct intel_digital_port *dig_port) +{ + return intel_tc_port_in_mode(dig_port, TC_PORT_LEGACY); +} + +bool intel_tc_cold_requires_aux_pw(struct intel_digital_port *dig_port) +{ + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + + return (DISPLAY_VER(i915) == 11 && dig_port->tc_legacy_port) || + IS_ALDERLAKE_P(i915); +} + +static enum intel_display_power_domain +tc_cold_get_power_domain(struct intel_digital_port *dig_port, enum tc_port_mode mode) +{ + if (mode == TC_PORT_TBT_ALT || !intel_tc_cold_requires_aux_pw(dig_port)) return POWER_DOMAIN_TC_COLD_OFF; + + return intel_legacy_aux_to_power_domain(dig_port->aux_ch); } static intel_wakeref_t -tc_cold_block(struct intel_digital_port *dig_port) +tc_cold_block_in_mode(struct intel_digital_port *dig_port, enum tc_port_mode mode, + enum intel_display_power_domain *domain) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - enum intel_display_power_domain domain; - if (DISPLAY_VER(i915) == 11 && !dig_port->tc_legacy_port) - return 0; + *domain = tc_cold_get_power_domain(dig_port, mode); - domain = tc_cold_get_power_domain(dig_port); - return intel_display_power_get(i915, domain); + return intel_display_power_get(i915, *domain); +} + +static intel_wakeref_t +tc_cold_block(struct intel_digital_port *dig_port, enum intel_display_power_domain *domain) +{ + return tc_cold_block_in_mode(dig_port, dig_port->tc_mode, domain); } static void -tc_cold_unblock(struct intel_digital_port *dig_port, intel_wakeref_t wakeref) +tc_cold_unblock(struct intel_digital_port *dig_port, enum intel_display_power_domain domain, + intel_wakeref_t wakeref) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - enum intel_display_power_domain domain; /* * wakeref == -1, means some error happened saving save_depot_stack but @@ -59,8 +96,7 @@ tc_cold_unblock(struct intel_digital_port *dig_port, intel_wakeref_t wakeref) if (wakeref == 0) return; - domain = tc_cold_get_power_domain(dig_port); - intel_display_power_put_async(i915, domain, wakeref); + intel_display_power_put(i915, domain, wakeref); } static void @@ -69,11 +105,9 @@ assert_tc_cold_blocked(struct intel_digital_port *dig_port) struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); bool enabled; - if (DISPLAY_VER(i915) == 11 && !dig_port->tc_legacy_port) - return; - enabled = intel_display_power_is_enabled(i915, - tc_cold_get_power_domain(dig_port)); + tc_cold_get_power_domain(dig_port, + dig_port->tc_mode)); drm_WARN_ON(&i915->drm, !enabled); } @@ -244,6 +278,11 @@ static u32 adl_tc_port_live_status_mask(struct intel_digital_port *dig_port) struct intel_uncore *uncore = &i915->uncore; u32 val, mask = 0; + /* + * On ADL-P HW/FW will wake from TCCOLD to complete the read access of + * registers in IOM. Note that this doesn't apply to PHY and FIA + * registers. + */ val = intel_uncore_read(uncore, TCSS_DDI_STATUS(tc_port)); if (val & TCSS_DDI_STATUS_HPD_LIVE_STATUS_ALT) mask |= BIT(TC_PORT_DP_ALT); @@ -270,6 +309,14 @@ static u32 tc_port_live_status_mask(struct intel_digital_port *dig_port) return icl_tc_port_live_status_mask(dig_port); } +/* + * Return the PHY status complete flag indicating that display can acquire the + * PHY ownership. The IOM firmware sets this flag when a DP-alt or legacy sink + * is connected and it's ready to switch the ownership to display. The flag + * will be left cleared when a TBT-alt sink is connected, where the PHY is + * owned by the TBT subsystem and so switching the ownership to display is not + * required. + */ static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); @@ -288,6 +335,13 @@ static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port) return val & DP_PHY_MODE_STATUS_COMPLETED(dig_port->tc_phy_fia_idx); } +/* + * Return the PHY status complete flag indicating that display can acquire the + * PHY ownership. The IOM firmware sets this flag when it's ready to switch + * the ownership to display, regardless of what sink is connected (TBT-alt, + * DP-alt, legacy or nothing). For TBT-alt sinks the PHY is owned by the TBT + * subsystem and so switching the ownership to display is not required. + */ static bool adl_tc_phy_status_complete(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); @@ -339,11 +393,6 @@ static bool icl_tc_phy_take_ownership(struct intel_digital_port *dig_port, intel_uncore_write(uncore, PORT_TX_DFLEXDPCSSS(dig_port->tc_phy_fia), val); - if (!take && wait_for(!tc_phy_status_complete(dig_port), 10)) - drm_dbg_kms(&i915->drm, - "Port %s: PHY complete clear timed out\n", - dig_port->tc_port_name); - return true; } @@ -429,6 +478,7 @@ static void icl_tc_phy_connect(struct intel_digital_port *dig_port, int required_lanes) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + u32 live_status_mask; int max_lanes; if (!tc_phy_status_complete(dig_port)) { @@ -437,6 +487,13 @@ static void icl_tc_phy_connect(struct intel_digital_port *dig_port, goto out_set_tbt_alt_mode; } + live_status_mask = tc_port_live_status_mask(dig_port); + if (!(live_status_mask & (BIT(TC_PORT_DP_ALT) | BIT(TC_PORT_LEGACY)))) { + drm_dbg_kms(&i915->drm, "Port %s: PHY ownership not required (live status %02x)\n", + dig_port->tc_port_name, live_status_mask); + goto out_set_tbt_alt_mode; + } + if (!tc_phy_take_ownership(dig_port, true) && !drm_WARN_ON(&i915->drm, dig_port->tc_legacy_port)) goto out_set_tbt_alt_mode; @@ -485,14 +542,13 @@ static void icl_tc_phy_disconnect(struct intel_digital_port *dig_port) { switch (dig_port->tc_mode) { case TC_PORT_LEGACY: - /* Nothing to do, we never disconnect from legacy mode */ - break; case TC_PORT_DP_ALT: tc_phy_take_ownership(dig_port, false); - dig_port->tc_mode = TC_PORT_TBT_ALT; - break; + fallthrough; case TC_PORT_TBT_ALT: - /* Nothing to do, we stay in TBT-alt mode */ + dig_port->tc_mode = TC_PORT_DISCONNECTED; + fallthrough; + case TC_PORT_DISCONNECTED: break; default: MISSING_CASE(dig_port->tc_mode); @@ -509,6 +565,10 @@ static bool icl_tc_phy_is_connected(struct intel_digital_port *dig_port) return dig_port->tc_mode == TC_PORT_TBT_ALT; } + /* On ADL-P the PHY complete flag is set in TBT mode as well. */ + if (IS_ALDERLAKE_P(i915) && dig_port->tc_mode == TC_PORT_TBT_ALT) + return true; + if (!tc_phy_is_owned(dig_port)) { drm_dbg_kms(&i915->drm, "Port %s: PHY not owned\n", dig_port->tc_port_name); @@ -550,9 +610,7 @@ intel_tc_port_get_target_mode(struct intel_digital_port *dig_port) if (live_status_mask) return fls(live_status_mask) - 1; - return tc_phy_status_complete(dig_port) && - dig_port->tc_legacy_port ? TC_PORT_LEGACY : - TC_PORT_TBT_ALT; + return TC_PORT_TBT_ALT; } static void intel_tc_port_reset_mode(struct intel_digital_port *dig_port, @@ -581,6 +639,43 @@ static void intel_tc_port_reset_mode(struct intel_digital_port *dig_port, tc_port_mode_name(dig_port->tc_mode)); } +static bool intel_tc_port_needs_reset(struct intel_digital_port *dig_port) +{ + return intel_tc_port_get_target_mode(dig_port) != dig_port->tc_mode; +} + +static void intel_tc_port_update_mode(struct intel_digital_port *dig_port, + int required_lanes, bool force_disconnect) +{ + enum intel_display_power_domain domain; + intel_wakeref_t wref; + bool needs_reset = force_disconnect; + + if (!needs_reset) { + /* Get power domain required to check the hotplug live status. */ + wref = tc_cold_block(dig_port, &domain); + needs_reset = intel_tc_port_needs_reset(dig_port); + tc_cold_unblock(dig_port, domain, wref); + } + + if (!needs_reset) + return; + + /* Get power domain required for resetting the mode. */ + wref = tc_cold_block_in_mode(dig_port, TC_PORT_DISCONNECTED, &domain); + + intel_tc_port_reset_mode(dig_port, required_lanes, force_disconnect); + + /* Get power domain matching the new mode after reset. */ + tc_cold_unblock(dig_port, dig_port->tc_lock_power_domain, + fetch_and_zero(&dig_port->tc_lock_wakeref)); + if (dig_port->tc_mode != TC_PORT_DISCONNECTED) + dig_port->tc_lock_wakeref = tc_cold_block(dig_port, + &dig_port->tc_lock_power_domain); + + tc_cold_unblock(dig_port, domain, wref); +} + static void intel_tc_port_link_init_refcount(struct intel_digital_port *dig_port, int refcount) @@ -595,45 +690,42 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_encoder *encoder = &dig_port->base; - intel_wakeref_t tc_cold_wref; int active_links = 0; mutex_lock(&dig_port->tc_lock); - tc_cold_wref = tc_cold_block(dig_port); - dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port); if (dig_port->dp.is_mst) active_links = intel_dp_mst_encoder_active_links(dig_port); else if (encoder->base.crtc) active_links = to_intel_crtc(encoder->base.crtc)->active; + drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED); + drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref); if (active_links) { + enum intel_display_power_domain domain; + intel_wakeref_t tc_cold_wref = tc_cold_block(dig_port, &domain); + + dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port); + if (!icl_tc_phy_is_connected(dig_port)) drm_dbg_kms(&i915->drm, "Port %s: PHY disconnected with %d active link(s)\n", dig_port->tc_port_name, active_links); intel_tc_port_link_init_refcount(dig_port, active_links); - goto out; + dig_port->tc_lock_wakeref = tc_cold_block(dig_port, + &dig_port->tc_lock_power_domain); + + tc_cold_unblock(dig_port, domain, tc_cold_wref); } - if (dig_port->tc_legacy_port) - icl_tc_phy_connect(dig_port, 1); - -out: drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n", dig_port->tc_port_name, tc_port_mode_name(dig_port->tc_mode)); - tc_cold_unblock(dig_port, tc_cold_wref); mutex_unlock(&dig_port->tc_lock); } -static bool intel_tc_port_needs_reset(struct intel_digital_port *dig_port) -{ - return intel_tc_port_get_target_mode(dig_port) != dig_port->tc_mode; -} - /* * The type-C ports are different because even when they are connected, they may * not be available/usable by the graphics driver: see the comment on @@ -648,78 +740,79 @@ bool intel_tc_port_connected(struct intel_encoder *encoder) { struct intel_digital_port *dig_port = enc_to_dig_port(encoder); bool is_connected; - intel_wakeref_t tc_cold_wref; intel_tc_port_lock(dig_port); - tc_cold_wref = tc_cold_block(dig_port); is_connected = tc_port_live_status_mask(dig_port) & BIT(dig_port->tc_mode); - tc_cold_unblock(dig_port, tc_cold_wref); intel_tc_port_unlock(dig_port); return is_connected; } static void __intel_tc_port_lock(struct intel_digital_port *dig_port, - int required_lanes, bool force_disconnect) + int required_lanes) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - intel_wakeref_t wakeref; - - wakeref = intel_display_power_get(i915, POWER_DOMAIN_DISPLAY_CORE); mutex_lock(&dig_port->tc_lock); - if (!dig_port->tc_link_refcount) { - intel_wakeref_t tc_cold_wref; + cancel_delayed_work(&dig_port->tc_disconnect_phy_work); - tc_cold_wref = tc_cold_block(dig_port); + if (!dig_port->tc_link_refcount) + intel_tc_port_update_mode(dig_port, required_lanes, + false); - if (force_disconnect || intel_tc_port_needs_reset(dig_port)) - intel_tc_port_reset_mode(dig_port, required_lanes, - force_disconnect); - - tc_cold_unblock(dig_port, tc_cold_wref); - } - - drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref); - dig_port->tc_lock_wakeref = wakeref; + drm_WARN_ON(&i915->drm, dig_port->tc_mode == TC_PORT_DISCONNECTED); + drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_TBT_ALT && + !tc_phy_is_owned(dig_port)); } void intel_tc_port_lock(struct intel_digital_port *dig_port) { - __intel_tc_port_lock(dig_port, 1, false); + __intel_tc_port_lock(dig_port, 1); +} + +/** + * intel_tc_port_disconnect_phy_work: disconnect TypeC PHY from display port + * @dig_port: digital port + * + * Disconnect the given digital port from its TypeC PHY (handing back the + * control of the PHY to the TypeC subsystem). This will happen in a delayed + * manner after each aux transactions and modeset disables. + */ +static void intel_tc_port_disconnect_phy_work(struct work_struct *work) +{ + struct intel_digital_port *dig_port = + container_of(work, struct intel_digital_port, tc_disconnect_phy_work.work); + + mutex_lock(&dig_port->tc_lock); + + if (!dig_port->tc_link_refcount) + intel_tc_port_update_mode(dig_port, 1, true); + + mutex_unlock(&dig_port->tc_lock); +} + +/** + * intel_tc_port_flush_work: flush the work disconnecting the PHY + * @dig_port: digital port + * + * Flush the delayed work disconnecting an idle PHY. + */ +void intel_tc_port_flush_work(struct intel_digital_port *dig_port) +{ + flush_delayed_work(&dig_port->tc_disconnect_phy_work); } void intel_tc_port_unlock(struct intel_digital_port *dig_port) { - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - intel_wakeref_t wakeref = fetch_and_zero(&dig_port->tc_lock_wakeref); + if (!dig_port->tc_link_refcount && dig_port->tc_mode != TC_PORT_DISCONNECTED) + queue_delayed_work(system_unbound_wq, &dig_port->tc_disconnect_phy_work, + msecs_to_jiffies(1000)); mutex_unlock(&dig_port->tc_lock); - - intel_display_power_put_async(i915, POWER_DOMAIN_DISPLAY_CORE, - wakeref); -} - -/** - * intel_tc_port_disconnect_phy: disconnect TypeC PHY from display port - * @dig_port: digital port - * - * Disconnect the given digital port from its TypeC PHY (handing back the - * control of the PHY to the TypeC subsystem). The only purpose of this - * function is to force the disconnect even with a TypeC display output still - * plugged to the TypeC connector, which is required by the TypeC firmwares - * during system suspend and shutdown. Otherwise - during the unplug event - * handling - the PHY ownership is released automatically by - * intel_tc_port_reset_mode(), when calling this function is not required. - */ -void intel_tc_port_disconnect_phy(struct intel_digital_port *dig_port) -{ - __intel_tc_port_lock(dig_port, 1, true); - intel_tc_port_unlock(dig_port); } bool intel_tc_port_ref_held(struct intel_digital_port *dig_port) @@ -731,21 +824,30 @@ bool intel_tc_port_ref_held(struct intel_digital_port *dig_port) void intel_tc_port_get_link(struct intel_digital_port *dig_port, int required_lanes) { - __intel_tc_port_lock(dig_port, required_lanes, false); + __intel_tc_port_lock(dig_port, required_lanes); dig_port->tc_link_refcount++; intel_tc_port_unlock(dig_port); } void intel_tc_port_put_link(struct intel_digital_port *dig_port) { - mutex_lock(&dig_port->tc_lock); - dig_port->tc_link_refcount--; - mutex_unlock(&dig_port->tc_lock); + intel_tc_port_lock(dig_port); + --dig_port->tc_link_refcount; + intel_tc_port_unlock(dig_port); + + /* + * Disconnecting the PHY after the PHY's PLL gets disabled may + * hang the system on ADL-P, so disconnect the PHY here synchronously. + * TODO: remove this once the root cause of the ordering requirement + * is found/fixed. + */ + intel_tc_port_flush_work(dig_port); } static bool tc_has_modular_fia(struct drm_i915_private *i915, struct intel_digital_port *dig_port) { + enum intel_display_power_domain domain; intel_wakeref_t wakeref; u32 val; @@ -753,9 +855,9 @@ tc_has_modular_fia(struct drm_i915_private *i915, struct intel_digital_port *dig return false; mutex_lock(&dig_port->tc_lock); - wakeref = tc_cold_block(dig_port); + wakeref = tc_cold_block(dig_port, &domain); val = intel_uncore_read(&i915->uncore, PORT_TX_DFLEXDPSP(FIA1)); - tc_cold_unblock(dig_port, wakeref); + tc_cold_unblock(dig_port, domain, wakeref); mutex_unlock(&dig_port->tc_lock); drm_WARN_ON(&i915->drm, val == 0xffffffff); @@ -795,15 +897,9 @@ void intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy) "%c/TC#%d", port_name(port), tc_port + 1); mutex_init(&dig_port->tc_lock); + INIT_DELAYED_WORK(&dig_port->tc_disconnect_phy_work, intel_tc_port_disconnect_phy_work); dig_port->tc_legacy_port = is_legacy; + dig_port->tc_mode = TC_PORT_DISCONNECTED; dig_port->tc_link_refcount = 0; tc_port_load_fia_params(i915, dig_port); } - -bool intel_tc_cold_requires_aux_pw(struct intel_digital_port *dig_port) -{ - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - - return (DISPLAY_VER(i915) == 11 && dig_port->tc_legacy_port) || - IS_ALDERLAKE_P(i915); -} diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h index 0c881f645e27..6b47b29f551c 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.h +++ b/drivers/gpu/drm/i915/display/intel_tc.h @@ -12,8 +12,11 @@ struct intel_digital_port; struct intel_encoder; +bool intel_tc_port_in_tbt_alt_mode(struct intel_digital_port *dig_port); +bool intel_tc_port_in_dp_alt_mode(struct intel_digital_port *dig_port); +bool intel_tc_port_in_legacy_mode(struct intel_digital_port *dig_port); + bool intel_tc_port_connected(struct intel_encoder *encoder); -void intel_tc_port_disconnect_phy(struct intel_digital_port *dig_port); u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port); u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port); @@ -24,6 +27,7 @@ void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port, void intel_tc_port_sanitize(struct intel_digital_port *dig_port); void intel_tc_port_lock(struct intel_digital_port *dig_port); void intel_tc_port_unlock(struct intel_digital_port *dig_port); +void intel_tc_port_flush_work(struct intel_digital_port *dig_port); void intel_tc_port_get_link(struct intel_digital_port *dig_port, int required_lanes); void intel_tc_port_put_link(struct intel_digital_port *dig_port); diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index d02f09f7e750..88a398df9621 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -1529,7 +1529,7 @@ static void intel_tv_pre_enable(struct intel_atomic_state *state, intel_de_write(dev_priv, TV_CLR_LEVEL, ((video_levels->black << TV_BLACK_LEVEL_SHIFT) | (video_levels->blank << TV_BLANK_LEVEL_SHIFT))); - assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder); + assert_transcoder_disabled(dev_priv, pipe_config->cpu_transcoder); /* Filter ctl must be set before TV_WIN_SIZE */ tv_filter_ctl = TV_AUTO_SCALE; diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index df3286aa6999..2275f99ce9d7 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -357,11 +357,9 @@ bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state) return false; } -static bool is_pipe_dsc(const struct intel_crtc_state *crtc_state) +static bool is_pipe_dsc(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { - const struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - const struct drm_i915_private *i915 = to_i915(crtc->base.dev); - enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + struct drm_i915_private *i915 = to_i915(crtc->base.dev); if (DISPLAY_VER(i915) >= 12) return true; @@ -547,9 +545,8 @@ int intel_dsc_compute_params(struct intel_encoder *encoder, } enum intel_display_power_domain -intel_dsc_power_domain(const struct intel_crtc_state *crtc_state) +intel_dsc_power_domain(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *i915 = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; @@ -566,7 +563,7 @@ intel_dsc_power_domain(const struct intel_crtc_state *crtc_state) */ if (DISPLAY_VER(i915) == 12 && !IS_ROCKETLAKE(i915) && pipe == PIPE_A) return POWER_DOMAIN_TRANSCODER_VDSC_PW2; - else if (is_pipe_dsc(crtc_state)) + else if (is_pipe_dsc(crtc, cpu_transcoder)) return POWER_DOMAIN_PIPE(pipe); else return POWER_DOMAIN_TRANSCODER_VDSC_PW2; @@ -577,6 +574,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum pipe pipe = crtc->pipe; u32 pps_val = 0; u32 rc_buf_thresh_dword[4]; @@ -601,7 +599,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) if (vdsc_cfg->vbr_enable) pps_val |= DSC_VBR_ENABLE; drm_info(&dev_priv->drm, "PPS0 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_0, pps_val); /* @@ -625,7 +623,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val = 0; pps_val |= DSC_BPP(vdsc_cfg->bits_per_pixel); drm_info(&dev_priv->drm, "PPS1 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_1, pps_val); /* @@ -650,7 +648,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) | DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances); drm_info(&dev_priv->drm, "PPS2 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_2, pps_val); /* @@ -675,7 +673,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_SLICE_HEIGHT(vdsc_cfg->slice_height) | DSC_SLICE_WIDTH(vdsc_cfg->slice_width); drm_info(&dev_priv->drm, "PPS3 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_3, pps_val); /* @@ -700,7 +698,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_INITIAL_XMIT_DELAY(vdsc_cfg->initial_xmit_delay) | DSC_INITIAL_DEC_DELAY(vdsc_cfg->initial_dec_delay); drm_info(&dev_priv->drm, "PPS4 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_4, pps_val); /* @@ -725,7 +723,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_SCALE_INC_INT(vdsc_cfg->scale_increment_interval) | DSC_SCALE_DEC_INT(vdsc_cfg->scale_decrement_interval); drm_info(&dev_priv->drm, "PPS5 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_5, pps_val); /* @@ -752,7 +750,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) DSC_FLATNESS_MIN_QP(vdsc_cfg->flatness_min_qp) | DSC_FLATNESS_MAX_QP(vdsc_cfg->flatness_max_qp); drm_info(&dev_priv->drm, "PPS6 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_6, pps_val); /* @@ -777,7 +775,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_SLICE_BPG_OFFSET(vdsc_cfg->slice_bpg_offset) | DSC_NFL_BPG_OFFSET(vdsc_cfg->nfl_bpg_offset); drm_info(&dev_priv->drm, "PPS7 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_7, pps_val); /* @@ -802,7 +800,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_FINAL_OFFSET(vdsc_cfg->final_offset) | DSC_INITIAL_OFFSET(vdsc_cfg->initial_offset); drm_info(&dev_priv->drm, "PPS8 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_8, pps_val); /* @@ -827,7 +825,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) pps_val |= DSC_RC_MODEL_SIZE(vdsc_cfg->rc_model_size) | DSC_RC_EDGE_FACTOR(DSC_RC_EDGE_FACTOR_CONST); drm_info(&dev_priv->drm, "PPS9 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_9, pps_val); /* @@ -854,7 +852,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) DSC_RC_TARGET_OFF_HIGH(DSC_RC_TGT_OFFSET_HI_CONST) | DSC_RC_TARGET_OFF_LOW(DSC_RC_TGT_OFFSET_LO_CONST); drm_info(&dev_priv->drm, "PPS10 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_10, pps_val); /* @@ -882,7 +880,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) DSC_SLICE_ROW_PER_FRAME(vdsc_cfg->pic_height / vdsc_cfg->slice_height); drm_info(&dev_priv->drm, "PPS16 = 0x%08x\n", pps_val); - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_PICTURE_PARAMETER_SET_16, pps_val); /* @@ -911,7 +909,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) drm_info(&dev_priv->drm, " RC_BUF_THRESH%d = 0x%08x\n", i, rc_buf_thresh_dword[i / 4]); } - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_0, rc_buf_thresh_dword[0]); intel_de_write(dev_priv, DSCA_RC_BUF_THRESH_0_UDW, @@ -968,7 +966,7 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) drm_info(&dev_priv->drm, " RC_RANGE_PARAM_%d = 0x%08x\n", i, rc_range_params_dword[i / 2]); } - if (!is_pipe_dsc(crtc_state)) { + if (!is_pipe_dsc(crtc, cpu_transcoder)) { intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_0, rc_range_params_dword[0]); intel_de_write(dev_priv, DSCA_RC_RANGE_PARAMETERS_0_UDW, @@ -1095,18 +1093,16 @@ static void intel_dsc_dp_pps_write(struct intel_encoder *encoder, sizeof(dp_dsc_pps_sdp)); } -static i915_reg_t dss_ctl1_reg(const struct intel_crtc_state *crtc_state) +static i915_reg_t dss_ctl1_reg(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { - enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - - return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL1(pipe) : DSS_CTL1; + return is_pipe_dsc(crtc, cpu_transcoder) ? + ICL_PIPE_DSS_CTL1(crtc->pipe) : DSS_CTL1; } -static i915_reg_t dss_ctl2_reg(const struct intel_crtc_state *crtc_state) +static i915_reg_t dss_ctl2_reg(struct intel_crtc *crtc, enum transcoder cpu_transcoder) { - enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - - return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL2(pipe) : DSS_CTL2; + return is_pipe_dsc(crtc, cpu_transcoder) ? + ICL_PIPE_DSS_CTL2(crtc->pipe) : DSS_CTL2; } static struct intel_crtc * @@ -1142,7 +1138,7 @@ void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state) else dss_ctl1_val |= UNCOMPRESSED_JOINER_MASTER; - intel_de_write(dev_priv, dss_ctl1_reg(crtc_state), dss_ctl1_val); + intel_de_write(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), dss_ctl1_val); } } @@ -1176,8 +1172,8 @@ void intel_dsc_enable(struct intel_encoder *encoder, if (!crtc_state->bigjoiner_slave) dss_ctl1_val |= MASTER_BIG_JOINER_ENABLE; } - intel_de_write(dev_priv, dss_ctl1_reg(crtc_state), dss_ctl1_val); - intel_de_write(dev_priv, dss_ctl2_reg(crtc_state), dss_ctl2_val); + intel_de_write(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder), dss_ctl1_val); + intel_de_write(dev_priv, dss_ctl2_reg(crtc, crtc_state->cpu_transcoder), dss_ctl2_val); } void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state) @@ -1188,8 +1184,8 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state) /* Disable only if either of them is enabled */ if (old_crtc_state->dsc.compression_enable || old_crtc_state->bigjoiner) { - intel_de_write(dev_priv, dss_ctl1_reg(old_crtc_state), 0); - intel_de_write(dev_priv, dss_ctl2_reg(old_crtc_state), 0); + intel_de_write(dev_priv, dss_ctl1_reg(crtc, old_crtc_state->cpu_transcoder), 0); + intel_de_write(dev_priv, dss_ctl2_reg(crtc, old_crtc_state->cpu_transcoder), 0); } } @@ -1199,7 +1195,7 @@ void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state) struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); u32 dss_ctl1; - dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg(crtc_state)); + dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg(crtc, crtc_state->cpu_transcoder)); if (dss_ctl1 & UNCOMPRESSED_JOINER_MASTER) { crtc_state->bigjoiner = true; crtc_state->bigjoiner_linked_crtc = intel_dsc_get_bigjoiner_secondary(crtc); @@ -1214,9 +1210,10 @@ void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state) void intel_dsc_get_config(struct intel_crtc_state *crtc_state) { - struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config; + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum pipe pipe = crtc->pipe; enum intel_display_power_domain power_domain; intel_wakeref_t wakeref; @@ -1225,14 +1222,14 @@ void intel_dsc_get_config(struct intel_crtc_state *crtc_state) if (!intel_dsc_source_support(crtc_state)) return; - power_domain = intel_dsc_power_domain(crtc_state); + power_domain = intel_dsc_power_domain(crtc, cpu_transcoder); wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain); if (!wakeref) return; - dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg(crtc_state)); - dss_ctl2 = intel_de_read(dev_priv, dss_ctl2_reg(crtc_state)); + dss_ctl1 = intel_de_read(dev_priv, dss_ctl1_reg(crtc, cpu_transcoder)); + dss_ctl2 = intel_de_read(dev_priv, dss_ctl2_reg(crtc, cpu_transcoder)); crtc_state->dsc.compression_enable = dss_ctl2 & LEFT_BRANCH_VDSC_ENABLE; if (!crtc_state->dsc.compression_enable) @@ -1256,7 +1253,7 @@ void intel_dsc_get_config(struct intel_crtc_state *crtc_state) /* FIXME: add more state readout as needed */ /* PPS1 */ - if (!is_pipe_dsc(crtc_state)) + if (!is_pipe_dsc(crtc, cpu_transcoder)) val = intel_de_read(dev_priv, DSCA_PICTURE_PARAMETER_SET_1); else val = intel_de_read(dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h index dfb1fd38deb4..0c5d80a572da 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.h +++ b/drivers/gpu/drm/i915/display/intel_vdsc.h @@ -8,8 +8,10 @@ #include -struct intel_encoder; +enum transcoder; +struct intel_crtc; struct intel_crtc_state; +struct intel_encoder; bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state); void intel_uncompressed_joiner_enable(const struct intel_crtc_state *crtc_state); @@ -21,7 +23,7 @@ int intel_dsc_compute_params(struct intel_encoder *encoder, void intel_uncompressed_joiner_get_config(struct intel_crtc_state *crtc_state); void intel_dsc_get_config(struct intel_crtc_state *crtc_state); enum intel_display_power_domain -intel_dsc_power_domain(const struct intel_crtc_state *crtc_state); +intel_dsc_power_domain(struct intel_crtc *crtc, enum transcoder cpu_transcoder); struct intel_crtc *intel_dsc_get_bigjoiner_secondary(const struct intel_crtc *primary_crtc); #endif /* __INTEL_VDSC_H__ */ diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 724e7b04f3b6..a0e53a3b267a 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -18,6 +18,7 @@ #include "intel_sprite.h" #include "skl_scaler.h" #include "skl_universal_plane.h" +#include "pxp/intel_pxp.h" static const u32 skl_plane_formats[] = { DRM_FORMAT_C8, @@ -656,6 +657,7 @@ skl_disable_plane(struct intel_plane *plane, skl_write_plane_wm(plane, crtc_state); + intel_psr2_disable_plane_sel_fetch(plane, crtc_state); intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), 0); intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), 0); @@ -993,6 +995,11 @@ static u32 skl_surf_address(const struct intel_plane_state *plane_state, u32 offset = plane_state->view.color_plane[color_plane].offset; if (intel_fb_uses_dpt(fb)) { + /* + * The DPT object contains only one vma, so the VMA's offset + * within the DPT is always 0. + */ + WARN_ON(plane_state->dpt_vma->node.start); WARN_ON(offset & 0x1fffff); return offset >> 9; } else { @@ -1001,6 +1008,33 @@ static u32 skl_surf_address(const struct intel_plane_state *plane_state, } } +static void intel_load_plane_csc_black(struct intel_plane *intel_plane) +{ + struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev); + enum pipe pipe = intel_plane->pipe; + enum plane_id plane = intel_plane->id; + u16 postoff = 0; + + drm_dbg_kms(&dev_priv->drm, "plane color CTM to black %s:%d\n", + intel_plane->base.name, plane); + intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 0), 0); + intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 1), 0); + + intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 2), 0); + intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 3), 0); + + intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 4), 0); + intel_de_write_fw(dev_priv, PLANE_CSC_COEFF(pipe, plane, 5), 0); + + intel_de_write_fw(dev_priv, PLANE_CSC_PREOFF(pipe, plane, 0), 0); + intel_de_write_fw(dev_priv, PLANE_CSC_PREOFF(pipe, plane, 1), 0); + intel_de_write_fw(dev_priv, PLANE_CSC_PREOFF(pipe, plane, 2), 0); + + intel_de_write_fw(dev_priv, PLANE_CSC_POSTOFF(pipe, plane, 0), postoff); + intel_de_write_fw(dev_priv, PLANE_CSC_POSTOFF(pipe, plane, 1), postoff); + intel_de_write_fw(dev_priv, PLANE_CSC_POSTOFF(pipe, plane, 2), postoff); +} + static void skl_program_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, @@ -1024,7 +1058,7 @@ skl_program_plane(struct intel_plane *plane, u8 alpha = plane_state->hw.alpha >> 8; u32 plane_color_ctl = 0, aux_dist = 0; unsigned long irqflags; - u32 keymsk, keymax; + u32 keymsk, keymax, plane_surf; u32 plane_ctl = plane_state->ctl; plane_ctl |= skl_plane_ctl_crtc(crtc_state); @@ -1096,8 +1130,7 @@ skl_program_plane(struct intel_plane *plane, (plane_state->view.color_plane[1].y << 16) | plane_state->view.color_plane[1].x); - if (!drm_atomic_crtc_needs_modeset(&crtc_state->uapi)) - intel_psr2_program_plane_sel_fetch(plane, crtc_state, plane_state, color_plane); + intel_psr2_program_plane_sel_fetch(plane, crtc_state, plane_state, color_plane); /* * Enable the scaler before the plane so that we don't @@ -1113,8 +1146,23 @@ skl_program_plane(struct intel_plane *plane, * the control register just before the surface register. */ intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl); - intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), - intel_plane_ggtt_offset(plane_state) + surf_addr); + plane_surf = intel_plane_ggtt_offset(plane_state) + surf_addr; + plane_color_ctl = intel_de_read_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id)); + + /* + * FIXME: pxp session invalidation can hit any time even at time of commit + * or after the commit, display content will be garbage. + */ + if (plane_state->decrypt) { + plane_surf |= PLANE_SURF_DECRYPT; + } else if (plane_state->force_black) { + intel_load_plane_csc_black(plane); + plane_color_ctl |= PLANE_COLOR_PLANE_CSC_ENABLE; + } + + intel_de_write_fw(dev_priv, PLANE_COLOR_CTL(pipe, plane_id), + plane_color_ctl); + intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), plane_surf); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index b0a2b6b96799..07584695514b 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -40,8 +40,8 @@ #include "intel_dsi.h" #include "intel_fifo_underrun.h" #include "intel_panel.h" -#include "intel_sideband.h" #include "skl_scaler.h" +#include "vlv_sideband.h" /* return pixels in terms of txbyteclkhs */ static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count, @@ -271,20 +271,19 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder, struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi, base); struct intel_connector *intel_connector = intel_dsi->attached_connector; - const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode; struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; int ret; drm_dbg_kms(&dev_priv->drm, "\n"); pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; - if (fixed_mode) { - intel_panel_fixed_mode(fixed_mode, adjusted_mode); + ret = intel_panel_compute_config(intel_connector, adjusted_mode); + if (ret) + return ret; - ret = intel_panel_fitting(pipe_config, conn_state); - if (ret) - return ret; - } + ret = intel_panel_fitting(pipe_config, conn_state); + if (ret) + return ret; if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN) return -EINVAL; @@ -1631,25 +1630,21 @@ static const struct drm_connector_funcs intel_dsi_connector_funcs = { static void vlv_dsi_add_properties(struct intel_connector *connector) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); + u32 allowed_scalers; - if (connector->panel.fixed_mode) { - u32 allowed_scalers; + allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN); + if (!HAS_GMCH(dev_priv)) + allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); - allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN); - if (!HAS_GMCH(dev_priv)) - allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER); + drm_connector_attach_scaling_mode_property(&connector->base, + allowed_scalers); - drm_connector_attach_scaling_mode_property(&connector->base, - allowed_scalers); + connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT; - connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT; - - drm_connector_set_panel_orientation_with_quirk( - &connector->base, - intel_dsi_get_panel_orientation(connector), - connector->panel.fixed_mode->hdisplay, - connector->panel.fixed_mode->vdisplay); - } + drm_connector_set_panel_orientation_with_quirk(&connector->base, + intel_dsi_get_panel_orientation(connector), + connector->panel.fixed_mode->hdisplay, + connector->panel.fixed_mode->vdisplay); } #define NS_KHZ_RATIO 1000000 diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c index 90185b219447..5413b52ab6ba 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c @@ -31,7 +31,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_dsi.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" static const u16 lfsr_converts[] = { 426, 469, 234, 373, 442, 221, 110, 311, 411, /* 62 - 70 */ @@ -568,3 +568,26 @@ void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port) } intel_de_write(dev_priv, MIPI_EOT_DISABLE(port), CLOCKSTOP); } + +static void assert_dsi_pll(struct drm_i915_private *i915, bool state) +{ + bool cur_state; + + vlv_cck_get(i915); + cur_state = vlv_cck_read(i915, CCK_REG_DSI_PLL_CONTROL) & DSI_PLL_VCO_EN; + vlv_cck_put(i915); + + I915_STATE_WARN(cur_state != state, + "DSI PLL state assertion failure (expected %s, current %s)\n", + onoff(state), onoff(cur_state)); +} + +void assert_dsi_pll_enabled(struct drm_i915_private *i915) +{ + assert_dsi_pll(i915, true); +} + +void assert_dsi_pll_disabled(struct drm_i915_private *i915) +{ + assert_dsi_pll(i915, false); +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 6234e17259c1..7358bebef15c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -4,6 +4,8 @@ * Copyright © 2014-2016 Intel Corporation */ +#include + #include "gt/intel_engine.h" #include "i915_gem_ioctls.h" @@ -36,7 +38,7 @@ static __always_inline u32 __busy_write_id(u16 id) } static __always_inline unsigned int -__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id)) +__busy_set_if_active(struct dma_fence *fence, u32 (*flag)(u16 id)) { const struct i915_request *rq; @@ -46,29 +48,60 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id)) * to eventually flush us, but to minimise latency just ask the * hardware. * - * Note we only report on the status of native fences. + * Note we only report on the status of native fences and we currently + * have two native fences: + * + * 1. A composite fence (dma_fence_array) constructed of i915 requests + * created during a parallel submission. In this case we deconstruct the + * composite fence into individual i915 requests and check the status of + * each request. + * + * 2. A single i915 request. */ - if (!dma_fence_is_i915(fence)) - return 0; + if (dma_fence_is_array(fence)) { + struct dma_fence_array *array = to_dma_fence_array(fence); + struct dma_fence **child = array->fences; + unsigned int nchild = array->num_fences; - /* opencode to_request() in order to avoid const warnings */ - rq = container_of(fence, const struct i915_request, fence); - if (i915_request_completed(rq)) - return 0; + do { + struct dma_fence *current_fence = *child++; - /* Beware type-expansion follies! */ - BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class)); - return flag(rq->engine->uabi_class); + /* Not an i915 fence, can't be busy per above */ + if (!dma_fence_is_i915(current_fence) || + !test_bit(I915_FENCE_FLAG_COMPOSITE, + ¤t_fence->flags)) { + return 0; + } + + rq = to_request(current_fence); + if (!i915_request_completed(rq)) + return flag(rq->engine->uabi_class); + } while (--nchild); + + /* All requests in array complete, not busy */ + return 0; + } else { + if (!dma_fence_is_i915(fence)) + return 0; + + rq = to_request(fence); + if (i915_request_completed(rq)) + return 0; + + /* Beware type-expansion follies! */ + BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class)); + return flag(rq->engine->uabi_class); + } } static __always_inline unsigned int -busy_check_reader(const struct dma_fence *fence) +busy_check_reader(struct dma_fence *fence) { return __busy_set_if_active(fence, __busy_read_flag); } static __always_inline unsigned int -busy_check_writer(const struct dma_fence *fence) +busy_check_writer(struct dma_fence *fence) { if (!fence) return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 65eabca57228..fb33d0322960 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -77,6 +77,8 @@ #include "gt/intel_gpu_commands.h" #include "gt/intel_ring.h" +#include "pxp/intel_pxp.h" + #include "i915_gem_context.h" #include "i915_trace.h" #include "i915_user_extensions.h" @@ -186,10 +188,13 @@ static int validate_priority(struct drm_i915_private *i915, return 0; } -static void proto_context_close(struct i915_gem_proto_context *pc) +static void proto_context_close(struct drm_i915_private *i915, + struct i915_gem_proto_context *pc) { int i; + if (pc->pxp_wakeref) + intel_runtime_pm_put(&i915->runtime_pm, pc->pxp_wakeref); if (pc->vm) i915_vm_put(pc->vm); if (pc->user_engines) { @@ -241,6 +246,35 @@ static int proto_context_set_persistence(struct drm_i915_private *i915, return 0; } +static int proto_context_set_protected(struct drm_i915_private *i915, + struct i915_gem_proto_context *pc, + bool protected) +{ + int ret = 0; + + if (!protected) { + pc->uses_protected_content = false; + } else if (!intel_pxp_is_enabled(&i915->gt.pxp)) { + ret = -ENODEV; + } else if ((pc->user_flags & BIT(UCONTEXT_RECOVERABLE)) || + !(pc->user_flags & BIT(UCONTEXT_BANNABLE))) { + ret = -EPERM; + } else { + pc->uses_protected_content = true; + + /* + * protected context usage requires the PXP session to be up, + * which in turn requires the device to be active. + */ + pc->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); + + if (!intel_pxp_is_active(&i915->gt.pxp)) + ret = intel_pxp_start(&i915->gt.pxp); + } + + return ret; +} + static struct i915_gem_proto_context * proto_context_create(struct drm_i915_private *i915, unsigned int flags) { @@ -269,7 +303,7 @@ proto_context_create(struct drm_i915_private *i915, unsigned int flags) return pc; proto_close: - proto_context_close(pc); + proto_context_close(i915, pc); return err; } @@ -522,9 +556,147 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data) return 0; } +static int +set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, + void *data) +{ + struct i915_context_engines_parallel_submit __user *ext = + container_of_user(base, typeof(*ext), base); + const struct set_proto_ctx_engines *set = data; + struct drm_i915_private *i915 = set->i915; + u64 flags; + int err = 0, n, i, j; + u16 slot, width, num_siblings; + struct intel_engine_cs **siblings = NULL; + intel_engine_mask_t prev_mask; + + /* FIXME: This is NIY for execlists */ + if (!(intel_uc_uses_guc_submission(&i915->gt.uc))) + return -ENODEV; + + if (get_user(slot, &ext->engine_index)) + return -EFAULT; + + if (get_user(width, &ext->width)) + return -EFAULT; + + if (get_user(num_siblings, &ext->num_siblings)) + return -EFAULT; + + if (slot >= set->num_engines) { + drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n", + slot, set->num_engines); + return -EINVAL; + } + + if (set->engines[slot].type != I915_GEM_ENGINE_TYPE_INVALID) { + drm_dbg(&i915->drm, + "Invalid placement[%d], already occupied\n", slot); + return -EINVAL; + } + + if (get_user(flags, &ext->flags)) + return -EFAULT; + + if (flags) { + drm_dbg(&i915->drm, "Unknown flags 0x%02llx", flags); + return -EINVAL; + } + + for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) { + err = check_user_mbz(&ext->mbz64[n]); + if (err) + return err; + } + + if (width < 2) { + drm_dbg(&i915->drm, "Width (%d) < 2\n", width); + return -EINVAL; + } + + if (num_siblings < 1) { + drm_dbg(&i915->drm, "Number siblings (%d) < 1\n", + num_siblings); + return -EINVAL; + } + + siblings = kmalloc_array(num_siblings * width, + sizeof(*siblings), + GFP_KERNEL); + if (!siblings) + return -ENOMEM; + + /* Create contexts / engines */ + for (i = 0; i < width; ++i) { + intel_engine_mask_t current_mask = 0; + struct i915_engine_class_instance prev_engine; + + for (j = 0; j < num_siblings; ++j) { + struct i915_engine_class_instance ci; + + n = i * num_siblings + j; + if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) { + err = -EFAULT; + goto out_err; + } + + siblings[n] = + intel_engine_lookup_user(i915, ci.engine_class, + ci.engine_instance); + if (!siblings[n]) { + drm_dbg(&i915->drm, + "Invalid sibling[%d]: { class:%d, inst:%d }\n", + n, ci.engine_class, ci.engine_instance); + err = -EINVAL; + goto out_err; + } + + if (n) { + if (prev_engine.engine_class != + ci.engine_class) { + drm_dbg(&i915->drm, + "Mismatched class %d, %d\n", + prev_engine.engine_class, + ci.engine_class); + err = -EINVAL; + goto out_err; + } + } + + prev_engine = ci; + current_mask |= siblings[n]->logical_mask; + } + + if (i > 0) { + if (current_mask != prev_mask << 1) { + drm_dbg(&i915->drm, + "Non contiguous logical mask 0x%x, 0x%x\n", + prev_mask, current_mask); + err = -EINVAL; + goto out_err; + } + } + prev_mask = current_mask; + } + + set->engines[slot].type = I915_GEM_ENGINE_TYPE_PARALLEL; + set->engines[slot].num_siblings = num_siblings; + set->engines[slot].width = width; + set->engines[slot].siblings = siblings; + + return 0; + +out_err: + kfree(siblings); + + return err; +} + static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = { [I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance, [I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond, + [I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT] = + set_proto_ctx_engines_parallel_submit, }; static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv, @@ -693,6 +865,8 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, ret = -EPERM; else if (args->value) pc->user_flags |= BIT(UCONTEXT_BANNABLE); + else if (pc->uses_protected_content) + ret = -EPERM; else pc->user_flags &= ~BIT(UCONTEXT_BANNABLE); break; @@ -700,10 +874,12 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; - else if (args->value) - pc->user_flags |= BIT(UCONTEXT_RECOVERABLE); - else + else if (!args->value) pc->user_flags &= ~BIT(UCONTEXT_RECOVERABLE); + else if (pc->uses_protected_content) + ret = -EPERM; + else + pc->user_flags |= BIT(UCONTEXT_RECOVERABLE); break; case I915_CONTEXT_PARAM_PRIORITY: @@ -731,6 +907,11 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, args->value); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: + ret = proto_context_set_protected(fpriv->dev_priv, pc, + args->value); + break; + case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_RINGSIZE: @@ -751,6 +932,7 @@ static int intel_context_set_gem(struct intel_context *ce, GEM_BUG_ON(rcu_access_pointer(ce->gem_context)); RCU_INIT_POINTER(ce->gem_context, ctx); + GEM_BUG_ON(intel_context_is_pinned(ce)); ce->ring_size = SZ_16K; i915_vm_put(ce->vm); @@ -761,7 +943,7 @@ static int intel_context_set_gem(struct intel_context *ce, intel_engine_has_semaphores(ce->engine)) __set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags); - if (IS_ACTIVE(CONFIG_DRM_I915_REQUEST_TIMEOUT) && + if (CONFIG_DRM_I915_REQUEST_TIMEOUT && ctx->i915->params.request_timeout_ms) { unsigned int timeout_ms = ctx->i915->params.request_timeout_ms; @@ -775,6 +957,25 @@ static int intel_context_set_gem(struct intel_context *ce, return ret; } +static void __unpin_engines(struct i915_gem_engines *e, unsigned int count) +{ + while (count--) { + struct intel_context *ce = e->engines[count], *child; + + if (!ce || !test_bit(CONTEXT_PERMA_PIN, &ce->flags)) + continue; + + for_each_child(ce, child) + intel_context_unpin(child); + intel_context_unpin(ce); + } +} + +static void unpin_engines(struct i915_gem_engines *e) +{ + __unpin_engines(e, e->num_engines); +} + static void __free_engines(struct i915_gem_engines *e, unsigned int count) { while (count--) { @@ -890,6 +1091,40 @@ free_engines: return err; } +static int perma_pin_contexts(struct intel_context *ce) +{ + struct intel_context *child; + int i = 0, j = 0, ret; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + ret = intel_context_pin(ce); + if (unlikely(ret)) + return ret; + + for_each_child(ce, child) { + ret = intel_context_pin(child); + if (unlikely(ret)) + goto unwind; + ++i; + } + + set_bit(CONTEXT_PERMA_PIN, &ce->flags); + + return 0; + +unwind: + intel_context_unpin(ce); + for_each_child(ce, child) { + if (j++ < i) + intel_context_unpin(child); + else + break; + } + + return ret; +} + static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, unsigned int num_engines, struct i915_gem_proto_engine *pe) @@ -903,7 +1138,7 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, e->num_engines = num_engines; for (n = 0; n < num_engines; n++) { - struct intel_context *ce; + struct intel_context *ce, *child; int ret; switch (pe[n].type) { @@ -913,7 +1148,13 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, case I915_GEM_ENGINE_TYPE_BALANCED: ce = intel_engine_create_virtual(pe[n].siblings, - pe[n].num_siblings); + pe[n].num_siblings, 0); + break; + + case I915_GEM_ENGINE_TYPE_PARALLEL: + ce = intel_engine_create_parallel(pe[n].siblings, + pe[n].num_siblings, + pe[n].width); break; case I915_GEM_ENGINE_TYPE_INVALID: @@ -934,6 +1175,30 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, err = ERR_PTR(ret); goto free_engines; } + for_each_child(ce, child) { + ret = intel_context_set_gem(child, ctx, pe->sseu); + if (ret) { + err = ERR_PTR(ret); + goto free_engines; + } + } + + /* + * XXX: Must be done after calling intel_context_set_gem as that + * function changes the ring size. The ring is allocated when + * the context is pinned. If the ring size is changed after + * allocation we have a mismatch of the ring size and will cause + * the context to hang. Presumably with a bit of reordering we + * could move the perma-pin step to the backend function + * intel_engine_create_parallel. + */ + if (pe[n].type == I915_GEM_ENGINE_TYPE_PARALLEL) { + ret = perma_pin_contexts(ce); + if (ret) { + err = ERR_PTR(ret); + goto free_engines; + } + } } return e; @@ -959,6 +1224,9 @@ static void i915_gem_context_release_work(struct work_struct *work) if (vm) i915_vm_put(vm); + if (ctx->pxp_wakeref) + intel_runtime_pm_put(&ctx->i915->runtime_pm, ctx->pxp_wakeref); + mutex_destroy(&ctx->engines_mutex); mutex_destroy(&ctx->lut_mutex); @@ -1173,6 +1441,7 @@ static void context_close(struct i915_gem_context *ctx) /* Flush any concurrent set_engines() */ mutex_lock(&ctx->engines_mutex); + unpin_engines(__context_engines_static(ctx)); engines_idle_release(ctx, rcu_replace_pointer(ctx->engines, NULL, 1)); i915_gem_context_set_closed(ctx); mutex_unlock(&ctx->engines_mutex); @@ -1290,7 +1559,7 @@ i915_gem_create_context(struct drm_i915_private *i915, } else if (HAS_FULL_PPGTT(i915)) { struct i915_ppgtt *ppgtt; - ppgtt = i915_ppgtt_create(&i915->gt); + ppgtt = i915_ppgtt_create(&i915->gt, 0); if (IS_ERR(ppgtt)) { drm_dbg(&i915->drm, "PPGTT setup failed (%ld)\n", PTR_ERR(ppgtt)); @@ -1341,6 +1610,11 @@ i915_gem_create_context(struct drm_i915_private *i915, goto err_engines; } + if (pc->uses_protected_content) { + ctx->pxp_wakeref = intel_runtime_pm_get(&i915->runtime_pm); + ctx->uses_protected_content = true; + } + trace_i915_context_create(ctx); return ctx; @@ -1412,7 +1686,7 @@ int i915_gem_context_open(struct drm_i915_private *i915, } ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err; @@ -1439,7 +1713,7 @@ void i915_gem_context_close(struct drm_file *file) unsigned long idx; xa_for_each(&file_priv->proto_context_xa, idx, pc) - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); xa_destroy(&file_priv->proto_context_xa); mutex_destroy(&file_priv->proto_context_lock); @@ -1468,7 +1742,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data, if (args->flags) return -EINVAL; - ppgtt = i915_ppgtt_create(&i915->gt); + ppgtt = i915_ppgtt_create(&i915->gt, 0); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); @@ -1734,6 +2008,15 @@ static int set_priority(struct i915_gem_context *ctx, return 0; } +static int get_protected(struct i915_gem_context *ctx, + struct drm_i915_gem_context_param *args) +{ + args->size = 0; + args->value = i915_gem_context_uses_protected_content(ctx); + + return 0; +} + static int ctx_setparam(struct drm_i915_file_private *fpriv, struct i915_gem_context *ctx, struct drm_i915_gem_context_param *args) @@ -1757,6 +2040,8 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, ret = -EPERM; else if (args->value) i915_gem_context_set_bannable(ctx); + else if (i915_gem_context_uses_protected_content(ctx)) + ret = -EPERM; /* can't clear this for protected contexts */ else i915_gem_context_clear_bannable(ctx); break; @@ -1764,10 +2049,12 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; - else if (args->value) - i915_gem_context_set_recoverable(ctx); - else + else if (!args->value) i915_gem_context_clear_recoverable(ctx); + else if (i915_gem_context_uses_protected_content(ctx)) + ret = -EPERM; /* can't set this for protected contexts */ + else + i915_gem_context_set_recoverable(ctx); break; case I915_CONTEXT_PARAM_PRIORITY: @@ -1782,6 +2069,7 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv, ret = set_persistence(ctx, args); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_RINGSIZE: @@ -1860,7 +2148,7 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv, old = xa_erase(&file_priv->proto_context_xa, id); GEM_BUG_ON(old != pc); - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); /* One for the xarray and one for the caller */ return i915_gem_context_get(ctx); @@ -1946,7 +2234,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, goto err_pc; } - proto_context_close(ext_data.pc); + proto_context_close(i915, ext_data.pc); gem_context_register(ctx, ext_data.fpriv, id); } else { ret = proto_context_register(ext_data.fpriv, ext_data.pc, &id); @@ -1960,7 +2248,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, return 0; err_pc: - proto_context_close(ext_data.pc); + proto_context_close(i915, ext_data.pc); return ret; } @@ -1991,7 +2279,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, GEM_WARN_ON(ctx && pc); if (pc) - proto_context_close(pc); + proto_context_close(file_priv->dev_priv, pc); if (ctx) context_close(ctx); @@ -2109,6 +2397,10 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, args->value = i915_gem_context_is_persistent(ctx); break; + case I915_CONTEXT_PARAM_PROTECTED_CONTENT: + ret = get_protected(ctx, args); + break; + case I915_CONTEXT_PARAM_NO_ZEROMAP: case I915_CONTEXT_PARAM_BAN_PERIOD: case I915_CONTEXT_PARAM_ENGINES: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h index d3279086a5e7..babfecb17ad1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h @@ -108,6 +108,12 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx) clear_bit(CONTEXT_USER_ENGINES, &ctx->flags); } +static inline bool +i915_gem_context_uses_protected_content(const struct i915_gem_context *ctx) +{ + return ctx->uses_protected_content; +} + /* i915_gem_context.c */ void i915_gem_init__contexts(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index c4617e4d9fa9..282cdb8a5c5a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -78,13 +78,16 @@ enum i915_gem_engine_type { /** @I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set */ I915_GEM_ENGINE_TYPE_BALANCED, + + /** @I915_GEM_ENGINE_TYPE_PARALLEL: A parallel engine set */ + I915_GEM_ENGINE_TYPE_PARALLEL, }; /** * struct i915_gem_proto_engine - prototype engine * * This struct describes an engine that a context may contain. Engines - * have three types: + * have four types: * * - I915_GEM_ENGINE_TYPE_INVALID: Invalid engines can be created but they * show up as a NULL in i915_gem_engines::engines[i] and any attempt to @@ -97,6 +100,10 @@ enum i915_gem_engine_type { * * - I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set, described * i915_gem_proto_engine::num_siblings and i915_gem_proto_engine::siblings. + * + * - I915_GEM_ENGINE_TYPE_PARALLEL: A parallel submission engine set, described + * i915_gem_proto_engine::width, i915_gem_proto_engine::num_siblings, and + * i915_gem_proto_engine::siblings. */ struct i915_gem_proto_engine { /** @type: Type of this engine */ @@ -105,10 +112,13 @@ struct i915_gem_proto_engine { /** @engine: Engine, for physical */ struct intel_engine_cs *engine; - /** @num_siblings: Number of balanced siblings */ + /** @num_siblings: Number of balanced or parallel siblings */ unsigned int num_siblings; - /** @siblings: Balanced siblings */ + /** @width: Width of each sibling */ + unsigned int width; + + /** @siblings: Balanced siblings or num_siblings * width for parallel */ struct intel_engine_cs **siblings; /** @sseu: Client-set SSEU parameters */ @@ -198,6 +208,12 @@ struct i915_gem_proto_context { /** @single_timeline: See See &i915_gem_context.syncobj */ bool single_timeline; + + /** @uses_protected_content: See &i915_gem_context.uses_protected_content */ + bool uses_protected_content; + + /** @pxp_wakeref: See &i915_gem_context.pxp_wakeref */ + intel_wakeref_t pxp_wakeref; }; /** @@ -321,6 +337,28 @@ struct i915_gem_context { #define CONTEXT_CLOSED 0 #define CONTEXT_USER_ENGINES 1 + /** + * @uses_protected_content: context uses PXP-encrypted objects. + * + * This flag can only be set at ctx creation time and it's immutable for + * the lifetime of the context. See I915_CONTEXT_PARAM_PROTECTED_CONTENT + * in uapi/drm/i915_drm.h for more info on setting restrictions and + * expected behaviour of marked contexts. + */ + bool uses_protected_content; + + /** + * @pxp_wakeref: wakeref to keep the device awake when PXP is in use + * + * PXP sessions are invalidated when the device is suspended, which in + * turns invalidates all contexts and objects using it. To keep the + * flow simple, we keep the device awake when contexts using PXP objects + * are in use. It is expected that the userspace application only uses + * PXP when the display is on, so taking a wakeref here shouldn't worsen + * our power metrics. + */ + intel_wakeref_t pxp_wakeref; + /** @mutex: guards everything that isn't engines or handles_vma */ struct mutex mutex; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 1d341b8c47c0..8955d6abcef1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -6,6 +6,7 @@ #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" +#include "pxp/intel_pxp.h" #include "i915_drv.h" #include "i915_trace.h" @@ -82,21 +83,11 @@ static int i915_gem_publish(struct drm_i915_gem_object *obj, return 0; } -/** - * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT - * @i915: i915 private - * @size: size of the buffer, in bytes - * @placements: possible placement regions, in priority order - * @n_placements: number of possible placement regions - * - * This function is exposed primarily for selftests and does very little - * error checking. It is assumed that the set of placement regions has - * already been verified to be valid. - */ -struct drm_i915_gem_object * -__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, - struct intel_memory_region **placements, - unsigned int n_placements) +static struct drm_i915_gem_object * +__i915_gem_object_create_user_ext(struct drm_i915_private *i915, u64 size, + struct intel_memory_region **placements, + unsigned int n_placements, + unsigned int ext_flags) { struct intel_memory_region *mr = placements[0]; struct drm_i915_gem_object *obj; @@ -135,6 +126,9 @@ __i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, GEM_BUG_ON(size != obj->base.size); + /* Add any flag set by create_ext options */ + obj->flags |= ext_flags; + trace_i915_gem_object_create(obj); return obj; @@ -145,6 +139,26 @@ object_free: return ERR_PTR(ret); } +/** + * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT + * @i915: i915 private + * @size: size of the buffer, in bytes + * @placements: possible placement regions, in priority order + * @n_placements: number of possible placement regions + * + * This function is exposed primarily for selftests and does very little + * error checking. It is assumed that the set of placement regions has + * already been verified to be valid. + */ +struct drm_i915_gem_object * +__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size, + struct intel_memory_region **placements, + unsigned int n_placements) +{ + return __i915_gem_object_create_user_ext(i915, size, placements, + n_placements, 0); +} + int i915_gem_dumb_create(struct drm_file *file, struct drm_device *dev, @@ -224,6 +238,7 @@ struct create_ext { struct drm_i915_private *i915; struct intel_memory_region *placements[INTEL_REGION_UNKNOWN]; unsigned int n_placements; + unsigned long flags; }; static void repr_placements(char *buf, size_t size, @@ -353,8 +368,28 @@ static int ext_set_placements(struct i915_user_extension __user *base, return set_placements(&ext, data); } +static int ext_set_protected(struct i915_user_extension __user *base, void *data) +{ + struct drm_i915_gem_create_ext_protected_content ext; + struct create_ext *ext_data = data; + + if (copy_from_user(&ext, base, sizeof(ext))) + return -EFAULT; + + if (ext.flags) + return -EINVAL; + + if (!intel_pxp_is_enabled(&ext_data->i915->gt.pxp)) + return -ENODEV; + + ext_data->flags |= I915_BO_PROTECTED; + + return 0; +} + static const i915_user_extension_fn create_extensions[] = { [I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements, + [I915_GEM_CREATE_EXT_PROTECTED_CONTENT] = ext_set_protected, }; /** @@ -389,9 +424,10 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, ext_data.n_placements = 1; } - obj = __i915_gem_object_create_user(i915, args->size, - ext_data.placements, - ext_data.n_placements); + obj = __i915_gem_object_create_user_ext(i915, args->size, + ext_data.placements, + ext_data.n_placements, + ext_data.flags); if (IS_ERR(obj)) return PTR_ERR(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index afa34111de02..1adcd8e02d29 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -232,6 +232,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags) static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *pages; unsigned int sg_page_sizes; @@ -242,8 +243,11 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) if (IS_ERR(pages)) return PTR_ERR(pages); - sg_page_sizes = i915_sg_dma_sizes(pages->sgl); + /* XXX: consider doing a vmap flush or something */ + if (!HAS_LLC(i915) || i915_gem_object_can_bypass_llc(obj)) + wbinvd_on_all_cpus(); + sg_page_sizes = i915_sg_dma_sizes(pages->sgl); __i915_gem_object_set_pages(obj, pages, sg_page_sizes); return 0; @@ -301,7 +305,8 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, } drm_gem_private_object_init(dev, &obj->base, dma_buf->size); - i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops, &lock_class, 0); + i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops, &lock_class, + I915_BO_ALLOC_USER); obj->base.import_attach = attach; obj->base.resv = dma_buf->resv; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index c2f74dba0557..4d7da07442f2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -21,6 +21,8 @@ #include "gt/intel_gt_pm.h" #include "gt/intel_ring.h" +#include "pxp/intel_pxp.h" + #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_gem_context.h" @@ -244,17 +246,25 @@ struct i915_execbuffer { struct drm_i915_gem_exec_object2 *exec; /** ioctl execobj[] */ struct eb_vma *vma; - struct intel_engine_cs *engine; /** engine to queue the request to */ + struct intel_gt *gt; /* gt for the execbuf */ struct intel_context *context; /* logical state for the request */ struct i915_gem_context *gem_context; /** caller's context */ - struct i915_request *request; /** our request to build */ - struct eb_vma *batch; /** identity of the batch obj/vma */ + /** our requests to build */ + struct i915_request *requests[MAX_ENGINE_INSTANCE + 1]; + /** identity of the batch obj/vma */ + struct eb_vma *batches[MAX_ENGINE_INSTANCE + 1]; struct i915_vma *trampoline; /** trampoline used for chaining */ + /** used for excl fence in dma_resv objects when > 1 BB submitted */ + struct dma_fence *composite_fence; + /** actual size of execobj[] as we may extend it for the cmdparser */ unsigned int buffer_count; + /* number of batches in execbuf IOCTL */ + unsigned int num_batches; + /** list of vma not yet bound during reservation phase */ struct list_head unbound; @@ -281,7 +291,8 @@ struct i915_execbuffer { u64 invalid_flags; /** Set of execobj.flags that are invalid */ - u64 batch_len; /** Length of batch within object */ + /** Length of batch within object */ + u64 batch_len[MAX_ENGINE_INSTANCE + 1]; u32 batch_start_offset; /** Location within object of batch */ u32 batch_flags; /** Flags composed for emit_bb_start() */ struct intel_gt_buffer_pool_node *batch_pool; /** pool node for batch buffer */ @@ -299,14 +310,13 @@ struct i915_execbuffer { }; static int eb_parse(struct i915_execbuffer *eb); -static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb, - bool throttle); +static int eb_pin_engine(struct i915_execbuffer *eb, bool throttle); static void eb_unpin_engine(struct i915_execbuffer *eb); static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) { - return intel_engine_requires_cmd_parser(eb->engine) || - (intel_engine_using_cmd_parser(eb->engine) && + return intel_engine_requires_cmd_parser(eb->context->engine) || + (intel_engine_using_cmd_parser(eb->context->engine) && eb->args->batch_len); } @@ -533,11 +543,21 @@ eb_validate_vma(struct i915_execbuffer *eb, return 0; } -static void +static inline bool +is_batch_buffer(struct i915_execbuffer *eb, unsigned int buffer_idx) +{ + return eb->args->flags & I915_EXEC_BATCH_FIRST ? + buffer_idx < eb->num_batches : + buffer_idx >= eb->args->buffer_count - eb->num_batches; +} + +static int eb_add_vma(struct i915_execbuffer *eb, - unsigned int i, unsigned batch_idx, + unsigned int *current_batch, + unsigned int i, struct i915_vma *vma) { + struct drm_i915_private *i915 = eb->i915; struct drm_i915_gem_exec_object2 *entry = &eb->exec[i]; struct eb_vma *ev = &eb->vma[i]; @@ -564,15 +584,43 @@ eb_add_vma(struct i915_execbuffer *eb, * Note that actual hangs have only been observed on gen7, but for * paranoia do it everywhere. */ - if (i == batch_idx) { + if (is_batch_buffer(eb, i)) { if (entry->relocation_count && !(ev->flags & EXEC_OBJECT_PINNED)) ev->flags |= __EXEC_OBJECT_NEEDS_BIAS; if (eb->reloc_cache.has_fence) ev->flags |= EXEC_OBJECT_NEEDS_FENCE; - eb->batch = ev; + eb->batches[*current_batch] = ev; + + if (unlikely(ev->flags & EXEC_OBJECT_WRITE)) { + drm_dbg(&i915->drm, + "Attempting to use self-modifying batch buffer\n"); + return -EINVAL; + } + + if (range_overflows_t(u64, + eb->batch_start_offset, + eb->args->batch_len, + ev->vma->size)) { + drm_dbg(&i915->drm, "Attempting to use out-of-bounds batch\n"); + return -EINVAL; + } + + if (eb->args->batch_len == 0) + eb->batch_len[*current_batch] = ev->vma->size - + eb->batch_start_offset; + else + eb->batch_len[*current_batch] = eb->args->batch_len; + if (unlikely(eb->batch_len[*current_batch] == 0)) { /* impossible! */ + drm_dbg(&i915->drm, "Invalid batch length\n"); + return -EINVAL; + } + + ++*current_batch; } + + return 0; } static inline int use_cpu_reloc(const struct reloc_cache *cache, @@ -716,14 +764,6 @@ static int eb_reserve(struct i915_execbuffer *eb) } while (1); } -static unsigned int eb_batch_index(const struct i915_execbuffer *eb) -{ - if (eb->args->flags & I915_EXEC_BATCH_FIRST) - return 0; - else - return eb->buffer_count - 1; -} - static int eb_select_context(struct i915_execbuffer *eb) { struct i915_gem_context *ctx; @@ -810,6 +850,22 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) if (unlikely(!obj)) return ERR_PTR(-ENOENT); + /* + * If the user has opted-in for protected-object tracking, make + * sure the object encryption can be used. + * We only need to do this when the object is first used with + * this context, because the context itself will be banned when + * the protected objects become invalid. + */ + if (i915_gem_context_uses_protected_content(eb->gem_context) && + i915_gem_object_is_protected(obj)) { + err = intel_pxp_key_check(&vm->gt->pxp, obj, true); + if (err) { + i915_gem_object_put(obj); + return ERR_PTR(err); + } + } + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { i915_gem_object_put(obj); @@ -828,9 +884,7 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle) static int eb_lookup_vmas(struct i915_execbuffer *eb) { - struct drm_i915_private *i915 = eb->i915; - unsigned int batch = eb_batch_index(eb); - unsigned int i; + unsigned int i, current_batch = 0; int err = 0; INIT_LIST_HEAD(&eb->relocs); @@ -850,7 +904,9 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) goto err; } - eb_add_vma(eb, i, batch, vma); + err = eb_add_vma(eb, ¤t_batch, i, vma); + if (err) + return err; if (i915_gem_object_is_userptr(vma->obj)) { err = i915_gem_object_userptr_submit_init(vma->obj); @@ -873,26 +929,6 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) } } - if (unlikely(eb->batch->flags & EXEC_OBJECT_WRITE)) { - drm_dbg(&i915->drm, - "Attempting to use self-modifying batch buffer\n"); - return -EINVAL; - } - - if (range_overflows_t(u64, - eb->batch_start_offset, eb->batch_len, - eb->batch->vma->size)) { - drm_dbg(&i915->drm, "Attempting to use out-of-bounds batch\n"); - return -EINVAL; - } - - if (eb->batch_len == 0) - eb->batch_len = eb->batch->vma->size - eb->batch_start_offset; - if (unlikely(eb->batch_len == 0)) { /* impossible! */ - drm_dbg(&i915->drm, "Invalid batch length\n"); - return -EINVAL; - } - return 0; err: @@ -1625,8 +1661,7 @@ static int eb_reinit_userptr(struct i915_execbuffer *eb) return 0; } -static noinline int eb_relocate_parse_slow(struct i915_execbuffer *eb, - struct i915_request *rq) +static noinline int eb_relocate_parse_slow(struct i915_execbuffer *eb) { bool have_copy = false; struct eb_vma *ev; @@ -1642,21 +1677,6 @@ repeat: eb_release_vmas(eb, false); i915_gem_ww_ctx_fini(&eb->ww); - if (rq) { - /* nonblocking is always false */ - if (i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE, - MAX_SCHEDULE_TIMEOUT) < 0) { - i915_request_put(rq); - rq = NULL; - - err = -EINTR; - goto err_relock; - } - - i915_request_put(rq); - rq = NULL; - } - /* * We take 3 passes through the slowpatch. * @@ -1683,28 +1703,21 @@ repeat: if (!err) err = eb_reinit_userptr(eb); -err_relock: i915_gem_ww_ctx_init(&eb->ww, true); if (err) goto out; /* reacquire the objects */ repeat_validate: - rq = eb_pin_engine(eb, false); - if (IS_ERR(rq)) { - err = PTR_ERR(rq); - rq = NULL; + err = eb_pin_engine(eb, false); + if (err) goto err; - } - - /* We didn't throttle, should be NULL */ - GEM_WARN_ON(rq); err = eb_validate_vmas(eb); if (err) goto err; - GEM_BUG_ON(!eb->batch); + GEM_BUG_ON(!eb->batches[0]); list_for_each_entry(ev, &eb->relocs, reloc_link) { if (!have_copy) { @@ -1768,46 +1781,23 @@ out: } } - if (rq) - i915_request_put(rq); - return err; } static int eb_relocate_parse(struct i915_execbuffer *eb) { int err; - struct i915_request *rq = NULL; bool throttle = true; retry: - rq = eb_pin_engine(eb, throttle); - if (IS_ERR(rq)) { - err = PTR_ERR(rq); - rq = NULL; + err = eb_pin_engine(eb, throttle); + if (err) { if (err != -EDEADLK) return err; goto err; } - if (rq) { - bool nonblock = eb->file->filp->f_flags & O_NONBLOCK; - - /* Need to drop all locks now for throttling, take slowpath */ - err = i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE, 0); - if (err == -ETIME) { - if (nonblock) { - err = -EWOULDBLOCK; - i915_request_put(rq); - goto err; - } - goto slow; - } - i915_request_put(rq); - rq = NULL; - } - /* only throttle once, even if we didn't need to throttle */ throttle = false; @@ -1847,7 +1837,7 @@ err: return err; slow: - err = eb_relocate_parse_slow(eb, rq); + err = eb_relocate_parse_slow(eb); if (err) /* * If the user expects the execobject.offset and @@ -1861,11 +1851,40 @@ slow: return err; } +/* + * Using two helper loops for the order of which requests / batches are created + * and added the to backend. Requests are created in order from the parent to + * the last child. Requests are added in the reverse order, from the last child + * to parent. This is done for locking reasons as the timeline lock is acquired + * during request creation and released when the request is added to the + * backend. To make lockdep happy (see intel_context_timeline_lock) this must be + * the ordering. + */ +#define for_each_batch_create_order(_eb, _i) \ + for ((_i) = 0; (_i) < (_eb)->num_batches; ++(_i)) +#define for_each_batch_add_order(_eb, _i) \ + BUILD_BUG_ON(!typecheck(int, _i)); \ + for ((_i) = (_eb)->num_batches - 1; (_i) >= 0; --(_i)) + +static struct i915_request * +eb_find_first_request_added(struct i915_execbuffer *eb) +{ + int i; + + for_each_batch_add_order(eb, i) + if (eb->requests[i]) + return eb->requests[i]; + + GEM_BUG_ON("Request not found"); + + return NULL; +} + static int eb_move_to_gpu(struct i915_execbuffer *eb) { const unsigned int count = eb->buffer_count; unsigned int i = count; - int err = 0; + int err = 0, j; while (i--) { struct eb_vma *ev = &eb->vma[i]; @@ -1878,11 +1897,17 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) if (flags & EXEC_OBJECT_CAPTURE) { struct i915_capture_list *capture; - capture = kmalloc(sizeof(*capture), GFP_KERNEL); - if (capture) { - capture->next = eb->request->capture_list; - capture->vma = vma; - eb->request->capture_list = capture; + for_each_batch_create_order(eb, j) { + if (!eb->requests[j]) + break; + + capture = kmalloc(sizeof(*capture), GFP_KERNEL); + if (capture) { + capture->next = + eb->requests[j]->capture_list; + capture->vma = vma; + eb->requests[j]->capture_list = capture; + } } } @@ -1897,20 +1922,43 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) * !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ) * but gcc's optimiser doesn't handle that as well and emits * two jumps instead of one. Maybe one day... + * + * FIXME: There is also sync flushing in set_pages(), which + * serves a different purpose(some of the time at least). + * + * We should consider: + * + * 1. Rip out the async flush code. + * + * 2. Or make the sync flushing use the async clflush path + * using mandatory fences underneath. Currently the below + * async flush happens after we bind the object. */ if (unlikely(obj->cache_dirty & ~obj->cache_coherent)) { if (i915_gem_clflush_object(obj, 0)) flags &= ~EXEC_OBJECT_ASYNC; } + /* We only need to await on the first request */ if (err == 0 && !(flags & EXEC_OBJECT_ASYNC)) { err = i915_request_await_object - (eb->request, obj, flags & EXEC_OBJECT_WRITE); + (eb_find_first_request_added(eb), obj, + flags & EXEC_OBJECT_WRITE); } - if (err == 0) - err = i915_vma_move_to_active(vma, eb->request, - flags | __EXEC_OBJECT_NO_RESERVE); + for_each_batch_add_order(eb, j) { + if (err) + break; + if (!eb->requests[j]) + continue; + + err = _i915_vma_move_to_active(vma, eb->requests[j], + j ? NULL : + eb->composite_fence ? + eb->composite_fence : + &eb->requests[j]->fence, + flags | __EXEC_OBJECT_NO_RESERVE); + } } #ifdef CONFIG_MMU_NOTIFIER @@ -1941,11 +1989,16 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) goto err_skip; /* Unconditionally flush any chipset caches (for streaming writes). */ - intel_gt_chipset_flush(eb->engine->gt); + intel_gt_chipset_flush(eb->gt); return 0; err_skip: - i915_request_set_error_once(eb->request, err); + for_each_batch_create_order(eb, j) { + if (!eb->requests[j]) + break; + + i915_request_set_error_once(eb->requests[j], err); + } return err; } @@ -2040,14 +2093,17 @@ static int eb_parse(struct i915_execbuffer *eb) int err; if (!eb_use_cmdparser(eb)) { - batch = eb_dispatch_secure(eb, eb->batch->vma); + batch = eb_dispatch_secure(eb, eb->batches[0]->vma); if (IS_ERR(batch)) return PTR_ERR(batch); goto secure_batch; } - len = eb->batch_len; + if (intel_context_is_parallel(eb->context)) + return -EINVAL; + + len = eb->batch_len[0]; if (!CMDPARSER_USES_GGTT(eb->i915)) { /* * ppGTT backed shadow buffers must be mapped RO, to prevent @@ -2061,11 +2117,11 @@ static int eb_parse(struct i915_execbuffer *eb) } else { len += I915_CMD_PARSER_TRAMPOLINE_SIZE; } - if (unlikely(len < eb->batch_len)) /* last paranoid check of overflow */ + if (unlikely(len < eb->batch_len[0])) /* last paranoid check of overflow */ return -EINVAL; if (!pool) { - pool = intel_gt_get_buffer_pool(eb->engine->gt, len, + pool = intel_gt_get_buffer_pool(eb->gt, len, I915_MAP_WB); if (IS_ERR(pool)) return PTR_ERR(pool); @@ -2090,7 +2146,7 @@ static int eb_parse(struct i915_execbuffer *eb) trampoline = shadow; shadow = shadow_batch_pin(eb, pool->obj, - &eb->engine->gt->ggtt->vm, + &eb->gt->ggtt->vm, PIN_GLOBAL); if (IS_ERR(shadow)) { err = PTR_ERR(shadow); @@ -2112,26 +2168,29 @@ static int eb_parse(struct i915_execbuffer *eb) if (err) goto err_trampoline; - err = intel_engine_cmd_parser(eb->engine, - eb->batch->vma, + err = intel_engine_cmd_parser(eb->context->engine, + eb->batches[0]->vma, eb->batch_start_offset, - eb->batch_len, + eb->batch_len[0], shadow, trampoline); if (err) goto err_unpin_batch; - eb->batch = &eb->vma[eb->buffer_count++]; - eb->batch->vma = i915_vma_get(shadow); - eb->batch->flags = __EXEC_OBJECT_HAS_PIN; + eb->batches[0] = &eb->vma[eb->buffer_count++]; + eb->batches[0]->vma = i915_vma_get(shadow); + eb->batches[0]->flags = __EXEC_OBJECT_HAS_PIN; eb->trampoline = trampoline; eb->batch_start_offset = 0; secure_batch: if (batch) { - eb->batch = &eb->vma[eb->buffer_count++]; - eb->batch->flags = __EXEC_OBJECT_HAS_PIN; - eb->batch->vma = i915_vma_get(batch); + if (intel_context_is_parallel(eb->context)) + return -EINVAL; + + eb->batches[0] = &eb->vma[eb->buffer_count++]; + eb->batches[0]->flags = __EXEC_OBJECT_HAS_PIN; + eb->batches[0]->vma = i915_vma_get(batch); } return 0; @@ -2147,19 +2206,18 @@ err: return err; } -static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch) +static int eb_request_submit(struct i915_execbuffer *eb, + struct i915_request *rq, + struct i915_vma *batch, + u64 batch_len) { int err; - if (intel_context_nopreempt(eb->context)) - __set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags); - - err = eb_move_to_gpu(eb); - if (err) - return err; + if (intel_context_nopreempt(rq->context)) + __set_bit(I915_FENCE_FLAG_NOPREEMPT, &rq->fence.flags); if (eb->args->flags & I915_EXEC_GEN7_SOL_RESET) { - err = i915_reset_gen7_sol_offsets(eb->request); + err = i915_reset_gen7_sol_offsets(rq); if (err) return err; } @@ -2170,26 +2228,26 @@ static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch) * allows us to determine if the batch is still waiting on the GPU * or actually running by checking the breadcrumb. */ - if (eb->engine->emit_init_breadcrumb) { - err = eb->engine->emit_init_breadcrumb(eb->request); + if (rq->context->engine->emit_init_breadcrumb) { + err = rq->context->engine->emit_init_breadcrumb(rq); if (err) return err; } - err = eb->engine->emit_bb_start(eb->request, - batch->node.start + - eb->batch_start_offset, - eb->batch_len, - eb->batch_flags); + err = rq->context->engine->emit_bb_start(rq, + batch->node.start + + eb->batch_start_offset, + batch_len, + eb->batch_flags); if (err) return err; if (eb->trampoline) { + GEM_BUG_ON(intel_context_is_parallel(rq->context)); GEM_BUG_ON(eb->batch_start_offset); - err = eb->engine->emit_bb_start(eb->request, - eb->trampoline->node.start + - eb->batch_len, - 0, 0); + err = rq->context->engine->emit_bb_start(rq, + eb->trampoline->node.start + + batch_len, 0, 0); if (err) return err; } @@ -2197,6 +2255,27 @@ static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch) return 0; } +static int eb_submit(struct i915_execbuffer *eb) +{ + unsigned int i; + int err; + + err = eb_move_to_gpu(eb); + + for_each_batch_create_order(eb, i) { + if (!eb->requests[i]) + break; + + trace_i915_request_queue(eb->requests[i], eb->batch_flags); + if (!err) + err = eb_request_submit(eb, eb->requests[i], + eb->batches[i]->vma, + eb->batch_len[i]); + } + + return err; +} + static int num_vcs_engines(const struct drm_i915_private *i915) { return hweight_long(VDBOX_MASK(&i915->gt)); @@ -2262,26 +2341,11 @@ static struct i915_request *eb_throttle(struct i915_execbuffer *eb, struct intel return i915_request_get(rq); } -static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb, bool throttle) +static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce, + bool throttle) { - struct intel_context *ce = eb->context; struct intel_timeline *tl; struct i915_request *rq = NULL; - int err; - - GEM_BUG_ON(eb->args->flags & __EXEC_ENGINE_PINNED); - - if (unlikely(intel_context_is_banned(ce))) - return ERR_PTR(-EIO); - - /* - * Pinning the contexts may generate requests in order to acquire - * GGTT space, so do this first before we reserve a seqno for - * ourselves. - */ - err = intel_context_pin_ww(ce, &eb->ww); - if (err) - return ERR_PTR(err); /* * Take a local wakeref for preparing to dispatch the execbuf as @@ -2292,33 +2356,108 @@ static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb, bool throt * taken on the engine, and the parent device. */ tl = intel_context_timeline_lock(ce); - if (IS_ERR(tl)) { - intel_context_unpin(ce); - return ERR_CAST(tl); - } + if (IS_ERR(tl)) + return PTR_ERR(tl); intel_context_enter(ce); if (throttle) rq = eb_throttle(eb, ce); intel_context_timeline_unlock(tl); + if (rq) { + bool nonblock = eb->file->filp->f_flags & O_NONBLOCK; + long timeout = nonblock ? 0 : MAX_SCHEDULE_TIMEOUT; + + if (i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE, + timeout) < 0) { + i915_request_put(rq); + + tl = intel_context_timeline_lock(ce); + intel_context_exit(ce); + intel_context_timeline_unlock(tl); + + if (nonblock) + return -EWOULDBLOCK; + else + return -EINTR; + } + i915_request_put(rq); + } + + return 0; +} + +static int eb_pin_engine(struct i915_execbuffer *eb, bool throttle) +{ + struct intel_context *ce = eb->context, *child; + int err; + int i = 0, j = 0; + + GEM_BUG_ON(eb->args->flags & __EXEC_ENGINE_PINNED); + + if (unlikely(intel_context_is_banned(ce))) + return -EIO; + + /* + * Pinning the contexts may generate requests in order to acquire + * GGTT space, so do this first before we reserve a seqno for + * ourselves. + */ + err = intel_context_pin_ww(ce, &eb->ww); + if (err) + return err; + for_each_child(ce, child) { + err = intel_context_pin_ww(child, &eb->ww); + GEM_BUG_ON(err); /* perma-pinned should incr a counter */ + } + + for_each_child(ce, child) { + err = eb_pin_timeline(eb, child, throttle); + if (err) + goto unwind; + ++i; + } + err = eb_pin_timeline(eb, ce, throttle); + if (err) + goto unwind; + eb->args->flags |= __EXEC_ENGINE_PINNED; - return rq; + return 0; + +unwind: + for_each_child(ce, child) { + if (j++ < i) { + mutex_lock(&child->timeline->mutex); + intel_context_exit(child); + mutex_unlock(&child->timeline->mutex); + } + } + for_each_child(ce, child) + intel_context_unpin(child); + intel_context_unpin(ce); + return err; } static void eb_unpin_engine(struct i915_execbuffer *eb) { - struct intel_context *ce = eb->context; - struct intel_timeline *tl = ce->timeline; + struct intel_context *ce = eb->context, *child; if (!(eb->args->flags & __EXEC_ENGINE_PINNED)) return; eb->args->flags &= ~__EXEC_ENGINE_PINNED; - mutex_lock(&tl->mutex); + for_each_child(ce, child) { + mutex_lock(&child->timeline->mutex); + intel_context_exit(child); + mutex_unlock(&child->timeline->mutex); + + intel_context_unpin(child); + } + + mutex_lock(&ce->timeline->mutex); intel_context_exit(ce); - mutex_unlock(&tl->mutex); + mutex_unlock(&ce->timeline->mutex); intel_context_unpin(ce); } @@ -2369,7 +2508,7 @@ eb_select_legacy_ring(struct i915_execbuffer *eb) static int eb_select_engine(struct i915_execbuffer *eb) { - struct intel_context *ce; + struct intel_context *ce, *child; unsigned int idx; int err; @@ -2382,6 +2521,20 @@ eb_select_engine(struct i915_execbuffer *eb) if (IS_ERR(ce)) return PTR_ERR(ce); + if (intel_context_is_parallel(ce)) { + if (eb->buffer_count < ce->parallel.number_children + 1) { + intel_context_put(ce); + return -EINVAL; + } + if (eb->batch_start_offset || eb->args->batch_len) { + intel_context_put(ce); + return -EINVAL; + } + } + eb->num_batches = ce->parallel.number_children + 1; + + for_each_child(ce, child) + intel_context_get(child); intel_gt_pm_get(ce->engine->gt); if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) { @@ -2389,6 +2542,13 @@ eb_select_engine(struct i915_execbuffer *eb) if (err) goto err; } + for_each_child(ce, child) { + if (!test_bit(CONTEXT_ALLOC_BIT, &child->flags)) { + err = intel_context_alloc_state(child); + if (err) + goto err; + } + } /* * ABI: Before userspace accesses the GPU (e.g. execbuffer), report @@ -2399,7 +2559,7 @@ eb_select_engine(struct i915_execbuffer *eb) goto err; eb->context = ce; - eb->engine = ce->engine; + eb->gt = ce->engine->gt; /* * Make sure engine pool stays alive even if we call intel_context_put @@ -2410,6 +2570,8 @@ eb_select_engine(struct i915_execbuffer *eb) err: intel_gt_pm_put(ce->engine->gt); + for_each_child(ce, child) + intel_context_put(child); intel_context_put(ce); return err; } @@ -2417,7 +2579,11 @@ err: static void eb_put_engine(struct i915_execbuffer *eb) { - intel_gt_pm_put(eb->engine->gt); + struct intel_context *child; + + intel_gt_pm_put(eb->gt); + for_each_child(eb->context, child) + intel_context_put(child); intel_context_put(eb->context); } @@ -2640,7 +2806,8 @@ static void put_fence_array(struct eb_fence *fences, int num_fences) } static int -await_fence_array(struct i915_execbuffer *eb) +await_fence_array(struct i915_execbuffer *eb, + struct i915_request *rq) { unsigned int n; int err; @@ -2654,8 +2821,7 @@ await_fence_array(struct i915_execbuffer *eb) if (!eb->fences[n].dma_fence) continue; - err = i915_request_await_dma_fence(eb->request, - eb->fences[n].dma_fence); + err = i915_request_await_dma_fence(rq, eb->fences[n].dma_fence); if (err < 0) return err; } @@ -2663,9 +2829,9 @@ await_fence_array(struct i915_execbuffer *eb) return 0; } -static void signal_fence_array(const struct i915_execbuffer *eb) +static void signal_fence_array(const struct i915_execbuffer *eb, + struct dma_fence * const fence) { - struct dma_fence * const fence = &eb->request->fence; unsigned int n; for (n = 0; n < eb->num_fences; n++) { @@ -2713,9 +2879,9 @@ static void retire_requests(struct intel_timeline *tl, struct i915_request *end) break; } -static int eb_request_add(struct i915_execbuffer *eb, int err) +static int eb_request_add(struct i915_execbuffer *eb, struct i915_request *rq, + int err, bool last_parallel) { - struct i915_request *rq = eb->request; struct intel_timeline * const tl = i915_request_timeline(rq); struct i915_sched_attr attr = {}; struct i915_request *prev; @@ -2737,6 +2903,17 @@ static int eb_request_add(struct i915_execbuffer *eb, int err) err = -ENOENT; /* override any transient errors */ } + if (intel_context_is_parallel(eb->context)) { + if (err) { + __i915_request_skip(rq); + set_bit(I915_FENCE_FLAG_SKIP_PARALLEL, + &rq->fence.flags); + } + if (last_parallel) + set_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, + &rq->fence.flags); + } + __i915_request_queue(rq, &attr); /* Try to clean up the client's timeline after submitting the request */ @@ -2748,6 +2925,25 @@ static int eb_request_add(struct i915_execbuffer *eb, int err) return err; } +static int eb_requests_add(struct i915_execbuffer *eb, int err) +{ + int i; + + /* + * We iterate in reverse order of creation to release timeline mutexes in + * same order. + */ + for_each_batch_add_order(eb, i) { + struct i915_request *rq = eb->requests[i]; + + if (!rq) + continue; + err |= eb_request_add(eb, rq, err, i == 0); + } + + return err; +} + static const i915_user_extension_fn execbuf_extensions[] = { [DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences, }; @@ -2774,6 +2970,185 @@ parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args, eb); } +static void eb_requests_get(struct i915_execbuffer *eb) +{ + unsigned int i; + + for_each_batch_create_order(eb, i) { + if (!eb->requests[i]) + break; + + i915_request_get(eb->requests[i]); + } +} + +static void eb_requests_put(struct i915_execbuffer *eb) +{ + unsigned int i; + + for_each_batch_create_order(eb, i) { + if (!eb->requests[i]) + break; + + i915_request_put(eb->requests[i]); + } +} + +static struct sync_file * +eb_composite_fence_create(struct i915_execbuffer *eb, int out_fence_fd) +{ + struct sync_file *out_fence = NULL; + struct dma_fence_array *fence_array; + struct dma_fence **fences; + unsigned int i; + + GEM_BUG_ON(!intel_context_is_parent(eb->context)); + + fences = kmalloc_array(eb->num_batches, sizeof(*fences), GFP_KERNEL); + if (!fences) + return ERR_PTR(-ENOMEM); + + for_each_batch_create_order(eb, i) { + fences[i] = &eb->requests[i]->fence; + __set_bit(I915_FENCE_FLAG_COMPOSITE, + &eb->requests[i]->fence.flags); + } + + fence_array = dma_fence_array_create(eb->num_batches, + fences, + eb->context->parallel.fence_context, + eb->context->parallel.seqno, + false); + if (!fence_array) { + kfree(fences); + return ERR_PTR(-ENOMEM); + } + + /* Move ownership to the dma_fence_array created above */ + for_each_batch_create_order(eb, i) + dma_fence_get(fences[i]); + + if (out_fence_fd != -1) { + out_fence = sync_file_create(&fence_array->base); + /* sync_file now owns fence_arry, drop creation ref */ + dma_fence_put(&fence_array->base); + if (!out_fence) + return ERR_PTR(-ENOMEM); + } + + eb->composite_fence = &fence_array->base; + + return out_fence; +} + +static struct sync_file * +eb_fences_add(struct i915_execbuffer *eb, struct i915_request *rq, + struct dma_fence *in_fence, int out_fence_fd) +{ + struct sync_file *out_fence = NULL; + int err; + + if (unlikely(eb->gem_context->syncobj)) { + struct dma_fence *fence; + + fence = drm_syncobj_fence_get(eb->gem_context->syncobj); + err = i915_request_await_dma_fence(rq, fence); + dma_fence_put(fence); + if (err) + return ERR_PTR(err); + } + + if (in_fence) { + if (eb->args->flags & I915_EXEC_FENCE_SUBMIT) + err = i915_request_await_execution(rq, in_fence); + else + err = i915_request_await_dma_fence(rq, in_fence); + if (err < 0) + return ERR_PTR(err); + } + + if (eb->fences) { + err = await_fence_array(eb, rq); + if (err) + return ERR_PTR(err); + } + + if (intel_context_is_parallel(eb->context)) { + out_fence = eb_composite_fence_create(eb, out_fence_fd); + if (IS_ERR(out_fence)) + return ERR_PTR(-ENOMEM); + } else if (out_fence_fd != -1) { + out_fence = sync_file_create(&rq->fence); + if (!out_fence) + return ERR_PTR(-ENOMEM); + } + + return out_fence; +} + +static struct intel_context * +eb_find_context(struct i915_execbuffer *eb, unsigned int context_number) +{ + struct intel_context *child; + + if (likely(context_number == 0)) + return eb->context; + + for_each_child(eb->context, child) + if (!--context_number) + return child; + + GEM_BUG_ON("Context not found"); + + return NULL; +} + +static struct sync_file * +eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence, + int out_fence_fd) +{ + struct sync_file *out_fence = NULL; + unsigned int i; + + for_each_batch_create_order(eb, i) { + /* Allocate a request for this batch buffer nice and early. */ + eb->requests[i] = i915_request_create(eb_find_context(eb, i)); + if (IS_ERR(eb->requests[i])) { + out_fence = ERR_PTR(PTR_ERR(eb->requests[i])); + eb->requests[i] = NULL; + return out_fence; + } + + /* + * Only the first request added (committed to backend) has to + * take the in fences into account as all subsequent requests + * will have fences inserted inbetween them. + */ + if (i + 1 == eb->num_batches) { + out_fence = eb_fences_add(eb, eb->requests[i], + in_fence, out_fence_fd); + if (IS_ERR(out_fence)) + return out_fence; + } + + /* + * Whilst this request exists, batch_obj will be on the + * active_list, and so will hold the active reference. Only when + * this request is retired will the batch_obj be moved onto + * the inactive_list and lose its active reference. Hence we do + * not need to explicitly hold another reference here. + */ + eb->requests[i]->batch = eb->batches[i]->vma; + if (eb->batch_pool) { + GEM_BUG_ON(intel_context_is_parallel(eb->context)); + intel_gt_buffer_pool_mark_active(eb->batch_pool, + eb->requests[i]); + } + } + + return out_fence; +} + static int i915_gem_do_execbuffer(struct drm_device *dev, struct drm_file *file, @@ -2784,7 +3159,6 @@ i915_gem_do_execbuffer(struct drm_device *dev, struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct sync_file *out_fence = NULL; - struct i915_vma *batch; int out_fence_fd = -1; int err; @@ -2808,12 +3182,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.buffer_count = args->buffer_count; eb.batch_start_offset = args->batch_start_offset; - eb.batch_len = args->batch_len; eb.trampoline = NULL; eb.fences = NULL; eb.num_fences = 0; + memset(eb.requests, 0, sizeof(struct i915_request *) * + ARRAY_SIZE(eb.requests)); + eb.composite_fence = NULL; + eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { if (GRAPHICS_VER(i915) >= 11) @@ -2897,70 +3274,25 @@ i915_gem_do_execbuffer(struct drm_device *dev, ww_acquire_done(&eb.ww.ctx); - batch = eb.batch->vma; - - /* Allocate a request for this batch buffer nice and early. */ - eb.request = i915_request_create(eb.context); - if (IS_ERR(eb.request)) { - err = PTR_ERR(eb.request); - goto err_vma; - } - - if (unlikely(eb.gem_context->syncobj)) { - struct dma_fence *fence; - - fence = drm_syncobj_fence_get(eb.gem_context->syncobj); - err = i915_request_await_dma_fence(eb.request, fence); - dma_fence_put(fence); - if (err) - goto err_ext; - } - - if (in_fence) { - if (args->flags & I915_EXEC_FENCE_SUBMIT) - err = i915_request_await_execution(eb.request, - in_fence); + out_fence = eb_requests_create(&eb, in_fence, out_fence_fd); + if (IS_ERR(out_fence)) { + err = PTR_ERR(out_fence); + if (eb.requests[0]) + goto err_request; else - err = i915_request_await_dma_fence(eb.request, - in_fence); - if (err < 0) - goto err_request; + goto err_vma; } - if (eb.fences) { - err = await_fence_array(&eb); - if (err) - goto err_request; - } - - if (out_fence_fd != -1) { - out_fence = sync_file_create(&eb.request->fence); - if (!out_fence) { - err = -ENOMEM; - goto err_request; - } - } - - /* - * Whilst this request exists, batch_obj will be on the - * active_list, and so will hold the active reference. Only when this - * request is retired will the the batch_obj be moved onto the - * inactive_list and lose its active reference. Hence we do not need - * to explicitly hold another reference here. - */ - eb.request->batch = batch; - if (eb.batch_pool) - intel_gt_buffer_pool_mark_active(eb.batch_pool, eb.request); - - trace_i915_request_queue(eb.request, eb.batch_flags); - err = eb_submit(&eb, batch); + err = eb_submit(&eb); err_request: - i915_request_get(eb.request); - err = eb_request_add(&eb, err); + eb_requests_get(&eb); + err = eb_requests_add(&eb, err); if (eb.fences) - signal_fence_array(&eb); + signal_fence_array(&eb, eb.composite_fence ? + eb.composite_fence : + &eb.requests[0]->fence); if (out_fence) { if (err == 0) { @@ -2975,10 +3307,15 @@ err_request: if (unlikely(eb.gem_context->syncobj)) { drm_syncobj_replace_fence(eb.gem_context->syncobj, - &eb.request->fence); + eb.composite_fence ? + eb.composite_fence : + &eb.requests[0]->fence); } - i915_request_put(eb.request); + if (!out_fence && eb.composite_fence) + dma_fence_put(eb.composite_fence); + + eb_requests_put(&eb); err_vma: eb_release_vmas(&eb, true); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index e5ae9c06510c..a57a6b7013c2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -134,6 +134,8 @@ static void i915_gem_object_put_pages_internal(struct drm_i915_gem_object *obj, internal_free_pages(pages); obj->mm.dirty = false; + + __start_cpu_write(obj); } static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index eb345305dc52..444f8268b9c5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -56,8 +56,8 @@ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) * @obj: The object to check. * * This function is intended to be called from within the fence signaling - * path where the fence keeps the object from being migrated. For example - * during gpu reset or similar. + * path where the fence, or a pin, keeps the object from being migrated. For + * example during gpu reset or similar. * * Return: Whether the object is resident in lmem. */ @@ -66,7 +66,8 @@ bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) struct intel_memory_region *mr = READ_ONCE(obj->mm.region); #ifdef CONFIG_LOCKDEP - GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, true)); + GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, true) && + i915_gem_object_evictable(obj)); #endif return mr && (mr->type == INTEL_MEMORY_LOCAL || mr->type == INTEL_MEMORY_STOLEN_LOCAL); @@ -103,6 +104,32 @@ __i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915, size, page_size, flags); } +struct drm_i915_gem_object * +i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915, + const void *data, size_t size) +{ + struct drm_i915_gem_object *obj; + void *map; + + obj = i915_gem_object_create_lmem(i915, + round_up(size, PAGE_SIZE), + I915_BO_ALLOC_CONTIGUOUS); + if (IS_ERR(obj)) + return obj; + + map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); + if (IS_ERR(map)) { + i915_gem_object_put(obj); + return map; + } + + memcpy(map, data, size); + + i915_gem_object_unpin_map(obj); + + return obj; +} + struct drm_i915_gem_object * i915_gem_object_create_lmem(struct drm_i915_private *i915, resource_size_t size, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h index 4ee81fc66302..1b88ea13435c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h @@ -23,6 +23,10 @@ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj); bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj); +struct drm_i915_gem_object * +i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915, + const void *data, size_t size); + struct drm_i915_gem_object * __i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915, resource_size_t size, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 5130e8ed9564..65fc6ff5f59d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -395,7 +395,7 @@ retry: /* Track the mmo associated with the fenced vma */ vma->mmo = mmo; - if (IS_ACTIVE(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)) + if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) intel_wakeref_auto(&i915->ggtt.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 6fb9afb65034..1e426a42a36c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -25,6 +25,7 @@ #include #include "display/intel_frontbuffer.h" +#include "pxp/intel_pxp.h" #include "i915_drv.h" #include "i915_gem_clflush.h" #include "i915_gem_context.h" @@ -89,6 +90,22 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, mutex_init(&obj->mm.get_dma_page.lock); } +/** + * i915_gem_object_fini - Clean up a GEM object initialization + * @obj: The gem object to cleanup + * + * This function cleans up gem object fields that are set up by + * drm_gem_private_object_init() and i915_gem_object_init(). + * It's primarily intended as a helper for backends that need to + * clean up the gem object in separate steps. + */ +void __i915_gem_object_fini(struct drm_i915_gem_object *obj) +{ + mutex_destroy(&obj->mm.get_page.lock); + mutex_destroy(&obj->mm.get_dma_page.lock); + dma_resv_fini(&obj->base._resv); +} + /** * Mark up the object's coherency levels for a given cache_level * @obj: #drm_i915_gem_object @@ -111,6 +128,32 @@ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj, !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE); } +bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + + /* + * This is purely from a security perspective, so we simply don't care + * about non-userspace objects being able to bypass the LLC. + */ + if (!(obj->flags & I915_BO_ALLOC_USER)) + return false; + + /* + * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it + * possible for userspace to bypass the GTT caching bits set by the + * kernel, as per the given object cache_level. This is troublesome + * since the heavy flush we apply when first gathering the pages is + * skipped if the kernel thinks the object is coherent with the GPU. As + * a result it might be possible to bypass the cache and read the + * contents of the page directly, which could be stale data. If it's + * just a case of userspace shooting themselves in the foot then so be + * it, but since i915 takes the stance of always zeroing memory before + * handing it to userspace, we need to prevent this. + */ + return IS_JSL_EHL(i915); +} + static void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file) { struct drm_i915_gem_object *obj = to_intel_bo(gem); @@ -174,7 +217,6 @@ void __i915_gem_free_object_rcu(struct rcu_head *head) container_of(head, typeof(*obj), rcu); struct drm_i915_private *i915 = to_i915(obj->base.dev); - dma_resv_fini(&obj->base._resv); i915_gem_object_free(obj); GEM_BUG_ON(!atomic_read(&i915->mm.free_count)); @@ -204,10 +246,17 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) } } -void __i915_gem_free_object(struct drm_i915_gem_object *obj) +/** + * __i915_gem_object_pages_fini - Clean up pages use of a gem object + * @obj: The gem object to clean up + * + * This function cleans up usage of the object mm.pages member. It + * is intended for backends that need to clean up a gem object in + * separate steps and needs to be called when the object is idle before + * the object's backing memory is freed. + */ +void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) { - trace_i915_gem_object_destroy(obj); - if (!list_empty(&obj->vma.list)) { struct i915_vma *vma; @@ -233,11 +282,17 @@ void __i915_gem_free_object(struct drm_i915_gem_object *obj) __i915_gem_object_free_mmaps(obj); - GEM_BUG_ON(!list_empty(&obj->lut_list)); - atomic_set(&obj->mm.pages_pin_count, 0); __i915_gem_object_put_pages(obj); GEM_BUG_ON(i915_gem_object_has_pages(obj)); +} + +void __i915_gem_free_object(struct drm_i915_gem_object *obj) +{ + trace_i915_gem_object_destroy(obj); + + GEM_BUG_ON(!list_empty(&obj->lut_list)); + bitmap_free(obj->bit_17); if (obj->base.import_attach) @@ -253,6 +308,8 @@ void __i915_gem_free_object(struct drm_i915_gem_object *obj) if (obj->shares_resv_from) i915_vm_resv_put(obj->shares_resv_from); + + __i915_gem_object_fini(obj); } static void __i915_gem_free_objects(struct drm_i915_private *i915, @@ -266,6 +323,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, obj->ops->delayed_free(obj); continue; } + __i915_gem_object_pages_fini(obj); __i915_gem_free_object(obj); /* But keep the pointer alive for RCU-protected lookups */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 48112b9d76df..59201801cec5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -58,6 +58,9 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, const struct drm_i915_gem_object_ops *ops, struct lock_class_key *key, unsigned alloc_flags); + +void __i915_gem_object_fini(struct drm_i915_gem_object *obj); + struct drm_i915_gem_object * i915_gem_object_create_shmem(struct drm_i915_private *i915, resource_size_t size); @@ -269,6 +272,12 @@ i915_gem_object_clear_tiling_quirk(struct drm_i915_gem_object *obj) clear_bit(I915_TILING_QUIRK_BIT, &obj->flags); } +static inline bool +i915_gem_object_is_protected(const struct drm_i915_gem_object *obj) +{ + return obj->flags & I915_BO_PROTECTED; +} + static inline bool i915_gem_object_type_has(const struct drm_i915_gem_object *obj, unsigned long flags) @@ -503,25 +512,9 @@ i915_gem_object_finish_access(struct drm_i915_gem_object *obj) i915_gem_object_unpin_pages(obj); } -static inline struct intel_engine_cs * -i915_gem_object_last_write_engine(struct drm_i915_gem_object *obj) -{ - struct intel_engine_cs *engine = NULL; - struct dma_fence *fence; - - rcu_read_lock(); - fence = dma_resv_get_excl_unlocked(obj->base.resv); - rcu_read_unlock(); - - if (fence && dma_fence_is_i915(fence) && !dma_fence_is_signaled(fence)) - engine = to_request(fence)->engine; - dma_fence_put(fence); - - return engine; -} - void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj, unsigned int cache_level); +bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj); void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj); void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj); @@ -599,6 +592,8 @@ bool i915_gem_object_is_shmem(const struct drm_i915_gem_object *obj); void __i915_gem_free_object_rcu(struct rcu_head *head); +void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj); + void __i915_gem_free_object(struct drm_i915_gem_object *obj); bool i915_gem_object_evictable(struct drm_i915_gem_object *obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 2471f36aaff3..da85169006d4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -288,17 +288,23 @@ struct drm_i915_gem_object { I915_SELFTEST_DECLARE(struct list_head st_link); unsigned long flags; -#define I915_BO_ALLOC_CONTIGUOUS BIT(0) -#define I915_BO_ALLOC_VOLATILE BIT(1) -#define I915_BO_ALLOC_CPU_CLEAR BIT(2) -#define I915_BO_ALLOC_USER BIT(3) +#define I915_BO_ALLOC_CONTIGUOUS BIT(0) +#define I915_BO_ALLOC_VOLATILE BIT(1) +#define I915_BO_ALLOC_CPU_CLEAR BIT(2) +#define I915_BO_ALLOC_USER BIT(3) +/* Object is allowed to lose its contents on suspend / resume, even if pinned */ +#define I915_BO_ALLOC_PM_VOLATILE BIT(4) +/* Object needs to be restored early using memcpy during resume */ +#define I915_BO_ALLOC_PM_EARLY BIT(5) #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \ I915_BO_ALLOC_VOLATILE | \ I915_BO_ALLOC_CPU_CLEAR | \ - I915_BO_ALLOC_USER) -#define I915_BO_READONLY BIT(4) -#define I915_TILING_QUIRK_BIT 5 /* unknown swizzling; do not release! */ - + I915_BO_ALLOC_USER | \ + I915_BO_ALLOC_PM_VOLATILE | \ + I915_BO_ALLOC_PM_EARLY) +#define I915_BO_READONLY BIT(6) +#define I915_TILING_QUIRK_BIT 7 /* unknown swizzling; do not release! */ +#define I915_BO_PROTECTED BIT(8) /** * @mem_flags - Mutable placement-related flags * @@ -421,6 +427,33 @@ struct drm_i915_gem_object { * can freely bypass the CPU cache when touching the pages with the GPU, * where the kernel is completely unaware. On such platform we need * apply the sledgehammer-on-acquire regardless of the @cache_coherent. + * + * Special care is taken on non-LLC platforms, to prevent potential + * information leak. The driver currently ensures: + * + * 1. All userspace objects, by default, have @cache_level set as + * I915_CACHE_NONE. The only exception is userptr objects, where we + * instead force I915_CACHE_LLC, but we also don't allow userspace to + * ever change the @cache_level for such objects. Another special case + * is dma-buf, which doesn't rely on @cache_dirty, but there we + * always do a forced flush when acquiring the pages, if there is a + * chance that the pages can be read directly from main memory with + * the GPU. + * + * 2. All I915_CACHE_NONE objects have @cache_dirty initially true. + * + * 3. All swapped-out objects(i.e shmem) have @cache_dirty set to + * true. + * + * 4. The @cache_dirty is never freely reset before the initial + * flush, even if userspace adjusts the @cache_level through the + * i915_gem_set_caching_ioctl. + * + * 5. All @cache_dirty objects(including swapped-in) are initially + * flushed with a synchronous call to drm_clflush_sg in + * __i915_gem_object_set_pages. The @cache_dirty can be freely reset + * at this point. All further asynchronous clfushes are never security + * critical, i.e userspace is free to race against itself. */ unsigned int cache_dirty:1; @@ -534,9 +567,17 @@ struct drm_i915_gem_object { struct { struct sg_table *cached_io_st; struct i915_gem_object_page_iter get_io_page; + struct drm_i915_gem_object *backup; bool created:1; } ttm; + /* + * Record which PXP key instance this object was created against (if + * any), so we can use it to determine if the encryption is valid by + * comparing against the current key instance. + */ + u32 pxp_key_instance; + /** Record of address bit 17 of each page at last unbind. */ unsigned long *bit_17; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 8b9d7d14c4bd..726b40e1fbb0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -5,6 +5,7 @@ */ #include "gem/i915_gem_pm.h" +#include "gem/i915_gem_ttm_pm.h" #include "gt/intel_gt.h" #include "gt/intel_gt_pm.h" #include "gt/intel_gt_requests.h" @@ -39,6 +40,88 @@ void i915_gem_suspend(struct drm_i915_private *i915) i915_gem_drain_freed_objects(i915); } +static int lmem_restore(struct drm_i915_private *i915, u32 flags) +{ + struct intel_memory_region *mr; + int ret = 0, id; + + for_each_memory_region(mr, i915, id) { + if (mr->type == INTEL_MEMORY_LOCAL) { + ret = i915_ttm_restore_region(mr, flags); + if (ret) + break; + } + } + + return ret; +} + +static int lmem_suspend(struct drm_i915_private *i915, u32 flags) +{ + struct intel_memory_region *mr; + int ret = 0, id; + + for_each_memory_region(mr, i915, id) { + if (mr->type == INTEL_MEMORY_LOCAL) { + ret = i915_ttm_backup_region(mr, flags); + if (ret) + break; + } + } + + return ret; +} + +static void lmem_recover(struct drm_i915_private *i915) +{ + struct intel_memory_region *mr; + int id; + + for_each_memory_region(mr, i915, id) + if (mr->type == INTEL_MEMORY_LOCAL) + i915_ttm_recover_region(mr); +} + +int i915_gem_backup_suspend(struct drm_i915_private *i915) +{ + int ret; + + /* Opportunistically try to evict unpinned objects */ + ret = lmem_suspend(i915, I915_TTM_BACKUP_ALLOW_GPU); + if (ret) + goto out_recover; + + i915_gem_suspend(i915); + + /* + * More objects may have become unpinned as requests were + * retired. Now try to evict again. The gt may be wedged here + * in which case we automatically fall back to memcpy. + * We allow also backing up pinned objects that have not been + * marked for early recover, and that may contain, for example, + * page-tables for the migrate context. + */ + ret = lmem_suspend(i915, I915_TTM_BACKUP_ALLOW_GPU | + I915_TTM_BACKUP_PINNED); + if (ret) + goto out_recover; + + /* + * Remaining objects are backed up using memcpy once we've stopped + * using the migrate context. + */ + ret = lmem_suspend(i915, I915_TTM_BACKUP_PINNED); + if (ret) + goto out_recover; + + return 0; + +out_recover: + lmem_recover(i915); + + return ret; +} + void i915_gem_suspend_late(struct drm_i915_private *i915) { struct drm_i915_gem_object *obj; @@ -128,12 +211,20 @@ int i915_gem_freeze_late(struct drm_i915_private *i915) void i915_gem_resume(struct drm_i915_private *i915) { + int ret; + GEM_TRACE("%s\n", dev_name(i915->drm.dev)); + ret = lmem_restore(i915, 0); + GEM_WARN_ON(ret); + /* * As we didn't flush the kernel context before suspend, we cannot * guarantee that the context image is complete. So let's just reset * it and start again. */ intel_gt_resume(&i915->gt); + + ret = lmem_restore(i915, I915_TTM_BACKUP_ALLOW_GPU); + GEM_WARN_ON(ret); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.h b/drivers/gpu/drm/i915/gem/i915_gem_pm.h index c9a66630e92e..bedf1e95941a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.h @@ -18,6 +18,7 @@ void i915_gem_idle_work_handler(struct work_struct *work); void i915_gem_suspend(struct drm_i915_private *i915); void i915_gem_suspend_late(struct drm_i915_private *i915); +int i915_gem_backup_suspend(struct drm_i915_private *i915); int i915_gem_freeze(struct drm_i915_private *i915); int i915_gem_freeze_late(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index 1f557b2178ed..a016ccec36f3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -80,3 +80,73 @@ err_object_free: i915_gem_object_free(obj); return ERR_PTR(err); } + +/** + * i915_gem_process_region - Iterate over all objects of a region using ops + * to process and optionally skip objects + * @mr: The memory region + * @apply: ops and private data + * + * This function can be used to iterate over the regions object list, + * checking whether to skip objects, and, if not, lock the objects and + * process them using the supplied ops. Note that this function temporarily + * removes objects from the region list while iterating, so that if run + * concurrently with itself may not iterate over all objects. + * + * Return: 0 if successful, negative error code on failure. + */ +int i915_gem_process_region(struct intel_memory_region *mr, + struct i915_gem_apply_to_region *apply) +{ + const struct i915_gem_apply_to_region_ops *ops = apply->ops; + struct drm_i915_gem_object *obj; + struct list_head still_in_list; + int ret = 0; + + /* + * In the future, a non-NULL apply->ww could mean the caller is + * already in a locking transaction and provides its own context. + */ + GEM_WARN_ON(apply->ww); + + INIT_LIST_HEAD(&still_in_list); + mutex_lock(&mr->objects.lock); + for (;;) { + struct i915_gem_ww_ctx ww; + + obj = list_first_entry_or_null(&mr->objects.list, typeof(*obj), + mm.region_link); + if (!obj) + break; + + list_move_tail(&obj->mm.region_link, &still_in_list); + if (!kref_get_unless_zero(&obj->base.refcount)) + continue; + + /* + * Note: Someone else might be migrating the object at this + * point. The object's region is not stable until we lock + * the object. + */ + mutex_unlock(&mr->objects.lock); + apply->ww = &ww; + for_i915_gem_ww(&ww, ret, apply->interruptible) { + ret = i915_gem_object_lock(obj, apply->ww); + if (ret) + continue; + + if (obj->mm.region == mr) + ret = ops->process_obj(apply, obj); + /* Implicit object unlock */ + } + + i915_gem_object_put(obj); + mutex_lock(&mr->objects.lock); + if (ret) + break; + } + list_splice_tail(&still_in_list, &mr->objects.list); + mutex_unlock(&mr->objects.lock); + + return ret; +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.h b/drivers/gpu/drm/i915/gem/i915_gem_region.h index 1008e580a89a..fcaa12d657d4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.h @@ -12,6 +12,41 @@ struct intel_memory_region; struct drm_i915_gem_object; struct sg_table; +struct i915_gem_apply_to_region; + +/** + * struct i915_gem_apply_to_region_ops - ops to use when iterating over all + * region objects. + */ +struct i915_gem_apply_to_region_ops { + /** + * process_obj - Process the current object + * @apply: Embed this for private data. + * @obj: The current object. + * + * Note that if this function is part of a ww transaction, and + * if returns -EDEADLK for one of the objects, it may be + * rerun for that same object in the same pass. + */ + int (*process_obj)(struct i915_gem_apply_to_region *apply, + struct drm_i915_gem_object *obj); +}; + +/** + * struct i915_gem_apply_to_region - Argument to the struct + * i915_gem_apply_to_region_ops functions. + * @ops: The ops for the operation. + * @ww: Locking context used for the transaction. + * @interruptible: Whether to perform object locking interruptible. + * + * This structure is intended to be embedded in a private struct if needed + */ +struct i915_gem_apply_to_region { + const struct i915_gem_apply_to_region_ops *ops; + struct i915_gem_ww_ctx *ww; + u32 interruptible:1; +}; + void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj, struct intel_memory_region *mem); void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj); @@ -22,4 +57,6 @@ i915_gem_object_create_region(struct intel_memory_region *mem, resource_size_t page_size, unsigned int flags); +int i915_gem_process_region(struct intel_memory_region *mr, + struct i915_gem_apply_to_region *apply); #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 11f072193f3b..d77da59fae04 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -182,22 +182,7 @@ rebuild_st: if (i915_gem_object_needs_bit17_swizzle(obj)) i915_gem_object_do_bit_17_swizzle(obj, st); - /* - * EHL and JSL add the 'Bypass LLC' MOCS entry, which should make it - * possible for userspace to bypass the GTT caching bits set by the - * kernel, as per the given object cache_level. This is troublesome - * since the heavy flush we apply when first gathering the pages is - * skipped if the kernel thinks the object is coherent with the GPU. As - * a result it might be possible to bypass the cache and read the - * contents of the page directly, which could be stale data. If it's - * just a case of userspace shooting themselves in the foot then so be - * it, but since i915 takes the stance of always zeroing memory before - * handing it to userspace, we need to prevent this. - * - * By setting cache_dirty here we make the clflush in set_pages - * unconditional on such platforms. - */ - if (IS_JSL_EHL(i915) && obj->flags & I915_BO_ALLOC_USER) + if (i915_gem_object_can_bypass_llc(obj)) obj->cache_dirty = true; __i915_gem_object_set_pages(obj, st, sg_page_sizes); @@ -301,6 +286,8 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages, bool needs_clflush) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); + GEM_BUG_ON(obj->mm.madv == __I915_MADV_PURGED); if (obj->mm.madv == I915_MADV_DONTNEED) @@ -312,6 +299,16 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj, drm_clflush_sg(pages); __start_cpu_write(obj); + /* + * On non-LLC platforms, force the flush-on-acquire if this is ever + * swapped-in. Our async flush path is not trust worthy enough yet(and + * happens in the wrong order), and with some tricks it's conceivable + * for userspace to change the cache-level to I915_CACHE_NONE after the + * pages are swapped-in, and since execbuf binds the object before doing + * the async flush, we have a race window. + */ + if (!HAS_LLC(i915)) + obj->cache_dirty = true; } void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_table *pages) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 2f672f06b169..74a1ffd0d7dd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -10,18 +10,16 @@ #include "intel_memory_region.h" #include "intel_region_ttm.h" +#include "gem/i915_gem_mman.h" #include "gem/i915_gem_object.h" #include "gem/i915_gem_region.h" #include "gem/i915_gem_ttm.h" -#include "gem/i915_gem_mman.h" +#include "gem/i915_gem_ttm_pm.h" + -#include "gt/intel_migrate.h" #include "gt/intel_engine_pm.h" - -#define I915_PL_LMEM0 TTM_PL_PRIV -#define I915_PL_SYSTEM TTM_PL_SYSTEM -#define I915_PL_STOLEN TTM_PL_VRAM -#define I915_PL_GGTT TTM_PL_TT +#include "gt/intel_gt.h" +#include "gt/intel_migrate.h" #define I915_TTM_PRIO_PURGE 0 #define I915_TTM_PRIO_NO_PAGES 1 @@ -64,6 +62,20 @@ static struct ttm_placement i915_sys_placement = { .busy_placement = &sys_placement_flags, }; +/** + * i915_ttm_sys_placement - Return the struct ttm_placement to be + * used for an object in system memory. + * + * Rather than making the struct extern, use this + * function. + * + * Return: A pointer to a static variable for sys placement. + */ +struct ttm_placement *i915_ttm_sys_placement(void) +{ + return &i915_sys_placement; +} + static int i915_ttm_err_to_gem(int err) { /* Fastpath */ @@ -182,7 +194,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && man->use_tt) - page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + page_flags |= TTM_TT_FLAG_ZERO_ALLOC; ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, i915_ttm_select_tt_caching(obj)); @@ -355,8 +367,10 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - if (likely(obj)) + if (likely(obj)) { + __i915_gem_object_pages_fini(obj); i915_ttm_free_cached_io_st(obj); + } } static struct intel_memory_region * @@ -428,6 +442,7 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, static int i915_ttm_accel_move(struct ttm_buffer_object *bo, bool clear, struct ttm_resource *dst_mem, + struct ttm_tt *dst_ttm, struct sg_table *dst_st) { struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915), @@ -437,14 +452,14 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo, struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); struct sg_table *src_st; struct i915_request *rq; - struct ttm_tt *ttm = bo->ttm; + struct ttm_tt *src_ttm = bo->ttm; enum i915_cache_level src_level, dst_level; int ret; - if (!i915->gt.migrate.context) + if (!i915->gt.migrate.context || intel_gt_is_wedged(&i915->gt)) return -EINVAL; - dst_level = i915_ttm_cache_level(i915, dst_mem, ttm); + dst_level = i915_ttm_cache_level(i915, dst_mem, dst_ttm); if (clear) { if (bo->type == ttm_bo_type_kernel) return -EINVAL; @@ -461,10 +476,10 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo, } intel_engine_pm_put(i915->gt.migrate.context->engine); } else { - src_st = src_man->use_tt ? i915_ttm_tt_get_st(ttm) : + src_st = src_man->use_tt ? i915_ttm_tt_get_st(src_ttm) : obj->ttm.cached_io_st; - src_level = i915_ttm_cache_level(i915, bo->resource, ttm); + src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm); intel_engine_pm_get(i915->gt.migrate.context->engine); ret = intel_context_migrate_copy(i915->gt.migrate.context, NULL, src_st->sgl, src_level, @@ -484,11 +499,14 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo, static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear, struct ttm_resource *dst_mem, - struct sg_table *dst_st) + struct ttm_tt *dst_ttm, + struct sg_table *dst_st, + bool allow_accel) { - int ret; + int ret = -EINVAL; - ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_st); + if (allow_accel) + ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm, dst_st); if (ret) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); struct intel_memory_region *dst_reg, *src_reg; @@ -503,7 +521,7 @@ static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear, GEM_BUG_ON(!dst_reg || !src_reg); dst_iter = !cpu_maps_iomem(dst_mem) ? - ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) : + ttm_kmap_iter_tt_init(&_dst_iter.tt, dst_ttm) : ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap, dst_st, dst_reg->region.start); @@ -546,7 +564,7 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, } /* Populate ttm with pages if needed. Typically system memory. */ - if (ttm && (dst_man->use_tt || (ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) { + if (ttm && (dst_man->use_tt || (ttm->page_flags & TTM_TT_FLAG_SWAPPED))) { ret = ttm_tt_populate(bo->bdev, ttm, ctx); if (ret) return ret; @@ -557,8 +575,8 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, return PTR_ERR(dst_st); clear = !cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm)); - if (!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))) - __i915_ttm_move(bo, clear, dst_mem, dst_st); + if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC))) + __i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_st, true); ttm_bo_move_sync_cleanup(bo, dst_mem); i915_ttm_adjust_domains_after_move(obj); @@ -797,12 +815,9 @@ static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) */ static void i915_ttm_delayed_free(struct drm_i915_gem_object *obj) { - if (obj->ttm.created) { - ttm_bo_put(i915_gem_to_ttm(obj)); - } else { - __i915_gem_free_object(obj); - call_rcu(&obj->rcu, __i915_gem_free_object_rcu); - } + GEM_BUG_ON(!obj->ttm.created); + + ttm_bo_put(i915_gem_to_ttm(obj)); } static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) @@ -882,14 +897,19 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - /* This releases all gem object bindings to the backend. */ - __i915_gem_free_object(obj); - i915_gem_object_release_memory_region(obj); mutex_destroy(&obj->ttm.get_io_page.lock); - if (obj->ttm.created) + if (obj->ttm.created) { + i915_ttm_backup_free(obj); + + /* This releases all gem object bindings to the backend. */ + __i915_gem_free_object(obj); + call_rcu(&obj->rcu, __i915_gem_free_object_rcu); + } else { + __i915_gem_object_fini(obj); + } } /** @@ -918,7 +938,11 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, drm_gem_private_object_init(&i915->drm, &obj->base, size); i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags); - i915_gem_object_init_memory_region(obj, mem); + + /* Don't put on a region list until we're either locked or fully initialized. */ + obj->mm.region = intel_memory_region_get(mem); + INIT_LIST_HEAD(&obj->mm.region_link); + i915_gem_object_make_unshrinkable(obj); INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN); mutex_init(&obj->ttm.get_io_page.lock); @@ -945,6 +969,8 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, return i915_ttm_err_to_gem(ret); obj->ttm.created = true; + i915_gem_object_release_memory_region(obj); + i915_gem_object_init_memory_region(obj, mem); i915_ttm_adjust_domains_after_move(obj); i915_ttm_adjust_gem_after_move(obj); i915_gem_object_unlock(obj); @@ -973,3 +999,50 @@ i915_gem_ttm_system_setup(struct drm_i915_private *i915, intel_memory_region_set_name(mr, "system-ttm"); return mr; } + +/** + * i915_gem_obj_copy_ttm - Copy the contents of one ttm-based gem object to + * another + * @dst: The destination object + * @src: The source object + * @allow_accel: Allow using the blitter. Otherwise TTM memcpy is used. + * @intr: Whether to perform waits interruptible: + * + * Note: The caller is responsible for assuring that the underlying + * TTM objects are populated if needed and locked. + * + * Return: Zero on success. Negative error code on error. If @intr == true, + * then it may return -ERESTARTSYS or -EINTR. + */ +int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, + struct drm_i915_gem_object *src, + bool allow_accel, bool intr) +{ + struct ttm_buffer_object *dst_bo = i915_gem_to_ttm(dst); + struct ttm_buffer_object *src_bo = i915_gem_to_ttm(src); + struct ttm_operation_ctx ctx = { + .interruptible = intr, + }; + struct sg_table *dst_st; + int ret; + + assert_object_held(dst); + assert_object_held(src); + + /* + * Sync for now. This will change with async moves. + */ + ret = ttm_bo_wait_ctx(dst_bo, &ctx); + if (!ret) + ret = ttm_bo_wait_ctx(src_bo, &ctx); + if (ret) + return ret; + + dst_st = gpu_binds_iomem(dst_bo->resource) ? + dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo->ttm); + + __i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo->ttm, + dst_st, allow_accel); + + return 0; +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h index 40927f67b6d9..0b7291dd897c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h @@ -46,4 +46,18 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem, resource_size_t size, resource_size_t page_size, unsigned int flags); + +int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, + struct drm_i915_gem_object *src, + bool allow_accel, bool intr); + +/* Internal I915 TTM declarations and definitions below. */ + +#define I915_PL_LMEM0 TTM_PL_PRIV +#define I915_PL_SYSTEM TTM_PL_SYSTEM +#define I915_PL_STOLEN TTM_PL_VRAM +#define I915_PL_GGTT TTM_PL_TT + +struct ttm_placement *i915_ttm_sys_placement(void); + #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c new file mode 100644 index 000000000000..3b6d14b5c604 --- /dev/null +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include +#include + +#include "i915_drv.h" +#include "intel_memory_region.h" +#include "intel_region_ttm.h" + +#include "gem/i915_gem_region.h" +#include "gem/i915_gem_ttm.h" +#include "gem/i915_gem_ttm_pm.h" + +/** + * i915_ttm_backup_free - Free any backup attached to this object + * @obj: The object whose backup is to be freed. + */ +void i915_ttm_backup_free(struct drm_i915_gem_object *obj) +{ + if (obj->ttm.backup) { + i915_gem_object_put(obj->ttm.backup); + obj->ttm.backup = NULL; + } +} + +/** + * struct i915_gem_ttm_pm_apply - Apply-to-region subclass for restore + * @base: The i915_gem_apply_to_region we derive from. + * @allow_gpu: Whether using the gpu blitter is allowed. + * @backup_pinned: On backup, backup also pinned objects. + */ +struct i915_gem_ttm_pm_apply { + struct i915_gem_apply_to_region base; + bool allow_gpu : 1; + bool backup_pinned : 1; +}; + +static int i915_ttm_backup(struct i915_gem_apply_to_region *apply, + struct drm_i915_gem_object *obj) +{ + struct i915_gem_ttm_pm_apply *pm_apply = + container_of(apply, typeof(*pm_apply), base); + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct ttm_buffer_object *backup_bo; + struct drm_i915_private *i915 = + container_of(bo->bdev, typeof(*i915), bdev); + struct drm_i915_gem_object *backup; + struct ttm_operation_ctx ctx = {}; + int err = 0; + + if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup) + return 0; + + if (pm_apply->allow_gpu && i915_gem_object_evictable(obj)) + return ttm_bo_validate(bo, i915_ttm_sys_placement(), &ctx); + + if (!pm_apply->backup_pinned || + (pm_apply->allow_gpu && (obj->flags & I915_BO_ALLOC_PM_EARLY))) + return 0; + + if (obj->flags & I915_BO_ALLOC_PM_VOLATILE) + return 0; + + backup = i915_gem_object_create_shmem(i915, obj->base.size); + if (IS_ERR(backup)) + return PTR_ERR(backup); + + err = i915_gem_object_lock(backup, apply->ww); + if (err) + goto out_no_lock; + + backup_bo = i915_gem_to_ttm(backup); + err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx); + if (err) + goto out_no_populate; + + err = i915_gem_obj_copy_ttm(backup, obj, pm_apply->allow_gpu, false); + GEM_WARN_ON(err); + + obj->ttm.backup = backup; + return 0; + +out_no_populate: + i915_gem_ww_unlock_single(backup); +out_no_lock: + i915_gem_object_put(backup); + + return err; +} + +static int i915_ttm_recover(struct i915_gem_apply_to_region *apply, + struct drm_i915_gem_object *obj) +{ + i915_ttm_backup_free(obj); + return 0; +} + +/** + * i915_ttm_recover_region - Free the backup of all objects of a region + * @mr: The memory region + * + * Checks all objects of a region if there is backup attached and if so + * frees that backup. Typically this is called to recover after a partially + * performed backup. + */ +void i915_ttm_recover_region(struct intel_memory_region *mr) +{ + static const struct i915_gem_apply_to_region_ops recover_ops = { + .process_obj = i915_ttm_recover, + }; + struct i915_gem_apply_to_region apply = {.ops = &recover_ops}; + int ret; + + ret = i915_gem_process_region(mr, &apply); + GEM_WARN_ON(ret); +} + +/** + * i915_ttm_backup_region - Back up all objects of a region to smem. + * @mr: The memory region + * @allow_gpu: Whether to allow the gpu blitter for this backup. + * @backup_pinned: Backup also pinned objects. + * + * Loops over all objects of a region and either evicts them if they are + * evictable or backs them up using a backup object if they are pinned. + * + * Return: Zero on success. Negative error code on error. + */ +int i915_ttm_backup_region(struct intel_memory_region *mr, u32 flags) +{ + static const struct i915_gem_apply_to_region_ops backup_ops = { + .process_obj = i915_ttm_backup, + }; + struct i915_gem_ttm_pm_apply pm_apply = { + .base = {.ops = &backup_ops}, + .allow_gpu = flags & I915_TTM_BACKUP_ALLOW_GPU, + .backup_pinned = flags & I915_TTM_BACKUP_PINNED, + }; + + return i915_gem_process_region(mr, &pm_apply.base); +} + +static int i915_ttm_restore(struct i915_gem_apply_to_region *apply, + struct drm_i915_gem_object *obj) +{ + struct i915_gem_ttm_pm_apply *pm_apply = + container_of(apply, typeof(*pm_apply), base); + struct drm_i915_gem_object *backup = obj->ttm.backup; + struct ttm_buffer_object *backup_bo = i915_gem_to_ttm(backup); + struct ttm_operation_ctx ctx = {}; + int err; + + if (!backup) + return 0; + + if (!pm_apply->allow_gpu && !(obj->flags & I915_BO_ALLOC_PM_EARLY)) + return 0; + + err = i915_gem_object_lock(backup, apply->ww); + if (err) + return err; + + /* Content may have been swapped. */ + err = ttm_tt_populate(backup_bo->bdev, backup_bo->ttm, &ctx); + if (!err) { + err = i915_gem_obj_copy_ttm(obj, backup, pm_apply->allow_gpu, + false); + GEM_WARN_ON(err); + + obj->ttm.backup = NULL; + err = 0; + } + + i915_gem_ww_unlock_single(backup); + + if (!err) + i915_gem_object_put(backup); + + return err; +} + +/** + * i915_ttm_restore_region - Restore backed-up objects of a region from smem. + * @mr: The memory region + * @allow_gpu: Whether to allow the gpu blitter to recover. + * + * Loops over all objects of a region and if they are backed-up, restores + * them from smem. + * + * Return: Zero on success. Negative error code on error. + */ +int i915_ttm_restore_region(struct intel_memory_region *mr, u32 flags) +{ + static const struct i915_gem_apply_to_region_ops restore_ops = { + .process_obj = i915_ttm_restore, + }; + struct i915_gem_ttm_pm_apply pm_apply = { + .base = {.ops = &restore_ops}, + .allow_gpu = flags & I915_TTM_BACKUP_ALLOW_GPU, + }; + + return i915_gem_process_region(mr, &pm_apply.base); +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.h new file mode 100644 index 000000000000..25ed67a31571 --- /dev/null +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef _I915_GEM_TTM_PM_H_ +#define _I915_GEM_TTM_PM_H_ + +#include + +struct intel_memory_region; +struct drm_i915_gem_object; + +#define I915_TTM_BACKUP_ALLOW_GPU BIT(0) +#define I915_TTM_BACKUP_PINNED BIT(1) + +int i915_ttm_backup_region(struct intel_memory_region *mr, u32 flags); + +void i915_ttm_recover_region(struct intel_memory_region *mr); + +int i915_ttm_restore_region(struct intel_memory_region *mr, u32 flags); + +/* Internal I915 TTM functions below. */ +void i915_ttm_backup_free(struct drm_i915_gem_object *obj); + +#endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 8ea0fa665e53..3173c9f9a040 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -165,8 +165,11 @@ alloc_table: goto err; } - sg_page_sizes = i915_sg_dma_sizes(st->sgl); + WARN_ON_ONCE(!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE)); + if (i915_gem_object_can_bypass_llc(obj)) + obj->cache_dirty = true; + sg_page_sizes = i915_sg_dma_sizes(st->sgl); __i915_gem_object_set_pages(obj, st, sg_page_sizes); return 0; @@ -546,7 +549,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev, return -ENOMEM; drm_gem_private_object_init(dev, &obj->base, args->user_size); - i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class, 0); + i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class, + I915_BO_ALLOC_USER); obj->mem_flags = I915_BO_FLAG_STRUCT_PAGE; obj->read_domains = I915_GEM_DOMAIN_CPU; obj->write_domain = I915_GEM_DOMAIN_CPU; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index 0827634c842c..b2003133deaf 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -136,6 +136,8 @@ static void put_huge_pages(struct drm_i915_gem_object *obj, huge_pages_free_pages(pages); obj->mm.dirty = false; + + __start_cpu_write(obj); } static const struct drm_i915_gem_object_ops huge_page_ops = { @@ -152,6 +154,7 @@ huge_pages_object(struct drm_i915_private *i915, { static struct lock_class_key lock_class; struct drm_i915_gem_object *obj; + unsigned int cache_level; GEM_BUG_ON(!size); GEM_BUG_ON(!IS_ALIGNED(size, BIT(__ffs(page_mask)))); @@ -173,7 +176,9 @@ huge_pages_object(struct drm_i915_private *i915, obj->write_domain = I915_GEM_DOMAIN_CPU; obj->read_domains = I915_GEM_DOMAIN_CPU; - obj->cache_level = I915_CACHE_NONE; + + cache_level = HAS_LLC(i915) ? I915_CACHE_LLC : I915_CACHE_NONE; + i915_gem_object_set_cache_coherency(obj, cache_level); obj->mm.page_mask = page_mask; @@ -1589,7 +1594,8 @@ static int igt_shrink_thp(void *arg) i915_gem_shrink(NULL, i915, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | - I915_SHRINK_ACTIVE); + I915_SHRINK_ACTIVE | + I915_SHRINK_WRITEBACK); if (should_swap == i915_gem_object_has_pages(obj)) { pr_err("unexpected pages mismatch, should_swap=%s\n", yesno(should_swap)); @@ -1645,7 +1651,7 @@ int i915_gem_huge_page_mock_selftests(void) mkwrite_device_info(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL; mkwrite_device_info(dev_priv)->ppgtt_size = 48; - ppgtt = i915_ppgtt_create(&dev_priv->gt); + ppgtt = i915_ppgtt_create(&dev_priv->gt, 0); if (IS_ERR(ppgtt)) { err = PTR_ERR(ppgtt); goto out_unlock; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index ecbcbb86ae1e..8402ed925a69 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -17,13 +17,20 @@ #include "huge_gem_object.h" #include "mock_context.h" +enum client_tiling { + CLIENT_TILING_LINEAR, + CLIENT_TILING_X, + CLIENT_TILING_Y, + CLIENT_NUM_TILING_TYPES +}; + #define WIDTH 512 #define HEIGHT 32 struct blit_buffer { struct i915_vma *vma; u32 start_val; - u32 tiling; + enum client_tiling tiling; }; struct tiled_blits { @@ -53,9 +60,9 @@ static int prepare_blit(const struct tiled_blits *t, *cs++ = MI_LOAD_REGISTER_IMM(1); *cs++ = i915_mmio_reg_offset(BCS_SWCTRL); cmd = (BCS_SRC_Y | BCS_DST_Y) << 16; - if (src->tiling == I915_TILING_Y) + if (src->tiling == CLIENT_TILING_Y) cmd |= BCS_SRC_Y; - if (dst->tiling == I915_TILING_Y) + if (dst->tiling == CLIENT_TILING_Y) cmd |= BCS_DST_Y; *cs++ = cmd; @@ -172,7 +179,7 @@ static int tiled_blits_create_buffers(struct tiled_blits *t, t->buffers[i].vma = vma; t->buffers[i].tiling = - i915_prandom_u32_max_state(I915_TILING_Y + 1, prng); + i915_prandom_u32_max_state(CLIENT_TILING_Y + 1, prng); } return 0; @@ -197,17 +204,17 @@ static u64 swizzle_bit(unsigned int bit, u64 offset) static u64 tiled_offset(const struct intel_gt *gt, u64 v, unsigned int stride, - unsigned int tiling) + enum client_tiling tiling) { unsigned int swizzle; u64 x, y; - if (tiling == I915_TILING_NONE) + if (tiling == CLIENT_TILING_LINEAR) return v; y = div64_u64_rem(v, stride, &x); - if (tiling == I915_TILING_X) { + if (tiling == CLIENT_TILING_X) { v = div64_u64_rem(y, 8, &y) * stride * 8; v += y * 512; v += div64_u64_rem(x, 512, &x) << 12; @@ -244,12 +251,12 @@ static u64 tiled_offset(const struct intel_gt *gt, return v; } -static const char *repr_tiling(int tiling) +static const char *repr_tiling(enum client_tiling tiling) { switch (tiling) { - case I915_TILING_NONE: return "linear"; - case I915_TILING_X: return "X"; - case I915_TILING_Y: return "Y"; + case CLIENT_TILING_LINEAR: return "linear"; + case CLIENT_TILING_X: return "X"; + case CLIENT_TILING_Y: return "Y"; default: return "unknown"; } } diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index a2c34e5a1c54..6d30cdfa80f3 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -903,7 +903,9 @@ static int __igt_mmap(struct drm_i915_private *i915, pr_debug("igt_mmap(%s, %d) @ %lx\n", obj->mm.region->name, type, addr); + mmap_read_lock(current->mm); area = vma_lookup(current->mm, addr); + mmap_read_unlock(current->mm); if (!area) { pr_err("%s: Did not create a vm_area_struct for the mmap\n", obj->mm.region->name); diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c index 067d68a6fe4c..c0a8ef368044 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c @@ -88,7 +88,7 @@ live_context(struct drm_i915_private *i915, struct file *file) return ERR_CAST(pc); ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) return ctx; @@ -163,7 +163,7 @@ kernel_context(struct drm_i915_private *i915, } ctx = i915_gem_create_context(i915, pc); - proto_context_close(pc); + proto_context_close(i915, pc); if (IS_ERR(ctx)) return ctx; diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.h b/drivers/gpu/drm/i915/gt/debugfs_engines.h deleted file mode 100644 index f69257eaa1cc..000000000000 --- a/drivers/gpu/drm/i915/gt/debugfs_engines.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2019 Intel Corporation - */ - -#ifndef DEBUGFS_ENGINES_H -#define DEBUGFS_ENGINES_H - -struct intel_gt; -struct dentry; - -void debugfs_engines_register(struct intel_gt *gt, struct dentry *root); - -#endif /* DEBUGFS_ENGINES_H */ diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.c b/drivers/gpu/drm/i915/gt/debugfs_gt.c deleted file mode 100644 index 591eb60785db..000000000000 --- a/drivers/gpu/drm/i915/gt/debugfs_gt.c +++ /dev/null @@ -1,47 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2019 Intel Corporation - */ - -#include - -#include "debugfs_engines.h" -#include "debugfs_gt.h" -#include "debugfs_gt_pm.h" -#include "intel_sseu_debugfs.h" -#include "uc/intel_uc_debugfs.h" -#include "i915_drv.h" - -void debugfs_gt_register(struct intel_gt *gt) -{ - struct dentry *root; - - if (!gt->i915->drm.primary->debugfs_root) - return; - - root = debugfs_create_dir("gt", gt->i915->drm.primary->debugfs_root); - if (IS_ERR(root)) - return; - - debugfs_engines_register(gt, root); - debugfs_gt_pm_register(gt, root); - intel_sseu_debugfs_register(gt, root); - - intel_uc_debugfs_register(>->uc, root); -} - -void intel_gt_debugfs_register_files(struct dentry *root, - const struct debugfs_gt_file *files, - unsigned long count, void *data) -{ - while (count--) { - umode_t mode = files->fops->write ? 0644 : 0444; - - if (!files->eval || files->eval(data)) - debugfs_create_file(files->name, - mode, root, data, - files->fops); - - files++; - } -} diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h deleted file mode 100644 index 4cf5f5c9da7d..000000000000 --- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2019 Intel Corporation - */ - -#ifndef DEBUGFS_GT_PM_H -#define DEBUGFS_GT_PM_H - -struct intel_gt; -struct dentry; - -void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root); - -#endif /* DEBUGFS_GT_PM_H */ diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index 1aee5e6b1b23..890191f286e3 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -429,7 +429,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) mutex_init(&ppgtt->flush); mutex_init(&ppgtt->pin_mutex); - ppgtt_init(&ppgtt->base, gt); + ppgtt_init(&ppgtt->base, gt, 0); ppgtt->base.vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen6_pte_t)); ppgtt->base.vm.top = 1; diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 6a5af995f5b1..037a9a6e4889 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -753,7 +753,8 @@ err_pd: * space. * */ -struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt) +struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, + unsigned long lmem_pt_obj_flags) { struct i915_ppgtt *ppgtt; int err; @@ -762,7 +763,7 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt) if (!ppgtt) return ERR_PTR(-ENOMEM); - ppgtt_init(ppgtt, gt); + ppgtt_init(ppgtt, gt, lmem_pt_obj_flags); ppgtt->vm.top = i915_vm_is_4lvl(&ppgtt->vm) ? 3 : 2; ppgtt->vm.pd_shift = ilog2(SZ_4K * SZ_4K / sizeof(gen8_pte_t)); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h index b9028c2ad3c7..f541d19264b4 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h @@ -12,7 +12,9 @@ struct i915_address_space; struct intel_gt; enum i915_cache_level; -struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt); +struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, + unsigned long lmem_pt_obj_flags); + u64 gen8_ggtt_pte_encode(dma_addr_t addr, enum i915_cache_level level, u32 flags); diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index c35c151f652f..5634d14052bc 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -240,6 +240,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce, if (err) goto err_post_unpin; + intel_engine_pm_might_get(ce->engine); + if (unlikely(intel_context_is_closed(ce))) { err = -ENOENT; goto err_unlock; @@ -400,6 +402,10 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) ce->guc_id.id = GUC_INVALID_LRC_ID; INIT_LIST_HEAD(&ce->guc_id.link); + INIT_LIST_HEAD(&ce->destroyed_link); + + INIT_LIST_HEAD(&ce->parallel.child_list); + /* * Initialize fence to be complete as this is expected to be complete * unless there is a pending schedule disable outstanding. @@ -414,12 +420,20 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) void intel_context_fini(struct intel_context *ce) { + struct intel_context *child, *next; + if (ce->timeline) intel_timeline_put(ce->timeline); i915_vm_put(ce->vm); + /* Need to put the creation ref for the children */ + if (intel_context_is_parent(ce)) + for_each_child_safe(ce, child, next) + intel_context_put(child); + mutex_destroy(&ce->pin_mutex); i915_active_fini(&ce->active); + i915_sw_fence_fini(&ce->guc_state.blocked); } void i915_context_module_exit(void) @@ -515,24 +529,53 @@ retry: struct i915_request *intel_context_find_active_request(struct intel_context *ce) { + struct intel_context *parent = intel_context_to_parent(ce); struct i915_request *rq, *active = NULL; unsigned long flags; GEM_BUG_ON(!intel_engine_uses_guc(ce->engine)); - spin_lock_irqsave(&ce->guc_state.lock, flags); - list_for_each_entry_reverse(rq, &ce->guc_state.requests, + /* + * We search the parent list to find an active request on the submitted + * context. The parent list contains the requests for all the contexts + * in the relationship so we have to do a compare of each request's + * context. + */ + spin_lock_irqsave(&parent->guc_state.lock, flags); + list_for_each_entry_reverse(rq, &parent->guc_state.requests, sched.link) { + if (rq->context != ce) + continue; if (i915_request_completed(rq)) break; active = rq; } - spin_unlock_irqrestore(&ce->guc_state.lock, flags); + spin_unlock_irqrestore(&parent->guc_state.lock, flags); return active; } +void intel_context_bind_parent_child(struct intel_context *parent, + struct intel_context *child) +{ + /* + * Callers responsibility to validate that this function is used + * correctly but we use GEM_BUG_ON here ensure that they do. + */ + GEM_BUG_ON(!intel_engine_uses_guc(parent->engine)); + GEM_BUG_ON(intel_context_is_pinned(parent)); + GEM_BUG_ON(intel_context_is_child(parent)); + GEM_BUG_ON(intel_context_is_pinned(child)); + GEM_BUG_ON(intel_context_is_child(child)); + GEM_BUG_ON(intel_context_is_parent(child)); + + parent->parallel.child_index = parent->parallel.number_children++; + list_add_tail(&child->parallel.child_link, + &parent->parallel.child_list); + child->parallel.parent = parent; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_context.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index c41098950746..246c37d72cd7 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -44,6 +44,54 @@ void intel_context_free(struct intel_context *ce); int intel_context_reconfigure_sseu(struct intel_context *ce, const struct intel_sseu sseu); +#define PARENT_SCRATCH_SIZE PAGE_SIZE + +static inline bool intel_context_is_child(struct intel_context *ce) +{ + return !!ce->parallel.parent; +} + +static inline bool intel_context_is_parent(struct intel_context *ce) +{ + return !!ce->parallel.number_children; +} + +static inline bool intel_context_is_pinned(struct intel_context *ce); + +static inline struct intel_context * +intel_context_to_parent(struct intel_context *ce) +{ + if (intel_context_is_child(ce)) { + /* + * The parent holds ref count to the child so it is always safe + * for the parent to access the child, but the child has a + * pointer to the parent without a ref. To ensure this is safe + * the child should only access the parent pointer while the + * parent is pinned. + */ + GEM_BUG_ON(!intel_context_is_pinned(ce->parallel.parent)); + + return ce->parallel.parent; + } else { + return ce; + } +} + +static inline bool intel_context_is_parallel(struct intel_context *ce) +{ + return intel_context_is_child(ce) || intel_context_is_parent(ce); +} + +void intel_context_bind_parent_child(struct intel_context *parent, + struct intel_context *child); + +#define for_each_child(parent, ce)\ + list_for_each_entry(ce, &(parent)->parallel.child_list,\ + parallel.child_link) +#define for_each_child_safe(parent, ce, cn)\ + list_for_each_entry_safe(ce, cn, &(parent)->parallel.child_list,\ + parallel.child_link) + /** * intel_context_lock_pinned - Stablises the 'pinned' status of the HW context * @ce - the context @@ -193,7 +241,13 @@ intel_context_timeline_lock(struct intel_context *ce) struct intel_timeline *tl = ce->timeline; int err; - err = mutex_lock_interruptible(&tl->mutex); + if (intel_context_is_parent(ce)) + err = mutex_lock_interruptible_nested(&tl->mutex, 0); + else if (intel_context_is_child(ce)) + err = mutex_lock_interruptible_nested(&tl->mutex, + ce->parallel.child_index + 1); + else + err = mutex_lock_interruptible(&tl->mutex); if (err) return ERR_PTR(err); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 930569a1a01f..9e0177dc5484 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -55,9 +55,13 @@ struct intel_context_ops { void (*reset)(struct intel_context *ce); void (*destroy)(struct kref *kref); - /* virtual engine/context interface */ + /* virtual/parallel engine/context interface */ struct intel_context *(*create_virtual)(struct intel_engine_cs **engine, - unsigned int count); + unsigned int count, + unsigned long flags); + struct intel_context *(*create_parallel)(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width); struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine, unsigned int sibling); }; @@ -113,6 +117,7 @@ struct intel_context { #define CONTEXT_NOPREEMPT 8 #define CONTEXT_LRCA_DIRTY 9 #define CONTEXT_GUC_INIT 10 +#define CONTEXT_PERMA_PIN 11 struct { u64 timeout_us; @@ -153,6 +158,14 @@ struct intel_context { /** sseu: Control eu/slice partitioning */ struct intel_sseu sseu; + /** + * pinned_contexts_link: List link for the engine's pinned contexts. + * This is only used if this is a perma-pinned kernel context and + * the list is assumed to only be manipulated during driver load + * or unload time so no mutex protection currently. + */ + struct list_head pinned_contexts_link; + u8 wa_bb_page; /* if set, page num reserved for context workarounds */ struct { @@ -189,22 +202,80 @@ struct intel_context { struct { /** * @id: handle which is used to uniquely identify this context - * with the GuC, protected by guc->contexts_lock + * with the GuC, protected by guc->submission_state.lock */ u16 id; /** * @ref: the number of references to the guc_id, when * transitioning in and out of zero protected by - * guc->contexts_lock + * guc->submission_state.lock */ atomic_t ref; /** * @link: in guc->guc_id_list when the guc_id has no refs but is - * still valid, protected by guc->contexts_lock + * still valid, protected by guc->submission_state.lock */ struct list_head link; } guc_id; + /** + * @destroyed_link: link in guc->submission_state.destroyed_contexts, in + * list when context is pending to be destroyed (deregistered with the + * GuC), protected by guc->submission_state.lock + */ + struct list_head destroyed_link; + + /** @parallel: sub-structure for parallel submission members */ + struct { + union { + /** + * @child_list: parent's list of children + * contexts, no protection as immutable after context + * creation + */ + struct list_head child_list; + /** + * @child_link: child's link into parent's list of + * children + */ + struct list_head child_link; + }; + /** @parent: pointer to parent if child */ + struct intel_context *parent; + /** + * @last_rq: last request submitted on a parallel context, used + * to insert submit fences between requests in the parallel + * context + */ + struct i915_request *last_rq; + /** + * @fence_context: fence context composite fence when doing + * parallel submission + */ + u64 fence_context; + /** + * @seqno: seqno for composite fence when doing parallel + * submission + */ + u32 seqno; + /** @number_children: number of children if parent */ + u8 number_children; + /** @child_index: index into child_list if child */ + u8 child_index; + /** @guc: GuC specific members for parallel submission */ + struct { + /** @wqi_head: head pointer in work queue */ + u16 wqi_head; + /** @wqi_tail: tail pointer in work queue */ + u16 wqi_tail; + /** + * @parent_page: page in context state (ce->state) used + * by parent for work queue, process descriptor + */ + u8 parent_page; + } guc; + } parallel; + #ifdef CONFIG_DRM_I915_SELFTEST /** * @drop_schedule_enable: Force drop of schedule enable G2H for selftest diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 87579affb952..08559ace0ada 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -2,6 +2,7 @@ #ifndef _INTEL_RINGBUFFER_H_ #define _INTEL_RINGBUFFER_H_ +#include #include #include @@ -175,6 +176,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value) #define I915_GEM_HWS_SEQNO 0x40 #define I915_GEM_HWS_SEQNO_ADDR (I915_GEM_HWS_SEQNO * sizeof(u32)) #define I915_GEM_HWS_MIGRATE (0x42 * sizeof(u32)) +#define I915_GEM_HWS_PXP 0x60 +#define I915_GEM_HWS_PXP_ADDR (I915_GEM_HWS_PXP * sizeof(u32)) #define I915_GEM_HWS_SCRATCH 0x80 #define I915_HWS_CSB_BUF0_INDEX 0x10 @@ -273,15 +276,25 @@ static inline bool intel_engine_uses_guc(const struct intel_engine_cs *engine) static inline bool intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) { - if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) + if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT) return false; return intel_engine_has_preemption(engine); } +#define FORCE_VIRTUAL BIT(0) struct intel_context * intel_engine_create_virtual(struct intel_engine_cs **siblings, - unsigned int count); + unsigned int count, unsigned long flags); + +static inline struct intel_context * +intel_engine_create_parallel(struct intel_engine_cs **engines, + unsigned int num_engines, + unsigned int width) +{ + GEM_BUG_ON(!engines[0]->cops->create_parallel); + return engines[0]->cops->create_parallel(engines, num_engines, width); +} static inline bool intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) @@ -300,7 +313,7 @@ intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) static inline bool intel_engine_has_heartbeat(const struct intel_engine_cs *engine) { - if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) + if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL) return false; if (intel_engine_is_virtual(engine)) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 332efea696a5..ff6753ccb129 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -290,7 +290,8 @@ static void nop_irq_handler(struct intel_engine_cs *engine, u16 iir) GEM_DEBUG_WARN_ON(iir); } -static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) +static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, + u8 logical_instance) { const struct engine_info *info = &intel_engines[id]; struct drm_i915_private *i915 = gt->i915; @@ -320,6 +321,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES); + INIT_LIST_HEAD(&engine->pinned_contexts_list); engine->id = id; engine->legacy_idx = INVALID_ENGINE; engine->mask = BIT(id); @@ -334,6 +336,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) engine->class = info->class; engine->instance = info->instance; + engine->logical_mask = BIT(logical_instance); __sprint_engine_name(engine); engine->props.heartbeat_interval_ms = @@ -398,7 +401,8 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine) engine->uabi_capabilities |= I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC; } else if (engine->class == VIDEO_ENHANCEMENT_CLASS) { - if (GRAPHICS_VER(i915) >= 9) + if (GRAPHICS_VER(i915) >= 9 && + engine->gt->info.sfc_mask & BIT(engine->instance)) engine->uabi_capabilities |= I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC; } @@ -474,18 +478,25 @@ void intel_engines_free(struct intel_gt *gt) } static -bool gen11_vdbox_has_sfc(struct drm_i915_private *i915, +bool gen11_vdbox_has_sfc(struct intel_gt *gt, unsigned int physical_vdbox, unsigned int logical_vdbox, u16 vdbox_mask) { + struct drm_i915_private *i915 = gt->i915; + /* * In Gen11, only even numbered logical VDBOXes are hooked * up to an SFC (Scaler & Format Converter) unit. * In Gen12, Even numbered physical instance always are connected * to an SFC. Odd numbered physical instances have SFC only if * previous even instance is fused off. + * + * Starting with Xe_HP, there's also a dedicated SFC_ENABLE field + * in the fuse register that tells us whether a specific SFC is present. */ - if (GRAPHICS_VER(i915) == 12) + if ((gt->info.sfc_mask & BIT(physical_vdbox / 2)) == 0) + return false; + else if (GRAPHICS_VER(i915) == 12) return (physical_vdbox % 2 == 0) || !(BIT(physical_vdbox - 1) & vdbox_mask); else if (GRAPHICS_VER(i915) == 11) @@ -512,7 +523,7 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) struct intel_uncore *uncore = gt->uncore; unsigned int logical_vdbox = 0; unsigned int i; - u32 media_fuse; + u32 media_fuse, fuse1; u16 vdbox_mask; u16 vebox_mask; @@ -534,6 +545,13 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) vebox_mask = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >> GEN11_GT_VEBOX_DISABLE_SHIFT; + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { + fuse1 = intel_uncore_read(uncore, HSW_PAVP_FUSE1); + gt->info.sfc_mask = REG_FIELD_GET(XEHP_SFC_ENABLE_MASK, fuse1); + } else { + gt->info.sfc_mask = ~0; + } + for (i = 0; i < I915_MAX_VCS; i++) { if (!HAS_ENGINE(gt, _VCS(i))) { vdbox_mask &= ~BIT(i); @@ -546,7 +564,7 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) continue; } - if (gen11_vdbox_has_sfc(i915, i, logical_vdbox, vdbox_mask)) + if (gen11_vdbox_has_sfc(gt, i, logical_vdbox, vdbox_mask)) gt->info.vdbox_sfc_access |= BIT(i); logical_vdbox++; } @@ -572,6 +590,37 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) return info->engine_mask; } +static void populate_logical_ids(struct intel_gt *gt, u8 *logical_ids, + u8 class, const u8 *map, u8 num_instances) +{ + int i, j; + u8 current_logical_id = 0; + + for (j = 0; j < num_instances; ++j) { + for (i = 0; i < ARRAY_SIZE(intel_engines); ++i) { + if (!HAS_ENGINE(gt, i) || + intel_engines[i].class != class) + continue; + + if (intel_engines[i].instance == map[j]) { + logical_ids[intel_engines[i].instance] = + current_logical_id++; + break; + } + } + } +} + +static void setup_logical_ids(struct intel_gt *gt, u8 *logical_ids, u8 class) +{ + int i; + u8 map[MAX_ENGINE_INSTANCE + 1]; + + for (i = 0; i < MAX_ENGINE_INSTANCE + 1; ++i) + map[i] = i; + populate_logical_ids(gt, logical_ids, class, map, ARRAY_SIZE(map)); +} + /** * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers * @gt: pointer to struct intel_gt @@ -583,7 +632,8 @@ int intel_engines_init_mmio(struct intel_gt *gt) struct drm_i915_private *i915 = gt->i915; const unsigned int engine_mask = init_engine_mask(gt); unsigned int mask = 0; - unsigned int i; + unsigned int i, class; + u8 logical_ids[MAX_ENGINE_INSTANCE + 1]; int err; drm_WARN_ON(&i915->drm, engine_mask == 0); @@ -593,15 +643,23 @@ int intel_engines_init_mmio(struct intel_gt *gt) if (i915_inject_probe_failure(i915)) return -ENODEV; - for (i = 0; i < ARRAY_SIZE(intel_engines); i++) { - if (!HAS_ENGINE(gt, i)) - continue; + for (class = 0; class < MAX_ENGINE_CLASS + 1; ++class) { + setup_logical_ids(gt, logical_ids, class); - err = intel_engine_setup(gt, i); - if (err) - goto cleanup; + for (i = 0; i < ARRAY_SIZE(intel_engines); ++i) { + u8 instance = intel_engines[i].instance; - mask |= BIT(i); + if (intel_engines[i].class != class || + !HAS_ENGINE(gt, i)) + continue; + + err = intel_engine_setup(gt, i, + logical_ids[instance]); + if (err) + goto cleanup; + + mask |= BIT(i); + } } /* @@ -875,6 +933,8 @@ intel_engine_create_pinned_context(struct intel_engine_cs *engine, return ERR_PTR(err); } + list_add_tail(&ce->pinned_contexts_link, &engine->pinned_contexts_list); + /* * Give our perma-pinned kernel timelines a separate lockdep class, * so that we can use them from within the normal user timelines @@ -897,6 +957,7 @@ void intel_engine_destroy_pinned_context(struct intel_context *ce) list_del(&ce->timeline->engine_link); mutex_unlock(&hwsp->vm->mutex); + list_del(&ce->pinned_contexts_link); intel_context_unpin(ce); intel_context_put(ce); } @@ -1892,16 +1953,16 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) struct intel_context * intel_engine_create_virtual(struct intel_engine_cs **siblings, - unsigned int count) + unsigned int count, unsigned long flags) { if (count == 0) return ERR_PTR(-EINVAL); - if (count == 1) + if (count == 1 && !(flags & FORCE_VIRTUAL)) return intel_context_create(siblings[0]); GEM_BUG_ON(!siblings[0]->cops->create_virtual); - return siblings[0]->cops->create_virtual(siblings, count); + return siblings[0]->cops->create_virtual(siblings, count, flags); } struct i915_request * diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index 74775ae961b2..a3698f611f45 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -207,7 +207,7 @@ out: void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine) { - if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) + if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL) return; next_heartbeat(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 1f07ac4e0672..a1334b48dde7 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -162,6 +162,19 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine) unsigned long flags; bool result = true; + /* + * This is execlist specific behaviour intended to ensure the GPU is + * idle by switching to a known 'safe' context. With GuC submission, the + * same idle guarantee is achieved by other means (disabling + * scheduling). Further, switching to a 'safe' context has no effect + * with GuC submission as the scheduler can just switch back again. + * + * FIXME: Move this backend scheduler specific behaviour into the + * scheduler backend. + */ + if (intel_engine_uses_guc(engine)) + return true; + /* GPU is pointing to the void, as good as in the kernel context. */ if (intel_gt_is_wedged(engine->gt)) return true; @@ -298,6 +311,29 @@ void intel_engine_init__pm(struct intel_engine_cs *engine) intel_engine_init_heartbeat(engine); } +/** + * intel_engine_reset_pinned_contexts - Reset the pinned contexts of + * an engine. + * @engine: The engine whose pinned contexts we want to reset. + * + * Typically the pinned context LMEM images lose or get their content + * corrupted on suspend. This function resets their images. + */ +void intel_engine_reset_pinned_contexts(struct intel_engine_cs *engine) +{ + struct intel_context *ce; + + list_for_each_entry(ce, &engine->pinned_contexts_list, + pinned_contexts_link) { + /* kernel context gets reset at __engine_unpark() */ + if (ce == engine->kernel_context) + continue; + + dbg_poison_ce(ce); + ce->ops->reset(ce); + } +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_engine_pm.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index 70ea46d6cfb0..d68675925b79 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -6,9 +6,11 @@ #ifndef INTEL_ENGINE_PM_H #define INTEL_ENGINE_PM_H +#include "i915_drv.h" #include "i915_request.h" #include "intel_engine_types.h" #include "intel_wakeref.h" +#include "intel_gt_pm.h" static inline bool intel_engine_pm_is_awake(const struct intel_engine_cs *engine) @@ -16,6 +18,11 @@ intel_engine_pm_is_awake(const struct intel_engine_cs *engine) return intel_wakeref_is_active(&engine->wakeref); } +static inline void __intel_engine_pm_get(struct intel_engine_cs *engine) +{ + __intel_wakeref_get(&engine->wakeref); +} + static inline void intel_engine_pm_get(struct intel_engine_cs *engine) { intel_wakeref_get(&engine->wakeref); @@ -26,6 +33,21 @@ static inline bool intel_engine_pm_get_if_awake(struct intel_engine_cs *engine) return intel_wakeref_get_if_active(&engine->wakeref); } +static inline void intel_engine_pm_might_get(struct intel_engine_cs *engine) +{ + if (!intel_engine_is_virtual(engine)) { + intel_wakeref_might_get(&engine->wakeref); + } else { + struct intel_gt *gt = engine->gt; + struct intel_engine_cs *tengine; + intel_engine_mask_t tmp, mask = engine->mask; + + for_each_engine_masked(tengine, gt, mask, tmp) + intel_wakeref_might_get(&tengine->wakeref); + } + intel_gt_pm_might_get(engine->gt); +} + static inline void intel_engine_pm_put(struct intel_engine_cs *engine) { intel_wakeref_put(&engine->wakeref); @@ -47,6 +69,21 @@ static inline void intel_engine_pm_flush(struct intel_engine_cs *engine) intel_wakeref_unlock_wait(&engine->wakeref); } +static inline void intel_engine_pm_might_put(struct intel_engine_cs *engine) +{ + if (!intel_engine_is_virtual(engine)) { + intel_wakeref_might_put(&engine->wakeref); + } else { + struct intel_gt *gt = engine->gt; + struct intel_engine_cs *tengine; + intel_engine_mask_t tmp, mask = engine->mask; + + for_each_engine_masked(tengine, gt, mask, tmp) + intel_wakeref_might_put(&tengine->wakeref); + } + intel_gt_pm_might_put(engine->gt); +} + static inline struct i915_request * intel_engine_create_kernel_request(struct intel_engine_cs *engine) { @@ -69,4 +106,6 @@ intel_engine_create_kernel_request(struct intel_engine_cs *engine) void intel_engine_init__pm(struct intel_engine_cs *engine); +void intel_engine_reset_pinned_contexts(struct intel_engine_cs *engine); + #endif /* INTEL_ENGINE_PM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index bfbfe53c23dd..e0f773585c29 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -269,6 +269,13 @@ struct intel_engine_cs { unsigned int guc_id; intel_engine_mask_t mask; + /** + * @logical_mask: logical mask of engine, reported to user space via + * query IOCTL and used to communicate with the GuC in logical space. + * The logical instance of a physical engine can change based on product + * and fusing. + */ + intel_engine_mask_t logical_mask; u8 class; u8 instance; @@ -307,6 +314,13 @@ struct intel_engine_cs { struct intel_context *kernel_context; /* pinned */ + /** + * pinned_contexts_list: List of pinned contexts. This list is only + * assumed to be manipulated during driver load- or unload time and + * does therefore not have any additional protection. + */ + struct list_head pinned_contexts_list; + intel_engine_mask_t saturated; /* submitting semaphores too late? */ struct { @@ -549,7 +563,7 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine) static inline bool intel_engine_has_timeslices(const struct intel_engine_cs *engine) { - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + if (!CONFIG_DRM_I915_TIMESLICE_DURATION) return false; return engine->flags & I915_ENGINE_HAS_TIMESLICES; diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 87c595e4efe2..bedb80057046 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -201,7 +201,8 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine) } static struct intel_context * -execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count); +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags); static struct i915_request * __active_request(const struct intel_timeline * const tl, @@ -2787,6 +2788,8 @@ static void execlists_sanitize(struct intel_engine_cs *engine) /* And scrub the dirty cachelines for the HWSP */ clflush_cache_range(engine->status_page.addr, PAGE_SIZE); + + intel_engine_reset_pinned_contexts(engine); } static void enable_error_interrupt(struct intel_engine_cs *engine) @@ -3337,7 +3340,7 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) engine->flags |= I915_ENGINE_HAS_SEMAPHORES; if (can_preempt(engine)) { engine->flags |= I915_ENGINE_HAS_PREEMPTION; - if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + if (CONFIG_DRM_I915_TIMESLICE_DURATION) engine->flags |= I915_ENGINE_HAS_TIMESLICES; } } @@ -3782,7 +3785,8 @@ unlock: } static struct intel_context * -execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags) { struct virtual_engine *ve; unsigned int n; @@ -3875,6 +3879,7 @@ execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) ve->siblings[ve->num_siblings++] = sibling; ve->base.mask |= sibling->mask; + ve->base.logical_mask |= sibling->logical_mask; /* * All physical engines must be compatible for their emission diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 8d71f67926f1..f17383e76eb7 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -644,7 +644,7 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt) struct i915_ppgtt *ppgtt; int err; - ppgtt = i915_ppgtt_create(ggtt->vm.gt); + ppgtt = i915_ppgtt_create(ggtt->vm.gt, 0); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); @@ -813,6 +813,21 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl) return 0; } +static unsigned int gen6_gttmmadr_size(struct drm_i915_private *i915) +{ + /* + * GEN6: GTTMMADR size is 4MB and GTTADR starts at 2MB offset + * GEN8: GTTMMADR size is 16MB and GTTADR starts at 8MB offset + */ + GEM_BUG_ON(GRAPHICS_VER(i915) < 6); + return (GRAPHICS_VER(i915) < 8) ? SZ_4M : SZ_16M; +} + +static unsigned int gen6_gttadr_offset(struct drm_i915_private *i915) +{ + return gen6_gttmmadr_size(i915) / 2; +} + static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) { struct drm_i915_private *i915 = ggtt->vm.i915; @@ -821,8 +836,8 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) u32 pte_flags; int ret; - /* For Modern GENs the PTEs and register space are split in the BAR */ - phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2; + GEM_WARN_ON(pci_resource_len(pdev, 0) != gen6_gttmmadr_size(i915)); + phys_addr = pci_resource_start(pdev, 0) + gen6_gttadr_offset(i915); /* * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range @@ -909,6 +924,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) size = gen8_get_total_gtt_size(snb_gmch_ctl); ggtt->vm.alloc_pt_dma = alloc_pt_dma; + ggtt->vm.lmem_pt_obj_flags = I915_BO_ALLOC_PM_EARLY; ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE; ggtt->vm.cleanup = gen6_gmch_remove; @@ -1372,13 +1388,28 @@ err_st_alloc: } static struct scatterlist * -remap_pages(struct drm_i915_gem_object *obj, unsigned int offset, +remap_pages(struct drm_i915_gem_object *obj, + unsigned int offset, unsigned int alignment_pad, unsigned int width, unsigned int height, unsigned int src_stride, unsigned int dst_stride, struct sg_table *st, struct scatterlist *sg) { unsigned int row; + if (alignment_pad) { + st->nents++; + + /* + * The DE ignores the PTEs for the padding tiles, the sg entry + * here is just a convenience to indicate how many padding PTEs + * to insert at this spot. + */ + sg_set_page(sg, NULL, alignment_pad * 4096, 0); + sg_dma_address(sg) = 0; + sg_dma_len(sg) = alignment_pad * 4096; + sg = sg_next(sg); + } + for (row = 0; row < height; row++) { unsigned int left = width * I915_GTT_PAGE_SIZE; @@ -1438,6 +1469,7 @@ intel_remap_pages(struct intel_remapped_info *rem_info, struct drm_i915_private *i915 = to_i915(obj->base.dev); struct sg_table *st; struct scatterlist *sg; + unsigned int gtt_offset = 0; int ret = -ENOMEM; int i; @@ -1454,10 +1486,19 @@ intel_remap_pages(struct intel_remapped_info *rem_info, sg = st->sgl; for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { - sg = remap_pages(obj, rem_info->plane[i].offset, + unsigned int alignment_pad = 0; + + if (rem_info->plane_alignment) + alignment_pad = ALIGN(gtt_offset, rem_info->plane_alignment) - gtt_offset; + + sg = remap_pages(obj, + rem_info->plane[i].offset, alignment_pad, rem_info->plane[i].width, rem_info->plane[i].height, rem_info->plane[i].src_stride, rem_info->plane[i].dst_stride, st, sg); + + gtt_offset += alignment_pad + + rem_info->plane[i].dst_stride * rem_info->plane[i].height; } i915_sg_trim(st); diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 1c3af0fc0456..f8253012d166 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -28,10 +28,13 @@ #define INSTR_26_TO_24_MASK 0x7000000 #define INSTR_26_TO_24_SHIFT 24 +#define __INSTR(client) ((client) << INSTR_CLIENT_SHIFT) + /* * Memory interface instructions used by the kernel */ -#define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags)) +#define MI_INSTR(opcode, flags) \ + (__INSTR(INSTR_MI_CLIENT) | (opcode) << 23 | (flags)) /* Many MI commands use bit 22 of the header dword for GGTT vs PPGTT */ #define MI_GLOBAL_GTT (1<<22) @@ -57,6 +60,7 @@ #define MI_SUSPEND_FLUSH MI_INSTR(0x0b, 0) #define MI_SUSPEND_FLUSH_EN (1<<0) #define MI_SET_APPID MI_INSTR(0x0e, 0) +#define MI_SET_APPID_SESSION_ID(x) ((x) << 0) #define MI_OVERLAY_FLIP MI_INSTR(0x11, 0) #define MI_OVERLAY_CONTINUE (0x0<<21) #define MI_OVERLAY_ON (0x1<<21) @@ -146,6 +150,7 @@ #define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2) #define MI_SRM_LRM_GLOBAL_GTT (1<<22) #define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */ +#define MI_FLUSH_DW_PROTECTED_MEM_EN (1 << 22) #define MI_FLUSH_DW_STORE_INDEX (1<<21) #define MI_INVALIDATE_TLB (1<<18) #define MI_FLUSH_DW_OP_STOREDW (1<<14) @@ -272,6 +277,19 @@ #define MI_MATH_REG_ZF 0x32 #define MI_MATH_REG_CF 0x33 +/* + * Media instructions used by the kernel + */ +#define MEDIA_INSTR(pipe, op, sub_op, flags) \ + (__INSTR(INSTR_RC_CLIENT) | (pipe) << INSTR_SUBCLIENT_SHIFT | \ + (op) << INSTR_26_TO_24_SHIFT | (sub_op) << 16 | (flags)) + +#define MFX_WAIT MEDIA_INSTR(1, 0, 0, 0) +#define MFX_WAIT_DW0_MFX_SYNC_CONTROL_FLAG REG_BIT(8) +#define MFX_WAIT_DW0_PXP_SYNC_CONTROL_FLAG REG_BIT(9) + +#define CRYPTO_KEY_EXCHANGE MEDIA_INSTR(2, 6, 9, 0) + /* * Commands used only by the command parser */ @@ -328,8 +346,6 @@ #define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS \ ((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x47<<16)) -#define MFX_WAIT ((0x3<<29)|(0x1<<27)|(0x0<<16)) - #define COLOR_BLT ((0x2<<29)|(0x40<<22)) #define SRC_COPY_BLT ((0x2<<29)|(0x43<<22)) diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 2aeaae036a6f..1cb1948ac959 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -3,7 +3,7 @@ * Copyright © 2019 Intel Corporation */ -#include "debugfs_gt.h" +#include "intel_gt_debugfs.h" #include "gem/i915_gem_lmem.h" #include "i915_drv.h" @@ -15,12 +15,13 @@ #include "intel_gt_requests.h" #include "intel_migrate.h" #include "intel_mocs.h" +#include "intel_pm.h" #include "intel_rc6.h" #include "intel_renderstate.h" #include "intel_rps.h" #include "intel_uncore.h" -#include "intel_pm.h" #include "shmem_utils.h" +#include "pxp/intel_pxp.h" void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) { @@ -434,7 +435,7 @@ void intel_gt_driver_register(struct intel_gt *gt) { intel_rps_driver_register(>->rps); - debugfs_gt_register(gt); + intel_gt_debugfs_register(gt); } static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size) @@ -481,7 +482,7 @@ static void intel_gt_fini_scratch(struct intel_gt *gt) static struct i915_address_space *kernel_vm(struct intel_gt *gt) { if (INTEL_PPGTT(gt->i915) > INTEL_PPGTT_ALIASING) - return &i915_ppgtt_create(gt)->vm; + return &i915_ppgtt_create(gt, I915_BO_ALLOC_PM_EARLY)->vm; else return i915_vm_get(>->ggtt->vm); } @@ -660,6 +661,8 @@ int intel_gt_init(struct intel_gt *gt) if (err) return err; + intel_gt_init_workarounds(gt); + /* * This is just a security blanket to placate dragons. * On some systems, we very sporadically observe that the first TLBs @@ -682,7 +685,7 @@ int intel_gt_init(struct intel_gt *gt) goto err_pm; } - set_mocs_index(gt); + intel_set_mocs_index(gt); err = intel_engines_init(gt); if (err) @@ -712,6 +715,8 @@ int intel_gt_init(struct intel_gt *gt) intel_migrate_init(>->migrate, gt); + intel_pxp_init(>->pxp); + goto out_fw; err_gt: __intel_gt_disable(gt); @@ -739,6 +744,8 @@ void intel_gt_driver_remove(struct intel_gt *gt) intel_uc_driver_remove(>->uc); intel_engines_release(gt); + + intel_gt_flush_buffer_pool(gt); } void intel_gt_driver_unregister(struct intel_gt *gt) @@ -747,12 +754,14 @@ void intel_gt_driver_unregister(struct intel_gt *gt) intel_rps_driver_unregister(>->rps); + intel_pxp_fini(>->pxp); + /* * Upon unregistering the device to prevent any new users, cancel * all in-flight requests so that we can quickly unbind the active * resources. */ - intel_gt_set_wedged(gt); + intel_gt_set_wedged_on_fini(gt); /* Scrub all HW state upon release */ with_intel_runtime_pm(gt->uncore->rpm, wakeref) @@ -767,6 +776,7 @@ void intel_gt_driver_release(struct intel_gt *gt) if (vm) /* FIXME being called twice on error paths :( */ i915_vm_put(vm); + intel_wa_list_free(>->wa_list); intel_gt_pm_fini(gt); intel_gt_fini_scratch(gt); intel_gt_fini_buffer_pool(gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c index aa0a59c5b614..acc49c56a9f3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c @@ -245,8 +245,6 @@ void intel_gt_fini_buffer_pool(struct intel_gt *gt) struct intel_gt_buffer_pool *pool = >->buffer_pool; int n; - intel_gt_flush_buffer_pool(gt); - for (n = 0; n < ARRAY_SIZE(pool->cache_list); n++) GEM_BUG_ON(!list_empty(&pool->cache_list[n])); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c new file mode 100644 index 000000000000..f103664b71d4 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2019 Intel Corporation + */ + +#include + +#include "i915_drv.h" +#include "intel_gt_debugfs.h" +#include "intel_gt_engines_debugfs.h" +#include "intel_gt_pm_debugfs.h" +#include "intel_sseu_debugfs.h" +#include "pxp/intel_pxp_debugfs.h" +#include "uc/intel_uc_debugfs.h" + +int intel_gt_debugfs_reset_show(struct intel_gt *gt, u64 *val) +{ + int ret = intel_gt_terminally_wedged(gt); + + switch (ret) { + case -EIO: + *val = 1; + return 0; + case 0: + *val = 0; + return 0; + default: + return ret; + } +} + +int intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val) +{ + /* Flush any previous reset before applying for a new one */ + wait_event(gt->reset.queue, + !test_bit(I915_RESET_BACKOFF, >->reset.flags)); + + intel_gt_handle_error(gt, val, I915_ERROR_CAPTURE, + "Manually reset engine mask to %llx", val); + return 0; +} + +/* + * keep the interface clean where the first parameter + * is a 'struct intel_gt *' instead of 'void *' + */ +static int __intel_gt_debugfs_reset_show(void *data, u64 *val) +{ + return intel_gt_debugfs_reset_show(data, val); +} + +static int __intel_gt_debugfs_reset_store(void *data, u64 val) +{ + return intel_gt_debugfs_reset_store(data, val); +} + +DEFINE_SIMPLE_ATTRIBUTE(reset_fops, __intel_gt_debugfs_reset_show, + __intel_gt_debugfs_reset_store, "%llu\n"); + +static void gt_debugfs_register(struct intel_gt *gt, struct dentry *root) +{ + static const struct intel_gt_debugfs_file files[] = { + { "reset", &reset_fops, NULL }, + }; + + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), gt); +} + +void intel_gt_debugfs_register(struct intel_gt *gt) +{ + struct dentry *root; + + if (!gt->i915->drm.primary->debugfs_root) + return; + + root = debugfs_create_dir("gt", gt->i915->drm.primary->debugfs_root); + if (IS_ERR(root)) + return; + + gt_debugfs_register(gt, root); + + intel_gt_engines_debugfs_register(gt, root); + intel_gt_pm_debugfs_register(gt, root); + intel_sseu_debugfs_register(gt, root); + + intel_uc_debugfs_register(>->uc, root); + intel_pxp_debugfs_register(>->pxp, root); +} + +void intel_gt_debugfs_register_files(struct dentry *root, + const struct intel_gt_debugfs_file *files, + unsigned long count, void *data) +{ + while (count--) { + umode_t mode = files->fops->write ? 0644 : 0444; + + if (!files->eval || files->eval(data)) + debugfs_create_file(files->name, + mode, root, data, + files->fops); + + files++; + } +} diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.h b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.h similarity index 58% rename from drivers/gpu/drm/i915/gt/debugfs_gt.h rename to drivers/gpu/drm/i915/gt/intel_gt_debugfs.h index f77540f727e9..e307ceb99031 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.h @@ -3,14 +3,14 @@ * Copyright © 2019 Intel Corporation */ -#ifndef DEBUGFS_GT_H -#define DEBUGFS_GT_H +#ifndef INTEL_GT_DEBUGFS_H +#define INTEL_GT_DEBUGFS_H #include struct intel_gt; -#define DEFINE_GT_DEBUGFS_ATTRIBUTE(__name) \ +#define DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ return single_open(file, __name ## _show, inode->i_private); \ @@ -23,16 +23,20 @@ static const struct file_operations __name ## _fops = { \ .release = single_release, \ } -void debugfs_gt_register(struct intel_gt *gt); +void intel_gt_debugfs_register(struct intel_gt *gt); -struct debugfs_gt_file { +struct intel_gt_debugfs_file { const char *name; const struct file_operations *fops; bool (*eval)(void *data); }; void intel_gt_debugfs_register_files(struct dentry *root, - const struct debugfs_gt_file *files, + const struct intel_gt_debugfs_file *files, unsigned long count, void *data); -#endif /* DEBUGFS_GT_H */ +/* functions that need to be accessed by the upper level non-gt interfaces */ +int intel_gt_debugfs_reset_show(struct intel_gt *gt, u64 *val); +int intel_gt_debugfs_reset_store(struct intel_gt *gt, u64 val); + +#endif /* INTEL_GT_DEBUGFS_H */ diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.c b/drivers/gpu/drm/i915/gt/intel_gt_engines_debugfs.c similarity index 70% rename from drivers/gpu/drm/i915/gt/debugfs_engines.c rename to drivers/gpu/drm/i915/gt/intel_gt_engines_debugfs.c index 5e3725e62241..8f9b874fdc9c 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_engines.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_engines_debugfs.c @@ -6,10 +6,10 @@ #include -#include "debugfs_engines.h" -#include "debugfs_gt.h" #include "i915_drv.h" /* for_each_engine! */ #include "intel_engine.h" +#include "intel_gt_debugfs.h" +#include "intel_gt_engines_debugfs.h" static int engines_show(struct seq_file *m, void *data) { @@ -24,11 +24,11 @@ static int engines_show(struct seq_file *m, void *data) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(engines); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(engines); -void debugfs_engines_register(struct intel_gt *gt, struct dentry *root) +void intel_gt_engines_debugfs_register(struct intel_gt *gt, struct dentry *root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "engines", &engines_fops }, }; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_engines_debugfs.h b/drivers/gpu/drm/i915/gt/intel_gt_engines_debugfs.h new file mode 100644 index 000000000000..dda113452da9 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_engines_debugfs.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef INTEL_GT_ENGINES_DEBUGFS_H +#define INTEL_GT_ENGINES_DEBUGFS_H + +struct intel_gt; +struct dentry; + +void intel_gt_engines_debugfs_register(struct intel_gt *gt, struct dentry *root); + +#endif /* INTEL_GT_ENGINES_DEBUGFS_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index b2de83be4d97..699a74582d32 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -13,6 +13,7 @@ #include "intel_lrc_reg.h" #include "intel_uncore.h" #include "intel_rps.h" +#include "pxp/intel_pxp_irq.h" static void guc_irq_handler(struct intel_guc *guc, u16 iir) { @@ -64,6 +65,9 @@ gen11_other_irq_handler(struct intel_gt *gt, const u8 instance, if (instance == OTHER_GTPM_INSTANCE) return gen11_rps_irq_handler(>->rps, iir); + if (instance == OTHER_KCR_INSTANCE) + return intel_pxp_irq_handler(>->pxp, iir); + WARN_ONCE(1, "unhandled other interrupt instance=0x%x, iir=0x%x\n", instance, iir); } @@ -196,6 +200,9 @@ void gen11_gt_irq_reset(struct intel_gt *gt) intel_uncore_write(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK, ~0); intel_uncore_write(uncore, GEN11_GUC_SG_INTR_ENABLE, 0); intel_uncore_write(uncore, GEN11_GUC_SG_INTR_MASK, ~0); + + intel_uncore_write(uncore, GEN11_CRYPTO_RSVD_INTR_ENABLE, 0); + intel_uncore_write(uncore, GEN11_CRYPTO_RSVD_INTR_MASK, ~0); } void gen11_gt_irq_postinstall(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index dea8e2479897..524eaf678790 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -18,6 +18,9 @@ #include "intel_rc6.h" #include "intel_rps.h" #include "intel_wakeref.h" +#include "pxp/intel_pxp_pm.h" + +#define I915_GT_SUSPEND_IDLE_TIMEOUT (HZ / 2) static void user_forcewake(struct intel_gt *gt, bool suspend) { @@ -262,6 +265,8 @@ int intel_gt_resume(struct intel_gt *gt) intel_uc_resume(>->uc); + intel_pxp_resume(>->pxp); + user_forcewake(gt, false); out_fw: @@ -279,7 +284,7 @@ static void wait_for_suspend(struct intel_gt *gt) if (!intel_gt_pm_is_awake(gt)) return; - if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) { + if (intel_gt_wait_for_idle(gt, I915_GT_SUSPEND_IDLE_TIMEOUT) == -ETIME) { /* * Forcibly cancel outstanding work and leave * the gpu quiet. @@ -296,7 +301,7 @@ void intel_gt_suspend_prepare(struct intel_gt *gt) user_forcewake(gt, true); wait_for_suspend(gt); - intel_uc_suspend(>->uc); + intel_pxp_suspend(>->pxp, false); } static suspend_state_t pm_suspend_target(void) @@ -320,6 +325,8 @@ void intel_gt_suspend_late(struct intel_gt *gt) GEM_BUG_ON(gt->awake); + intel_uc_suspend(>->uc); + /* * On disabling the device, we want to turn off HW access to memory * that we no longer own. @@ -346,6 +353,7 @@ void intel_gt_suspend_late(struct intel_gt *gt) void intel_gt_runtime_suspend(struct intel_gt *gt) { + intel_pxp_suspend(>->pxp, true); intel_uc_runtime_suspend(>->uc); GT_TRACE(gt, "\n"); @@ -353,11 +361,19 @@ void intel_gt_runtime_suspend(struct intel_gt *gt) int intel_gt_runtime_resume(struct intel_gt *gt) { + int ret; + GT_TRACE(gt, "\n"); intel_gt_init_swizzling(gt); intel_ggtt_restore_fences(gt->ggtt); - return intel_uc_runtime_resume(>->uc); + ret = intel_uc_runtime_resume(>->uc); + if (ret) + return ret; + + intel_pxp_resume(>->pxp); + + return 0; } static ktime_t __intel_gt_get_awake_time(const struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index d0588d8aaa44..bc898df7a48c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -31,6 +31,11 @@ static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt) return intel_wakeref_get_if_active(>->wakeref); } +static inline void intel_gt_pm_might_get(struct intel_gt *gt) +{ + intel_wakeref_might_get(>->wakeref); +} + static inline void intel_gt_pm_put(struct intel_gt *gt) { intel_wakeref_put(>->wakeref); @@ -41,6 +46,15 @@ static inline void intel_gt_pm_put_async(struct intel_gt *gt) intel_wakeref_put_async(>->wakeref); } +static inline void intel_gt_pm_might_put(struct intel_gt *gt) +{ + intel_wakeref_might_put(>->wakeref); +} + +#define with_intel_gt_pm(gt, tmp) \ + for (tmp = 1, intel_gt_pm_get(gt); tmp; \ + intel_gt_pm_put(gt), tmp = 0) + static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt) { return intel_wakeref_wait_for_idle(>->wakeref); diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c similarity index 80% rename from drivers/gpu/drm/i915/gt/debugfs_gt_pm.c rename to drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c index f6733f279890..404dfa7673c6 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -6,18 +6,59 @@ #include -#include "debugfs_gt.h" -#include "debugfs_gt_pm.h" #include "i915_drv.h" #include "intel_gt.h" #include "intel_gt_clock_utils.h" +#include "intel_gt_debugfs.h" #include "intel_gt_pm.h" +#include "intel_gt_pm_debugfs.h" #include "intel_llc.h" +#include "intel_pcode.h" #include "intel_rc6.h" #include "intel_rps.h" #include "intel_runtime_pm.h" -#include "intel_sideband.h" #include "intel_uncore.h" +#include "vlv_sideband.h" + +int intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt) +{ + atomic_inc(>->user_wakeref); + intel_gt_pm_get(gt); + if (GRAPHICS_VER(gt->i915) >= 6) + intel_uncore_forcewake_user_get(gt->uncore); + + return 0; +} + +int intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt) +{ + if (GRAPHICS_VER(gt->i915) >= 6) + intel_uncore_forcewake_user_put(gt->uncore); + intel_gt_pm_put(gt); + atomic_dec(>->user_wakeref); + + return 0; +} + +static int forcewake_user_open(struct inode *inode, struct file *file) +{ + struct intel_gt *gt = inode->i_private; + + return intel_gt_pm_debugfs_forcewake_user_open(gt); +} + +static int forcewake_user_release(struct inode *inode, struct file *file) +{ + struct intel_gt *gt = inode->i_private; + + return intel_gt_pm_debugfs_forcewake_user_release(gt); +} + +static const struct file_operations forcewake_user_fops = { + .owner = THIS_MODULE, + .open = forcewake_user_open, + .release = forcewake_user_release, +}; static int fw_domains_show(struct seq_file *m, void *data) { @@ -36,7 +77,7 @@ static int fw_domains_show(struct seq_file *m, void *data) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(fw_domains); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(fw_domains); static void print_rc6_res(struct seq_file *m, const char *title, @@ -238,11 +279,10 @@ static int drpc_show(struct seq_file *m, void *unused) return err; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(drpc); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(drpc); -static int frequency_show(struct seq_file *m, void *unused) +void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *p) { - struct intel_gt *gt = m->private; struct drm_i915_private *i915 = gt->i915; struct intel_uncore *uncore = gt->uncore; struct intel_rps *rps = >->rps; @@ -254,21 +294,21 @@ static int frequency_show(struct seq_file *m, void *unused) u16 rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); u16 rgvstat = intel_uncore_read16(uncore, MEMSTAT_ILK); - seq_printf(m, "Requested P-state: %d\n", (rgvswctl >> 8) & 0xf); - seq_printf(m, "Requested VID: %d\n", rgvswctl & 0x3f); - seq_printf(m, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >> + drm_printf(p, "Requested P-state: %d\n", (rgvswctl >> 8) & 0xf); + drm_printf(p, "Requested VID: %d\n", rgvswctl & 0x3f); + drm_printf(p, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >> MEMSTAT_VID_SHIFT); - seq_printf(m, "Current P-state: %d\n", + drm_printf(p, "Current P-state: %d\n", (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT); } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { u32 rpmodectl, freq_sts; rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL); - seq_printf(m, "Video Turbo Mode: %s\n", + drm_printf(p, "Video Turbo Mode: %s\n", yesno(rpmodectl & GEN6_RP_MEDIA_TURBO)); - seq_printf(m, "HW control enabled: %s\n", + drm_printf(p, "HW control enabled: %s\n", yesno(rpmodectl & GEN6_RP_ENABLE)); - seq_printf(m, "SW control enabled: %s\n", + drm_printf(p, "SW control enabled: %s\n", yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE)); @@ -276,25 +316,25 @@ static int frequency_show(struct seq_file *m, void *unused) freq_sts = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS); vlv_punit_put(i915); - seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts); - seq_printf(m, "DDR freq: %d MHz\n", i915->mem_freq); + drm_printf(p, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts); + drm_printf(p, "DDR freq: %d MHz\n", i915->mem_freq); - seq_printf(m, "actual GPU freq: %d MHz\n", + drm_printf(p, "actual GPU freq: %d MHz\n", intel_gpu_freq(rps, (freq_sts >> 8) & 0xff)); - seq_printf(m, "current GPU freq: %d MHz\n", + drm_printf(p, "current GPU freq: %d MHz\n", intel_gpu_freq(rps, rps->cur_freq)); - seq_printf(m, "max GPU freq: %d MHz\n", + drm_printf(p, "max GPU freq: %d MHz\n", intel_gpu_freq(rps, rps->max_freq)); - seq_printf(m, "min GPU freq: %d MHz\n", + drm_printf(p, "min GPU freq: %d MHz\n", intel_gpu_freq(rps, rps->min_freq)); - seq_printf(m, "idle GPU freq: %d MHz\n", + drm_printf(p, "idle GPU freq: %d MHz\n", intel_gpu_freq(rps, rps->idle_freq)); - seq_printf(m, "efficient (RPe) frequency: %d MHz\n", + drm_printf(p, "efficient (RPe) frequency: %d MHz\n", intel_gpu_freq(rps, rps->efficient_freq)); } else if (GRAPHICS_VER(i915) >= 6) { u32 rp_state_limits; @@ -374,113 +414,121 @@ static int frequency_show(struct seq_file *m, void *unused) } pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK); - seq_printf(m, "Video Turbo Mode: %s\n", + drm_printf(p, "Video Turbo Mode: %s\n", yesno(rpmodectl & GEN6_RP_MEDIA_TURBO)); - seq_printf(m, "HW control enabled: %s\n", + drm_printf(p, "HW control enabled: %s\n", yesno(rpmodectl & GEN6_RP_ENABLE)); - seq_printf(m, "SW control enabled: %s\n", + drm_printf(p, "SW control enabled: %s\n", yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == GEN6_RP_MEDIA_SW_MODE)); - seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", + drm_printf(p, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", pm_ier, pm_imr, pm_mask); if (GRAPHICS_VER(i915) <= 10) - seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n", + drm_printf(p, "PM ISR=0x%08x IIR=0x%08x\n", pm_isr, pm_iir); - seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n", + drm_printf(p, "pm_intrmsk_mbz: 0x%08x\n", rps->pm_intrmsk_mbz); - seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); - seq_printf(m, "Render p-state ratio: %d\n", + drm_printf(p, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); + drm_printf(p, "Render p-state ratio: %d\n", (gt_perf_status & (GRAPHICS_VER(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8); - seq_printf(m, "Render p-state VID: %d\n", + drm_printf(p, "Render p-state VID: %d\n", gt_perf_status & 0xff); - seq_printf(m, "Render p-state limit: %d\n", + drm_printf(p, "Render p-state limit: %d\n", rp_state_limits & 0xff); - seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat); - seq_printf(m, "RPMODECTL: 0x%08x\n", rpmodectl); - seq_printf(m, "RPINCLIMIT: 0x%08x\n", rpinclimit); - seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit); - seq_printf(m, "RPNSWREQ: %dMHz\n", reqf); - seq_printf(m, "CAGF: %dMHz\n", cagf); - seq_printf(m, "RP CUR UP EI: %d (%lldns)\n", + drm_printf(p, "RPSTAT1: 0x%08x\n", rpstat); + drm_printf(p, "RPMODECTL: 0x%08x\n", rpmodectl); + drm_printf(p, "RPINCLIMIT: 0x%08x\n", rpinclimit); + drm_printf(p, "RPDECLIMIT: 0x%08x\n", rpdeclimit); + drm_printf(p, "RPNSWREQ: %dMHz\n", reqf); + drm_printf(p, "CAGF: %dMHz\n", cagf); + drm_printf(p, "RP CUR UP EI: %d (%lldns)\n", rpcurupei, intel_gt_pm_interval_to_ns(gt, rpcurupei)); - seq_printf(m, "RP CUR UP: %d (%lldns)\n", + drm_printf(p, "RP CUR UP: %d (%lldns)\n", rpcurup, intel_gt_pm_interval_to_ns(gt, rpcurup)); - seq_printf(m, "RP PREV UP: %d (%lldns)\n", + drm_printf(p, "RP PREV UP: %d (%lldns)\n", rpprevup, intel_gt_pm_interval_to_ns(gt, rpprevup)); - seq_printf(m, "Up threshold: %d%%\n", + drm_printf(p, "Up threshold: %d%%\n", rps->power.up_threshold); - seq_printf(m, "RP UP EI: %d (%lldns)\n", + drm_printf(p, "RP UP EI: %d (%lldns)\n", rpupei, intel_gt_pm_interval_to_ns(gt, rpupei)); - seq_printf(m, "RP UP THRESHOLD: %d (%lldns)\n", + drm_printf(p, "RP UP THRESHOLD: %d (%lldns)\n", rpupt, intel_gt_pm_interval_to_ns(gt, rpupt)); - seq_printf(m, "RP CUR DOWN EI: %d (%lldns)\n", + drm_printf(p, "RP CUR DOWN EI: %d (%lldns)\n", rpcurdownei, intel_gt_pm_interval_to_ns(gt, rpcurdownei)); - seq_printf(m, "RP CUR DOWN: %d (%lldns)\n", + drm_printf(p, "RP CUR DOWN: %d (%lldns)\n", rpcurdown, intel_gt_pm_interval_to_ns(gt, rpcurdown)); - seq_printf(m, "RP PREV DOWN: %d (%lldns)\n", + drm_printf(p, "RP PREV DOWN: %d (%lldns)\n", rpprevdown, intel_gt_pm_interval_to_ns(gt, rpprevdown)); - seq_printf(m, "Down threshold: %d%%\n", + drm_printf(p, "Down threshold: %d%%\n", rps->power.down_threshold); - seq_printf(m, "RP DOWN EI: %d (%lldns)\n", + drm_printf(p, "RP DOWN EI: %d (%lldns)\n", rpdownei, intel_gt_pm_interval_to_ns(gt, rpdownei)); - seq_printf(m, "RP DOWN THRESHOLD: %d (%lldns)\n", + drm_printf(p, "RP DOWN THRESHOLD: %d (%lldns)\n", rpdownt, intel_gt_pm_interval_to_ns(gt, rpdownt)); max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 : rp_state_cap >> 16) & 0xff; max_freq *= (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1); - seq_printf(m, "Lowest (RPN) frequency: %dMHz\n", + drm_printf(p, "Lowest (RPN) frequency: %dMHz\n", intel_gpu_freq(rps, max_freq)); max_freq = (rp_state_cap & 0xff00) >> 8; max_freq *= (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1); - seq_printf(m, "Nominal (RP1) frequency: %dMHz\n", + drm_printf(p, "Nominal (RP1) frequency: %dMHz\n", intel_gpu_freq(rps, max_freq)); max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 16 : rp_state_cap >> 0) & 0xff; max_freq *= (IS_GEN9_BC(i915) || GRAPHICS_VER(i915) >= 11 ? GEN9_FREQ_SCALER : 1); - seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n", + drm_printf(p, "Max non-overclocked (RP0) frequency: %dMHz\n", intel_gpu_freq(rps, max_freq)); - seq_printf(m, "Max overclocked frequency: %dMHz\n", + drm_printf(p, "Max overclocked frequency: %dMHz\n", intel_gpu_freq(rps, rps->max_freq)); - seq_printf(m, "Current freq: %d MHz\n", + drm_printf(p, "Current freq: %d MHz\n", intel_gpu_freq(rps, rps->cur_freq)); - seq_printf(m, "Actual freq: %d MHz\n", cagf); - seq_printf(m, "Idle freq: %d MHz\n", + drm_printf(p, "Actual freq: %d MHz\n", cagf); + drm_printf(p, "Idle freq: %d MHz\n", intel_gpu_freq(rps, rps->idle_freq)); - seq_printf(m, "Min freq: %d MHz\n", + drm_printf(p, "Min freq: %d MHz\n", intel_gpu_freq(rps, rps->min_freq)); - seq_printf(m, "Boost freq: %d MHz\n", + drm_printf(p, "Boost freq: %d MHz\n", intel_gpu_freq(rps, rps->boost_freq)); - seq_printf(m, "Max freq: %d MHz\n", + drm_printf(p, "Max freq: %d MHz\n", intel_gpu_freq(rps, rps->max_freq)); - seq_printf(m, + drm_printf(p, "efficient (RPe) frequency: %d MHz\n", intel_gpu_freq(rps, rps->efficient_freq)); } else { - seq_puts(m, "no P-state info available\n"); + drm_puts(p, "no P-state info available\n"); } - seq_printf(m, "Current CD clock frequency: %d kHz\n", i915->cdclk.hw.cdclk); - seq_printf(m, "Max CD clock frequency: %d kHz\n", i915->max_cdclk_freq); - seq_printf(m, "Max pixel clock frequency: %d kHz\n", i915->max_dotclk_freq); + drm_printf(p, "Current CD clock frequency: %d kHz\n", i915->cdclk.hw.cdclk); + drm_printf(p, "Max CD clock frequency: %d kHz\n", i915->max_cdclk_freq); + drm_printf(p, "Max pixel clock frequency: %d kHz\n", i915->max_dotclk_freq); intel_runtime_pm_put(uncore->rpm, wakeref); +} + +static int frequency_show(struct seq_file *m, void *unused) +{ + struct intel_gt *gt = m->private; + struct drm_printer p = drm_seq_file_printer(m); + + intel_gt_pm_frequency_dump(gt, &p); return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(frequency); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(frequency); static int llc_show(struct seq_file *m, void *data) { @@ -533,7 +581,7 @@ static bool llc_eval(void *data) return HAS_LLC(gt->i915); } -DEFINE_GT_DEBUGFS_ATTRIBUTE(llc); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(llc); static const char *rps_power_to_str(unsigned int power) { @@ -612,14 +660,15 @@ static bool rps_eval(void *data) return HAS_RPS(gt->i915); } -DEFINE_GT_DEBUGFS_ATTRIBUTE(rps_boost); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(rps_boost); -void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root) +void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "drpc", &drpc_fops, NULL }, { "frequency", &frequency_fops, NULL }, { "forcewake", &fw_domains_fops, NULL }, + { "forcewake_user", &forcewake_user_fops, NULL}, { "llc", &llc_fops, llc_eval }, { "rps_boost", &rps_boost_fops, rps_eval }, }; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.h b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.h new file mode 100644 index 000000000000..a8457887ec65 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2019 Intel Corporation + */ + +#ifndef INTEL_GT_PM_DEBUGFS_H +#define INTEL_GT_PM_DEBUGFS_H + +struct intel_gt; +struct dentry; +struct drm_printer; + +void intel_gt_pm_debugfs_register(struct intel_gt *gt, struct dentry *root); +void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *m); + +/* functions that need to be accessed by the upper level non-gt interfaces */ +int intel_gt_pm_debugfs_forcewake_user_open(struct intel_gt *gt); +int intel_gt_pm_debugfs_forcewake_user_release(struct intel_gt *gt); + +#endif /* INTEL_GT_PM_DEBUGFS_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 6fdcde64c180..14216cc471b1 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -26,6 +26,7 @@ #include "intel_rps_types.h" #include "intel_migrate_types.h" #include "intel_wakeref.h" +#include "pxp/intel_pxp_types.h" struct drm_i915_private; struct i915_ggtt; @@ -72,6 +73,8 @@ struct intel_gt { struct intel_uc uc; + struct i915_wa_list wa_list; + struct intel_gt_timelines { spinlock_t lock; /* protects active_list */ struct list_head active_list; @@ -184,6 +187,9 @@ struct intel_gt { u8 num_engines; + /* General presence of SFC units */ + u8 sfc_mask; + /* Media engine access to SFC per instance */ u8 vdbox_sfc_access; @@ -196,6 +202,8 @@ struct intel_gt { struct { u8 uc_index; } mocs; + + struct intel_pxp pxp; }; enum intel_gt_scratch_field { diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index a0c2b952aa57..67d14afa6623 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -28,7 +28,8 @@ struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz) * used the passed in size for the page size, which should ensure it * also has the same alignment. */ - obj = __i915_gem_object_create_lmem_with_ps(vm->i915, sz, sz, 0); + obj = __i915_gem_object_create_lmem_with_ps(vm->i915, sz, sz, + vm->lmem_pt_obj_flags); /* * Ensure all paging structures for this vm share the same dma-resv * object underneath, with the idea that one object_lock() will lock diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 5b539bd7645d..bc6750263359 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -260,6 +260,9 @@ struct i915_address_space { u8 pd_shift; u8 scratch_order; + /* Flags used when creating page-table objects for this vm */ + unsigned long lmem_pt_obj_flags; + struct drm_i915_gem_object * (*alloc_pt_dma)(struct i915_address_space *vm, int sz); @@ -519,7 +522,8 @@ i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n) return __px_dma(pt ? px_base(pt) : ppgtt->vm.scratch[ppgtt->vm.top]); } -void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt); +void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt, + unsigned long lmem_pt_obj_flags); int i915_ggtt_probe_hw(struct drm_i915_private *i915); int i915_ggtt_init_hw(struct drm_i915_private *i915); @@ -537,7 +541,8 @@ static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt) int i915_ppgtt_init_hw(struct intel_gt *gt); -struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt); +struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt, + unsigned long lmem_pt_obj_flags); void i915_ggtt_suspend(struct i915_ggtt *gtt); void i915_ggtt_resume(struct i915_ggtt *ggtt); diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c index eb1a15deed22..08d7d5ae263a 100644 --- a/drivers/gpu/drm/i915/gt/intel_llc.c +++ b/drivers/gpu/drm/i915/gt/intel_llc.c @@ -3,12 +3,13 @@ * Copyright © 2019 Intel Corporation */ +#include #include #include "i915_drv.h" #include "intel_gt.h" #include "intel_llc.h" -#include "intel_sideband.h" +#include "intel_pcode.h" struct ia_constants { unsigned int min_gpu_freq; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 6ba8daea2f56..56156cf18c41 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -942,7 +942,13 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) context_size += PAGE_SIZE; } - obj = i915_gem_object_create_lmem(engine->i915, context_size, 0); + if (intel_context_is_parent(ce) && intel_engine_uses_guc(engine)) { + ce->parallel.guc.parent_page = context_size / PAGE_SIZE; + context_size += PARENT_SCRATCH_SIZE; + } + + obj = i915_gem_object_create_lmem(engine->i915, context_size, + I915_BO_ALLOC_PM_VOLATILE); if (IS_ERR(obj)) obj = i915_gem_object_create_shmem(engine->i915, context_size); if (IS_ERR(obj)) diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index 1dac21aa7e5c..afb1cce9a352 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -78,7 +78,7 @@ static struct i915_address_space *migrate_vm(struct intel_gt *gt) * TODO: Add support for huge LMEM PTEs */ - vm = i915_ppgtt_create(gt); + vm = i915_ppgtt_create(gt, I915_BO_ALLOC_PM_EARLY); if (IS_ERR(vm)) return ERR_CAST(vm); diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index e4b97cd14cf9..15f9ada28a7a 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -616,7 +616,7 @@ static u32 global_mocs_offset(void) return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0)); } -void set_mocs_index(struct intel_gt *gt) +void intel_set_mocs_index(struct intel_gt *gt) { struct drm_i915_mocs_table table; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.h b/drivers/gpu/drm/i915/gt/intel_mocs.h index 8a09d64b115f..76db827210c0 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.h +++ b/drivers/gpu/drm/i915/gt/intel_mocs.h @@ -36,6 +36,6 @@ struct intel_gt; void intel_mocs_init(struct intel_gt *gt); void intel_mocs_init_engine(struct intel_engine_cs *engine); -void set_mocs_index(struct intel_gt *gt); +void intel_set_mocs_index(struct intel_gt *gt); #endif diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 886060f7e6fc..4396bfd630d8 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -155,19 +155,20 @@ int i915_ppgtt_init_hw(struct intel_gt *gt) } static struct i915_ppgtt * -__ppgtt_create(struct intel_gt *gt) +__ppgtt_create(struct intel_gt *gt, unsigned long lmem_pt_obj_flags) { if (GRAPHICS_VER(gt->i915) < 8) return gen6_ppgtt_create(gt); else - return gen8_ppgtt_create(gt); + return gen8_ppgtt_create(gt, lmem_pt_obj_flags); } -struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt) +struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt, + unsigned long lmem_pt_obj_flags) { struct i915_ppgtt *ppgtt; - ppgtt = __ppgtt_create(gt); + ppgtt = __ppgtt_create(gt, lmem_pt_obj_flags); if (IS_ERR(ppgtt)) return ppgtt; @@ -298,7 +299,8 @@ int ppgtt_set_pages(struct i915_vma *vma) return 0; } -void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt) +void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt, + unsigned long lmem_pt_obj_flags) { struct drm_i915_private *i915 = gt->i915; @@ -306,6 +308,7 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt) ppgtt->vm.i915 = i915; ppgtt->vm.dma = i915->drm.dev; ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size); + ppgtt->vm.lmem_pt_obj_flags = lmem_pt_obj_flags; dma_resv_init(&ppgtt->vm._resv); i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT); diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 799d382eea79..43093dd2d0c9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -9,8 +9,8 @@ #include "i915_vgpu.h" #include "intel_gt.h" #include "intel_gt_pm.h" +#include "intel_pcode.h" #include "intel_rc6.h" -#include "intel_sideband.h" /** * DOC: RC6 diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index a74b72f50cc9..afb35d2e5c73 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -32,7 +32,7 @@ static int init_fake_lmem_bar(struct intel_memory_region *mem) mem->remap_addr = dma_map_resource(i915->drm.dev, mem->region.start, mem->fake_mappable.size, - PCI_DMA_BIDIRECTIONAL, + DMA_BIDIRECTIONAL, DMA_ATTR_FORCE_CONTIGUOUS); if (dma_mapping_error(i915->drm.dev, mem->remap_addr)) { drm_mm_remove_node(&mem->fake_mappable); @@ -62,7 +62,7 @@ static void release_fake_lmem_bar(struct intel_memory_region *mem) dma_unmap_resource(mem->i915->drm.dev, mem->remap_addr, mem->fake_mappable.size, - PCI_DMA_BIDIRECTIONAL, + DMA_BIDIRECTIONAL, DMA_ATTR_FORCE_CONTIGUOUS); } diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 7c4d5158e03b..2fdd52b62092 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -112,7 +112,8 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size) struct drm_i915_gem_object *obj; struct i915_vma *vma; - obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE); + obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE | + I915_BO_ALLOC_PM_VOLATILE); if (IS_ERR(obj) && i915_ggtt_has_aperture(ggtt)) obj = i915_gem_object_create_stolen(i915, size); if (IS_ERR(obj)) diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 3c65efcb7bed..586dca1731ce 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -17,6 +17,7 @@ #include "intel_ring.h" #include "shmem_utils.h" #include "intel_engine_heartbeat.h" +#include "intel_engine_pm.h" /* Rough estimate of the typical request size, performing a flush, * set-context and then emitting the batch. @@ -291,7 +292,9 @@ static void xcs_sanitize(struct intel_engine_cs *engine) sanitize_hwsp(engine); /* And scrub the dirty cachelines for the HWSP */ - clflush_cache_range(engine->status_page.addr, PAGE_SIZE); + drm_clflush_virt_range(engine->status_page.addr, PAGE_SIZE); + + intel_engine_reset_pinned_contexts(engine); } static void reset_prepare(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 172de6c9f949..5e275f8dda8c 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -11,8 +11,9 @@ #include "intel_gt_clock_utils.h" #include "intel_gt_irq.h" #include "intel_gt_pm_irq.h" +#include "intel_pcode.h" #include "intel_rps.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" #include "../../../platform/x86/intel_ips.h" #define BUSY_MAX_EI 20u /* ms */ diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c index b0e09b58005e..bdf09051b8a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c @@ -514,10 +514,9 @@ static void hsw_sseu_info_init(struct intel_gt *gt) } fuse1 = intel_uncore_read(gt->uncore, HSW_PAVP_FUSE1); - switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) { + switch (REG_FIELD_GET(HSW_F1_EU_DIS_MASK, fuse1)) { default: - MISSING_CASE((fuse1 & HSW_F1_EU_DIS_MASK) >> - HSW_F1_EU_DIS_SHIFT); + MISSING_CASE(REG_FIELD_GET(HSW_F1_EU_DIS_MASK, fuse1)); fallthrough; case HSW_F1_EU_DIS_10EUS: sseu->eu_per_subslice = 10; diff --git a/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c b/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c index 1ba8b7da9d37..8bb3a91dad82 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu_debugfs.c @@ -4,9 +4,9 @@ * Copyright © 2020 Intel Corporation */ -#include "debugfs_gt.h" -#include "intel_sseu_debugfs.h" #include "i915_drv.h" +#include "intel_gt_debugfs.h" +#include "intel_sseu_debugfs.h" static void sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice, u8 *to_mask) @@ -282,7 +282,7 @@ static int sseu_status_show(struct seq_file *m, void *unused) return intel_sseu_status(m, gt); } -DEFINE_GT_DEBUGFS_ATTRIBUTE(sseu_status); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(sseu_status); static int rcs_topology_show(struct seq_file *m, void *unused) { @@ -293,11 +293,11 @@ static int rcs_topology_show(struct seq_file *m, void *unused) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(rcs_topology); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(rcs_topology); void intel_sseu_debugfs_register(struct intel_gt *gt, struct dentry *root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "sseu_status", &sseu_status_fops, NULL }, { "rcs_topology", &rcs_topology_fops, NULL }, }; diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index c314d4917b6b..e1f362530889 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -804,7 +804,7 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq) } static void -gen4_gt_workarounds_init(struct drm_i915_private *i915, +gen4_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { /* WaDisable_RenderCache_OperationalFlush:gen4,ilk */ @@ -812,29 +812,29 @@ gen4_gt_workarounds_init(struct drm_i915_private *i915, } static void -g4x_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +g4x_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen4_gt_workarounds_init(i915, wal); + gen4_gt_workarounds_init(gt, wal); /* WaDisableRenderCachePipelinedFlush:g4x,ilk */ wa_masked_en(wal, CACHE_MODE_0, CM0_PIPELINED_RENDER_FLUSH_DISABLE); } static void -ilk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +ilk_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - g4x_gt_workarounds_init(i915, wal); + g4x_gt_workarounds_init(gt, wal); wa_masked_en(wal, _3D_CHICKEN2, _3D_CHICKEN2_WM_READ_PIPELINED); } static void -snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +snb_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { } static void -ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +ivb_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { /* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */ wa_masked_dis(wal, @@ -850,7 +850,7 @@ ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -vlv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +vlv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { /* WaForceL3Serialization:vlv */ wa_write_clr(wal, GEN7_L3SQCREG4, L3SQ_URB_READ_CAM_MATCH_DISABLE); @@ -863,7 +863,7 @@ vlv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +hsw_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { /* L3 caching of data atomics doesn't work -- disable it. */ wa_write(wal, HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE); @@ -878,8 +878,10 @@ hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +gen9_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { + struct drm_i915_private *i915 = gt->i915; + /* WaDisableKillLogic:bxt,skl,kbl */ if (!IS_COFFEELAKE(i915) && !IS_COMETLAKE(i915)) wa_write_or(wal, @@ -904,9 +906,9 @@ gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal } static void -skl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +skl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen9_gt_workarounds_init(i915, wal); + gen9_gt_workarounds_init(gt, wal); /* WaDisableGafsUnitClkGating:skl */ wa_write_or(wal, @@ -914,19 +916,19 @@ skl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:skl */ - if (IS_SKL_GT_STEP(i915, STEP_A0, STEP_H0)) + if (IS_SKL_GT_STEP(gt->i915, STEP_A0, STEP_H0)) wa_write_or(wal, GEN9_GAMT_ECO_REG_RW_IA, GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } static void -kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +kbl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen9_gt_workarounds_init(i915, wal); + gen9_gt_workarounds_init(gt, wal); /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_GT_STEP(i915, 0, STEP_C0)) + if (IS_KBL_GT_STEP(gt->i915, 0, STEP_C0)) wa_write_or(wal, GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); @@ -943,15 +945,15 @@ kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -glk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +glk_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen9_gt_workarounds_init(i915, wal); + gen9_gt_workarounds_init(gt, wal); } static void -cfl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +cfl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen9_gt_workarounds_init(i915, wal); + gen9_gt_workarounds_init(gt, wal); /* WaDisableGafsUnitClkGating:cfl */ wa_write_or(wal, @@ -976,21 +978,21 @@ static void __set_mcr_steering(struct i915_wa_list *wal, wa_write_clr_set(wal, steering_reg, mcr_mask, mcr); } -static void __add_mcr_wa(struct drm_i915_private *i915, struct i915_wa_list *wal, +static void __add_mcr_wa(struct intel_gt *gt, struct i915_wa_list *wal, unsigned int slice, unsigned int subslice) { - drm_dbg(&i915->drm, "MCR slice=0x%x, subslice=0x%x\n", slice, subslice); + drm_dbg(>->i915->drm, "MCR slice=0x%x, subslice=0x%x\n", slice, subslice); __set_mcr_steering(wal, GEN8_MCR_SELECTOR, slice, subslice); } static void -icl_wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal) +icl_wa_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) { - const struct sseu_dev_info *sseu = &i915->gt.info.sseu; + const struct sseu_dev_info *sseu = >->info.sseu; unsigned int slice, subslice; - GEM_BUG_ON(GRAPHICS_VER(i915) < 11); + GEM_BUG_ON(GRAPHICS_VER(gt->i915) < 11); GEM_BUG_ON(hweight8(sseu->slice_mask) > 1); slice = 0; @@ -1010,16 +1012,15 @@ icl_wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal) * then we can just rely on the default steering and won't need to * worry about explicitly re-steering L3BANK reads later. */ - if (i915->gt.info.l3bank_mask & BIT(subslice)) - i915->gt.steering_table[L3BANK] = NULL; + if (gt->info.l3bank_mask & BIT(subslice)) + gt->steering_table[L3BANK] = NULL; - __add_mcr_wa(i915, wal, slice, subslice); + __add_mcr_wa(gt, wal, slice, subslice); } static void xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) { - struct drm_i915_private *i915 = gt->i915; const struct sseu_dev_info *sseu = >->info.sseu; unsigned long slice, subslice = 0, slice_mask = 0; u64 dss_mask = 0; @@ -1083,7 +1084,7 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) WARN_ON(subslice > GEN_DSS_PER_GSLICE); WARN_ON(dss_mask >> (slice * GEN_DSS_PER_GSLICE) == 0); - __add_mcr_wa(i915, wal, slice, subslice); + __add_mcr_wa(gt, wal, slice, subslice); /* * SQIDI ranges are special because they use different steering @@ -1099,9 +1100,11 @@ xehp_init_mcr(struct intel_gt *gt, struct i915_wa_list *wal) } static void -icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - icl_wa_init_mcr(i915, wal); + struct drm_i915_private *i915 = gt->i915; + + icl_wa_init_mcr(gt, wal); /* WaModifyGamTlbPartitioning:icl */ wa_write_clr_set(wal, @@ -1152,10 +1155,9 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) * the engine-specific workaround list. */ static void -wa_14011060649(struct drm_i915_private *i915, struct i915_wa_list *wal) +wa_14011060649(struct intel_gt *gt, struct i915_wa_list *wal) { struct intel_engine_cs *engine; - struct intel_gt *gt = &i915->gt; int id; for_each_engine(engine, gt, id) { @@ -1169,22 +1171,23 @@ wa_14011060649(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -gen12_gt_workarounds_init(struct drm_i915_private *i915, - struct i915_wa_list *wal) +gen12_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - icl_wa_init_mcr(i915, wal); + icl_wa_init_mcr(gt, wal); /* Wa_14011060649:tgl,rkl,dg1,adl-s,adl-p */ - wa_14011060649(i915, wal); + wa_14011060649(gt, wal); /* Wa_14011059788:tgl,rkl,adl-s,dg1,adl-p */ wa_write_or(wal, GEN10_DFR_RATIO_EN_AND_CHICKEN, DFR_DISABLE); } static void -tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +tgl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen12_gt_workarounds_init(i915, wal); + struct drm_i915_private *i915 = gt->i915; + + gen12_gt_workarounds_init(gt, wal); /* Wa_1409420604:tgl */ if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) @@ -1205,9 +1208,11 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -dg1_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +dg1_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - gen12_gt_workarounds_init(i915, wal); + struct drm_i915_private *i915 = gt->i915; + + gen12_gt_workarounds_init(gt, wal); /* Wa_1607087056:dg1 */ if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0)) @@ -1229,60 +1234,62 @@ dg1_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) } static void -xehpsdv_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) +xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - xehp_init_mcr(&i915->gt, wal); + xehp_init_mcr(gt, wal); } static void -gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal) +gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) { + struct drm_i915_private *i915 = gt->i915; + if (IS_XEHPSDV(i915)) - xehpsdv_gt_workarounds_init(i915, wal); + xehpsdv_gt_workarounds_init(gt, wal); else if (IS_DG1(i915)) - dg1_gt_workarounds_init(i915, wal); + dg1_gt_workarounds_init(gt, wal); else if (IS_TIGERLAKE(i915)) - tgl_gt_workarounds_init(i915, wal); + tgl_gt_workarounds_init(gt, wal); else if (GRAPHICS_VER(i915) == 12) - gen12_gt_workarounds_init(i915, wal); + gen12_gt_workarounds_init(gt, wal); else if (GRAPHICS_VER(i915) == 11) - icl_gt_workarounds_init(i915, wal); + icl_gt_workarounds_init(gt, wal); else if (IS_COFFEELAKE(i915) || IS_COMETLAKE(i915)) - cfl_gt_workarounds_init(i915, wal); + cfl_gt_workarounds_init(gt, wal); else if (IS_GEMINILAKE(i915)) - glk_gt_workarounds_init(i915, wal); + glk_gt_workarounds_init(gt, wal); else if (IS_KABYLAKE(i915)) - kbl_gt_workarounds_init(i915, wal); + kbl_gt_workarounds_init(gt, wal); else if (IS_BROXTON(i915)) - gen9_gt_workarounds_init(i915, wal); + gen9_gt_workarounds_init(gt, wal); else if (IS_SKYLAKE(i915)) - skl_gt_workarounds_init(i915, wal); + skl_gt_workarounds_init(gt, wal); else if (IS_HASWELL(i915)) - hsw_gt_workarounds_init(i915, wal); + hsw_gt_workarounds_init(gt, wal); else if (IS_VALLEYVIEW(i915)) - vlv_gt_workarounds_init(i915, wal); + vlv_gt_workarounds_init(gt, wal); else if (IS_IVYBRIDGE(i915)) - ivb_gt_workarounds_init(i915, wal); + ivb_gt_workarounds_init(gt, wal); else if (GRAPHICS_VER(i915) == 6) - snb_gt_workarounds_init(i915, wal); + snb_gt_workarounds_init(gt, wal); else if (GRAPHICS_VER(i915) == 5) - ilk_gt_workarounds_init(i915, wal); + ilk_gt_workarounds_init(gt, wal); else if (IS_G4X(i915)) - g4x_gt_workarounds_init(i915, wal); + g4x_gt_workarounds_init(gt, wal); else if (GRAPHICS_VER(i915) == 4) - gen4_gt_workarounds_init(i915, wal); + gen4_gt_workarounds_init(gt, wal); else if (GRAPHICS_VER(i915) <= 8) ; else MISSING_CASE(GRAPHICS_VER(i915)); } -void intel_gt_init_workarounds(struct drm_i915_private *i915) +void intel_gt_init_workarounds(struct intel_gt *gt) { - struct i915_wa_list *wal = &i915->gt_wa_list; + struct i915_wa_list *wal = >->wa_list; wa_init_start(wal, "GT", "global"); - gt_init_workarounds(i915, wal); + gt_init_workarounds(gt, wal); wa_init_finish(wal); } @@ -1353,7 +1360,7 @@ wa_list_apply(struct intel_gt *gt, const struct i915_wa_list *wal) void intel_gt_apply_workarounds(struct intel_gt *gt) { - wa_list_apply(gt, >->i915->gt_wa_list); + wa_list_apply(gt, >->wa_list); } static bool wa_list_verify(struct intel_gt *gt, @@ -1385,7 +1392,7 @@ static bool wa_list_verify(struct intel_gt *gt, bool intel_gt_verify_workarounds(struct intel_gt *gt, const char *from) { - return wa_list_verify(gt, >->i915->gt_wa_list, from); + return wa_list_verify(gt, >->wa_list, from); } __maybe_unused diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.h b/drivers/gpu/drm/i915/gt/intel_workarounds.h index 15abb68b6c00..9beaab77c7f0 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.h +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.h @@ -24,7 +24,7 @@ static inline void intel_wa_list_free(struct i915_wa_list *wal) void intel_engine_init_ctx_wa(struct intel_engine_cs *engine); int intel_engine_emit_ctx_wa(struct i915_request *rq); -void intel_gt_init_workarounds(struct drm_i915_private *i915); +void intel_gt_init_workarounds(struct intel_gt *gt); void intel_gt_apply_workarounds(struct intel_gt *gt); bool intel_gt_verify_workarounds(struct intel_gt *gt, const char *from); diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index 2c1af030310c..8b89215afe46 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -376,6 +376,8 @@ int mock_engine_init(struct intel_engine_cs *engine) { struct intel_context *ce; + INIT_LIST_HEAD(&engine->pinned_contexts_list); + engine->sched_engine = i915_sched_engine_create(ENGINE_MOCK); if (!engine->sched_engine) return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c index 317eebf086c3..6e6e4d747cca 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c @@ -290,7 +290,7 @@ static int live_heartbeat_fast(void *arg) int err = 0; /* Check that the heartbeat ticks at the desired rate. */ - if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) + if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL) return 0; for_each_engine(engine, gt, id) { @@ -352,7 +352,7 @@ static int live_heartbeat_off(void *arg) int err = 0; /* Check that we can turn off heartbeat and not interrupt VIP */ - if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) + if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL) return 0; for_each_engine(engine, gt, id) { diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index b3863abc51f5..b367ecfa42de 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -992,7 +992,7 @@ static int live_timeslice_preempt(void *arg) * need to preempt the current task and replace it with another * ready task. */ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + if (!CONFIG_DRM_I915_TIMESLICE_DURATION) return 0; obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE); @@ -1122,7 +1122,7 @@ static int live_timeslice_rewind(void *arg) * but only a few of those requests, forcing us to rewind the * RING_TAIL of the original request. */ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + if (!CONFIG_DRM_I915_TIMESLICE_DURATION) return 0; for_each_engine(engine, gt, id) { @@ -1299,7 +1299,7 @@ static int live_timeslice_queue(void *arg) * ELSP[1] is already occupied, so must rely on timeslicing to * eject ELSP[0] in favour of the queue.) */ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + if (!CONFIG_DRM_I915_TIMESLICE_DURATION) return 0; obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE); @@ -1420,7 +1420,7 @@ static int live_timeslice_nopreempt(void *arg) * We should not timeslice into a request that is marked with * I915_REQUEST_NOPREEMPT. */ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + if (!CONFIG_DRM_I915_TIMESLICE_DURATION) return 0; if (igt_spinner_init(&spin, gt)) @@ -2260,7 +2260,7 @@ static int __cancel_hostile(struct live_preempt_cancel *arg) int err; /* Preempt cancel non-preemptible spinner in ELSP0 */ - if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) + if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT) return 0; if (!intel_has_reset_engine(arg->engine->gt)) @@ -2316,7 +2316,7 @@ static int __cancel_fail(struct live_preempt_cancel *arg) struct i915_request *rq; int err; - if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) + if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT) return 0; if (!intel_has_reset_engine(engine->gt)) @@ -3375,7 +3375,7 @@ static int live_preempt_timeout(void *arg) * Check that we force preemption to occur by cancelling the previous * context if it refuses to yield the GPU. */ - if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) + if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT) return 0; if (!intel_has_reset_engine(gt)) @@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt, GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve)); for (n = 0; n < nctx; n++) { - ve[n] = intel_engine_create_virtual(siblings, nsibling); + ve[n] = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve[n])) { err = PTR_ERR(ve[n]); nctx = n; @@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt, * restrict it to our desired engine within the virtual engine. */ - ve = intel_engine_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_close; @@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt, i915_request_add(rq); } - ce = intel_engine_create_virtual(siblings, nsibling); + ce = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ce)) { err = PTR_ERR(ce); goto out; @@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt, /* XXX We do not handle oversubscription and fairness with normal rq */ for (n = 0; n < nsibling; n++) { - ce = intel_engine_create_virtual(siblings, nsibling); + ce = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ce)) { err = PTR_ERR(ce); goto out; @@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, if (err) goto out_scratch; - ve = intel_engine_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_scratch; @@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt, if (igt_spinner_init(&spin, gt)) return -ENOMEM; - ve = intel_engine_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling, 0); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_spin; diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 7e6fdabac599..7e2d99dd012d 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -1596,7 +1596,7 @@ static int igt_reset_evict_ppgtt(void *arg) if (INTEL_PPGTT(gt->i915) < INTEL_PPGTT_FULL) return 0; - ppgtt = i915_ppgtt_create(gt); + ppgtt = i915_ppgtt_create(gt, 0); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index e623ac45f4aa..962e91ba3be4 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -66,7 +66,7 @@ reference_lists_init(struct intel_gt *gt, struct wa_lists *lists) memset(lists, 0, sizeof(*lists)); wa_init_start(&lists->gt_wa_list, "GT_REF", "global"); - gt_init_workarounds(gt->i915, &lists->gt_wa_list); + gt_init_workarounds(gt, &lists->gt_wa_list); wa_init_finish(&lists->gt_wa_list); for_each_engine(engine, gt, id) { diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h index 8ff582222aff..ba10bd374cee 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h @@ -142,6 +142,7 @@ enum intel_guc_action { INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505, INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506, INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE = 0x4600, + INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601, INTEL_GUC_ACTION_RESET_CLIENT = 0x5507, INTEL_GUC_ACTION_LIMIT }; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index fbfcae727d7f..6e228343e8cb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -3,6 +3,7 @@ * Copyright © 2014-2019 Intel Corporation */ +#include "gem/i915_gem_lmem.h" #include "gt/intel_gt.h" #include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm_irq.h" @@ -647,7 +648,14 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size) u64 flags; int ret; - obj = i915_gem_object_create_shmem(gt->i915, size); + if (HAS_LMEM(gt->i915)) + obj = i915_gem_object_create_lmem(gt->i915, size, + I915_BO_ALLOC_CPU_CLEAR | + I915_BO_ALLOC_CONTIGUOUS | + I915_BO_ALLOC_PM_EARLY); + else + obj = i915_gem_object_create_shmem(gt->i915, size); + if (IS_ERR(obj)) return ERR_CAST(obj); @@ -748,3 +756,32 @@ void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p) } } } + +void intel_guc_write_barrier(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + + if (i915_gem_object_is_lmem(guc->ct.vma->obj)) { + /* + * Ensure intel_uncore_write_fw can be used rather than + * intel_uncore_write. + */ + GEM_BUG_ON(guc->send_regs.fw_domains); + + /* + * This register is used by the i915 and GuC for MMIO based + * communication. Once we are in this code CTBs are the only + * method the i915 uses to communicate with the GuC so it is + * safe to write to this register (a value of 0 is NOP for MMIO + * communication). If we ever start mixing CTBs and MMIOs a new + * register will have to be chosen. This function is also used + * to enforce ordering of a work queue item write and an update + * to the process descriptor. When a work queue is being used, + * CTBs are also the only mechanism of communication. + */ + intel_uncore_write_fw(gt->uncore, GEN11_SOFT_SCRATCH(0), 0); + } else { + /* wmb() sufficient for a barrier if in smem */ + wmb(); + } +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 5dd174babf7a..31cf9fb48c7e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -46,6 +46,15 @@ struct intel_guc { * submitted until the stalled request is processed. */ struct i915_request *stalled_request; + /** + * @submission_stall_reason: reason why submission is stalled + */ + enum { + STALL_NONE, + STALL_REGISTER_CONTEXT, + STALL_MOVE_LRC_TAIL, + STALL_ADD_REQUEST, + } submission_stall_reason; /* intel_guc_recv interrupt related state */ /** @irq_lock: protects GuC irq state */ @@ -71,16 +80,41 @@ struct intel_guc { } interrupts; /** - * @contexts_lock: protects guc_ids, guc_id_list, ce->guc_id.id, and - * ce->guc_id.ref when transitioning in and out of zero + * @submission_state: sub-structure for submission state protected by + * single lock */ - spinlock_t contexts_lock; - /** @guc_ids: used to allocate unique ce->guc_id.id values */ - struct ida guc_ids; - /** - * @guc_id_list: list of intel_context with valid guc_ids but no refs - */ - struct list_head guc_id_list; + struct { + /** + * @lock: protects everything in submission_state, + * ce->guc_id.id, and ce->guc_id.ref when transitioning in and + * out of zero + */ + spinlock_t lock; + /** + * @guc_ids: used to allocate new guc_ids, single-lrc + */ + struct ida guc_ids; + /** + * @guc_ids_bitmap: used to allocate new guc_ids, multi-lrc + */ + unsigned long *guc_ids_bitmap; + /** + * @guc_id_list: list of intel_context with valid guc_ids but no + * refs + */ + struct list_head guc_id_list; + /** + * @destroyed_contexts: list of contexts waiting to be destroyed + * (deregistered with the GuC) + */ + struct list_head destroyed_contexts; + /** + * @destroyed_worker: worker to deregister contexts, need as we + * need to take a GT PM reference and can't from destroy + * function as it might be in an atomic context (no sleeping) + */ + struct work_struct destroyed_worker; + } submission_state; /** * @submission_supported: tracks whether we support GuC submission on @@ -342,4 +376,6 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc); void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p); +void intel_guc_write_barrier(struct intel_guc *guc); + #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index 2c6ea64af7ec..621c893a009f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -176,7 +176,7 @@ static void guc_mapping_table_init(struct intel_gt *gt, for_each_engine(engine, gt, id) { u8 guc_class = engine_class_to_guc_class(engine->class); - system_info->mapping_table[guc_class][engine->instance] = + system_info->mapping_table[guc_class][ilog2(engine->logical_mask)] = engine->instance; } } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 20c710a74498..a0cc34be7b56 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -168,12 +168,15 @@ static int guc_action_register_ct_buffer(struct intel_guc *guc, u32 type, FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_2_DESC_ADDR, desc_addr), FIELD_PREP(HOST2GUC_REGISTER_CTB_REQUEST_MSG_3_BUFF_ADDR, buff_addr), }; + int ret; GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST); GEM_BUG_ON(size % SZ_4K); /* CT registration must go over MMIO */ - return intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); + ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); + + return ret > 0 ? -EPROTO : ret; } static int ct_register_buffer(struct intel_guc_ct *ct, u32 type, @@ -188,8 +191,8 @@ static int ct_register_buffer(struct intel_guc_ct *ct, u32 type, err = guc_action_register_ct_buffer(ct_to_guc(ct), type, desc_addr, buff_addr, size); if (unlikely(err)) - CT_ERROR(ct, "Failed to register %s buffer (err=%d)\n", - guc_ct_buffer_type_to_str(type), err); + CT_ERROR(ct, "Failed to register %s buffer (%pe)\n", + guc_ct_buffer_type_to_str(type), ERR_PTR(err)); return err; } @@ -201,11 +204,14 @@ static int guc_action_deregister_ct_buffer(struct intel_guc *guc, u32 type) FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_HOST2GUC_DEREGISTER_CTB), FIELD_PREP(HOST2GUC_DEREGISTER_CTB_REQUEST_MSG_1_TYPE, type), }; + int ret; GEM_BUG_ON(type != GUC_CTB_TYPE_HOST2GUC && type != GUC_CTB_TYPE_GUC2HOST); /* CT deregistration must go over MMIO */ - return intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); + ret = intel_guc_send_mmio(guc, request, ARRAY_SIZE(request), NULL, 0); + + return ret > 0 ? -EPROTO : ret; } static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type) @@ -213,8 +219,8 @@ static int ct_deregister_buffer(struct intel_guc_ct *ct, u32 type) int err = guc_action_deregister_ct_buffer(ct_to_guc(ct), type); if (unlikely(err)) - CT_ERROR(ct, "Failed to deregister %s buffer (err=%d)\n", - guc_ct_buffer_type_to_str(type), err); + CT_ERROR(ct, "Failed to deregister %s buffer (%pe)\n", + guc_ct_buffer_type_to_str(type), ERR_PTR(err)); return err; } @@ -377,28 +383,6 @@ static u32 ct_get_next_fence(struct intel_guc_ct *ct) return ++ct->requests.last_fence; } -static void write_barrier(struct intel_guc_ct *ct) -{ - struct intel_guc *guc = ct_to_guc(ct); - struct intel_gt *gt = guc_to_gt(guc); - - if (i915_gem_object_is_lmem(guc->ct.vma->obj)) { - GEM_BUG_ON(guc->send_regs.fw_domains); - /* - * This register is used by the i915 and GuC for MMIO based - * communication. Once we are in this code CTBs are the only - * method the i915 uses to communicate with the GuC so it is - * safe to write to this register (a value of 0 is NOP for MMIO - * communication). If we ever start mixing CTBs and MMIOs a new - * register will have to be chosen. - */ - intel_uncore_write_fw(gt->uncore, GEN11_SOFT_SCRATCH(0), 0); - } else { - /* wmb() sufficient for a barrier if in smem */ - wmb(); - } -} - static int ct_write(struct intel_guc_ct *ct, const u32 *action, u32 len /* in dwords */, @@ -468,7 +452,7 @@ static int ct_write(struct intel_guc_ct *ct, * make sure H2G buffer update and LRC tail update (if this triggering a * submission) are visible before updating the descriptor tail */ - write_barrier(ct); + intel_guc_write_barrier(ct_to_guc(ct)); /* update local copies */ ctb->tail = tail; @@ -522,9 +506,6 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status) err = wait_for(done, GUC_CTB_RESPONSE_TIMEOUT_LONG_MS); #undef done - if (unlikely(err)) - DRM_ERROR("CT: fence %u err %d\n", req->fence, err); - *status = req->status; return err; } @@ -722,8 +703,11 @@ retry: err = wait_for_ct_request_update(&request, status); g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); - if (unlikely(err)) + if (unlikely(err)) { + CT_ERROR(ct, "No response for request %#x (fence %u)\n", + action[0], request.fence); goto unlink; + } if (FIELD_GET(GUC_HXG_MSG_0_TYPE, *status) != GUC_HXG_TYPE_RESPONSE_SUCCESS) { err = -EIO; @@ -775,8 +759,8 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, ret = ct_send(ct, action, len, response_buf, response_buf_size, &status); if (unlikely(ret < 0)) { - CT_ERROR(ct, "Sending action %#x failed (err=%d status=%#X)\n", - action[0], ret, status); + CT_ERROR(ct, "Sending action %#x failed (%pe) status=%#X\n", + action[0], ERR_PTR(ret), status); } else if (unlikely(ret)) { CT_DEBUG(ct, "send action %#x returned %d (%#x)\n", action[0], ret, ret); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c index 887c8c8f35db..25f09a420561 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c @@ -5,14 +5,14 @@ #include -#include "gt/debugfs_gt.h" +#include "gt/intel_gt_debugfs.h" +#include "gt/uc/intel_guc_ads.h" +#include "gt/uc/intel_guc_ct.h" +#include "gt/uc/intel_guc_slpc.h" +#include "gt/uc/intel_guc_submission.h" #include "intel_guc.h" #include "intel_guc_debugfs.h" #include "intel_guc_log_debugfs.h" -#include "gt/uc/intel_guc_ct.h" -#include "gt/uc/intel_guc_ads.h" -#include "gt/uc/intel_guc_submission.h" -#include "gt/uc/intel_guc_slpc.h" static int guc_info_show(struct seq_file *m, void *data) { @@ -35,7 +35,7 @@ static int guc_info_show(struct seq_file *m, void *data) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_info); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_info); static int guc_registered_contexts_show(struct seq_file *m, void *data) { @@ -49,7 +49,7 @@ static int guc_registered_contexts_show(struct seq_file *m, void *data) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_registered_contexts); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_registered_contexts); static int guc_slpc_info_show(struct seq_file *m, void *unused) { @@ -62,7 +62,7 @@ static int guc_slpc_info_show(struct seq_file *m, void *unused) return intel_guc_slpc_print_info(slpc, &p); } -DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_slpc_info); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_slpc_info); static bool intel_eval_slpc_support(void *data) { @@ -73,7 +73,7 @@ static bool intel_eval_slpc_support(void *data) void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "guc_info", &guc_info_fops, NULL }, { "guc_registered_contexts", &guc_registered_contexts_fops, NULL }, { "guc_slpc_info", &guc_slpc_info_fops, &intel_eval_slpc_support}, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index 76fe766ad1bc..196424be0998 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -41,18 +41,21 @@ static void guc_prepare_xfer(struct intel_uncore *uncore) } /* Copy RSA signature from the fw image to HW for verification */ -static void guc_xfer_rsa(struct intel_uc_fw *guc_fw, - struct intel_uncore *uncore) +static int guc_xfer_rsa(struct intel_uc_fw *guc_fw, + struct intel_uncore *uncore) { u32 rsa[UOS_RSA_SCRATCH_COUNT]; size_t copied; int i; copied = intel_uc_fw_copy_rsa(guc_fw, rsa, sizeof(rsa)); - GEM_BUG_ON(copied < sizeof(rsa)); + if (copied < sizeof(rsa)) + return -ENOMEM; for (i = 0; i < UOS_RSA_SCRATCH_COUNT; i++) intel_uncore_write(uncore, UOS_RSA_SCRATCH(i), rsa[i]); + + return 0; } /* @@ -141,7 +144,9 @@ int intel_guc_fw_upload(struct intel_guc *guc) * by the DMA engine in one operation, whereas the RSA signature is * loaded via MMIO. */ - guc_xfer_rsa(&guc->fw, uncore); + ret = guc_xfer_rsa(&guc->fw, uncore); + if (ret) + goto out; /* * Current uCode expects the code to be loaded at 8k; locations below diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index fa4be13c8854..722933e26347 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -52,27 +52,27 @@ #define GUC_DOORBELL_INVALID 256 -#define GUC_WQ_SIZE (PAGE_SIZE * 2) - -/* Work queue item header definitions */ +/* + * Work queue item header definitions + * + * Work queue is circular buffer used to submit complex (multi-lrc) submissions + * to the GuC. A work queue item is an entry in the circular buffer. + */ #define WQ_STATUS_ACTIVE 1 #define WQ_STATUS_SUSPENDED 2 #define WQ_STATUS_CMD_ERROR 3 #define WQ_STATUS_ENGINE_ID_NOT_USED 4 #define WQ_STATUS_SUSPENDED_FROM_RESET 5 -#define WQ_TYPE_SHIFT 0 -#define WQ_TYPE_BATCH_BUF (0x1 << WQ_TYPE_SHIFT) -#define WQ_TYPE_PSEUDO (0x2 << WQ_TYPE_SHIFT) -#define WQ_TYPE_INORDER (0x3 << WQ_TYPE_SHIFT) -#define WQ_TYPE_NOOP (0x4 << WQ_TYPE_SHIFT) -#define WQ_TARGET_SHIFT 10 -#define WQ_LEN_SHIFT 16 -#define WQ_NO_WCFLUSH_WAIT (1 << 27) -#define WQ_PRESENT_WORKLOAD (1 << 28) +#define WQ_TYPE_BATCH_BUF 0x1 +#define WQ_TYPE_PSEUDO 0x2 +#define WQ_TYPE_INORDER 0x3 +#define WQ_TYPE_NOOP 0x4 +#define WQ_TYPE_MULTI_LRC 0x5 +#define WQ_TYPE_MASK GENMASK(7, 0) +#define WQ_LEN_MASK GENMASK(26, 16) -#define WQ_RING_TAIL_SHIFT 20 -#define WQ_RING_TAIL_MAX 0x7FF /* 2^11 QWords */ -#define WQ_RING_TAIL_MASK (WQ_RING_TAIL_MAX << WQ_RING_TAIL_SHIFT) +#define WQ_GUC_ID_MASK GENMASK(15, 0) +#define WQ_RING_TAIL_MASK GENMASK(28, 18) #define GUC_STAGE_DESC_ATTR_ACTIVE BIT(0) #define GUC_STAGE_DESC_ATTR_PENDING_DB BIT(1) @@ -186,7 +186,7 @@ struct guc_process_desc { u32 wq_status; u32 engine_presence; u32 priority; - u32 reserved[30]; + u32 reserved[36]; } __packed; #define CONTEXT_REGISTRATION_FLAG_KMD BIT(0) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c index 64e0b86bf258..46026c2c1722 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log_debugfs.c @@ -6,7 +6,7 @@ #include #include -#include "gt/debugfs_gt.h" +#include "gt/intel_gt_debugfs.h" #include "intel_guc.h" #include "intel_guc_log.h" #include "intel_guc_log_debugfs.h" @@ -17,7 +17,7 @@ static int guc_log_dump_show(struct seq_file *m, void *data) return intel_guc_log_dump(m->private, &p, false); } -DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_log_dump); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_log_dump); static int guc_load_err_log_dump_show(struct seq_file *m, void *data) { @@ -25,7 +25,7 @@ static int guc_load_err_log_dump_show(struct seq_file *m, void *data) return intel_guc_log_dump(m->private, &p, true); } -DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_load_err_log_dump); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(guc_load_err_log_dump); static int guc_log_level_get(void *data, u64 *val) { @@ -109,7 +109,7 @@ static const struct file_operations guc_log_relay_fops = { void intel_guc_log_debugfs_register(struct intel_guc_log *log, struct dentry *root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "guc_log_dump", &guc_log_dump_fops, NULL }, { "guc_load_err_log_dump", &guc_load_err_log_dump_fops, NULL }, { "guc_log_level", &guc_log_level_fops, NULL }, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index c7a41802b448..d7710debcd47 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -11,6 +11,7 @@ #include "gt/intel_context.h" #include "gt/intel_engine_pm.h" #include "gt/intel_engine_heartbeat.h" +#include "gt/intel_gpu_commands.h" #include "gt/intel_gt.h" #include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm.h" @@ -68,7 +69,7 @@ * fence is used to stall all requests associated with this guc_id until the * corresponding G2H returns indicating the guc_id has been deregistered. * - * guc_ids: + * submission_state.guc_ids: * Unique number associated with private GuC context data passed in during * context registration / submission / deregistration. 64k available. Simple ida * is used for allocation. @@ -89,9 +90,9 @@ * sched_engine can be submitting at a time. Currently only one sched_engine is * used for all of GuC submission but that could change in the future. * - * guc->contexts_lock - * Protects guc_id allocation for the given GuC, i.e. only one context can be - * doing guc_id allocation operations at a time for each GuC in the system. + * guc->submission_state.lock + * Global lock for GuC submission state. Protects guc_ids and destroyed contexts + * list. * * ce->guc_state.lock * Protects everything under ce->guc_state. Ensures that a context is in the @@ -103,7 +104,7 @@ * * Lock ordering rules: * sched_engine->lock -> ce->guc_state.lock - * guc->contexts_lock -> ce->guc_state.lock + * guc->submission_state.lock -> ce->guc_state.lock * * Reset races: * When a full GT reset is triggered it is assumed that some G2H responses to @@ -124,10 +125,26 @@ struct guc_virtual_engine { }; static struct intel_context * -guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags); + +static struct intel_context * +guc_create_parallel(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width); #define GUC_REQUEST_SIZE 64 /* bytes */ +/* + * We reserve 1/16 of the guc_ids for multi-lrc as these need to be contiguous + * per the GuC submission interface. A different allocation algorithm is used + * (bitmap vs. ida) between multi-lrc and single-lrc hence the reason to + * partition the guc_id space. We believe the number of multi-lrc contexts in + * use should be low and 1/16 should be sufficient. Minimum of 32 guc_ids for + * multi-lrc. + */ +#define NUMBER_MULTI_LRC_GUC_ID (GUC_MAX_LRC_DESCRIPTORS / 16) + /* * Below is a set of functions which control the GuC scheduling state which * require a lock. @@ -324,6 +341,12 @@ static inline void decr_context_committed_requests(struct intel_context *ce) GEM_BUG_ON(ce->guc_state.number_committed_requests < 0); } +static struct intel_context * +request_to_scheduling_context(struct i915_request *rq) +{ + return intel_context_to_parent(rq->context); +} + static inline bool context_guc_id_invalid(struct intel_context *ce) { return ce->guc_id.id == GUC_INVALID_LRC_ID; @@ -344,6 +367,104 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb) return rb_entry(rb, struct i915_priolist, node); } +/* + * When using multi-lrc submission a scratch memory area is reserved in the + * parent's context state for the process descriptor, work queue, and handshake + * between the parent + children contexts to insert safe preemption points + * between each of the BBs. Currently the scratch area is sized to a page. + * + * The layout of this scratch area is below: + * 0 guc_process_desc + * + sizeof(struct guc_process_desc) child go + * + CACHELINE_BYTES child join[0] + * ... + * + CACHELINE_BYTES child join[n - 1] + * ... unused + * PARENT_SCRATCH_SIZE / 2 work queue start + * ... work queue + * PARENT_SCRATCH_SIZE - 1 work queue end + */ +#define WQ_SIZE (PARENT_SCRATCH_SIZE / 2) +#define WQ_OFFSET (PARENT_SCRATCH_SIZE - WQ_SIZE) + +struct sync_semaphore { + u32 semaphore; + u8 unused[CACHELINE_BYTES - sizeof(u32)]; +}; + +struct parent_scratch { + struct guc_process_desc pdesc; + + struct sync_semaphore go; + struct sync_semaphore join[MAX_ENGINE_INSTANCE + 1]; + + u8 unused[WQ_OFFSET - sizeof(struct guc_process_desc) - + sizeof(struct sync_semaphore) * (MAX_ENGINE_INSTANCE + 2)]; + + u32 wq[WQ_SIZE / sizeof(u32)]; +}; + +static u32 __get_parent_scratch_offset(struct intel_context *ce) +{ + GEM_BUG_ON(!ce->parallel.guc.parent_page); + + return ce->parallel.guc.parent_page * PAGE_SIZE; +} + +static u32 __get_wq_offset(struct intel_context *ce) +{ + BUILD_BUG_ON(offsetof(struct parent_scratch, wq) != WQ_OFFSET); + + return __get_parent_scratch_offset(ce) + WQ_OFFSET; +} + +static struct parent_scratch * +__get_parent_scratch(struct intel_context *ce) +{ + BUILD_BUG_ON(sizeof(struct parent_scratch) != PARENT_SCRATCH_SIZE); + BUILD_BUG_ON(sizeof(struct sync_semaphore) != CACHELINE_BYTES); + + /* + * Need to subtract LRC_STATE_OFFSET here as the + * parallel.guc.parent_page is the offset into ce->state while + * ce->lrc_reg_reg is ce->state + LRC_STATE_OFFSET. + */ + return (struct parent_scratch *) + (ce->lrc_reg_state + + ((__get_parent_scratch_offset(ce) - + LRC_STATE_OFFSET) / sizeof(u32))); +} + +static struct guc_process_desc * +__get_process_desc(struct intel_context *ce) +{ + struct parent_scratch *ps = __get_parent_scratch(ce); + + return &ps->pdesc; +} + +static u32 *get_wq_pointer(struct guc_process_desc *desc, + struct intel_context *ce, + u32 wqi_size) +{ + /* + * Check for space in work queue. Caching a value of head pointer in + * intel_context structure in order reduce the number accesses to shared + * GPU memory which may be across a PCIe bus. + */ +#define AVAILABLE_SPACE \ + CIRC_SPACE(ce->parallel.guc.wqi_tail, ce->parallel.guc.wqi_head, WQ_SIZE) + if (wqi_size > AVAILABLE_SPACE) { + ce->parallel.guc.wqi_head = READ_ONCE(desc->head); + + if (wqi_size > AVAILABLE_SPACE) + return NULL; + } +#undef AVAILABLE_SPACE + + return &__get_parent_scratch(ce)->wq[ce->parallel.guc.wqi_tail / sizeof(u32)]; +} + static struct guc_lrc_desc *__get_lrc_desc(struct intel_guc *guc, u32 index) { struct guc_lrc_desc *base = guc->lrc_desc_pool_vaddr; @@ -503,10 +624,10 @@ int intel_guc_wait_for_idle(struct intel_guc *guc, long timeout) static int guc_lrc_desc_pin(struct intel_context *ce, bool loop); -static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) +static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq) { int err = 0; - struct intel_context *ce = rq->context; + struct intel_context *ce = request_to_scheduling_context(rq); u32 action[3]; int len = 0; u32 g2h_len_dw = 0; @@ -527,26 +648,17 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) GEM_BUG_ON(!atomic_read(&ce->guc_id.ref)); GEM_BUG_ON(context_guc_id_invalid(ce)); - /* - * Corner case where the GuC firmware was blown away and reloaded while - * this context was pinned. - */ - if (unlikely(!lrc_desc_registered(guc, ce->guc_id.id))) { - err = guc_lrc_desc_pin(ce, false); - if (unlikely(err)) - return err; - } - spin_lock(&ce->guc_state.lock); /* * The request / context will be run on the hardware when scheduling - * gets enabled in the unblock. + * gets enabled in the unblock. For multi-lrc we still submit the + * context to move the LRC tails. */ - if (unlikely(context_blocked(ce))) + if (unlikely(context_blocked(ce) && !intel_context_is_parent(ce))) goto out; - enabled = context_enabled(ce); + enabled = context_enabled(ce) || context_blocked(ce); if (!enabled) { action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET; @@ -565,6 +677,18 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) trace_intel_context_sched_enable(ce); atomic_inc(&guc->outstanding_submission_g2h); set_context_enabled(ce); + + /* + * Without multi-lrc KMD does the submission step (moving the + * lrc tail) so enabling scheduling is sufficient to submit the + * context. This isn't the case in multi-lrc submission as the + * GuC needs to move the tails, hence the need for another H2G + * to submit a multi-lrc context after enabling scheduling. + */ + if (intel_context_is_parent(ce)) { + action[0] = INTEL_GUC_ACTION_SCHED_CONTEXT; + err = intel_guc_send_nb(guc, action, len - 1, 0); + } } else if (!enabled) { clr_context_pending_enable(ce); intel_context_put(ce); @@ -577,6 +701,18 @@ out: return err; } +static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) +{ + int ret = __guc_add_request(guc, rq); + + if (unlikely(ret == -EBUSY)) { + guc->stalled_request = rq; + guc->submission_stall_reason = STALL_ADD_REQUEST; + } + + return ret; +} + static inline void guc_set_lrc_tail(struct i915_request *rq) { rq->context->lrc_reg_state[CTX_RING_TAIL] = @@ -588,6 +724,135 @@ static inline int rq_prio(const struct i915_request *rq) return rq->sched.attr.priority; } +static bool is_multi_lrc_rq(struct i915_request *rq) +{ + return intel_context_is_parallel(rq->context); +} + +static bool can_merge_rq(struct i915_request *rq, + struct i915_request *last) +{ + return request_to_scheduling_context(rq) == + request_to_scheduling_context(last); +} + +static u32 wq_space_until_wrap(struct intel_context *ce) +{ + return (WQ_SIZE - ce->parallel.guc.wqi_tail); +} + +static void write_wqi(struct guc_process_desc *desc, + struct intel_context *ce, + u32 wqi_size) +{ + BUILD_BUG_ON(!is_power_of_2(WQ_SIZE)); + + /* + * Ensure WQI are visible before updating tail + */ + intel_guc_write_barrier(ce_to_guc(ce)); + + ce->parallel.guc.wqi_tail = (ce->parallel.guc.wqi_tail + wqi_size) & + (WQ_SIZE - 1); + WRITE_ONCE(desc->tail, ce->parallel.guc.wqi_tail); +} + +static int guc_wq_noop_append(struct intel_context *ce) +{ + struct guc_process_desc *desc = __get_process_desc(ce); + u32 *wqi = get_wq_pointer(desc, ce, wq_space_until_wrap(ce)); + u32 len_dw = wq_space_until_wrap(ce) / sizeof(u32) - 1; + + if (!wqi) + return -EBUSY; + + GEM_BUG_ON(!FIELD_FIT(WQ_LEN_MASK, len_dw)); + + *wqi = FIELD_PREP(WQ_TYPE_MASK, WQ_TYPE_NOOP) | + FIELD_PREP(WQ_LEN_MASK, len_dw); + ce->parallel.guc.wqi_tail = 0; + + return 0; +} + +static int __guc_wq_item_append(struct i915_request *rq) +{ + struct intel_context *ce = request_to_scheduling_context(rq); + struct intel_context *child; + struct guc_process_desc *desc = __get_process_desc(ce); + unsigned int wqi_size = (ce->parallel.number_children + 4) * + sizeof(u32); + u32 *wqi; + u32 len_dw = (wqi_size / sizeof(u32)) - 1; + int ret; + + /* Ensure context is in correct state updating work queue */ + GEM_BUG_ON(!atomic_read(&ce->guc_id.ref)); + GEM_BUG_ON(context_guc_id_invalid(ce)); + GEM_BUG_ON(context_wait_for_deregister_to_register(ce)); + GEM_BUG_ON(!lrc_desc_registered(ce_to_guc(ce), ce->guc_id.id)); + + /* Insert NOOP if this work queue item will wrap the tail pointer. */ + if (wqi_size > wq_space_until_wrap(ce)) { + ret = guc_wq_noop_append(ce); + if (ret) + return ret; + } + + wqi = get_wq_pointer(desc, ce, wqi_size); + if (!wqi) + return -EBUSY; + + GEM_BUG_ON(!FIELD_FIT(WQ_LEN_MASK, len_dw)); + + *wqi++ = FIELD_PREP(WQ_TYPE_MASK, WQ_TYPE_MULTI_LRC) | + FIELD_PREP(WQ_LEN_MASK, len_dw); + *wqi++ = ce->lrc.lrca; + *wqi++ = FIELD_PREP(WQ_GUC_ID_MASK, ce->guc_id.id) | + FIELD_PREP(WQ_RING_TAIL_MASK, ce->ring->tail / sizeof(u64)); + *wqi++ = 0; /* fence_id */ + for_each_child(ce, child) + *wqi++ = child->ring->tail / sizeof(u64); + + write_wqi(desc, ce, wqi_size); + + return 0; +} + +static int guc_wq_item_append(struct intel_guc *guc, + struct i915_request *rq) +{ + struct intel_context *ce = request_to_scheduling_context(rq); + int ret = 0; + + if (likely(!intel_context_is_banned(ce))) { + ret = __guc_wq_item_append(rq); + + if (unlikely(ret == -EBUSY)) { + guc->stalled_request = rq; + guc->submission_stall_reason = STALL_MOVE_LRC_TAIL; + } + } + + return ret; +} + +static bool multi_lrc_submit(struct i915_request *rq) +{ + struct intel_context *ce = request_to_scheduling_context(rq); + + intel_ring_set_tail(rq->ring, rq->tail); + + /* + * We expect the front end (execbuf IOCTL) to set this flag on the last + * request generated from a multi-BB submission. This indicates to the + * backend (GuC interface) that we should submit this context thus + * submitting all the requests generated in parallel. + */ + return test_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, &rq->fence.flags) || + intel_context_is_banned(ce); +} + static int guc_dequeue_one_context(struct intel_guc *guc) { struct i915_sched_engine * const sched_engine = guc->sched_engine; @@ -601,7 +866,17 @@ static int guc_dequeue_one_context(struct intel_guc *guc) if (guc->stalled_request) { submit = true; last = guc->stalled_request; - goto resubmit; + + switch (guc->submission_stall_reason) { + case STALL_REGISTER_CONTEXT: + goto register_context; + case STALL_MOVE_LRC_TAIL: + goto move_lrc_tail; + case STALL_ADD_REQUEST: + goto add_request; + default: + MISSING_CASE(guc->submission_stall_reason); + } } while ((rb = rb_first_cached(&sched_engine->queue))) { @@ -609,8 +884,8 @@ static int guc_dequeue_one_context(struct intel_guc *guc) struct i915_request *rq, *rn; priolist_for_each_request_consume(rq, rn, p) { - if (last && rq->context != last->context) - goto done; + if (last && !can_merge_rq(rq, last)) + goto register_context; list_del_init(&rq->sched.link); @@ -618,33 +893,84 @@ static int guc_dequeue_one_context(struct intel_guc *guc) trace_i915_request_in(rq, 0); last = rq; - submit = true; + + if (is_multi_lrc_rq(rq)) { + /* + * We need to coalesce all multi-lrc requests in + * a relationship into a single H2G. We are + * guaranteed that all of these requests will be + * submitted sequentially. + */ + if (multi_lrc_submit(rq)) { + submit = true; + goto register_context; + } + } else { + submit = true; + } } rb_erase_cached(&p->node, &sched_engine->queue); i915_priolist_free(p); } -done: + +register_context: if (submit) { - guc_set_lrc_tail(last); -resubmit: + struct intel_context *ce = request_to_scheduling_context(last); + + if (unlikely(!lrc_desc_registered(guc, ce->guc_id.id) && + !intel_context_is_banned(ce))) { + ret = guc_lrc_desc_pin(ce, false); + if (unlikely(ret == -EPIPE)) { + goto deadlk; + } else if (ret == -EBUSY) { + guc->stalled_request = last; + guc->submission_stall_reason = + STALL_REGISTER_CONTEXT; + goto schedule_tasklet; + } else if (ret != 0) { + GEM_WARN_ON(ret); /* Unexpected */ + goto deadlk; + } + } + +move_lrc_tail: + if (is_multi_lrc_rq(last)) { + ret = guc_wq_item_append(guc, last); + if (ret == -EBUSY) { + goto schedule_tasklet; + } else if (ret != 0) { + GEM_WARN_ON(ret); /* Unexpected */ + goto deadlk; + } + } else { + guc_set_lrc_tail(last); + } + +add_request: ret = guc_add_request(guc, last); - if (unlikely(ret == -EPIPE)) + if (unlikely(ret == -EPIPE)) { + goto deadlk; + } else if (ret == -EBUSY) { + goto schedule_tasklet; + } else if (ret != 0) { + GEM_WARN_ON(ret); /* Unexpected */ goto deadlk; - else if (ret == -EBUSY) { - tasklet_schedule(&sched_engine->tasklet); - guc->stalled_request = last; - return false; } } guc->stalled_request = NULL; + guc->submission_stall_reason = STALL_NONE; return submit; deadlk: sched_engine->tasklet.callback = NULL; tasklet_disable_nosync(&sched_engine->tasklet); return false; + +schedule_tasklet: + tasklet_schedule(&sched_engine->tasklet); + return false; } static void guc_submission_tasklet(struct tasklet_struct *t) @@ -719,6 +1045,7 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc) if (deregister) guc_signal_context_fence(ce); if (destroyed) { + intel_gt_pm_put_async(guc_to_gt(guc)); release_guc_id(guc, ce); __guc_context_destroy(ce); } @@ -797,6 +1124,8 @@ static void guc_flush_submissions(struct intel_guc *guc) spin_unlock_irqrestore(&sched_engine->lock, flags); } +static void guc_flush_destroyed_contexts(struct intel_guc *guc); + void intel_guc_submission_reset_prepare(struct intel_guc *guc) { int i; @@ -815,6 +1144,7 @@ void intel_guc_submission_reset_prepare(struct intel_guc *guc) spin_unlock_irq(&guc_to_gt(guc)->irq_lock); guc_flush_submissions(guc); + guc_flush_destroyed_contexts(guc); /* * Handle any outstanding G2Hs before reset. Call IRQ handler directly @@ -929,10 +1259,15 @@ __unwind_incomplete_requests(struct intel_context *ce) static void __guc_reset_context(struct intel_context *ce, bool stalled) { + bool local_stalled; struct i915_request *rq; unsigned long flags; u32 head; + int i, number_children = ce->parallel.number_children; bool skip = false; + struct intel_context *parent = ce; + + GEM_BUG_ON(intel_context_is_child(ce)); intel_context_get(ce); @@ -958,25 +1293,38 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) if (unlikely(skip)) goto out_put; - rq = intel_context_find_active_request(ce); - if (!rq) { - head = ce->ring->tail; - stalled = false; - goto out_replay; + /* + * For each context in the relationship find the hanging request + * resetting each context / request as needed + */ + for (i = 0; i < number_children + 1; ++i) { + if (!intel_context_is_pinned(ce)) + goto next_context; + + local_stalled = false; + rq = intel_context_find_active_request(ce); + if (!rq) { + head = ce->ring->tail; + goto out_replay; + } + + if (i915_request_started(rq)) + local_stalled = true; + + GEM_BUG_ON(i915_active_is_idle(&ce->active)); + head = intel_ring_wrap(ce->ring, rq->head); + + __i915_request_reset(rq, local_stalled && stalled); +out_replay: + guc_reset_state(ce, head, local_stalled && stalled); +next_context: + if (i != number_children) + ce = list_next_entry(ce, parallel.child_link); } - if (!i915_request_started(rq)) - stalled = false; - - GEM_BUG_ON(i915_active_is_idle(&ce->active)); - head = intel_ring_wrap(ce->ring, rq->head); - __i915_request_reset(rq, stalled); - -out_replay: - guc_reset_state(ce, head, stalled); - __unwind_incomplete_requests(ce); + __unwind_incomplete_requests(parent); out_put: - intel_context_put(ce); + intel_context_put(parent); } void intel_guc_submission_reset(struct intel_guc *guc, bool stalled) @@ -997,7 +1345,8 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled) xa_unlock(&guc->context_lookup); - if (intel_context_is_pinned(ce)) + if (intel_context_is_pinned(ce) && + !intel_context_is_child(ce)) __guc_reset_context(ce, stalled); intel_context_put(ce); @@ -1089,7 +1438,8 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc) xa_unlock(&guc->context_lookup); - if (intel_context_is_pinned(ce)) + if (intel_context_is_pinned(ce) && + !intel_context_is_child(ce)) guc_cancel_context_requests(ce); intel_context_put(ce); @@ -1126,6 +1476,8 @@ void intel_guc_submission_reset_finish(struct intel_guc *guc) intel_gt_unpark_heartbeats(guc_to_gt(guc)); } +static void destroyed_worker_func(struct work_struct *w); + /* * Set up the memory resources to be shared with the GuC (via the GGTT) * at firmware loading time. @@ -1148,9 +1500,17 @@ int intel_guc_submission_init(struct intel_guc *guc) xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ); - spin_lock_init(&guc->contexts_lock); - INIT_LIST_HEAD(&guc->guc_id_list); - ida_init(&guc->guc_ids); + spin_lock_init(&guc->submission_state.lock); + INIT_LIST_HEAD(&guc->submission_state.guc_id_list); + ida_init(&guc->submission_state.guc_ids); + INIT_LIST_HEAD(&guc->submission_state.destroyed_contexts); + INIT_WORK(&guc->submission_state.destroyed_worker, + destroyed_worker_func); + + guc->submission_state.guc_ids_bitmap = + bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID, GFP_KERNEL); + if (!guc->submission_state.guc_ids_bitmap) + return -ENOMEM; return 0; } @@ -1160,8 +1520,10 @@ void intel_guc_submission_fini(struct intel_guc *guc) if (!guc->lrc_desc_pool) return; + guc_flush_destroyed_contexts(guc); guc_lrc_desc_pool_destroy(guc); i915_sched_engine_put(guc->sched_engine); + bitmap_free(guc->submission_state.guc_ids_bitmap); } static inline void queue_request(struct i915_sched_engine *sched_engine, @@ -1178,16 +1540,22 @@ static inline void queue_request(struct i915_sched_engine *sched_engine, static int guc_bypass_tasklet_submit(struct intel_guc *guc, struct i915_request *rq) { - int ret; + int ret = 0; __i915_request_submit(rq); trace_i915_request_in(rq, 0); - guc_set_lrc_tail(rq); - ret = guc_add_request(guc, rq); - if (ret == -EBUSY) - guc->stalled_request = rq; + if (is_multi_lrc_rq(rq)) { + if (multi_lrc_submit(rq)) { + ret = guc_wq_item_append(guc, rq); + if (!ret) + ret = guc_add_request(guc, rq); + } + } else { + guc_set_lrc_tail(rq); + ret = guc_add_request(guc, rq); + } if (unlikely(ret == -EPIPE)) disable_submission(guc); @@ -1195,6 +1563,16 @@ static int guc_bypass_tasklet_submit(struct intel_guc *guc, return ret; } +static bool need_tasklet(struct intel_guc *guc, struct i915_request *rq) +{ + struct i915_sched_engine *sched_engine = rq->engine->sched_engine; + struct intel_context *ce = request_to_scheduling_context(rq); + + return submission_disabled(guc) || guc->stalled_request || + !i915_sched_engine_is_empty(sched_engine) || + !lrc_desc_registered(guc, ce->guc_id.id); +} + static void guc_submit_request(struct i915_request *rq) { struct i915_sched_engine *sched_engine = rq->engine->sched_engine; @@ -1204,8 +1582,7 @@ static void guc_submit_request(struct i915_request *rq) /* Will be called from irq-context when using foreign fences. */ spin_lock_irqsave(&sched_engine->lock, flags); - if (submission_disabled(guc) || guc->stalled_request || - !i915_sched_engine_is_empty(sched_engine)) + if (need_tasklet(guc, rq)) queue_request(sched_engine, rq, rq_prio(rq)); else if (guc_bypass_tasklet_submit(guc, rq) == -EBUSY) tasklet_hi_schedule(&sched_engine->tasklet); @@ -1213,17 +1590,43 @@ static void guc_submit_request(struct i915_request *rq) spin_unlock_irqrestore(&sched_engine->lock, flags); } -static int new_guc_id(struct intel_guc *guc) +static int new_guc_id(struct intel_guc *guc, struct intel_context *ce) { - return ida_simple_get(&guc->guc_ids, 0, - GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL | - __GFP_RETRY_MAYFAIL | __GFP_NOWARN); + int ret; + + GEM_BUG_ON(intel_context_is_child(ce)); + + if (intel_context_is_parent(ce)) + ret = bitmap_find_free_region(guc->submission_state.guc_ids_bitmap, + NUMBER_MULTI_LRC_GUC_ID, + order_base_2(ce->parallel.number_children + + 1)); + else + ret = ida_simple_get(&guc->submission_state.guc_ids, + NUMBER_MULTI_LRC_GUC_ID, + GUC_MAX_LRC_DESCRIPTORS, + GFP_KERNEL | __GFP_RETRY_MAYFAIL | + __GFP_NOWARN); + if (unlikely(ret < 0)) + return ret; + + ce->guc_id.id = ret; + return 0; } static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce) { + GEM_BUG_ON(intel_context_is_child(ce)); + if (!context_guc_id_invalid(ce)) { - ida_simple_remove(&guc->guc_ids, ce->guc_id.id); + if (intel_context_is_parent(ce)) + bitmap_release_region(guc->submission_state.guc_ids_bitmap, + ce->guc_id.id, + order_base_2(ce->parallel.number_children + + 1)); + else + ida_simple_remove(&guc->submission_state.guc_ids, + ce->guc_id.id); reset_lrc_desc(guc, ce->guc_id.id); set_context_guc_id_invalid(ce); } @@ -1235,54 +1638,69 @@ static void release_guc_id(struct intel_guc *guc, struct intel_context *ce) { unsigned long flags; - spin_lock_irqsave(&guc->contexts_lock, flags); + spin_lock_irqsave(&guc->submission_state.lock, flags); __release_guc_id(guc, ce); - spin_unlock_irqrestore(&guc->contexts_lock, flags); + spin_unlock_irqrestore(&guc->submission_state.lock, flags); } -static int steal_guc_id(struct intel_guc *guc) +static int steal_guc_id(struct intel_guc *guc, struct intel_context *ce) { - struct intel_context *ce; - int guc_id; + struct intel_context *cn; - lockdep_assert_held(&guc->contexts_lock); + lockdep_assert_held(&guc->submission_state.lock); + GEM_BUG_ON(intel_context_is_child(ce)); + GEM_BUG_ON(intel_context_is_parent(ce)); - if (!list_empty(&guc->guc_id_list)) { - ce = list_first_entry(&guc->guc_id_list, + if (!list_empty(&guc->submission_state.guc_id_list)) { + cn = list_first_entry(&guc->submission_state.guc_id_list, struct intel_context, guc_id.link); - GEM_BUG_ON(atomic_read(&ce->guc_id.ref)); - GEM_BUG_ON(context_guc_id_invalid(ce)); + GEM_BUG_ON(atomic_read(&cn->guc_id.ref)); + GEM_BUG_ON(context_guc_id_invalid(cn)); + GEM_BUG_ON(intel_context_is_child(cn)); + GEM_BUG_ON(intel_context_is_parent(cn)); - list_del_init(&ce->guc_id.link); - guc_id = ce->guc_id.id; + list_del_init(&cn->guc_id.link); + ce->guc_id = cn->guc_id; spin_lock(&ce->guc_state.lock); - clr_context_registered(ce); + clr_context_registered(cn); spin_unlock(&ce->guc_state.lock); - set_context_guc_id_invalid(ce); - return guc_id; + set_context_guc_id_invalid(cn); + + return 0; } else { return -EAGAIN; } } -static int assign_guc_id(struct intel_guc *guc, u16 *out) +static int assign_guc_id(struct intel_guc *guc, struct intel_context *ce) { int ret; - lockdep_assert_held(&guc->contexts_lock); + lockdep_assert_held(&guc->submission_state.lock); + GEM_BUG_ON(intel_context_is_child(ce)); - ret = new_guc_id(guc); + ret = new_guc_id(guc, ce); if (unlikely(ret < 0)) { - ret = steal_guc_id(guc); + if (intel_context_is_parent(ce)) + return -ENOSPC; + + ret = steal_guc_id(guc, ce); if (ret < 0) return ret; } - *out = ret; + if (intel_context_is_parent(ce)) { + struct intel_context *child; + int i = 1; + + for_each_child(ce, child) + child->guc_id.id = ce->guc_id.id + i++; + } + return 0; } @@ -1295,12 +1713,12 @@ static int pin_guc_id(struct intel_guc *guc, struct intel_context *ce) GEM_BUG_ON(atomic_read(&ce->guc_id.ref)); try_again: - spin_lock_irqsave(&guc->contexts_lock, flags); + spin_lock_irqsave(&guc->submission_state.lock, flags); might_lock(&ce->guc_state.lock); if (context_guc_id_invalid(ce)) { - ret = assign_guc_id(guc, &ce->guc_id.id); + ret = assign_guc_id(guc, ce); if (ret) goto out_unlock; ret = 1; /* Indidcates newly assigned guc_id */ @@ -1310,7 +1728,7 @@ try_again: atomic_inc(&ce->guc_id.ref); out_unlock: - spin_unlock_irqrestore(&guc->contexts_lock, flags); + spin_unlock_irqrestore(&guc->submission_state.lock, flags); /* * -EAGAIN indicates no guc_id are available, let's retire any @@ -1342,15 +1760,42 @@ static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce) unsigned long flags; GEM_BUG_ON(atomic_read(&ce->guc_id.ref) < 0); + GEM_BUG_ON(intel_context_is_child(ce)); - if (unlikely(context_guc_id_invalid(ce))) + if (unlikely(context_guc_id_invalid(ce) || + intel_context_is_parent(ce))) return; - spin_lock_irqsave(&guc->contexts_lock, flags); + spin_lock_irqsave(&guc->submission_state.lock, flags); if (!context_guc_id_invalid(ce) && list_empty(&ce->guc_id.link) && !atomic_read(&ce->guc_id.ref)) - list_add_tail(&ce->guc_id.link, &guc->guc_id_list); - spin_unlock_irqrestore(&guc->contexts_lock, flags); + list_add_tail(&ce->guc_id.link, + &guc->submission_state.guc_id_list); + spin_unlock_irqrestore(&guc->submission_state.lock, flags); +} + +static int __guc_action_register_multi_lrc(struct intel_guc *guc, + struct intel_context *ce, + u32 guc_id, + u32 offset, + bool loop) +{ + struct intel_context *child; + u32 action[4 + MAX_ENGINE_INSTANCE]; + int len = 0; + + GEM_BUG_ON(ce->parallel.number_children > MAX_ENGINE_INSTANCE); + + action[len++] = INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC; + action[len++] = guc_id; + action[len++] = ce->parallel.number_children + 1; + action[len++] = offset; + for_each_child(ce, child) { + offset += sizeof(struct guc_lrc_desc); + action[len++] = offset; + } + + return guc_submission_send_busy_loop(guc, action, len, 0, loop); } static int __guc_action_register_context(struct intel_guc *guc, @@ -1375,9 +1820,15 @@ static int register_context(struct intel_context *ce, bool loop) ce->guc_id.id * sizeof(struct guc_lrc_desc); int ret; + GEM_BUG_ON(intel_context_is_child(ce)); trace_intel_context_register(ce); - ret = __guc_action_register_context(guc, ce->guc_id.id, offset, loop); + if (intel_context_is_parent(ce)) + ret = __guc_action_register_multi_lrc(guc, ce, ce->guc_id.id, + offset, loop); + else + ret = __guc_action_register_context(guc, ce->guc_id.id, offset, + loop); if (likely(!ret)) { unsigned long flags; @@ -1406,26 +1857,31 @@ static int deregister_context(struct intel_context *ce, u32 guc_id) { struct intel_guc *guc = ce_to_guc(ce); + GEM_BUG_ON(intel_context_is_child(ce)); trace_intel_context_deregister(ce); return __guc_action_deregister_context(guc, guc_id); } -static intel_engine_mask_t adjust_engine_mask(u8 class, intel_engine_mask_t mask) +static inline void clear_children_join_go_memory(struct intel_context *ce) { - switch (class) { - case RENDER_CLASS: - return mask >> RCS0; - case VIDEO_ENHANCEMENT_CLASS: - return mask >> VECS0; - case VIDEO_DECODE_CLASS: - return mask >> VCS0; - case COPY_ENGINE_CLASS: - return mask >> BCS0; - default: - MISSING_CASE(class); - return 0; - } + struct parent_scratch *ps = __get_parent_scratch(ce); + int i; + + ps->go.semaphore = 0; + for (i = 0; i < ce->parallel.number_children + 1; ++i) + ps->join[i].semaphore = 0; +} + +static inline u32 get_children_go_value(struct intel_context *ce) +{ + return __get_parent_scratch(ce)->go.semaphore; +} + +static inline u32 get_children_join_value(struct intel_context *ce, + u8 child_index) +{ + return __get_parent_scratch(ce)->join[child_index].semaphore; } static void guc_context_policy_init(struct intel_engine_cs *engine, @@ -1450,6 +1906,7 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop) struct guc_lrc_desc *desc; bool context_registered; intel_wakeref_t wakeref; + struct intel_context *child; int ret = 0; GEM_BUG_ON(!engine->mask); @@ -1469,13 +1926,49 @@ static int guc_lrc_desc_pin(struct intel_context *ce, bool loop) desc = __get_lrc_desc(guc, desc_idx); desc->engine_class = engine_class_to_guc_class(engine->class); - desc->engine_submit_mask = adjust_engine_mask(engine->class, - engine->mask); + desc->engine_submit_mask = engine->logical_mask; desc->hw_context_desc = ce->lrc.lrca; desc->priority = ce->guc_state.prio; desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; guc_context_policy_init(engine, desc); + /* + * If context is a parent, we need to register a process descriptor + * describing a work queue and register all child contexts. + */ + if (intel_context_is_parent(ce)) { + struct guc_process_desc *pdesc; + + ce->parallel.guc.wqi_tail = 0; + ce->parallel.guc.wqi_head = 0; + + desc->process_desc = i915_ggtt_offset(ce->state) + + __get_parent_scratch_offset(ce); + desc->wq_addr = i915_ggtt_offset(ce->state) + + __get_wq_offset(ce); + desc->wq_size = WQ_SIZE; + + pdesc = __get_process_desc(ce); + memset(pdesc, 0, sizeof(*(pdesc))); + pdesc->stage_id = ce->guc_id.id; + pdesc->wq_base_addr = desc->wq_addr; + pdesc->wq_size_bytes = desc->wq_size; + pdesc->wq_status = WQ_STATUS_ACTIVE; + + for_each_child(ce, child) { + desc = __get_lrc_desc(guc, child->guc_id.id); + + desc->engine_class = + engine_class_to_guc_class(engine->class); + desc->hw_context_desc = child->lrc.lrca; + desc->priority = ce->guc_state.prio; + desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; + guc_context_policy_init(engine, desc); + } + + clear_children_join_go_memory(ce); + } + /* * The context_lookup xarray is used to determine if the hardware * context is currently registered. There are two cases in which it @@ -1559,7 +2052,12 @@ static int guc_context_pre_pin(struct intel_context *ce, static int guc_context_pin(struct intel_context *ce, void *vaddr) { - return __guc_context_pin(ce, ce->engine, vaddr); + int ret = __guc_context_pin(ce, ce->engine, vaddr); + + if (likely(!ret && !intel_context_is_barrier(ce))) + intel_engine_pm_get(ce->engine); + + return ret; } static void guc_context_unpin(struct intel_context *ce) @@ -1568,6 +2066,9 @@ static void guc_context_unpin(struct intel_context *ce) unpin_guc_id(guc, ce); lrc_unpin(ce); + + if (likely(!intel_context_is_barrier(ce))) + intel_engine_pm_put_async(ce->engine); } static void guc_context_post_unpin(struct intel_context *ce) @@ -1602,6 +2103,7 @@ static void __guc_context_sched_disable(struct intel_guc *guc, GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID); + GEM_BUG_ON(intel_context_is_child(ce)); trace_intel_context_sched_disable(ce); guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), @@ -1653,6 +2155,8 @@ static struct i915_sw_fence *guc_context_block(struct intel_context *ce) u16 guc_id; bool enabled; + GEM_BUG_ON(intel_context_is_child(ce)); + spin_lock_irqsave(&ce->guc_state.lock, flags); incr_context_blocked(ce); @@ -1707,6 +2211,7 @@ static void guc_context_unblock(struct intel_context *ce) bool enable; GEM_BUG_ON(context_enabled(ce)); + GEM_BUG_ON(intel_context_is_child(ce)); spin_lock_irqsave(&ce->guc_state.lock, flags); @@ -1733,11 +2238,14 @@ static void guc_context_unblock(struct intel_context *ce) static void guc_context_cancel_request(struct intel_context *ce, struct i915_request *rq) { + struct intel_context *block_context = + request_to_scheduling_context(rq); + if (i915_sw_fence_signaled(&rq->submit)) { struct i915_sw_fence *fence; intel_context_get(ce); - fence = guc_context_block(ce); + fence = guc_context_block(block_context); i915_sw_fence_wait(fence); if (!i915_request_completed(rq)) { __i915_request_skip(rq); @@ -1751,7 +2259,7 @@ static void guc_context_cancel_request(struct intel_context *ce, */ flush_work(&ce_to_guc(ce)->ct.requests.worker); - guc_context_unblock(ce); + guc_context_unblock(block_context); intel_context_put(ce); } } @@ -1777,6 +2285,8 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq) intel_wakeref_t wakeref; unsigned long flags; + GEM_BUG_ON(intel_context_is_child(ce)); + guc_flush_submissions(guc); spin_lock_irqsave(&ce->guc_state.lock, flags); @@ -1827,6 +2337,8 @@ static void guc_context_sched_disable(struct intel_context *ce) intel_wakeref_t wakeref; u16 guc_id; + GEM_BUG_ON(intel_context_is_child(ce)); + spin_lock_irqsave(&ce->guc_state.lock, flags); /* @@ -1857,11 +2369,30 @@ unpin: static inline void guc_lrc_desc_unpin(struct intel_context *ce) { struct intel_guc *guc = ce_to_guc(ce); + struct intel_gt *gt = guc_to_gt(guc); + unsigned long flags; + bool disabled; + GEM_BUG_ON(!intel_gt_pm_is_awake(gt)); GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id.id)); GEM_BUG_ON(ce != __get_context(guc, ce->guc_id.id)); GEM_BUG_ON(context_enabled(ce)); + /* Seal race with Reset */ + spin_lock_irqsave(&ce->guc_state.lock, flags); + disabled = submission_disabled(guc); + if (likely(!disabled)) { + __intel_gt_pm_get(gt); + set_context_destroyed(ce); + clr_context_registered(ce); + } + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + if (unlikely(disabled)) { + release_guc_id(guc, ce); + __guc_context_destroy(ce); + return; + } + deregister_context(ce, ce->guc_id.id); } @@ -1889,78 +2420,86 @@ static void __guc_context_destroy(struct intel_context *ce) } } +static void guc_flush_destroyed_contexts(struct intel_guc *guc) +{ + struct intel_context *ce, *cn; + unsigned long flags; + + GEM_BUG_ON(!submission_disabled(guc) && + guc_submission_initialized(guc)); + + spin_lock_irqsave(&guc->submission_state.lock, flags); + list_for_each_entry_safe(ce, cn, + &guc->submission_state.destroyed_contexts, + destroyed_link) { + list_del_init(&ce->destroyed_link); + __release_guc_id(guc, ce); + __guc_context_destroy(ce); + } + spin_unlock_irqrestore(&guc->submission_state.lock, flags); +} + +static void deregister_destroyed_contexts(struct intel_guc *guc) +{ + struct intel_context *ce, *cn; + unsigned long flags; + + spin_lock_irqsave(&guc->submission_state.lock, flags); + list_for_each_entry_safe(ce, cn, + &guc->submission_state.destroyed_contexts, + destroyed_link) { + list_del_init(&ce->destroyed_link); + guc_lrc_desc_unpin(ce); + } + spin_unlock_irqrestore(&guc->submission_state.lock, flags); +} + +static void destroyed_worker_func(struct work_struct *w) +{ + struct intel_guc *guc = container_of(w, struct intel_guc, + submission_state.destroyed_worker); + struct intel_gt *gt = guc_to_gt(guc); + int tmp; + + with_intel_gt_pm(gt, tmp) + deregister_destroyed_contexts(guc); +} + static void guc_context_destroy(struct kref *kref) { struct intel_context *ce = container_of(kref, typeof(*ce), ref); - struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm; struct intel_guc *guc = ce_to_guc(ce); - intel_wakeref_t wakeref; unsigned long flags; - bool disabled; + bool destroy; /* * If the guc_id is invalid this context has been stolen and we can free * it immediately. Also can be freed immediately if the context is not * registered with the GuC or the GuC is in the middle of a reset. */ - if (context_guc_id_invalid(ce)) { - __guc_context_destroy(ce); - return; - } else if (submission_disabled(guc) || - !lrc_desc_registered(guc, ce->guc_id.id)) { - release_guc_id(guc, ce); + spin_lock_irqsave(&guc->submission_state.lock, flags); + destroy = submission_disabled(guc) || context_guc_id_invalid(ce) || + !lrc_desc_registered(guc, ce->guc_id.id); + if (likely(!destroy)) { + if (!list_empty(&ce->guc_id.link)) + list_del_init(&ce->guc_id.link); + list_add_tail(&ce->destroyed_link, + &guc->submission_state.destroyed_contexts); + } else { + __release_guc_id(guc, ce); + } + spin_unlock_irqrestore(&guc->submission_state.lock, flags); + if (unlikely(destroy)) { __guc_context_destroy(ce); return; } /* - * We have to acquire the context spinlock and check guc_id again, if it - * is valid it hasn't been stolen and needs to be deregistered. We - * delete this context from the list of unpinned guc_id available to - * steal to seal a race with guc_lrc_desc_pin(). When the G2H CTB - * returns indicating this context has been deregistered the guc_id is - * returned to the pool of available guc_id. + * We use a worker to issue the H2G to deregister the context as we can + * take the GT PM for the first time which isn't allowed from an atomic + * context. */ - spin_lock_irqsave(&guc->contexts_lock, flags); - if (context_guc_id_invalid(ce)) { - spin_unlock_irqrestore(&guc->contexts_lock, flags); - __guc_context_destroy(ce); - return; - } - - if (!list_empty(&ce->guc_id.link)) - list_del_init(&ce->guc_id.link); - spin_unlock_irqrestore(&guc->contexts_lock, flags); - - /* Seal race with Reset */ - spin_lock_irqsave(&ce->guc_state.lock, flags); - disabled = submission_disabled(guc); - if (likely(!disabled)) { - set_context_destroyed(ce); - clr_context_registered(ce); - } - spin_unlock_irqrestore(&ce->guc_state.lock, flags); - if (unlikely(disabled)) { - release_guc_id(guc, ce); - __guc_context_destroy(ce); - return; - } - - /* - * We defer GuC context deregistration until the context is destroyed - * in order to save on CTBs. With this optimization ideally we only need - * 1 CTB to register the context during the first pin and 1 CTB to - * deregister the context when the context is destroyed. Without this - * optimization, a CTB would be needed every pin & unpin. - * - * XXX: Need to acqiure the runtime wakeref as this can be triggered - * from context_free_worker when runtime wakeref is not held. - * guc_lrc_desc_unpin requires the runtime as a GuC register is written - * in H2G CTB to deregister the context. A future patch may defer this - * H2G CTB if the runtime wakeref is zero. - */ - with_intel_runtime_pm(runtime_pm, wakeref) - guc_lrc_desc_unpin(ce); + queue_work(system_unbound_wq, &guc->submission_state.destroyed_worker); } static int guc_context_alloc(struct intel_context *ce) @@ -2056,9 +2595,10 @@ static inline bool new_guc_prio_higher(u8 old_guc_prio, u8 new_guc_prio) static void add_to_context(struct i915_request *rq) { - struct intel_context *ce = rq->context; + struct intel_context *ce = request_to_scheduling_context(rq); u8 new_guc_prio = map_i915_prio_to_guc_prio(rq_prio(rq)); + GEM_BUG_ON(intel_context_is_child(ce)); GEM_BUG_ON(rq->guc_prio == GUC_PRIO_FINI); spin_lock(&ce->guc_state.lock); @@ -2091,7 +2631,9 @@ static void guc_prio_fini(struct i915_request *rq, struct intel_context *ce) static void remove_from_context(struct i915_request *rq) { - struct intel_context *ce = rq->context; + struct intel_context *ce = request_to_scheduling_context(rq); + + GEM_BUG_ON(intel_context_is_child(ce)); spin_lock_irq(&ce->guc_state.lock); @@ -2132,6 +2674,7 @@ static const struct intel_context_ops guc_context_ops = { .destroy = guc_context_destroy, .create_virtual = guc_create_virtual, + .create_parallel = guc_create_parallel, }; static void submit_work_cb(struct irq_work *wrk) @@ -2168,6 +2711,8 @@ static void guc_signal_context_fence(struct intel_context *ce) { unsigned long flags; + GEM_BUG_ON(intel_context_is_child(ce)); + spin_lock_irqsave(&ce->guc_state.lock, flags); clr_context_wait_for_deregister_to_register(ce); __guc_signal_context_fence(ce); @@ -2198,7 +2743,7 @@ static void guc_context_init(struct intel_context *ce) static int guc_request_alloc(struct i915_request *rq) { - struct intel_context *ce = rq->context; + struct intel_context *ce = request_to_scheduling_context(rq); struct intel_guc *guc = ce_to_guc(ce); unsigned long flags; int ret; @@ -2302,8 +2847,30 @@ static int guc_virtual_context_pre_pin(struct intel_context *ce, static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) { struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + int ret = __guc_context_pin(ce, engine, vaddr); + intel_engine_mask_t tmp, mask = ce->engine->mask; - return __guc_context_pin(ce, engine, vaddr); + if (likely(!ret)) + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) + intel_engine_pm_get(engine); + + return ret; +} + +static void guc_virtual_context_unpin(struct intel_context *ce) +{ + intel_engine_mask_t tmp, mask = ce->engine->mask; + struct intel_engine_cs *engine; + struct intel_guc *guc = ce_to_guc(ce); + + GEM_BUG_ON(context_enabled(ce)); + GEM_BUG_ON(intel_context_is_barrier(ce)); + + unpin_guc_id(guc, ce); + lrc_unpin(ce); + + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) + intel_engine_pm_put_async(engine); } static void guc_virtual_context_enter(struct intel_context *ce) @@ -2340,7 +2907,7 @@ static const struct intel_context_ops virtual_guc_context_ops = { .pre_pin = guc_virtual_context_pre_pin, .pin = guc_virtual_context_pin, - .unpin = guc_context_unpin, + .unpin = guc_virtual_context_unpin, .post_unpin = guc_context_post_unpin, .ban = guc_context_ban, @@ -2357,6 +2924,201 @@ static const struct intel_context_ops virtual_guc_context_ops = { .get_sibling = guc_virtual_get_sibling, }; +static int guc_parent_context_pin(struct intel_context *ce, void *vaddr) +{ + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + struct intel_guc *guc = ce_to_guc(ce); + int ret; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + + ret = pin_guc_id(guc, ce); + if (unlikely(ret < 0)) + return ret; + + return __guc_context_pin(ce, engine, vaddr); +} + +static int guc_child_context_pin(struct intel_context *ce, void *vaddr) +{ + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + + GEM_BUG_ON(!intel_context_is_child(ce)); + GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + + __intel_context_pin(ce->parallel.parent); + return __guc_context_pin(ce, engine, vaddr); +} + +static void guc_parent_context_unpin(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + + GEM_BUG_ON(context_enabled(ce)); + GEM_BUG_ON(intel_context_is_barrier(ce)); + GEM_BUG_ON(!intel_context_is_parent(ce)); + GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + + if (ce->parallel.last_rq) + i915_request_put(ce->parallel.last_rq); + unpin_guc_id(guc, ce); + lrc_unpin(ce); +} + +static void guc_child_context_unpin(struct intel_context *ce) +{ + GEM_BUG_ON(context_enabled(ce)); + GEM_BUG_ON(intel_context_is_barrier(ce)); + GEM_BUG_ON(!intel_context_is_child(ce)); + GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + + lrc_unpin(ce); +} + +static void guc_child_context_post_unpin(struct intel_context *ce) +{ + GEM_BUG_ON(!intel_context_is_child(ce)); + GEM_BUG_ON(!intel_context_is_pinned(ce->parallel.parent)); + GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + + lrc_post_unpin(ce); + intel_context_unpin(ce->parallel.parent); +} + +static void guc_child_context_destroy(struct kref *kref) +{ + struct intel_context *ce = container_of(kref, typeof(*ce), ref); + + __guc_context_destroy(ce); +} + +static const struct intel_context_ops virtual_parent_context_ops = { + .alloc = guc_virtual_context_alloc, + + .pre_pin = guc_context_pre_pin, + .pin = guc_parent_context_pin, + .unpin = guc_parent_context_unpin, + .post_unpin = guc_context_post_unpin, + + .ban = guc_context_ban, + + .cancel_request = guc_context_cancel_request, + + .enter = guc_virtual_context_enter, + .exit = guc_virtual_context_exit, + + .sched_disable = guc_context_sched_disable, + + .destroy = guc_context_destroy, + + .get_sibling = guc_virtual_get_sibling, +}; + +static const struct intel_context_ops virtual_child_context_ops = { + .alloc = guc_virtual_context_alloc, + + .pre_pin = guc_context_pre_pin, + .pin = guc_child_context_pin, + .unpin = guc_child_context_unpin, + .post_unpin = guc_child_context_post_unpin, + + .cancel_request = guc_context_cancel_request, + + .enter = guc_virtual_context_enter, + .exit = guc_virtual_context_exit, + + .destroy = guc_child_context_destroy, + + .get_sibling = guc_virtual_get_sibling, +}; + +/* + * The below override of the breadcrumbs is enabled when the user configures a + * context for parallel submission (multi-lrc, parent-child). + * + * The overridden breadcrumbs implements an algorithm which allows the GuC to + * safely preempt all the hw contexts configured for parallel submission + * between each BB. The contract between the i915 and GuC is if the parent + * context can be preempted, all the children can be preempted, and the GuC will + * always try to preempt the parent before the children. A handshake between the + * parent / children breadcrumbs ensures the i915 holds up its end of the deal + * creating a window to preempt between each set of BBs. + */ +static int emit_bb_start_parent_no_preempt_mid_batch(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags); +static int emit_bb_start_child_no_preempt_mid_batch(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags); +static u32 * +emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq, + u32 *cs); +static u32 * +emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq, + u32 *cs); + +static struct intel_context * +guc_create_parallel(struct intel_engine_cs **engines, + unsigned int num_siblings, + unsigned int width) +{ + struct intel_engine_cs **siblings = NULL; + struct intel_context *parent = NULL, *ce, *err; + int i, j; + + siblings = kmalloc_array(num_siblings, + sizeof(*siblings), + GFP_KERNEL); + if (!siblings) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < width; ++i) { + for (j = 0; j < num_siblings; ++j) + siblings[j] = engines[i * num_siblings + j]; + + ce = intel_engine_create_virtual(siblings, num_siblings, + FORCE_VIRTUAL); + if (!ce) { + err = ERR_PTR(-ENOMEM); + goto unwind; + } + + if (i == 0) { + parent = ce; + parent->ops = &virtual_parent_context_ops; + } else { + ce->ops = &virtual_child_context_ops; + intel_context_bind_parent_child(parent, ce); + } + } + + parent->parallel.fence_context = dma_fence_context_alloc(1); + + parent->engine->emit_bb_start = + emit_bb_start_parent_no_preempt_mid_batch; + parent->engine->emit_fini_breadcrumb = + emit_fini_breadcrumb_parent_no_preempt_mid_batch; + parent->engine->emit_fini_breadcrumb_dw = + 12 + 4 * parent->parallel.number_children; + for_each_child(parent, ce) { + ce->engine->emit_bb_start = + emit_bb_start_child_no_preempt_mid_batch; + ce->engine->emit_fini_breadcrumb = + emit_fini_breadcrumb_child_no_preempt_mid_batch; + ce->engine->emit_fini_breadcrumb_dw = 16; + } + + kfree(siblings); + return parent; + +unwind: + if (parent) + intel_context_put(parent); + kfree(siblings); + return err; +} + static bool guc_irq_enable_breadcrumbs(struct intel_breadcrumbs *b) { @@ -2416,7 +3178,7 @@ static void guc_init_breadcrumbs(struct intel_engine_cs *engine) static void guc_bump_inflight_request_prio(struct i915_request *rq, int prio) { - struct intel_context *ce = rq->context; + struct intel_context *ce = request_to_scheduling_context(rq); u8 new_guc_prio = map_i915_prio_to_guc_prio(prio); /* Short circuit function */ @@ -2439,7 +3201,7 @@ static void guc_bump_inflight_request_prio(struct i915_request *rq, static void guc_retire_inflight_request_prio(struct i915_request *rq) { - struct intel_context *ce = rq->context; + struct intel_context *ce = request_to_scheduling_context(rq); spin_lock(&ce->guc_state.lock); guc_prio_fini(rq, ce); @@ -2477,6 +3239,8 @@ static void guc_sanitize(struct intel_engine_cs *engine) /* And scrub the dirty cachelines for the HWSP */ clflush_cache_range(engine->status_page.addr, PAGE_SIZE); + + intel_engine_reset_pinned_contexts(engine); } static void setup_hwsp(struct intel_engine_cs *engine) @@ -2552,9 +3316,13 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc) * and even it did this code would be run again. */ - for_each_engine(engine, gt, id) - if (engine->kernel_context) - guc_kernel_context_pin(guc, engine->kernel_context); + for_each_engine(engine, gt, id) { + struct intel_context *ce; + + list_for_each_entry(ce, &engine->pinned_contexts_list, + pinned_contexts_link) + guc_kernel_context_pin(guc, ce); + } } static void guc_release(struct intel_engine_cs *engine) @@ -2747,6 +3515,12 @@ g2h_context_lookup(struct intel_guc *guc, u32 desc_idx) return NULL; } + if (unlikely(intel_context_is_child(ce))) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Context is child, desc_idx %u", desc_idx); + return NULL; + } + return ce; } @@ -2790,6 +3564,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, intel_context_put(ce); } else if (context_destroyed(ce)) { /* Context has been destroyed */ + intel_gt_pm_put_async(guc_to_gt(guc)); release_guc_id(guc, ce); __guc_context_destroy(ce); } @@ -3116,6 +3891,25 @@ static inline void guc_log_context_priority(struct drm_printer *p, drm_printf(p, "\n"); } +static inline void guc_log_context(struct drm_printer *p, + struct intel_context *ce) +{ + drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id); + drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca); + drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", + ce->ring->head, + ce->lrc_reg_state[CTX_RING_HEAD]); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", + ce->ring->tail, + ce->lrc_reg_state[CTX_RING_TAIL]); + drm_printf(p, "\t\tContext Pin Count: %u\n", + atomic_read(&ce->pin_count)); + drm_printf(p, "\t\tGuC ID Ref Count: %u\n", + atomic_read(&ce->guc_id.ref)); + drm_printf(p, "\t\tSchedule State: 0x%x\n\n", + ce->guc_state.sched_state); +} + void intel_guc_submission_print_context_info(struct intel_guc *guc, struct drm_printer *p) { @@ -3125,28 +3919,310 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, xa_lock_irqsave(&guc->context_lookup, flags); xa_for_each(&guc->context_lookup, index, ce) { - drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id); - drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca); - drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", - ce->ring->head, - ce->lrc_reg_state[CTX_RING_HEAD]); - drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", - ce->ring->tail, - ce->lrc_reg_state[CTX_RING_TAIL]); - drm_printf(p, "\t\tContext Pin Count: %u\n", - atomic_read(&ce->pin_count)); - drm_printf(p, "\t\tGuC ID Ref Count: %u\n", - atomic_read(&ce->guc_id.ref)); - drm_printf(p, "\t\tSchedule State: 0x%x\n\n", - ce->guc_state.sched_state); + GEM_BUG_ON(intel_context_is_child(ce)); + guc_log_context(p, ce); guc_log_context_priority(p, ce); + + if (intel_context_is_parent(ce)) { + struct guc_process_desc *desc = __get_process_desc(ce); + struct intel_context *child; + + drm_printf(p, "\t\tNumber children: %u\n", + ce->parallel.number_children); + drm_printf(p, "\t\tWQI Head: %u\n", + READ_ONCE(desc->head)); + drm_printf(p, "\t\tWQI Tail: %u\n", + READ_ONCE(desc->tail)); + drm_printf(p, "\t\tWQI Status: %u\n\n", + READ_ONCE(desc->wq_status)); + + if (ce->engine->emit_bb_start == + emit_bb_start_parent_no_preempt_mid_batch) { + u8 i; + + drm_printf(p, "\t\tChildren Go: %u\n\n", + get_children_go_value(ce)); + for (i = 0; i < ce->parallel.number_children; ++i) + drm_printf(p, "\t\tChildren Join: %u\n", + get_children_join_value(ce, i)); + } + + for_each_child(ce, child) + guc_log_context(p, child); + } } xa_unlock_irqrestore(&guc->context_lookup, flags); } +static inline u32 get_children_go_addr(struct intel_context *ce) +{ + GEM_BUG_ON(!intel_context_is_parent(ce)); + + return i915_ggtt_offset(ce->state) + + __get_parent_scratch_offset(ce) + + offsetof(struct parent_scratch, go.semaphore); +} + +static inline u32 get_children_join_addr(struct intel_context *ce, + u8 child_index) +{ + GEM_BUG_ON(!intel_context_is_parent(ce)); + + return i915_ggtt_offset(ce->state) + + __get_parent_scratch_offset(ce) + + offsetof(struct parent_scratch, join[child_index].semaphore); +} + +#define PARENT_GO_BB 1 +#define PARENT_GO_FINI_BREADCRUMB 0 +#define CHILD_GO_BB 1 +#define CHILD_GO_FINI_BREADCRUMB 0 +static int emit_bb_start_parent_no_preempt_mid_batch(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags) +{ + struct intel_context *ce = rq->context; + u32 *cs; + u8 i; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + cs = intel_ring_begin(rq, 10 + 4 * ce->parallel.number_children); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + /* Wait on children */ + for (i = 0; i < ce->parallel.number_children; ++i) { + *cs++ = (MI_SEMAPHORE_WAIT | + MI_SEMAPHORE_GLOBAL_GTT | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD); + *cs++ = PARENT_GO_BB; + *cs++ = get_children_join_addr(ce, i); + *cs++ = 0; + } + + /* Turn off preemption */ + *cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; + *cs++ = MI_NOOP; + + /* Tell children go */ + cs = gen8_emit_ggtt_write(cs, + CHILD_GO_BB, + get_children_go_addr(ce), + 0); + + /* Jump to batch */ + *cs++ = MI_BATCH_BUFFER_START_GEN8 | + (flags & I915_DISPATCH_SECURE ? 0 : BIT(8)); + *cs++ = lower_32_bits(offset); + *cs++ = upper_32_bits(offset); + *cs++ = MI_NOOP; + + intel_ring_advance(rq, cs); + + return 0; +} + +static int emit_bb_start_child_no_preempt_mid_batch(struct i915_request *rq, + u64 offset, u32 len, + const unsigned int flags) +{ + struct intel_context *ce = rq->context; + struct intel_context *parent = intel_context_to_parent(ce); + u32 *cs; + + GEM_BUG_ON(!intel_context_is_child(ce)); + + cs = intel_ring_begin(rq, 12); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + /* Signal parent */ + cs = gen8_emit_ggtt_write(cs, + PARENT_GO_BB, + get_children_join_addr(parent, + ce->parallel.child_index), + 0); + + /* Wait on parent for go */ + *cs++ = (MI_SEMAPHORE_WAIT | + MI_SEMAPHORE_GLOBAL_GTT | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD); + *cs++ = CHILD_GO_BB; + *cs++ = get_children_go_addr(parent); + *cs++ = 0; + + /* Turn off preemption */ + *cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; + + /* Jump to batch */ + *cs++ = MI_BATCH_BUFFER_START_GEN8 | + (flags & I915_DISPATCH_SECURE ? 0 : BIT(8)); + *cs++ = lower_32_bits(offset); + *cs++ = upper_32_bits(offset); + + intel_ring_advance(rq, cs); + + return 0; +} + +static u32 * +__emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq, + u32 *cs) +{ + struct intel_context *ce = rq->context; + u8 i; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + /* Wait on children */ + for (i = 0; i < ce->parallel.number_children; ++i) { + *cs++ = (MI_SEMAPHORE_WAIT | + MI_SEMAPHORE_GLOBAL_GTT | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD); + *cs++ = PARENT_GO_FINI_BREADCRUMB; + *cs++ = get_children_join_addr(ce, i); + *cs++ = 0; + } + + /* Turn on preemption */ + *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; + *cs++ = MI_NOOP; + + /* Tell children go */ + cs = gen8_emit_ggtt_write(cs, + CHILD_GO_FINI_BREADCRUMB, + get_children_go_addr(ce), + 0); + + return cs; +} + +/* + * If this true, a submission of multi-lrc requests had an error and the + * requests need to be skipped. The front end (execuf IOCTL) should've called + * i915_request_skip which squashes the BB but we still need to emit the fini + * breadrcrumbs seqno write. At this point we don't know how many of the + * requests in the multi-lrc submission were generated so we can't do the + * handshake between the parent and children (e.g. if 4 requests should be + * generated but 2nd hit an error only 1 would be seen by the GuC backend). + * Simply skip the handshake, but still emit the breadcrumbd seqno, if an error + * has occurred on any of the requests in submission / relationship. + */ +static inline bool skip_handshake(struct i915_request *rq) +{ + return test_bit(I915_FENCE_FLAG_SKIP_PARALLEL, &rq->fence.flags); +} + +static u32 * +emit_fini_breadcrumb_parent_no_preempt_mid_batch(struct i915_request *rq, + u32 *cs) +{ + struct intel_context *ce = rq->context; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + if (unlikely(skip_handshake(rq))) { + /* + * NOP everything in __emit_fini_breadcrumb_parent_no_preempt_mid_batch, + * the -6 comes from the length of the emits below. + */ + memset(cs, 0, sizeof(u32) * + (ce->engine->emit_fini_breadcrumb_dw - 6)); + cs += ce->engine->emit_fini_breadcrumb_dw - 6; + } else { + cs = __emit_fini_breadcrumb_parent_no_preempt_mid_batch(rq, cs); + } + + /* Emit fini breadcrumb */ + cs = gen8_emit_ggtt_write(cs, + rq->fence.seqno, + i915_request_active_timeline(rq)->hwsp_offset, + 0); + + /* User interrupt */ + *cs++ = MI_USER_INTERRUPT; + *cs++ = MI_NOOP; + + rq->tail = intel_ring_offset(rq, cs); + + return cs; +} + +static u32 * +__emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq, + u32 *cs) +{ + struct intel_context *ce = rq->context; + struct intel_context *parent = intel_context_to_parent(ce); + + GEM_BUG_ON(!intel_context_is_child(ce)); + + /* Turn on preemption */ + *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; + *cs++ = MI_NOOP; + + /* Signal parent */ + cs = gen8_emit_ggtt_write(cs, + PARENT_GO_FINI_BREADCRUMB, + get_children_join_addr(parent, + ce->parallel.child_index), + 0); + + /* Wait parent on for go */ + *cs++ = (MI_SEMAPHORE_WAIT | + MI_SEMAPHORE_GLOBAL_GTT | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD); + *cs++ = CHILD_GO_FINI_BREADCRUMB; + *cs++ = get_children_go_addr(parent); + *cs++ = 0; + + return cs; +} + +static u32 * +emit_fini_breadcrumb_child_no_preempt_mid_batch(struct i915_request *rq, + u32 *cs) +{ + struct intel_context *ce = rq->context; + + GEM_BUG_ON(!intel_context_is_child(ce)); + + if (unlikely(skip_handshake(rq))) { + /* + * NOP everything in __emit_fini_breadcrumb_child_no_preempt_mid_batch, + * the -6 comes from the length of the emits below. + */ + memset(cs, 0, sizeof(u32) * + (ce->engine->emit_fini_breadcrumb_dw - 6)); + cs += ce->engine->emit_fini_breadcrumb_dw - 6; + } else { + cs = __emit_fini_breadcrumb_child_no_preempt_mid_batch(rq, cs); + } + + /* Emit fini breadcrumb */ + cs = gen8_emit_ggtt_write(cs, + rq->fence.seqno, + i915_request_active_timeline(rq)->hwsp_offset, + 0); + + /* User interrupt */ + *cs++ = MI_USER_INTERRUPT; + *cs++ = MI_NOOP; + + rq->tail = intel_ring_offset(rq, cs); + + return cs; +} + static struct intel_context * -guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, + unsigned long flags) { struct guc_virtual_engine *ve; struct intel_guc *guc; @@ -3195,6 +4271,7 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) } ve->base.mask |= sibling->mask; + ve->base.logical_mask |= sibling->logical_mask; if (n != 0 && ve->base.class != sibling->class) { DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", @@ -3253,4 +4330,5 @@ bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve) #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_guc.c" +#include "selftest_guc_multi_lrc.c" #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index fc5387b410a2..ff4b6869b80b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -87,17 +87,25 @@ static int intel_huc_rsa_data_create(struct intel_huc *huc) vma->obj, true)); if (IS_ERR(vaddr)) { i915_vma_unpin_and_release(&vma, 0); - return PTR_ERR(vaddr); + err = PTR_ERR(vaddr); + goto unpin_out; } copied = intel_uc_fw_copy_rsa(&huc->fw, vaddr, vma->size); - GEM_BUG_ON(copied < huc->fw.rsa_size); - i915_gem_object_unpin_map(vma->obj); + if (copied < huc->fw.rsa_size) { + err = -ENOMEM; + goto unpin_out; + } + huc->rsa_data = vma; return 0; + +unpin_out: + i915_vma_unpin_and_release(&vma, 0); + return err; } static void intel_huc_rsa_data_destroy(struct intel_huc *huc) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c index 5733c15fd123..15998963b863 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_debugfs.c @@ -5,7 +5,7 @@ #include -#include "gt/debugfs_gt.h" +#include "gt/intel_gt_debugfs.h" #include "intel_huc.h" #include "intel_huc_debugfs.h" @@ -21,11 +21,11 @@ static int huc_info_show(struct seq_file *m, void *data) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(huc_info); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(huc_info); void intel_huc_debugfs_register(struct intel_huc *huc, struct dentry *root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "huc_info", &huc_info_fops, NULL }, }; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index 86c318516e14..2fef3b0bbe95 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -35,7 +35,7 @@ static void uc_expand_default_options(struct intel_uc *uc) } /* Intermediate platforms are HuC authentication only */ - if (IS_DG1(i915) || IS_ALDERLAKE_S(i915)) { + if (IS_ALDERLAKE_S(i915)) { i915->params.enable_guc = ENABLE_GUC_LOAD_HUC; return; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c index 089d98662f46..c2f7924295e7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_debugfs.c @@ -6,7 +6,7 @@ #include #include -#include "gt/debugfs_gt.h" +#include "gt/intel_gt_debugfs.h" #include "intel_guc_debugfs.h" #include "intel_huc_debugfs.h" #include "intel_uc.h" @@ -32,11 +32,11 @@ static int uc_usage_show(struct seq_file *m, void *data) return 0; } -DEFINE_GT_DEBUGFS_ATTRIBUTE(uc_usage); +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(uc_usage); void intel_uc_debugfs_register(struct intel_uc *uc, struct dentry *gt_root) { - static const struct debugfs_gt_file files[] = { + static const struct intel_gt_debugfs_file files[] = { { "usage", &uc_usage_fops, NULL }, }; struct dentry *root; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index 3a16d08608a5..3aa87be4f2e4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -7,6 +7,7 @@ #include #include +#include "gem/i915_gem_lmem.h" #include "intel_uc_fw.h" #include "intel_uc_fw_abi.h" #include "i915_drv.h" @@ -50,6 +51,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \ fw_def(ALDERLAKE_P, 0, guc_def(adlp, 62, 0, 3), huc_def(tgl, 7, 9, 3)) \ fw_def(ALDERLAKE_S, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ + fw_def(DG1, 0, guc_def(dg1, 62, 0, 0), huc_def(dg1, 7, 9, 3)) \ fw_def(ROCKETLAKE, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ fw_def(TIGERLAKE, 0, guc_def(tgl, 62, 0, 0), huc_def(tgl, 7, 9, 3)) \ fw_def(JASPERLAKE, 0, guc_def(ehl, 62, 0, 0), huc_def(ehl, 9, 0, 0)) \ @@ -370,7 +372,14 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (uc_fw->type == INTEL_UC_FW_TYPE_GUC) uc_fw->private_data_size = css->private_data_size; - obj = i915_gem_object_create_shmem_from_data(i915, fw->data, fw->size); + if (HAS_LMEM(i915)) { + obj = i915_gem_object_create_lmem_from_data(i915, fw->data, fw->size); + if (!IS_ERR(obj)) + obj->flags |= I915_BO_ALLOC_PM_EARLY; + } else { + obj = i915_gem_object_create_shmem_from_data(i915, fw->data, fw->size); + } + if (IS_ERR(obj)) { err = PTR_ERR(obj); goto fail; @@ -413,20 +422,25 @@ static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw) { struct drm_i915_gem_object *obj = uc_fw->obj; struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt; - struct i915_vma dummy = { - .node.start = uc_fw_ggtt_offset(uc_fw), - .node.size = obj->base.size, - .pages = obj->mm.pages, - .vm = &ggtt->vm, - }; + struct i915_vma *dummy = &uc_fw->dummy; + u32 pte_flags = 0; + + dummy->node.start = uc_fw_ggtt_offset(uc_fw); + dummy->node.size = obj->base.size; + dummy->pages = obj->mm.pages; + dummy->vm = &ggtt->vm; GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); - GEM_BUG_ON(dummy.node.size > ggtt->uc_fw.size); + GEM_BUG_ON(dummy->node.size > ggtt->uc_fw.size); /* uc_fw->obj cache domains were not controlled across suspend */ - drm_clflush_sg(dummy.pages); + if (i915_gem_object_has_struct_page(obj)) + drm_clflush_sg(dummy->pages); - ggtt->vm.insert_entries(&ggtt->vm, &dummy, I915_CACHE_NONE, 0); + if (i915_gem_object_is_lmem(obj)) + pte_flags |= PTE_LM; + + ggtt->vm.insert_entries(&ggtt->vm, dummy, I915_CACHE_NONE, pte_flags); } static void uc_fw_unbind_ggtt(struct intel_uc_fw *uc_fw) @@ -585,13 +599,68 @@ void intel_uc_fw_cleanup_fetch(struct intel_uc_fw *uc_fw) */ size_t intel_uc_fw_copy_rsa(struct intel_uc_fw *uc_fw, void *dst, u32 max_len) { - struct sg_table *pages = uc_fw->obj->mm.pages; + struct intel_memory_region *mr = uc_fw->obj->mm.region; u32 size = min_t(u32, uc_fw->rsa_size, max_len); u32 offset = sizeof(struct uc_css_header) + uc_fw->ucode_size; + struct sgt_iter iter; + size_t count = 0; + int idx; + /* Called during reset handling, must be atomic [no fs_reclaim] */ GEM_BUG_ON(!intel_uc_fw_is_available(uc_fw)); - return sg_pcopy_to_buffer(pages->sgl, pages->nents, dst, size, offset); + idx = offset >> PAGE_SHIFT; + offset = offset_in_page(offset); + if (i915_gem_object_has_struct_page(uc_fw->obj)) { + struct page *page; + + for_each_sgt_page(page, iter, uc_fw->obj->mm.pages) { + u32 len = min_t(u32, size, PAGE_SIZE - offset); + void *vaddr; + + if (idx > 0) { + idx--; + continue; + } + + vaddr = kmap_atomic(page); + memcpy(dst, vaddr + offset, len); + kunmap_atomic(vaddr); + + offset = 0; + dst += len; + size -= len; + count += len; + if (!size) + break; + } + } else { + dma_addr_t addr; + + for_each_sgt_daddr(addr, iter, uc_fw->obj->mm.pages) { + u32 len = min_t(u32, size, PAGE_SIZE - offset); + void __iomem *vaddr; + + if (idx > 0) { + idx--; + continue; + } + + vaddr = io_mapping_map_atomic_wc(&mr->iomap, + addr - mr->region.start); + memcpy_fromio(dst, vaddr + offset, len); + io_mapping_unmap_atomic(vaddr); + + offset = 0; + dst += len; + size -= len; + count += len; + if (!size) + break; + } + } + + return count; } /** diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h index 99bb1fe1af66..1e00bf65639e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h @@ -10,6 +10,7 @@ #include "intel_uc_fw_abi.h" #include "intel_device_info.h" #include "i915_gem.h" +#include "i915_vma.h" struct drm_printer; struct drm_i915_private; @@ -75,6 +76,14 @@ struct intel_uc_fw { bool user_overridden; size_t size; struct drm_i915_gem_object *obj; + /** + * @dummy: A vma used in binding the uc fw to ggtt. We can't define this + * vma on the stack as it can lead to a stack overflow, so we define it + * here. Safe to have 1 copy per uc fw because the binding is single + * threaded as it done during driver load (inherently single threaded) + * or during a GT reset (mutex guarantees single threaded). + */ + struct i915_vma dummy; /* * The firmware build process will generate a version header file with major and diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c new file mode 100644 index 000000000000..50953c8e8b53 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc_multi_lrc.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright �� 2019 Intel Corporation + */ + +#include "selftests/igt_spinner.h" +#include "selftests/igt_reset.h" +#include "selftests/intel_scheduler_helpers.h" +#include "gt/intel_engine_heartbeat.h" +#include "gem/selftests/mock_context.h" + +static void logical_sort(struct intel_engine_cs **engines, int num_engines) +{ + struct intel_engine_cs *sorted[MAX_ENGINE_INSTANCE + 1]; + int i, j; + + for (i = 0; i < num_engines; ++i) + for (j = 0; j < MAX_ENGINE_INSTANCE + 1; ++j) { + if (engines[j]->logical_mask & BIT(i)) { + sorted[i] = engines[j]; + break; + } + } + + memcpy(*engines, *sorted, + sizeof(struct intel_engine_cs *) * num_engines); +} + +static struct intel_context * +multi_lrc_create_parent(struct intel_gt *gt, u8 class, + unsigned long flags) +{ + struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1]; + struct intel_engine_cs *engine; + enum intel_engine_id id; + int i = 0; + + for_each_engine(engine, gt, id) { + if (engine->class != class) + continue; + + siblings[i++] = engine; + } + + if (i <= 1) + return ERR_PTR(0); + + logical_sort(siblings, i); + + return intel_engine_create_parallel(siblings, 1, i); +} + +static void multi_lrc_context_unpin(struct intel_context *ce) +{ + struct intel_context *child; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + for_each_child(ce, child) + intel_context_unpin(child); + intel_context_unpin(ce); +} + +static void multi_lrc_context_put(struct intel_context *ce) +{ + GEM_BUG_ON(!intel_context_is_parent(ce)); + + /* + * Only the parent gets the creation ref put in the uAPI, the parent + * itself is responsible for creation ref put on the children. + */ + intel_context_put(ce); +} + +static struct i915_request * +multi_lrc_nop_request(struct intel_context *ce) +{ + struct intel_context *child; + struct i915_request *rq, *child_rq; + int i = 0; + + GEM_BUG_ON(!intel_context_is_parent(ce)); + + rq = intel_context_create_request(ce); + if (IS_ERR(rq)) + return rq; + + i915_request_get(rq); + i915_request_add(rq); + + for_each_child(ce, child) { + child_rq = intel_context_create_request(child); + if (IS_ERR(child_rq)) + goto child_error; + + if (++i == ce->parallel.number_children) + set_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, + &child_rq->fence.flags); + i915_request_add(child_rq); + } + + return rq; + +child_error: + i915_request_put(rq); + + return ERR_PTR(-ENOMEM); +} + +static int __intel_guc_multi_lrc_basic(struct intel_gt *gt, unsigned int class) +{ + struct intel_context *parent; + struct i915_request *rq; + int ret; + + parent = multi_lrc_create_parent(gt, class, 0); + if (IS_ERR(parent)) { + pr_err("Failed creating contexts: %ld", PTR_ERR(parent)); + return PTR_ERR(parent); + } else if (!parent) { + pr_debug("Not enough engines in class: %d", class); + return 0; + } + + rq = multi_lrc_nop_request(parent); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + pr_err("Failed creating requests: %d", ret); + goto out; + } + + ret = intel_selftest_wait_for_rq(rq); + if (ret) + pr_err("Failed waiting on request: %d", ret); + + i915_request_put(rq); + + if (ret >= 0) { + ret = intel_gt_wait_for_idle(gt, HZ * 5); + if (ret < 0) + pr_err("GT failed to idle: %d\n", ret); + } + +out: + multi_lrc_context_unpin(parent); + multi_lrc_context_put(parent); + return ret; +} + +static int intel_guc_multi_lrc_basic(void *arg) +{ + struct intel_gt *gt = arg; + unsigned int class; + int ret; + + for (class = 0; class < MAX_ENGINE_CLASS + 1; ++class) { + ret = __intel_guc_multi_lrc_basic(gt, class); + if (ret) + return ret; + } + + return 0; +} + +int intel_guc_multi_lrc_live_selftests(struct drm_i915_private *i915) +{ + static const struct i915_subtest tests[] = { + SUBTEST(intel_guc_multi_lrc_basic), + }; + struct intel_gt *gt = &i915->gt; + + if (intel_gt_is_wedged(gt)) + return 0; + + if (!intel_uc_uses_guc_submission(>->uc)) + return 0; + + return intel_gt_live_subtests(tests, gt); +} diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index e5c2fdfc20e3..53d0cb327539 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -745,7 +745,7 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt) trace_spt_free(spt->vgpu->id, spt, spt->guest_page.type); dma_unmap_page(kdev, spt->shadow_page.mfn << I915_GTT_PAGE_SHIFT, 4096, - PCI_DMA_BIDIRECTIONAL); + DMA_BIDIRECTIONAL); radix_tree_delete(&spt->vgpu->gtt.spt_tree, spt->shadow_page.mfn); @@ -849,7 +849,7 @@ retry: */ spt->shadow_page.type = type; daddr = dma_map_page(kdev, spt->shadow_page.page, - 0, 4096, PCI_DMA_BIDIRECTIONAL); + 0, 4096, DMA_BIDIRECTIONAL); if (dma_mapping_error(kdev, daddr)) { gvt_vgpu_err("fail to map dma addr\n"); ret = -EINVAL; @@ -865,7 +865,7 @@ retry: return spt; err_unmap_dma: - dma_unmap_page(kdev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); + dma_unmap_page(kdev, daddr, PAGE_SIZE, DMA_BIDIRECTIONAL); err_free_spt: free_spt(spt); return ERR_PTR(ret); @@ -2409,8 +2409,7 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, return -ENOMEM; } - daddr = dma_map_page(dev, virt_to_page(scratch_pt), 0, - 4096, PCI_DMA_BIDIRECTIONAL); + daddr = dma_map_page(dev, virt_to_page(scratch_pt), 0, 4096, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, daddr)) { gvt_vgpu_err("fail to dmamap scratch_pt\n"); __free_page(virt_to_page(scratch_pt)); @@ -2461,7 +2460,7 @@ static int release_scratch_page_tree(struct intel_vgpu *vgpu) if (vgpu->gtt.scratch_pt[i].page != NULL) { daddr = (dma_addr_t)(vgpu->gtt.scratch_pt[i].page_mfn << I915_GTT_PAGE_SHIFT); - dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL); + dma_unmap_page(dev, daddr, 4096, DMA_BIDIRECTIONAL); __free_page(vgpu->gtt.scratch_pt[i].page); vgpu->gtt.scratch_pt[i].page = NULL; vgpu->gtt.scratch_pt[i].page_mfn = 0; @@ -2741,7 +2740,7 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) } daddr = dma_map_page(dev, virt_to_page(page), 0, - 4096, PCI_DMA_BIDIRECTIONAL); + 4096, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, daddr)) { gvt_err("fail to dmamap scratch ggtt page\n"); __free_page(virt_to_page(page)); @@ -2755,7 +2754,7 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) ret = setup_spt_oos(gvt); if (ret) { gvt_err("fail to initialize SPT oos\n"); - dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL); + dma_unmap_page(dev, daddr, 4096, DMA_BIDIRECTIONAL); __free_page(gvt->gtt.scratch_page); return ret; } @@ -2779,7 +2778,7 @@ void intel_gvt_clean_gtt(struct intel_gvt *gvt) dma_addr_t daddr = (dma_addr_t)(gvt->gtt.scratch_mfn << I915_GTT_PAGE_SHIFT); - dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL); + dma_unmap_page(dev, daddr, 4096, DMA_BIDIRECTIONAL); __free_page(gvt->gtt.scratch_page); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 7efa386449d1..20b82fb036f8 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -328,7 +328,7 @@ static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn, return ret; /* Setup DMA mapping. */ - *dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL); + *dma_addr = dma_map_page(dev, page, 0, size, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) { gvt_vgpu_err("DMA mapping failed for pfn 0x%lx, ret %d\n", page_to_pfn(page), ret); @@ -344,7 +344,7 @@ static void gvt_dma_unmap_page(struct intel_vgpu *vgpu, unsigned long gfn, { struct device *dev = vgpu->gvt->gt->i915->drm.dev; - dma_unmap_page(dev, dma_addr, size, PCI_DMA_BIDIRECTIONAL); + dma_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL); gvt_unpin_guest_page(vgpu, gfn, size); } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 1bb1be5c48c8..6c804102528b 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1386,7 +1386,7 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) enum intel_engine_id i; int ret; - ppgtt = i915_ppgtt_create(&i915->gt); + ppgtt = i915_ppgtt_create(&i915->gt, I915_BO_ALLOC_PM_EARLY); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); diff --git a/drivers/gpu/drm/i915/i915_config.c b/drivers/gpu/drm/i915/i915_config.c index b79b5f6d2cfa..afb828dab53b 100644 --- a/drivers/gpu/drm/i915/i915_config.c +++ b/drivers/gpu/drm/i915/i915_config.c @@ -8,7 +8,7 @@ unsigned long i915_fence_context_timeout(const struct drm_i915_private *i915, u64 context) { - if (context && IS_ACTIVE(CONFIG_DRM_I915_FENCE_TIMEOUT)) + if (CONFIG_DRM_I915_FENCE_TIMEOUT && context) return msecs_to_jiffies_timeout(CONFIG_DRM_I915_FENCE_TIMEOUT); return 0; diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 04351a851586..fe638b5da7c0 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -32,13 +32,15 @@ #include #include "gem/i915_gem_context.h" +#include "gt/intel_gt.h" #include "gt/intel_gt_buffer_pool.h" #include "gt/intel_gt_clock_utils.h" -#include "gt/intel_gt.h" +#include "gt/intel_gt_debugfs.h" #include "gt/intel_gt_pm.h" +#include "gt/intel_gt_pm_debugfs.h" #include "gt/intel_gt_requests.h" -#include "gt/intel_reset.h" #include "gt/intel_rc6.h" +#include "gt/intel_reset.h" #include "gt/intel_rps.h" #include "gt/intel_sseu_debugfs.h" @@ -48,7 +50,6 @@ #include "i915_scheduler.h" #include "i915_trace.h" #include "intel_pm.h" -#include "intel_sideband.h" static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node) { @@ -139,7 +140,6 @@ void i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); - struct intel_engine_cs *engine; struct i915_vma *vma; int pin_count = 0; @@ -229,10 +229,6 @@ i915_debugfs_describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) seq_printf(m, " (stolen: %08llx)", obj->stolen->start); if (i915_gem_object_is_framebuffer(obj)) seq_printf(m, " (fb)"); - - engine = i915_gem_object_last_write_engine(obj); - if (engine) - seq_printf(m, " (%s)", engine->name); } static int i915_gem_object_info(struct seq_file *m, void *data) @@ -354,230 +350,12 @@ static const struct file_operations i915_error_state_fops = { static int i915_frequency_info(struct seq_file *m, void *unused) { - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct intel_uncore *uncore = &dev_priv->uncore; - struct intel_rps *rps = &dev_priv->gt.rps; - intel_wakeref_t wakeref; + struct drm_i915_private *i915 = node_to_i915(m->private); + struct intel_gt *gt = &i915->gt; + struct drm_printer p = drm_seq_file_printer(m); - wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); + intel_gt_pm_frequency_dump(gt, &p); - if (GRAPHICS_VER(dev_priv) == 5) { - u16 rgvswctl = intel_uncore_read16(uncore, MEMSWCTL); - u16 rgvstat = intel_uncore_read16(uncore, MEMSTAT_ILK); - - seq_printf(m, "Requested P-state: %d\n", (rgvswctl >> 8) & 0xf); - seq_printf(m, "Requested VID: %d\n", rgvswctl & 0x3f); - seq_printf(m, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >> - MEMSTAT_VID_SHIFT); - seq_printf(m, "Current P-state: %d\n", - (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT); - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - u32 rpmodectl, freq_sts; - - rpmodectl = intel_uncore_read(&dev_priv->uncore, GEN6_RP_CONTROL); - seq_printf(m, "Video Turbo Mode: %s\n", - yesno(rpmodectl & GEN6_RP_MEDIA_TURBO)); - seq_printf(m, "HW control enabled: %s\n", - yesno(rpmodectl & GEN6_RP_ENABLE)); - seq_printf(m, "SW control enabled: %s\n", - yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == - GEN6_RP_MEDIA_SW_MODE)); - - vlv_punit_get(dev_priv); - freq_sts = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS); - vlv_punit_put(dev_priv); - - seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts); - seq_printf(m, "DDR freq: %d MHz\n", dev_priv->mem_freq); - - seq_printf(m, "actual GPU freq: %d MHz\n", - intel_gpu_freq(rps, (freq_sts >> 8) & 0xff)); - - seq_printf(m, "current GPU freq: %d MHz\n", - intel_gpu_freq(rps, rps->cur_freq)); - - seq_printf(m, "max GPU freq: %d MHz\n", - intel_gpu_freq(rps, rps->max_freq)); - - seq_printf(m, "min GPU freq: %d MHz\n", - intel_gpu_freq(rps, rps->min_freq)); - - seq_printf(m, "idle GPU freq: %d MHz\n", - intel_gpu_freq(rps, rps->idle_freq)); - - seq_printf(m, - "efficient (RPe) frequency: %d MHz\n", - intel_gpu_freq(rps, rps->efficient_freq)); - } else if (GRAPHICS_VER(dev_priv) >= 6) { - u32 rp_state_limits; - u32 gt_perf_status; - u32 rp_state_cap; - u32 rpmodectl, rpinclimit, rpdeclimit; - u32 rpstat, cagf, reqf; - u32 rpupei, rpcurup, rpprevup; - u32 rpdownei, rpcurdown, rpprevdown; - u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask; - int max_freq; - - rp_state_limits = intel_uncore_read(&dev_priv->uncore, GEN6_RP_STATE_LIMITS); - rp_state_cap = intel_rps_read_state_cap(rps); - if (IS_GEN9_LP(dev_priv)) - gt_perf_status = intel_uncore_read(&dev_priv->uncore, BXT_GT_PERF_STATUS); - else - gt_perf_status = intel_uncore_read(&dev_priv->uncore, GEN6_GT_PERF_STATUS); - - /* RPSTAT1 is in the GT power well */ - intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL); - - reqf = intel_uncore_read(&dev_priv->uncore, GEN6_RPNSWREQ); - if (GRAPHICS_VER(dev_priv) >= 9) - reqf >>= 23; - else { - reqf &= ~GEN6_TURBO_DISABLE; - if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) - reqf >>= 24; - else - reqf >>= 25; - } - reqf = intel_gpu_freq(rps, reqf); - - rpmodectl = intel_uncore_read(&dev_priv->uncore, GEN6_RP_CONTROL); - rpinclimit = intel_uncore_read(&dev_priv->uncore, GEN6_RP_UP_THRESHOLD); - rpdeclimit = intel_uncore_read(&dev_priv->uncore, GEN6_RP_DOWN_THRESHOLD); - - rpstat = intel_uncore_read(&dev_priv->uncore, GEN6_RPSTAT1); - rpupei = intel_uncore_read(&dev_priv->uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK; - rpcurup = intel_uncore_read(&dev_priv->uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK; - rpprevup = intel_uncore_read(&dev_priv->uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK; - rpdownei = intel_uncore_read(&dev_priv->uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK; - rpcurdown = intel_uncore_read(&dev_priv->uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK; - rpprevdown = intel_uncore_read(&dev_priv->uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK; - cagf = intel_rps_read_actual_frequency(rps); - - intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); - - if (GRAPHICS_VER(dev_priv) >= 11) { - pm_ier = intel_uncore_read(&dev_priv->uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE); - pm_imr = intel_uncore_read(&dev_priv->uncore, GEN11_GPM_WGBOXPERF_INTR_MASK); - /* - * The equivalent to the PM ISR & IIR cannot be read - * without affecting the current state of the system - */ - pm_isr = 0; - pm_iir = 0; - } else if (GRAPHICS_VER(dev_priv) >= 8) { - pm_ier = intel_uncore_read(&dev_priv->uncore, GEN8_GT_IER(2)); - pm_imr = intel_uncore_read(&dev_priv->uncore, GEN8_GT_IMR(2)); - pm_isr = intel_uncore_read(&dev_priv->uncore, GEN8_GT_ISR(2)); - pm_iir = intel_uncore_read(&dev_priv->uncore, GEN8_GT_IIR(2)); - } else { - pm_ier = intel_uncore_read(&dev_priv->uncore, GEN6_PMIER); - pm_imr = intel_uncore_read(&dev_priv->uncore, GEN6_PMIMR); - pm_isr = intel_uncore_read(&dev_priv->uncore, GEN6_PMISR); - pm_iir = intel_uncore_read(&dev_priv->uncore, GEN6_PMIIR); - } - pm_mask = intel_uncore_read(&dev_priv->uncore, GEN6_PMINTRMSK); - - seq_printf(m, "Video Turbo Mode: %s\n", - yesno(rpmodectl & GEN6_RP_MEDIA_TURBO)); - seq_printf(m, "HW control enabled: %s\n", - yesno(rpmodectl & GEN6_RP_ENABLE)); - seq_printf(m, "SW control enabled: %s\n", - yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) == - GEN6_RP_MEDIA_SW_MODE)); - - seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n", - pm_ier, pm_imr, pm_mask); - if (GRAPHICS_VER(dev_priv) <= 10) - seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n", - pm_isr, pm_iir); - seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n", - rps->pm_intrmsk_mbz); - seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); - seq_printf(m, "Render p-state ratio: %d\n", - (gt_perf_status & (GRAPHICS_VER(dev_priv) >= 9 ? 0x1ff00 : 0xff00)) >> 8); - seq_printf(m, "Render p-state VID: %d\n", - gt_perf_status & 0xff); - seq_printf(m, "Render p-state limit: %d\n", - rp_state_limits & 0xff); - seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat); - seq_printf(m, "RPMODECTL: 0x%08x\n", rpmodectl); - seq_printf(m, "RPINCLIMIT: 0x%08x\n", rpinclimit); - seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit); - seq_printf(m, "RPNSWREQ: %dMHz\n", reqf); - seq_printf(m, "CAGF: %dMHz\n", cagf); - seq_printf(m, "RP CUR UP EI: %d (%lldns)\n", - rpupei, - intel_gt_pm_interval_to_ns(&dev_priv->gt, rpupei)); - seq_printf(m, "RP CUR UP: %d (%lldun)\n", - rpcurup, - intel_gt_pm_interval_to_ns(&dev_priv->gt, rpcurup)); - seq_printf(m, "RP PREV UP: %d (%lldns)\n", - rpprevup, - intel_gt_pm_interval_to_ns(&dev_priv->gt, rpprevup)); - seq_printf(m, "Up threshold: %d%%\n", - rps->power.up_threshold); - - seq_printf(m, "RP CUR DOWN EI: %d (%lldns)\n", - rpdownei, - intel_gt_pm_interval_to_ns(&dev_priv->gt, - rpdownei)); - seq_printf(m, "RP CUR DOWN: %d (%lldns)\n", - rpcurdown, - intel_gt_pm_interval_to_ns(&dev_priv->gt, - rpcurdown)); - seq_printf(m, "RP PREV DOWN: %d (%lldns)\n", - rpprevdown, - intel_gt_pm_interval_to_ns(&dev_priv->gt, - rpprevdown)); - seq_printf(m, "Down threshold: %d%%\n", - rps->power.down_threshold); - - max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 : - rp_state_cap >> 16) & 0xff; - max_freq *= (IS_GEN9_BC(dev_priv) || - GRAPHICS_VER(dev_priv) >= 11 ? GEN9_FREQ_SCALER : 1); - seq_printf(m, "Lowest (RPN) frequency: %dMHz\n", - intel_gpu_freq(rps, max_freq)); - - max_freq = (rp_state_cap & 0xff00) >> 8; - max_freq *= (IS_GEN9_BC(dev_priv) || - GRAPHICS_VER(dev_priv) >= 11 ? GEN9_FREQ_SCALER : 1); - seq_printf(m, "Nominal (RP1) frequency: %dMHz\n", - intel_gpu_freq(rps, max_freq)); - - max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 16 : - rp_state_cap >> 0) & 0xff; - max_freq *= (IS_GEN9_BC(dev_priv) || - GRAPHICS_VER(dev_priv) >= 11 ? GEN9_FREQ_SCALER : 1); - seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n", - intel_gpu_freq(rps, max_freq)); - seq_printf(m, "Max overclocked frequency: %dMHz\n", - intel_gpu_freq(rps, rps->max_freq)); - - seq_printf(m, "Current freq: %d MHz\n", - intel_gpu_freq(rps, rps->cur_freq)); - seq_printf(m, "Actual freq: %d MHz\n", cagf); - seq_printf(m, "Idle freq: %d MHz\n", - intel_gpu_freq(rps, rps->idle_freq)); - seq_printf(m, "Min freq: %d MHz\n", - intel_gpu_freq(rps, rps->min_freq)); - seq_printf(m, "Boost freq: %d MHz\n", - intel_gpu_freq(rps, rps->boost_freq)); - seq_printf(m, "Max freq: %d MHz\n", - intel_gpu_freq(rps, rps->max_freq)); - seq_printf(m, - "efficient (RPe) frequency: %d MHz\n", - intel_gpu_freq(rps, rps->efficient_freq)); - } else { - seq_puts(m, "no P-state info available\n"); - } - - seq_printf(m, "Current CD clock frequency: %d kHz\n", dev_priv->cdclk.hw.cdclk); - seq_printf(m, "Max CD clock frequency: %d kHz\n", dev_priv->max_cdclk_freq); - seq_printf(m, "Max pixel clock frequency: %d kHz\n", dev_priv->max_dotclk_freq); - - intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref); return 0; } @@ -776,36 +554,18 @@ static int i915_wa_registers(struct seq_file *m, void *unused) return 0; } -static int -i915_wedged_get(void *data, u64 *val) +static int i915_wedged_get(void *data, u64 *val) { struct drm_i915_private *i915 = data; - int ret = intel_gt_terminally_wedged(&i915->gt); - switch (ret) { - case -EIO: - *val = 1; - return 0; - case 0: - *val = 0; - return 0; - default: - return ret; - } + return intel_gt_debugfs_reset_show(&i915->gt, val); } -static int -i915_wedged_set(void *data, u64 val) +static int i915_wedged_set(void *data, u64 val) { struct drm_i915_private *i915 = data; - /* Flush any previous reset before applying for a new one */ - wait_event(i915->gt.reset.queue, - !test_bit(I915_RESET_BACKOFF, &i915->gt.reset.flags)); - - intel_gt_handle_error(&i915->gt, val, I915_ERROR_CAPTURE, - "Manually set wedged engine mask = %llx", val); - return 0; + return intel_gt_debugfs_reset_store(&i915->gt, val); } DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops, @@ -950,27 +710,15 @@ static int i915_sseu_status(struct seq_file *m, void *unused) static int i915_forcewake_open(struct inode *inode, struct file *file) { struct drm_i915_private *i915 = inode->i_private; - struct intel_gt *gt = &i915->gt; - atomic_inc(>->user_wakeref); - intel_gt_pm_get(gt); - if (GRAPHICS_VER(i915) >= 6) - intel_uncore_forcewake_user_get(gt->uncore); - - return 0; + return intel_gt_pm_debugfs_forcewake_user_open(&i915->gt); } static int i915_forcewake_release(struct inode *inode, struct file *file) { struct drm_i915_private *i915 = inode->i_private; - struct intel_gt *gt = &i915->gt; - if (GRAPHICS_VER(i915) >= 6) - intel_uncore_forcewake_user_put(&i915->uncore); - intel_gt_pm_put(gt); - atomic_dec(>->user_wakeref); - - return 0; + return intel_gt_pm_debugfs_forcewake_user_release(&i915->gt); } static const struct file_operations i915_forcewake_fops = { diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 59fb4c710c8c..b18a250e5d2e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -67,6 +67,8 @@ #include "gt/intel_gt_pm.h" #include "gt/intel_rc6.h" +#include "pxp/intel_pxp_pm.h" + #include "i915_debugfs.h" #include "i915_drv.h" #include "i915_ioc32.h" @@ -82,9 +84,9 @@ #include "intel_dram.h" #include "intel_gvt.h" #include "intel_memory_region.h" +#include "intel_pcode.h" #include "intel_pm.h" #include "intel_region_ttm.h" -#include "intel_sideband.h" #include "vlv_suspend.h" static const struct drm_driver driver; @@ -97,7 +99,7 @@ static int i915_get_bridge_dev(struct drm_i915_private *dev_priv) pci_get_domain_bus_and_slot(domain, 0, PCI_DEVFN(0, 0)); if (!dev_priv->bridge_dev) { drm_err(&dev_priv->drm, "bridge device not found\n"); - return -1; + return -EIO; } return 0; } @@ -409,8 +411,9 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) if (i915_inject_probe_failure(dev_priv)) return -ENODEV; - if (i915_get_bridge_dev(dev_priv)) - return -EIO; + ret = i915_get_bridge_dev(dev_priv); + if (ret < 0) + return ret; ret = intel_uncore_init_mmio(&dev_priv->uncore); if (ret < 0) @@ -588,8 +591,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) pci_set_master(pdev); - intel_gt_init_workarounds(dev_priv); - /* On the 945G/GM, the chipset reports the MSI capability on the * integrated graphics even though the support isn't actually there * according to the published specs. It doesn't appear to function @@ -1096,9 +1097,7 @@ static int i915_drm_prepare(struct drm_device *dev) * split out that work and pull it forward so that after point, * the GPU is not woken again. */ - i915_gem_suspend(i915); - - return 0; + return i915_gem_backup_suspend(i915); } static int i915_drm_suspend(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 37c1ca266bcd..12256218634f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -323,15 +323,15 @@ struct intel_crtc; struct intel_limit; struct dpll; -struct drm_i915_display_funcs { - void (*get_cdclk)(struct drm_i915_private *dev_priv, - struct intel_cdclk_config *cdclk_config); - void (*set_cdclk)(struct drm_i915_private *dev_priv, - const struct intel_cdclk_config *cdclk_config, - enum pipe pipe); - int (*bw_calc_min_cdclk)(struct intel_atomic_state *state); - int (*get_fifo_size)(struct drm_i915_private *dev_priv, - enum i9xx_plane_id i9xx_plane); +/* functions used internal in intel_pm.c */ +struct drm_i915_clock_gating_funcs { + void (*init_clock_gating)(struct drm_i915_private *dev_priv); +}; + +/* functions used for watermark calcs for display. */ +struct drm_i915_wm_disp_funcs { + /* update_wm is for legacy wm management */ + void (*update_wm)(struct drm_i915_private *dev_priv); int (*compute_pipe_wm)(struct intel_atomic_state *state, struct intel_crtc *crtc); int (*compute_intermediate_wm)(struct intel_atomic_state *state, @@ -343,38 +343,9 @@ struct drm_i915_display_funcs { void (*optimize_watermarks)(struct intel_atomic_state *state, struct intel_crtc *crtc); int (*compute_global_watermarks)(struct intel_atomic_state *state); - void (*update_wm)(struct intel_crtc *crtc); - int (*modeset_calc_cdclk)(struct intel_cdclk_state *state); - u8 (*calc_voltage_level)(int cdclk); - /* Returns the active state of the crtc, and if the crtc is active, - * fills out the pipe-config with the hw state. */ - bool (*get_pipe_config)(struct intel_crtc *, - struct intel_crtc_state *); - void (*get_initial_plane_config)(struct intel_crtc *, - struct intel_initial_plane_config *); - int (*crtc_compute_clock)(struct intel_crtc_state *crtc_state); - void (*crtc_enable)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*crtc_disable)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*commit_modeset_enables)(struct intel_atomic_state *state); - void (*commit_modeset_disables)(struct intel_atomic_state *state); - void (*audio_codec_enable)(struct intel_encoder *encoder, - const struct intel_crtc_state *crtc_state, - const struct drm_connector_state *conn_state); - void (*audio_codec_disable)(struct intel_encoder *encoder, - const struct intel_crtc_state *old_crtc_state, - const struct drm_connector_state *old_conn_state); - void (*fdi_link_train)(struct intel_crtc *crtc, - const struct intel_crtc_state *crtc_state); - void (*init_clock_gating)(struct drm_i915_private *dev_priv); - void (*hpd_irq_setup)(struct drm_i915_private *dev_priv); - /* clock updates for mode set */ - /* cursor updates */ - /* render clock increase/decrease */ - /* display clock increase/decrease */ - /* pll clock increase/decrease */ +}; +struct intel_color_funcs { int (*color_check)(struct intel_crtc_state *crtc_state); /* * Program double buffered color management registers during @@ -393,6 +364,53 @@ struct drm_i915_display_funcs { void (*read_luts)(struct intel_crtc_state *crtc_state); }; +struct intel_audio_funcs { + void (*audio_codec_enable)(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state); + void (*audio_codec_disable)(struct intel_encoder *encoder, + const struct intel_crtc_state *old_crtc_state, + const struct drm_connector_state *old_conn_state); +}; + +struct intel_cdclk_funcs { + void (*get_cdclk)(struct drm_i915_private *dev_priv, + struct intel_cdclk_config *cdclk_config); + void (*set_cdclk)(struct drm_i915_private *dev_priv, + const struct intel_cdclk_config *cdclk_config, + enum pipe pipe); + int (*bw_calc_min_cdclk)(struct intel_atomic_state *state); + int (*modeset_calc_cdclk)(struct intel_cdclk_state *state); + u8 (*calc_voltage_level)(int cdclk); +}; + +struct intel_hotplug_funcs { + void (*hpd_irq_setup)(struct drm_i915_private *dev_priv); +}; + +struct intel_fdi_funcs { + void (*fdi_link_train)(struct intel_crtc *crtc, + const struct intel_crtc_state *crtc_state); +}; + +struct intel_dpll_funcs { + int (*crtc_compute_clock)(struct intel_crtc_state *crtc_state); +}; + +struct drm_i915_display_funcs { + /* Returns the active state of the crtc, and if the crtc is active, + * fills out the pipe-config with the hw state. */ + bool (*get_pipe_config)(struct intel_crtc *, + struct intel_crtc_state *); + void (*get_initial_plane_config)(struct intel_crtc *, + struct intel_initial_plane_config *); + void (*crtc_enable)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*crtc_disable)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*commit_modeset_enables)(struct intel_atomic_state *state); +}; + #define I915_COLOR_UNEVICTABLE (-1) /* a non-vma sharing the address space */ @@ -453,7 +471,6 @@ struct intel_fbc { } fb; unsigned int fence_y_offset; - u16 override_cfb_stride; u16 interval; s8 fence_id; bool psr2_active; @@ -478,7 +495,8 @@ struct intel_fbc { u64 modifier; } fb; - int cfb_size; + unsigned int cfb_stride; + unsigned int cfb_size; unsigned int fence_y_offset; u16 override_cfb_stride; u16 interval; @@ -956,8 +974,32 @@ struct drm_i915_private { /* unbound hipri wq for page flips/plane updates */ struct workqueue_struct *flip_wq; + /* pm private clock gating functions */ + const struct drm_i915_clock_gating_funcs *clock_gating_funcs; + + /* pm display functions */ + const struct drm_i915_wm_disp_funcs *wm_disp; + + /* irq display functions */ + const struct intel_hotplug_funcs *hotplug_funcs; + + /* fdi display functions */ + const struct intel_fdi_funcs *fdi_funcs; + + /* display pll funcs */ + const struct intel_dpll_funcs *dpll_funcs; + /* Display functions */ - struct drm_i915_display_funcs display; + const struct drm_i915_display_funcs *display; + + /* Display internal color functions */ + const struct intel_color_funcs *color_funcs; + + /* Display internal audio functions */ + const struct intel_audio_funcs *audio_funcs; + + /* Display CDCLK functions */ + const struct intel_cdclk_funcs *cdclk_funcs; /* PCH chipset type */ enum intel_pch pch_type; @@ -998,7 +1040,11 @@ struct drm_i915_private { struct list_head global_obj_list; - struct i915_wa_list gt_wa_list; + /* + * For reading active_pipes holding any crtc lock is + * sufficient, for writing must hold all of them. + */ + u8 active_pipes; struct i915_frontbuffer_tracking fb_tracking; @@ -1641,6 +1687,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_IPS(dev_priv) (IS_HSW_ULT(dev_priv) || IS_BROADWELL(dev_priv)) #define HAS_DP_MST(dev_priv) (INTEL_INFO(dev_priv)->display.has_dp_mst) +#define HAS_DP20(dev_priv) (IS_DG2(dev_priv)) #define HAS_CDCLK_CRAWL(dev_priv) (INTEL_INFO(dev_priv)->display.has_cdclk_crawl) #define HAS_DDI(dev_priv) (INTEL_INFO(dev_priv)->display.has_ddi) @@ -1678,6 +1725,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_GLOBAL_MOCS_REGISTERS(dev_priv) (INTEL_INFO(dev_priv)->has_global_mocs) +#define HAS_PXP(dev_priv) ((IS_ENABLED(CONFIG_DRM_I915_PXP) && \ + INTEL_INFO(dev_priv)->has_pxp) && \ + VDBOX_MASK(&dev_priv->gt)) #define HAS_GMCH(dev_priv) (INTEL_INFO(dev_priv)->display.has_gmch) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 590efc8b0265..981e383d1a5d 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1139,8 +1139,6 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv) { intel_gt_driver_release(&dev_priv->gt); - intel_wa_list_free(&dev_priv->gt_wa_list); - intel_uc_cleanup_firmwares(&dev_priv->gt.uc); i915_gem_drain_freed_objects(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 36489be4896b..cd5f2348a187 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -30,7 +30,7 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj, do { if (dma_map_sg_attrs(obj->base.dev->dev, pages->sgl, pages->nents, - PCI_DMA_BIDIRECTIONAL, + DMA_BIDIRECTIONAL, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN)) @@ -64,7 +64,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj, usleep_range(100, 250); dma_unmap_sg(i915->drm.dev, pages->sgl, pages->nents, - PCI_DMA_BIDIRECTIONAL); + DMA_BIDIRECTIONAL); } /** diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index b9f66dbd46bb..2a2d7643b551 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -753,7 +753,8 @@ static void err_print_gt(struct drm_i915_error_state_buf *m, * only exists if the corresponding VCS engine is * present. */ - if (!HAS_ENGINE(gt->_gt, _VCS(i * 2))) + if ((gt->_gt->info.sfc_mask & BIT(i)) == 0 || + !HAS_ENGINE(gt->_gt, _VCS(i * 2))) continue; err_printf(m, " SFC_DONE[%d]: 0x%08x\n", i, @@ -1632,7 +1633,8 @@ static void gt_record_regs(struct intel_gt_coredump *gt) * only exists if the corresponding VCS engine is * present. */ - if (!HAS_ENGINE(gt->_gt, _VCS(i * 2))) + if ((gt->_gt->info.sfc_mask & BIT(i)) == 0 || + !HAS_ENGINE(gt->_gt, _VCS(i * 2))) continue; gt->sfc_done[i] = diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0a1681384c84..77680bca46ee 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -4345,6 +4345,20 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) return ret; } +#define HPD_FUNCS(platform) \ +static const struct intel_hotplug_funcs platform##_hpd_funcs = { \ + .hpd_irq_setup = platform##_hpd_irq_setup, \ +} + +HPD_FUNCS(i915); +HPD_FUNCS(dg1); +HPD_FUNCS(gen11); +HPD_FUNCS(bxt); +HPD_FUNCS(icp); +HPD_FUNCS(spt); +HPD_FUNCS(ilk); +#undef HPD_FUNCS + /** * intel_irq_init - initializes irq support * @dev_priv: i915 device instance @@ -4395,20 +4409,20 @@ void intel_irq_init(struct drm_i915_private *dev_priv) if (HAS_GMCH(dev_priv)) { if (I915_HAS_HOTPLUG(dev_priv)) - dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup; + dev_priv->hotplug_funcs = &i915_hpd_funcs; } else { if (HAS_PCH_DG1(dev_priv)) - dev_priv->display.hpd_irq_setup = dg1_hpd_irq_setup; + dev_priv->hotplug_funcs = &dg1_hpd_funcs; else if (DISPLAY_VER(dev_priv) >= 11) - dev_priv->display.hpd_irq_setup = gen11_hpd_irq_setup; + dev_priv->hotplug_funcs = &gen11_hpd_funcs; else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - dev_priv->display.hpd_irq_setup = bxt_hpd_irq_setup; + dev_priv->hotplug_funcs = &bxt_hpd_funcs; else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP) - dev_priv->display.hpd_irq_setup = icp_hpd_irq_setup; + dev_priv->hotplug_funcs = &icp_hpd_funcs; else if (INTEL_PCH_TYPE(dev_priv) >= PCH_SPT) - dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup; + dev_priv->hotplug_funcs = &spt_hpd_funcs; else - dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; + dev_priv->hotplug_funcs = &ilk_hpd_funcs; } } diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index f27eceb82c0f..8d725b64592d 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -55,7 +55,7 @@ struct drm_printer; param(int, enable_fbc, -1, 0600) \ param(int, enable_psr, -1, 0600) \ param(bool, psr_safest_params, false, 0400) \ - param(bool, enable_psr2_sel_fetch, false, 0400) \ + param(bool, enable_psr2_sel_fetch, true, 0400) \ param(int, disable_power_well, -1, 0400) \ param(int, enable_ips, 1, 0600) \ param(int, invert_brightness, 0, 0600) \ diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index d4a6a9dcf182..169837de395d 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -865,6 +865,7 @@ static const struct intel_device_info jsl_info = { }, \ TGL_CURSOR_OFFSETS, \ .has_global_mocs = 1, \ + .has_pxp = 1, \ .display.has_dsb = 1 static const struct intel_device_info tgl_info = { @@ -891,6 +892,7 @@ static const struct intel_device_info rkl_info = { #define DGFX_FEATURES \ .memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \ .has_llc = 0, \ + .has_pxp = 0, \ .has_snoop = 1, \ .is_dgfx = 1 diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 5e2b909827f4..51b368be0fc4 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -124,7 +124,9 @@ query_engine_info(struct drm_i915_private *i915, for_each_uabi_engine(engine, i915) { info.engine.engine_class = engine->uabi_class; info.engine.engine_instance = engine->uabi_instance; + info.flags = I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE; info.capabilities = engine->uabi_capabilities; + info.logical_instance = ilog2(engine->logical_mask); if (copy_to_user(info_ptr, &info, sizeof(info))) return -EFAULT; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 251d6ddebcff..da9055c3ebf0 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1968,7 +1968,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) _ICL_PORT_PCS_LN(ln) + 4 * (dw)) #define ICL_PORT_PCS_DW1_AUX(phy) _MMIO(_ICL_PORT_PCS_DW_AUX(1, phy)) #define ICL_PORT_PCS_DW1_GRP(phy) _MMIO(_ICL_PORT_PCS_DW_GRP(1, phy)) -#define ICL_PORT_PCS_DW1_LN0(phy) _MMIO(_ICL_PORT_PCS_DW_LN(1, 0, phy)) +#define ICL_PORT_PCS_DW1_LN(ln, phy) _MMIO(_ICL_PORT_PCS_DW_LN(1, ln, phy)) #define DCC_MODE_SELECT_MASK (0x3 << 20) #define DCC_MODE_SELECT_CONTINUOSLY (0x3 << 20) #define COMMON_KEEPER_EN (1 << 26) @@ -1989,7 +1989,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ICL_PORT_TX_DW2_AUX(phy) _MMIO(_ICL_PORT_TX_DW_AUX(2, phy)) #define ICL_PORT_TX_DW2_GRP(phy) _MMIO(_ICL_PORT_TX_DW_GRP(2, phy)) -#define ICL_PORT_TX_DW2_LN0(phy) _MMIO(_ICL_PORT_TX_DW_LN(2, 0, phy)) +#define ICL_PORT_TX_DW2_LN(ln, phy) _MMIO(_ICL_PORT_TX_DW_LN(2, ln, phy)) #define SWING_SEL_UPPER(x) (((x) >> 3) << 15) #define SWING_SEL_UPPER_MASK (1 << 15) #define SWING_SEL_LOWER(x) (((x) & 0x7) << 11) @@ -2001,7 +2001,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ICL_PORT_TX_DW4_AUX(phy) _MMIO(_ICL_PORT_TX_DW_AUX(4, phy)) #define ICL_PORT_TX_DW4_GRP(phy) _MMIO(_ICL_PORT_TX_DW_GRP(4, phy)) -#define ICL_PORT_TX_DW4_LN0(phy) _MMIO(_ICL_PORT_TX_DW_LN(4, 0, phy)) #define ICL_PORT_TX_DW4_LN(ln, phy) _MMIO(_ICL_PORT_TX_DW_LN(4, ln, phy)) #define LOADGEN_SELECT (1 << 31) #define POST_CURSOR_1(x) ((x) << 12) @@ -2013,7 +2012,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ICL_PORT_TX_DW5_AUX(phy) _MMIO(_ICL_PORT_TX_DW_AUX(5, phy)) #define ICL_PORT_TX_DW5_GRP(phy) _MMIO(_ICL_PORT_TX_DW_GRP(5, phy)) -#define ICL_PORT_TX_DW5_LN0(phy) _MMIO(_ICL_PORT_TX_DW_LN(5, 0, phy)) +#define ICL_PORT_TX_DW5_LN(ln, phy) _MMIO(_ICL_PORT_TX_DW_LN(5, ln, phy)) #define TX_TRAINING_EN (1 << 31) #define TAP2_DISABLE (1 << 30) #define TAP3_DISABLE (1 << 29) @@ -2024,14 +2023,13 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ICL_PORT_TX_DW7_AUX(phy) _MMIO(_ICL_PORT_TX_DW_AUX(7, phy)) #define ICL_PORT_TX_DW7_GRP(phy) _MMIO(_ICL_PORT_TX_DW_GRP(7, phy)) -#define ICL_PORT_TX_DW7_LN0(phy) _MMIO(_ICL_PORT_TX_DW_LN(7, 0, phy)) #define ICL_PORT_TX_DW7_LN(ln, phy) _MMIO(_ICL_PORT_TX_DW_LN(7, ln, phy)) #define N_SCALAR(x) ((x) << 24) #define N_SCALAR_MASK (0x7F << 24) #define ICL_PORT_TX_DW8_AUX(phy) _MMIO(_ICL_PORT_TX_DW_AUX(8, phy)) #define ICL_PORT_TX_DW8_GRP(phy) _MMIO(_ICL_PORT_TX_DW_GRP(8, phy)) -#define ICL_PORT_TX_DW8_LN0(phy) _MMIO(_ICL_PORT_TX_DW_LN(8, 0, phy)) +#define ICL_PORT_TX_DW8_LN(ln, phy) _MMIO(_ICL_PORT_TX_DW_LN(8, ln, phy)) #define ICL_PORT_TX_DW8_ODCC_CLK_SEL REG_BIT(31) #define ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_MASK REG_GENMASK(30, 29) #define ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_DIV2 REG_FIELD_PREP(ICL_PORT_TX_DW8_ODCC_CLK_DIV_SEL_MASK, 0x1) @@ -3112,8 +3110,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) /* Fuse readout registers for GT */ #define HSW_PAVP_FUSE1 _MMIO(0x911C) -#define HSW_F1_EU_DIS_SHIFT 16 -#define HSW_F1_EU_DIS_MASK (0x3 << HSW_F1_EU_DIS_SHIFT) +#define XEHP_SFC_ENABLE_MASK REG_GENMASK(27, 24) +#define HSW_F1_EU_DIS_MASK REG_GENMASK(17, 16) #define HSW_F1_EU_DIS_10EUS 0 #define HSW_F1_EU_DIS_8EUS 1 #define HSW_F1_EU_DIS_6EUS 2 @@ -3389,6 +3387,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define ILK_DPFC_DISABLE_DUMMY0 (1 << 8) #define ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL (1 << 14) #define ILK_DPFC_NUKE_ON_ANY_MODIFICATION (1 << 23) +#define GLK_FBC_STRIDE _MMIO(0x43228) +#define FBC_STRIDE_OVERRIDE REG_BIT(15) +#define FBC_STRIDE_MASK REG_GENMASK(14, 0) +#define FBC_STRIDE(x) REG_FIELD_PREP(FBC_STRIDE_MASK, (x)) #define ILK_FBC_RT_BASE _MMIO(0x2128) #define ILK_FBC_RT_VALID (1 << 0) #define SNB_FBC_FRONT_BUFFER (1 << 1) @@ -4265,6 +4267,7 @@ enum { #define DUPS1_GATING_DIS (1 << 15) #define DUPS2_GATING_DIS (1 << 19) #define DUPS3_GATING_DIS (1 << 23) +#define CURSOR_GATING_DIS REG_BIT(28) #define DPF_GATING_DIS (1 << 10) #define DPF_RAM_GATING_DIS (1 << 9) #define DPFR_GATING_DIS (1 << 8) @@ -7253,6 +7256,7 @@ enum { #define _PLANE_COLOR_CTL_3_A 0x703CC /* GLK+ */ #define PLANE_COLOR_PIPE_GAMMA_ENABLE (1 << 30) /* Pre-ICL */ #define PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE (1 << 28) +#define PLANE_COLOR_PLANE_CSC_ENABLE REG_BIT(21) /* ICL+ */ #define PLANE_COLOR_INPUT_CSC_ENABLE (1 << 20) /* ICL+ */ #define PLANE_COLOR_PIPE_CSC_ENABLE (1 << 23) /* Pre-ICL */ #define PLANE_COLOR_CSC_MODE_BYPASS (0 << 17) @@ -7376,6 +7380,7 @@ enum { #define _PLANE_SURF_3(pipe) _PIPE(pipe, _PLANE_SURF_3_A, _PLANE_SURF_3_B) #define PLANE_SURF(pipe, plane) \ _MMIO_PLANE(plane, _PLANE_SURF_1(pipe), _PLANE_SURF_2(pipe)) +#define PLANE_SURF_DECRYPT REG_BIT(2) #define _PLANE_OFFSET_1_B 0x711a4 #define _PLANE_OFFSET_2_B 0x712a4 @@ -8117,6 +8122,7 @@ enum { /* irq instances for OTHER_CLASS */ #define OTHER_GUC_INSTANCE 0 #define OTHER_GTPM_INSTANCE 1 +#define OTHER_KCR_INSTANCE 4 #define GEN11_INTR_IDENTITY_REG(x) _MMIO(0x190060 + ((x) * 4)) @@ -8240,6 +8246,7 @@ enum { #define VSC_DATA_SEL_SOFTWARE_CONTROL REG_BIT(25) /* GLK */ #define FECSTALL_DIS_DPTSTREAM_DPTTG REG_BIT(23) #define DDI_TRAINING_OVERRIDE_ENABLE REG_BIT(19) +#define ADLP_1_BASED_X_GRANULARITY REG_BIT(18) #define DDI_TRAINING_OVERRIDE_VALUE REG_BIT(18) #define DDIE_TRAINING_OVERRIDE_ENABLE REG_BIT(17) /* CHICKEN_TRANS_A only */ #define DDIE_TRAINING_OVERRIDE_VALUE REG_BIT(16) /* CHICKEN_TRANS_A only */ @@ -9762,6 +9769,11 @@ enum { #define AUDIO_CP_READY(trans) ((1 << 1) << ((trans) * 4)) #define AUDIO_ELD_VALID(trans) ((1 << 0) << ((trans) * 4)) +#define _AUD_TCA_DP_2DOT0_CTRL 0x650bc +#define _AUD_TCB_DP_2DOT0_CTRL 0x651bc +#define AUD_DP_2DOT0_CTRL(trans) _MMIO_TRANS(trans, _AUD_TCA_DP_2DOT0_CTRL, _AUD_TCB_DP_2DOT0_CTRL) +#define AUD_ENABLE_SDP_SPLIT REG_BIT(31) + #define HSW_AUD_CHICKENBIT _MMIO(0x65f10) #define SKL_AUD_CODEC_WAKE_SIGNAL (1 << 15) @@ -10207,7 +10219,7 @@ enum skl_power_gate { #define TRANS_DDI_MODE_SELECT_DVI (1 << 24) #define TRANS_DDI_MODE_SELECT_DP_SST (2 << 24) #define TRANS_DDI_MODE_SELECT_DP_MST (3 << 24) -#define TRANS_DDI_MODE_SELECT_FDI (4 << 24) +#define TRANS_DDI_MODE_SELECT_FDI_OR_128B132B (4 << 24) #define TRANS_DDI_BPC_MASK (7 << 20) #define TRANS_DDI_BPC_8 (0 << 20) #define TRANS_DDI_BPC_10 (1 << 20) @@ -11010,7 +11022,6 @@ enum skl_power_gate { _DKL_TX_DPCNTL1) #define _DKL_TX_DPCNTL2 0x2C8 -#define DKL_TX_LOADGEN_SHARING_PMD_DISABLE REG_BIT(12) #define DKL_TX_DP20BITMODE (1 << 2) #define DKL_TX_DPCNTL2(tc_port) _MMIO(_PORT(tc_port, \ _DKL_PHY1_BASE, \ @@ -11389,6 +11400,51 @@ enum skl_power_gate { _PAL_PREC_MULTI_SEG_DATA_A, \ _PAL_PREC_MULTI_SEG_DATA_B) +#define _MMIO_PLANE_GAMC(plane, i, a, b) _MMIO(_PIPE(plane, a, b) + (i) * 4) + +/* Plane CSC Registers */ +#define _PLANE_CSC_RY_GY_1_A 0x70210 +#define _PLANE_CSC_RY_GY_2_A 0x70310 + +#define _PLANE_CSC_RY_GY_1_B 0x71210 +#define _PLANE_CSC_RY_GY_2_B 0x71310 + +#define _PLANE_CSC_RY_GY_1(pipe) _PIPE(pipe, _PLANE_CSC_RY_GY_1_A, \ + _PLANE_CSC_RY_GY_1_B) +#define _PLANE_CSC_RY_GY_2(pipe) _PIPE(pipe, _PLANE_INPUT_CSC_RY_GY_2_A, \ + _PLANE_INPUT_CSC_RY_GY_2_B) +#define PLANE_CSC_COEFF(pipe, plane, index) _MMIO_PLANE(plane, \ + _PLANE_CSC_RY_GY_1(pipe) + (index) * 4, \ + _PLANE_CSC_RY_GY_2(pipe) + (index) * 4) + +#define _PLANE_CSC_PREOFF_HI_1_A 0x70228 +#define _PLANE_CSC_PREOFF_HI_2_A 0x70328 + +#define _PLANE_CSC_PREOFF_HI_1_B 0x71228 +#define _PLANE_CSC_PREOFF_HI_2_B 0x71328 + +#define _PLANE_CSC_PREOFF_HI_1(pipe) _PIPE(pipe, _PLANE_CSC_PREOFF_HI_1_A, \ + _PLANE_CSC_PREOFF_HI_1_B) +#define _PLANE_CSC_PREOFF_HI_2(pipe) _PIPE(pipe, _PLANE_CSC_PREOFF_HI_2_A, \ + _PLANE_CSC_PREOFF_HI_2_B) +#define PLANE_CSC_PREOFF(pipe, plane, index) _MMIO_PLANE(plane, _PLANE_CSC_PREOFF_HI_1(pipe) + \ + (index) * 4, _PLANE_CSC_PREOFF_HI_2(pipe) + \ + (index) * 4) + +#define _PLANE_CSC_POSTOFF_HI_1_A 0x70234 +#define _PLANE_CSC_POSTOFF_HI_2_A 0x70334 + +#define _PLANE_CSC_POSTOFF_HI_1_B 0x71234 +#define _PLANE_CSC_POSTOFF_HI_2_B 0x71334 + +#define _PLANE_CSC_POSTOFF_HI_1(pipe) _PIPE(pipe, _PLANE_CSC_POSTOFF_HI_1_A, \ + _PLANE_CSC_POSTOFF_HI_1_B) +#define _PLANE_CSC_POSTOFF_HI_2(pipe) _PIPE(pipe, _PLANE_CSC_POSTOFF_HI_2_A, \ + _PLANE_CSC_POSTOFF_HI_2_B) +#define PLANE_CSC_POSTOFF(pipe, plane, index) _MMIO_PLANE(plane, _PLANE_CSC_POSTOFF_HI_1(pipe) + \ + (index) * 4, _PLANE_CSC_POSTOFF_HI_2(pipe) + \ + (index) * 4) + /* pipe CSC & degamma/gamma LUTs on CHV */ #define _CGM_PIPE_A_CSC_COEFF01 (VLV_DISPLAY_BASE + 0x67900) #define _CGM_PIPE_A_CSC_COEFF23 (VLV_DISPLAY_BASE + 0x67904) @@ -12786,4 +12842,7 @@ enum skl_power_gate { #define CLKREQ_POLICY _MMIO(0x101038) #define CLKREQ_POLICY_MEM_UP_OVRD REG_BIT(1) +#define CLKGATE_DIS_MISC _MMIO(0x46534) +#define CLKGATE_DIS_MISC_DMASC_GATING_DIS REG_BIT(21) + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 79da5eca60af..2c3cd6e635b5 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1145,6 +1145,12 @@ __emit_semaphore_wait(struct i915_request *to, return 0; } +static bool +can_use_semaphore_wait(struct i915_request *to, struct i915_request *from) +{ + return to->engine->gt->ggtt == from->engine->gt->ggtt; +} + static int emit_semaphore_wait(struct i915_request *to, struct i915_request *from, @@ -1153,6 +1159,9 @@ emit_semaphore_wait(struct i915_request *to, const intel_engine_mask_t mask = READ_ONCE(from->engine)->mask; struct i915_sw_fence *wait = &to->submit; + if (!can_use_semaphore_wait(to, from)) + goto await_fence; + if (!intel_context_use_semaphores(to->context)) goto await_fence; @@ -1256,7 +1265,8 @@ __i915_request_await_execution(struct i915_request *to, * immediate execution, and so we must wait until it reaches the * active slot. */ - if (intel_engine_has_semaphores(to->engine) && + if (can_use_semaphore_wait(to, from) && + intel_engine_has_semaphores(to->engine) && !i915_request_has_initial_breadcrumb(to)) { err = __emit_semaphore_wait(to, from, from->fence.seqno - 1); if (err < 0) @@ -1325,6 +1335,25 @@ i915_request_await_external(struct i915_request *rq, struct dma_fence *fence) return err; } +static inline bool is_parallel_rq(struct i915_request *rq) +{ + return intel_context_is_parallel(rq->context); +} + +static inline struct intel_context *request_to_parent(struct i915_request *rq) +{ + return intel_context_to_parent(rq->context); +} + +static bool is_same_parallel_context(struct i915_request *to, + struct i915_request *from) +{ + if (is_parallel_rq(to)) + return request_to_parent(to) == request_to_parent(from); + + return false; +} + int i915_request_await_execution(struct i915_request *rq, struct dma_fence *fence) @@ -1356,11 +1385,14 @@ i915_request_await_execution(struct i915_request *rq, * want to run our callback in all cases. */ - if (dma_fence_is_i915(fence)) + if (dma_fence_is_i915(fence)) { + if (is_same_parallel_context(rq, to_request(fence))) + continue; ret = __i915_request_await_execution(rq, to_request(fence)); - else + } else { ret = i915_request_await_external(rq, fence); + } if (ret < 0) return ret; } while (--nchild); @@ -1461,10 +1493,13 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) fence)) continue; - if (dma_fence_is_i915(fence)) + if (dma_fence_is_i915(fence)) { + if (is_same_parallel_context(rq, to_request(fence))) + continue; ret = i915_request_await_request(rq, to_request(fence)); - else + } else { ret = i915_request_await_external(rq, fence); + } if (ret < 0) return ret; @@ -1539,6 +1574,81 @@ i915_request_await_object(struct i915_request *to, return ret; } +static struct i915_request * +__i915_request_ensure_parallel_ordering(struct i915_request *rq, + struct intel_timeline *timeline) +{ + struct i915_request *prev; + + GEM_BUG_ON(!is_parallel_rq(rq)); + + prev = request_to_parent(rq)->parallel.last_rq; + if (prev) { + if (!__i915_request_is_complete(prev)) { + i915_sw_fence_await_sw_fence(&rq->submit, + &prev->submit, + &rq->submitq); + + if (rq->engine->sched_engine->schedule) + __i915_sched_node_add_dependency(&rq->sched, + &prev->sched, + &rq->dep, + 0); + } + i915_request_put(prev); + } + + request_to_parent(rq)->parallel.last_rq = i915_request_get(rq); + + return to_request(__i915_active_fence_set(&timeline->last_request, + &rq->fence)); +} + +static struct i915_request * +__i915_request_ensure_ordering(struct i915_request *rq, + struct intel_timeline *timeline) +{ + struct i915_request *prev; + + GEM_BUG_ON(is_parallel_rq(rq)); + + prev = to_request(__i915_active_fence_set(&timeline->last_request, + &rq->fence)); + + if (prev && !__i915_request_is_complete(prev)) { + bool uses_guc = intel_engine_uses_guc(rq->engine); + bool pow2 = is_power_of_2(READ_ONCE(prev->engine)->mask | + rq->engine->mask); + bool same_context = prev->context == rq->context; + + /* + * The requests are supposed to be kept in order. However, + * we need to be wary in case the timeline->last_request + * is used as a barrier for external modification to this + * context. + */ + GEM_BUG_ON(same_context && + i915_seqno_passed(prev->fence.seqno, + rq->fence.seqno)); + + if ((same_context && uses_guc) || (!uses_guc && pow2)) + i915_sw_fence_await_sw_fence(&rq->submit, + &prev->submit, + &rq->submitq); + else + __i915_sw_fence_await_dma_fence(&rq->submit, + &prev->fence, + &rq->dmaq); + if (rq->engine->sched_engine->schedule) + __i915_sched_node_add_dependency(&rq->sched, + &prev->sched, + &rq->dep, + 0); + } + + return prev; +} + static struct i915_request * __i915_request_add_to_timeline(struct i915_request *rq) { @@ -1564,38 +1674,21 @@ __i915_request_add_to_timeline(struct i915_request *rq) * complete (to maximise our greedy late load balancing) and this * precludes optimising to use semaphores serialisation of a single * timeline across engines. + * + * We do not order parallel submission requests on the timeline as each + * parallel submission context has its own timeline and the ordering + * rules for parallel requests are that they must be submitted in the + * order received from the execbuf IOCTL. So rather than using the + * timeline we store a pointer to last request submitted in the + * relationship in the gem context and insert a submission fence + * between that request and request passed into this function or + * alternatively we use completion fence if gem context has a single + * timeline and this is the first submission of an execbuf IOCTL. */ - prev = to_request(__i915_active_fence_set(&timeline->last_request, - &rq->fence)); - if (prev && !__i915_request_is_complete(prev)) { - bool uses_guc = intel_engine_uses_guc(rq->engine); - - /* - * The requests are supposed to be kept in order. However, - * we need to be wary in case the timeline->last_request - * is used as a barrier for external modification to this - * context. - */ - GEM_BUG_ON(prev->context == rq->context && - i915_seqno_passed(prev->fence.seqno, - rq->fence.seqno)); - - if ((!uses_guc && - is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask)) || - (uses_guc && prev->context == rq->context)) - i915_sw_fence_await_sw_fence(&rq->submit, - &prev->submit, - &rq->submitq); - else - __i915_sw_fence_await_dma_fence(&rq->submit, - &prev->fence, - &rq->dmaq); - if (rq->engine->sched_engine->schedule) - __i915_sched_node_add_dependency(&rq->sched, - &prev->sched, - &rq->dep, - 0); - } + if (likely(!is_parallel_rq(rq))) + prev = __i915_request_ensure_ordering(rq, timeline); + else + prev = __i915_request_ensure_parallel_ordering(rq, timeline); /* * Make sure that no request gazumped us - if it was allocated after @@ -1852,7 +1945,7 @@ long i915_request_wait(struct i915_request *rq, * completion. That requires having a good predictor for the request * duration, which we currently lack. */ - if (IS_ACTIVE(CONFIG_DRM_I915_MAX_REQUEST_BUSYWAIT) && + if (CONFIG_DRM_I915_MAX_REQUEST_BUSYWAIT && __i915_spin_request(rq, state)) goto out; diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 7bd9ed20623e..dc359242d1ae 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -139,6 +139,29 @@ enum { * the GPU. Here we track such boost requests on a per-request basis. */ I915_FENCE_FLAG_BOOST, + + /* + * I915_FENCE_FLAG_SUBMIT_PARALLEL - request with a context in a + * parent-child relationship (parallel submission, multi-lrc) should + * trigger a submission to the GuC rather than just moving the context + * tail. + */ + I915_FENCE_FLAG_SUBMIT_PARALLEL, + + /* + * I915_FENCE_FLAG_SKIP_PARALLEL - request with a context in a + * parent-child relationship (parallel submission, multi-lrc) that + * hit an error while generating requests in the execbuf IOCTL. + * Indicates this request should be skipped as another request in + * submission / relationship encoutered an error. + */ + I915_FENCE_FLAG_SKIP_PARALLEL, + + /* + * I915_FENCE_FLAG_COMPOSITE - Indicates fence is part of a composite + * fence (dma_fence_array) and i915 generated for parallel submission. + */ + I915_FENCE_FLAG_COMPOSITE, }; /** diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index cdf0e9c6fd73..1804f4142740 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -37,7 +37,6 @@ #include "i915_drv.h" #include "i915_sysfs.h" #include "intel_pm.h" -#include "intel_sideband.h" static inline struct drm_i915_private *kdev_minor_to_i915(struct device *kdev) { diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 066a9118c374..7a5925072466 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -459,17 +459,4 @@ static inline bool timer_expired(const struct timer_list *t) return timer_active(t) && !timer_pending(t); } -/* - * This is a lookalike for IS_ENABLED() that takes a kconfig value, - * e.g. CONFIG_DRM_I915_SPIN_REQUEST, and evaluates whether it is non-zero - * i.e. whether the configuration is active. Wrapping up the config inside - * a boolean context prevents clang and smatch from complaining about potential - * issues in confusing logical-&& with bitwise-& for constants. - * - * Sadly IS_ENABLED() itself does not work with kconfig values. - * - * Returns 0 if @config is 0, 1 if set to any value. - */ -#define IS_ACTIVE(config) ((config) != 0) - #endif /* !__I915_UTILS_H */ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 4b7fc4647e46..90546fa58fc1 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1234,9 +1234,10 @@ int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq) return i915_active_add_request(&vma->active, rq); } -int i915_vma_move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags) +int _i915_vma_move_to_active(struct i915_vma *vma, + struct i915_request *rq, + struct dma_fence *fence, + unsigned int flags) { struct drm_i915_gem_object *obj = vma->obj; int err; @@ -1257,9 +1258,11 @@ int i915_vma_move_to_active(struct i915_vma *vma, intel_frontbuffer_put(front); } - dma_resv_add_excl_fence(vma->resv, &rq->fence); - obj->write_domain = I915_GEM_DOMAIN_RENDER; - obj->read_domains = 0; + if (fence) { + dma_resv_add_excl_fence(vma->resv, fence); + obj->write_domain = I915_GEM_DOMAIN_RENDER; + obj->read_domains = 0; + } } else { if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { err = dma_resv_reserve_shared(vma->resv, 1); @@ -1267,8 +1270,10 @@ int i915_vma_move_to_active(struct i915_vma *vma, return err; } - dma_resv_add_shared_fence(vma->resv, &rq->fence); - obj->write_domain = 0; + if (fence) { + dma_resv_add_shared_fence(vma->resv, fence); + obj->write_domain = 0; + } } if (flags & EXEC_OBJECT_NEEDS_FENCE && vma->fence) diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index ed69f66c7ab0..648dbe744c96 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -57,9 +57,16 @@ static inline bool i915_vma_is_active(const struct i915_vma *vma) int __must_check __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq); -int __must_check i915_vma_move_to_active(struct i915_vma *vma, - struct i915_request *rq, - unsigned int flags); +int __must_check _i915_vma_move_to_active(struct i915_vma *vma, + struct i915_request *rq, + struct dma_fence *fence, + unsigned int flags); +static inline int __must_check +i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq, + unsigned int flags) +{ + return _i915_vma_move_to_active(vma, rq, &rq->fence, flags); +} #define __i915_vma_flags(v) ((unsigned long *)&(v)->flags.counter) diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h index 995b502d7e5d..80e93bf00f2e 100644 --- a/drivers/gpu/drm/i915/i915_vma_types.h +++ b/drivers/gpu/drm/i915/i915_vma_types.h @@ -105,8 +105,9 @@ struct intel_remapped_plane_info { } __packed; struct intel_remapped_info { - struct intel_remapped_plane_info plane[2]; - u32 unused_mbz; + struct intel_remapped_plane_info plane[4]; + /* in gtt pages */ + u32 plane_alignment; } __packed; struct intel_rotation_info { @@ -129,7 +130,7 @@ static inline void assert_i915_gem_gtt_types(void) { BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 2 * sizeof(u32) + 8 * sizeof(u16)); BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int)); - BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 3 * sizeof(u32) + 8 * sizeof(u16)); + BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 5 * sizeof(u32) + 16 * sizeof(u16)); /* Check that rotation/remapped shares offsets for simplicity */ BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) != diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index d328bb95c49b..8e6f48d1eb7b 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -133,6 +133,7 @@ enum intel_ppgtt_type { func(has_logical_ring_elsq); \ func(has_mslices); \ func(has_pooled_eu); \ + func(has_pxp); \ func(has_rc6); \ func(has_rc6p); \ func(has_rps); \ diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 7acce64b0941..84bb212bae4b 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -5,7 +5,7 @@ #include "i915_drv.h" #include "intel_dram.h" -#include "intel_sideband.h" +#include "intel_pcode.h" struct dram_dimm_info { u16 size; @@ -418,7 +418,7 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv) break; default: MISSING_CASE(val & 0xf); - return -1; + return -EINVAL; } } else { switch (val & 0xf) { @@ -436,7 +436,7 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv) break; default: MISSING_CASE(val & 0xf); - return -1; + return -EINVAL; } } diff --git a/drivers/gpu/drm/i915/intel_pcode.c b/drivers/gpu/drm/i915/intel_pcode.c new file mode 100644 index 000000000000..e8c886e4e78d --- /dev/null +++ b/drivers/gpu/drm/i915/intel_pcode.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2013-2021 Intel Corporation + */ + +#include "i915_drv.h" +#include "intel_pcode.h" + +static int gen6_check_mailbox_status(u32 mbox) +{ + switch (mbox & GEN6_PCODE_ERROR_MASK) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_UNIMPLEMENTED_CMD: + return -ENODEV; + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + case GEN6_PCODE_TIMEOUT: + return -ETIMEDOUT; + default: + MISSING_CASE(mbox & GEN6_PCODE_ERROR_MASK); + return 0; + } +} + +static int gen7_check_mailbox_status(u32 mbox) +{ + switch (mbox & GEN6_PCODE_ERROR_MASK) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN7_PCODE_TIMEOUT: + return -ETIMEDOUT; + case GEN7_PCODE_ILLEGAL_DATA: + return -EINVAL; + case GEN11_PCODE_ILLEGAL_SUBCOMMAND: + return -ENXIO; + case GEN11_PCODE_LOCKED: + return -EBUSY; + case GEN11_PCODE_REJECTED: + return -EACCES; + case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + default: + MISSING_CASE(mbox & GEN6_PCODE_ERROR_MASK); + return 0; + } +} + +static int __sandybridge_pcode_rw(struct drm_i915_private *i915, + u32 mbox, u32 *val, u32 *val1, + int fast_timeout_us, + int slow_timeout_ms, + bool is_read) +{ + struct intel_uncore *uncore = &i915->uncore; + + lockdep_assert_held(&i915->sb_lock); + + /* + * GEN6_PCODE_* are outside of the forcewake domain, we can use + * intel_uncore_read/write_fw variants to reduce the amount of work + * required when reading/writing. + */ + + if (intel_uncore_read_fw(uncore, GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) + return -EAGAIN; + + intel_uncore_write_fw(uncore, GEN6_PCODE_DATA, *val); + intel_uncore_write_fw(uncore, GEN6_PCODE_DATA1, val1 ? *val1 : 0); + intel_uncore_write_fw(uncore, + GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox); + + if (__intel_wait_for_register_fw(uncore, + GEN6_PCODE_MAILBOX, + GEN6_PCODE_READY, 0, + fast_timeout_us, + slow_timeout_ms, + &mbox)) + return -ETIMEDOUT; + + if (is_read) + *val = intel_uncore_read_fw(uncore, GEN6_PCODE_DATA); + if (is_read && val1) + *val1 = intel_uncore_read_fw(uncore, GEN6_PCODE_DATA1); + + if (GRAPHICS_VER(i915) > 6) + return gen7_check_mailbox_status(mbox); + else + return gen6_check_mailbox_status(mbox); +} + +int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox, + u32 *val, u32 *val1) +{ + int err; + + mutex_lock(&i915->sb_lock); + err = __sandybridge_pcode_rw(i915, mbox, val, val1, + 500, 20, + true); + mutex_unlock(&i915->sb_lock); + + if (err) { + drm_dbg(&i915->drm, + "warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n", + mbox, __builtin_return_address(0), err); + } + + return err; +} + +int sandybridge_pcode_write_timeout(struct drm_i915_private *i915, + u32 mbox, u32 val, + int fast_timeout_us, + int slow_timeout_ms) +{ + int err; + + mutex_lock(&i915->sb_lock); + err = __sandybridge_pcode_rw(i915, mbox, &val, NULL, + fast_timeout_us, slow_timeout_ms, + false); + mutex_unlock(&i915->sb_lock); + + if (err) { + drm_dbg(&i915->drm, + "warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n", + val, mbox, __builtin_return_address(0), err); + } + + return err; +} + +static bool skl_pcode_try_request(struct drm_i915_private *i915, u32 mbox, + u32 request, u32 reply_mask, u32 reply, + u32 *status) +{ + *status = __sandybridge_pcode_rw(i915, mbox, &request, NULL, + 500, 0, + true); + + return *status || ((request & reply_mask) == reply); +} + +/** + * skl_pcode_request - send PCODE request until acknowledgment + * @i915: device private + * @mbox: PCODE mailbox ID the request is targeted for + * @request: request ID + * @reply_mask: mask used to check for request acknowledgment + * @reply: value used to check for request acknowledgment + * @timeout_base_ms: timeout for polling with preemption enabled + * + * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE + * reports an error or an overall timeout of @timeout_base_ms+50 ms expires. + * The request is acknowledged once the PCODE reply dword equals @reply after + * applying @reply_mask. Polling is first attempted with preemption enabled + * for @timeout_base_ms and if this times out for another 50 ms with + * preemption disabled. + * + * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some + * other error as reported by PCODE. + */ +int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request, + u32 reply_mask, u32 reply, int timeout_base_ms) +{ + u32 status; + int ret; + + mutex_lock(&i915->sb_lock); + +#define COND \ + skl_pcode_try_request(i915, mbox, request, reply_mask, reply, &status) + + /* + * Prime the PCODE by doing a request first. Normally it guarantees + * that a subsequent request, at most @timeout_base_ms later, succeeds. + * _wait_for() doesn't guarantee when its passed condition is evaluated + * first, so send the first request explicitly. + */ + if (COND) { + ret = 0; + goto out; + } + ret = _wait_for(COND, timeout_base_ms * 1000, 10, 10); + if (!ret) + goto out; + + /* + * The above can time out if the number of requests was low (2 in the + * worst case) _and_ PCODE was busy for some reason even after a + * (queued) request and @timeout_base_ms delay. As a workaround retry + * the poll with preemption disabled to maximize the number of + * requests. Increase the timeout from @timeout_base_ms to 50ms to + * account for interrupts that could reduce the number of these + * requests, and for any quirks of the PCODE firmware that delays + * the request completion. + */ + drm_dbg_kms(&i915->drm, + "PCODE timeout, retrying with preemption disabled\n"); + drm_WARN_ON_ONCE(&i915->drm, timeout_base_ms > 3); + preempt_disable(); + ret = wait_for_atomic(COND, 50); + preempt_enable(); + +out: + mutex_unlock(&i915->sb_lock); + return ret ? ret : status; +#undef COND +} + +int intel_pcode_init(struct drm_i915_private *i915) +{ + int ret = 0; + + if (!IS_DGFX(i915)) + return ret; + + ret = skl_pcode_request(i915, DG1_PCODE_STATUS, + DG1_UNCORE_GET_INIT_STATUS, + DG1_UNCORE_INIT_STATUS_COMPLETE, + DG1_UNCORE_INIT_STATUS_COMPLETE, 180000); + + drm_dbg(&i915->drm, "PCODE init status %d\n", ret); + + if (ret) + drm_err(&i915->drm, "Pcode did not report uncore initialization completion!\n"); + + return ret; +} diff --git a/drivers/gpu/drm/i915/intel_pcode.h b/drivers/gpu/drm/i915/intel_pcode.h new file mode 100644 index 000000000000..50806649d4b6 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_pcode.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2013-2021 Intel Corporation + */ + +#ifndef _INTEL_PCODE_H_ +#define _INTEL_PCODE_H_ + +#include + +struct drm_i915_private; + +int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox, + u32 *val, u32 *val1); +int sandybridge_pcode_write_timeout(struct drm_i915_private *i915, u32 mbox, + u32 val, int fast_timeout_us, + int slow_timeout_ms); +#define sandybridge_pcode_write(i915, mbox, val) \ + sandybridge_pcode_write_timeout(i915, mbox, val, 500, 0) + +int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request, + u32 reply_mask, u32 reply, int timeout_base_ms); + +int intel_pcode_init(struct drm_i915_private *i915); + +#endif /* _INTEL_PCODE_H */ diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index e442845eca91..ecbb3d141632 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -47,8 +47,9 @@ #include "i915_fixed.h" #include "i915_irq.h" #include "i915_trace.h" +#include "intel_pcode.h" #include "intel_pm.h" -#include "intel_sideband.h" +#include "vlv_sideband.h" #include "../../../platform/x86/intel_ips.h" /* Stores plane specific WM parameters */ @@ -893,9 +894,8 @@ static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv) return enabled; } -static void pnv_update_wm(struct intel_crtc *unused_crtc) +static void pnv_update_wm(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev); struct intel_crtc *crtc; const struct cxsr_latency *latency; u32 reg; @@ -1164,17 +1164,13 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state, cpp = plane_state->hw.fb->format->cpp[0]; /* - * Not 100% sure which way ELK should go here as the - * spec only says CL/CTG should assume 32bpp and BW - * doesn't need to. But as these things followed the - * mobile vs. desktop lines on gen3 as well, let's - * assume ELK doesn't need this. + * WaUse32BppForSRWM:ctg,elk * - * The spec also fails to list such a restriction for - * the HPLL watermark, which seems a little strange. + * The spec fails to list this restriction for the + * HPLL watermark, which seems a little strange. * Let's use 32bpp for the HPLL watermark as well. */ - if (IS_GM45(dev_priv) && plane->id == PLANE_PRIMARY && + if (plane->id == PLANE_PRIMARY && level != G4X_WM_LEVEL_NORMAL) cpp = max(cpp, 4u); @@ -1388,8 +1384,7 @@ static int g4x_compute_pipe_wm(struct intel_atomic_state *state, struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal; - int num_active_planes = hweight8(crtc_state->active_planes & - ~BIT(PLANE_CURSOR)); + u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); const struct g4x_pipe_wm *raw; const struct intel_plane_state *old_plane_state; const struct intel_plane_state *new_plane_state; @@ -1429,7 +1424,7 @@ static int g4x_compute_pipe_wm(struct intel_atomic_state *state, wm_state->sr.cursor = raw->plane[PLANE_CURSOR]; wm_state->sr.fbc = raw->fbc; - wm_state->cxsr = num_active_planes == BIT(PLANE_PRIMARY); + wm_state->cxsr = active_planes == BIT(PLANE_PRIMARY); level = G4X_WM_LEVEL_HPLL; if (!g4x_raw_crtc_wm_is_valid(crtc_state, level)) @@ -1720,7 +1715,7 @@ static int vlv_compute_fifo(struct intel_crtc_state *crtc_state) const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2]; struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state; - unsigned int active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); + u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); int num_active_planes = hweight8(active_planes); const int fifo_size = 511; int fifo_extra, fifo_left = fifo_size; @@ -1912,8 +1907,8 @@ static int vlv_compute_pipe_wm(struct intel_atomic_state *state, struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal; const struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state; - int num_active_planes = hweight8(crtc_state->active_planes & - ~BIT(PLANE_CURSOR)); + u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR); + int num_active_planes = hweight8(active_planes); bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi); const struct intel_plane_state *old_plane_state; const struct intel_plane_state *new_plane_state; @@ -2265,9 +2260,8 @@ static void vlv_optimize_watermarks(struct intel_atomic_state *state, mutex_unlock(&dev_priv->wm.wm_mutex); } -static void i965_update_wm(struct intel_crtc *unused_crtc) +static void i965_update_wm(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev); struct intel_crtc *crtc; int srwm = 1; int cursor_sr = 16; @@ -2341,9 +2335,8 @@ static void i965_update_wm(struct intel_crtc *unused_crtc) #undef FW_WM -static void i9xx_update_wm(struct intel_crtc *unused_crtc) +static void i9xx_update_wm(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev); const struct intel_watermark_params *wm_info; u32 fwater_lo; u32 fwater_hi; @@ -2359,7 +2352,10 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) else wm_info = &i830_a_wm_info; - fifo_size = dev_priv->display.get_fifo_size(dev_priv, PLANE_A); + if (DISPLAY_VER(dev_priv) == 2) + fifo_size = i830_get_fifo_size(dev_priv, PLANE_A); + else + fifo_size = i9xx_get_fifo_size(dev_priv, PLANE_A); crtc = intel_get_crtc_for_plane(dev_priv, PLANE_A); if (intel_crtc_active(crtc)) { const struct drm_display_mode *pipe_mode = @@ -2386,7 +2382,10 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) if (DISPLAY_VER(dev_priv) == 2) wm_info = &i830_bc_wm_info; - fifo_size = dev_priv->display.get_fifo_size(dev_priv, PLANE_B); + if (DISPLAY_VER(dev_priv) == 2) + fifo_size = i830_get_fifo_size(dev_priv, PLANE_B); + else + fifo_size = i9xx_get_fifo_size(dev_priv, PLANE_B); crtc = intel_get_crtc_for_plane(dev_priv, PLANE_B); if (intel_crtc_active(crtc)) { const struct drm_display_mode *pipe_mode = @@ -2487,9 +2486,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) intel_set_memory_cxsr(dev_priv, true); } -static void i845_update_wm(struct intel_crtc *unused_crtc) +static void i845_update_wm(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev); struct intel_crtc *crtc; const struct drm_display_mode *pipe_mode; u32 fwater_lo; @@ -2502,7 +2500,7 @@ static void i845_update_wm(struct intel_crtc *unused_crtc) pipe_mode = &crtc->config->hw.pipe_mode; planea_wm = intel_calculate_wm(pipe_mode->crtc_clock, &i845_wm_info, - dev_priv->display.get_fifo_size(dev_priv, PLANE_A), + i845_get_fifo_size(dev_priv, PLANE_A), 4, pessimal_latency_ns); fwater_lo = intel_uncore_read(&dev_priv->uncore, FW_BLC) & ~0xfff; fwater_lo |= (3<<8) | planea_wm; @@ -6845,7 +6843,8 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv) for_each_plane_id_on_crtc(crtc, plane_id) raw->plane[plane_id] = active->wm.plane[plane_id]; - if (++level > max_level) + level = G4X_WM_LEVEL_SR; + if (level > max_level) goto out; raw = &crtc_state->wm.g4x.raw[level]; @@ -6854,7 +6853,8 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv) raw->plane[PLANE_SPRITE0] = 0; raw->fbc = active->sr.fbc; - if (++level > max_level) + level = G4X_WM_LEVEL_HPLL; + if (level > max_level) goto out; raw = &crtc_state->wm.g4x.raw[level]; @@ -6863,6 +6863,7 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv) raw->plane[PLANE_SPRITE0] = 0; raw->fbc = active->hpll.fbc; + level++; out: for_each_plane_id_on_crtc(crtc, plane_id) g4x_raw_plane_wm_set(crtc_state, level, @@ -7142,47 +7143,6 @@ void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv) !(intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) & DISP_FBC_WM_DIS); } -/** - * intel_update_watermarks - update FIFO watermark values based on current modes - * @crtc: the #intel_crtc on which to compute the WM - * - * Calculate watermark values for the various WM regs based on current mode - * and plane configuration. - * - * There are several cases to deal with here: - * - normal (i.e. non-self-refresh) - * - self-refresh (SR) mode - * - lines are large relative to FIFO size (buffer can hold up to 2) - * - lines are small relative to FIFO size (buffer can hold more than 2 - * lines), so need to account for TLB latency - * - * The normal calculation is: - * watermark = dotclock * bytes per pixel * latency - * where latency is platform & configuration dependent (we assume pessimal - * values here). - * - * The SR calculation is: - * watermark = (trunc(latency/line time)+1) * surface width * - * bytes per pixel - * where - * line time = htotal / dotclock - * surface width = hdisplay for normal plane and 64 for cursor - * and latency is assumed to be high, as above. - * - * The final value programmed to the register should always be rounded up, - * and include an extra 2 entries to account for clock crossings. - * - * We don't use the sprite, so we can ignore that. And on Crestline we have - * to set the non-SR watermarks to 8. - */ -void intel_update_watermarks(struct intel_crtc *crtc) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - - if (dev_priv->display.update_wm) - dev_priv->display.update_wm(crtc); -} - void intel_enable_ipc(struct drm_i915_private *dev_priv) { u32 val; @@ -7640,11 +7600,6 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) | BDW_DPRS_MASK_VBLANK_SRD); - - /* Undocumented but fixes async flip + VT-d corruption */ - if (intel_vtd_active()) - intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), - HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1); } /* WaVSRefCountFullforceMissDisable:bdw */ @@ -7680,20 +7635,11 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv) static void hsw_init_clock_gating(struct drm_i915_private *dev_priv) { - enum pipe pipe; - /* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */ intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A), intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) | HSW_FBCQ_DIS); - for_each_pipe(dev_priv, pipe) { - /* Undocumented but fixes async flip + VT-d corruption */ - if (intel_vtd_active()) - intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), - HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1); - } - /* This is required by WaCatErrorRejectionIssue:hsw */ intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG, intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | @@ -7922,7 +7868,7 @@ static void i830_init_clock_gating(struct drm_i915_private *dev_priv) void intel_init_clock_gating(struct drm_i915_private *dev_priv) { - dev_priv->display.init_clock_gating(dev_priv); + dev_priv->clock_gating_funcs->init_clock_gating(dev_priv); } void intel_suspend_hw(struct drm_i915_private *dev_priv) @@ -7937,6 +7883,36 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv) "No clock gating settings or workarounds applied.\n"); } +#define CG_FUNCS(platform) \ +static const struct drm_i915_clock_gating_funcs platform##_clock_gating_funcs = { \ + .init_clock_gating = platform##_init_clock_gating, \ +} + +CG_FUNCS(adlp); +CG_FUNCS(dg1); +CG_FUNCS(gen12lp); +CG_FUNCS(icl); +CG_FUNCS(cfl); +CG_FUNCS(skl); +CG_FUNCS(kbl); +CG_FUNCS(bxt); +CG_FUNCS(glk); +CG_FUNCS(bdw); +CG_FUNCS(chv); +CG_FUNCS(hsw); +CG_FUNCS(ivb); +CG_FUNCS(vlv); +CG_FUNCS(gen6); +CG_FUNCS(ilk); +CG_FUNCS(g4x); +CG_FUNCS(i965gm); +CG_FUNCS(i965g); +CG_FUNCS(gen3); +CG_FUNCS(i85x); +CG_FUNCS(i830); +CG_FUNCS(nop); +#undef CG_FUNCS + /** * intel_init_clock_gating_hooks - setup the clock gating hooks * @dev_priv: device private @@ -7949,55 +7925,100 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv) void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) { if (IS_ALDERLAKE_P(dev_priv)) - dev_priv->display.init_clock_gating = adlp_init_clock_gating; + dev_priv->clock_gating_funcs = &adlp_clock_gating_funcs; else if (IS_DG1(dev_priv)) - dev_priv->display.init_clock_gating = dg1_init_clock_gating; + dev_priv->clock_gating_funcs = &dg1_clock_gating_funcs; else if (GRAPHICS_VER(dev_priv) == 12) - dev_priv->display.init_clock_gating = gen12lp_init_clock_gating; + dev_priv->clock_gating_funcs = &gen12lp_clock_gating_funcs; else if (GRAPHICS_VER(dev_priv) == 11) - dev_priv->display.init_clock_gating = icl_init_clock_gating; + dev_priv->clock_gating_funcs = &icl_clock_gating_funcs; else if (IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv)) - dev_priv->display.init_clock_gating = cfl_init_clock_gating; + dev_priv->clock_gating_funcs = &cfl_clock_gating_funcs; else if (IS_SKYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = skl_init_clock_gating; + dev_priv->clock_gating_funcs = &skl_clock_gating_funcs; else if (IS_KABYLAKE(dev_priv)) - dev_priv->display.init_clock_gating = kbl_init_clock_gating; + dev_priv->clock_gating_funcs = &kbl_clock_gating_funcs; else if (IS_BROXTON(dev_priv)) - dev_priv->display.init_clock_gating = bxt_init_clock_gating; + dev_priv->clock_gating_funcs = &bxt_clock_gating_funcs; else if (IS_GEMINILAKE(dev_priv)) - dev_priv->display.init_clock_gating = glk_init_clock_gating; + dev_priv->clock_gating_funcs = &glk_clock_gating_funcs; else if (IS_BROADWELL(dev_priv)) - dev_priv->display.init_clock_gating = bdw_init_clock_gating; + dev_priv->clock_gating_funcs = &bdw_clock_gating_funcs; else if (IS_CHERRYVIEW(dev_priv)) - dev_priv->display.init_clock_gating = chv_init_clock_gating; + dev_priv->clock_gating_funcs = &chv_clock_gating_funcs; else if (IS_HASWELL(dev_priv)) - dev_priv->display.init_clock_gating = hsw_init_clock_gating; + dev_priv->clock_gating_funcs = &hsw_clock_gating_funcs; else if (IS_IVYBRIDGE(dev_priv)) - dev_priv->display.init_clock_gating = ivb_init_clock_gating; + dev_priv->clock_gating_funcs = &ivb_clock_gating_funcs; else if (IS_VALLEYVIEW(dev_priv)) - dev_priv->display.init_clock_gating = vlv_init_clock_gating; + dev_priv->clock_gating_funcs = &vlv_clock_gating_funcs; else if (GRAPHICS_VER(dev_priv) == 6) - dev_priv->display.init_clock_gating = gen6_init_clock_gating; + dev_priv->clock_gating_funcs = &gen6_clock_gating_funcs; else if (GRAPHICS_VER(dev_priv) == 5) - dev_priv->display.init_clock_gating = ilk_init_clock_gating; + dev_priv->clock_gating_funcs = &ilk_clock_gating_funcs; else if (IS_G4X(dev_priv)) - dev_priv->display.init_clock_gating = g4x_init_clock_gating; + dev_priv->clock_gating_funcs = &g4x_clock_gating_funcs; else if (IS_I965GM(dev_priv)) - dev_priv->display.init_clock_gating = i965gm_init_clock_gating; + dev_priv->clock_gating_funcs = &i965gm_clock_gating_funcs; else if (IS_I965G(dev_priv)) - dev_priv->display.init_clock_gating = i965g_init_clock_gating; + dev_priv->clock_gating_funcs = &i965g_clock_gating_funcs; else if (GRAPHICS_VER(dev_priv) == 3) - dev_priv->display.init_clock_gating = gen3_init_clock_gating; + dev_priv->clock_gating_funcs = &gen3_clock_gating_funcs; else if (IS_I85X(dev_priv) || IS_I865G(dev_priv)) - dev_priv->display.init_clock_gating = i85x_init_clock_gating; + dev_priv->clock_gating_funcs = &i85x_clock_gating_funcs; else if (GRAPHICS_VER(dev_priv) == 2) - dev_priv->display.init_clock_gating = i830_init_clock_gating; + dev_priv->clock_gating_funcs = &i830_clock_gating_funcs; else { MISSING_CASE(INTEL_DEVID(dev_priv)); - dev_priv->display.init_clock_gating = nop_init_clock_gating; + dev_priv->clock_gating_funcs = &nop_clock_gating_funcs; } } +static const struct drm_i915_wm_disp_funcs skl_wm_funcs = { + .compute_global_watermarks = skl_compute_wm, +}; + +static const struct drm_i915_wm_disp_funcs ilk_wm_funcs = { + .compute_pipe_wm = ilk_compute_pipe_wm, + .compute_intermediate_wm = ilk_compute_intermediate_wm, + .initial_watermarks = ilk_initial_watermarks, + .optimize_watermarks = ilk_optimize_watermarks, +}; + +static const struct drm_i915_wm_disp_funcs vlv_wm_funcs = { + .compute_pipe_wm = vlv_compute_pipe_wm, + .compute_intermediate_wm = vlv_compute_intermediate_wm, + .initial_watermarks = vlv_initial_watermarks, + .optimize_watermarks = vlv_optimize_watermarks, + .atomic_update_watermarks = vlv_atomic_update_fifo, +}; + +static const struct drm_i915_wm_disp_funcs g4x_wm_funcs = { + .compute_pipe_wm = g4x_compute_pipe_wm, + .compute_intermediate_wm = g4x_compute_intermediate_wm, + .initial_watermarks = g4x_initial_watermarks, + .optimize_watermarks = g4x_optimize_watermarks, +}; + +static const struct drm_i915_wm_disp_funcs pnv_wm_funcs = { + .update_wm = pnv_update_wm, +}; + +static const struct drm_i915_wm_disp_funcs i965_wm_funcs = { + .update_wm = i965_update_wm, +}; + +static const struct drm_i915_wm_disp_funcs i9xx_wm_funcs = { + .update_wm = i9xx_update_wm, +}; + +static const struct drm_i915_wm_disp_funcs i845_wm_funcs = { + .update_wm = i845_update_wm, +}; + +static const struct drm_i915_wm_disp_funcs nop_funcs = { +}; + /* Set up chip specific power management-related functions */ void intel_init_pm(struct drm_i915_private *dev_priv) { @@ -8013,7 +8034,7 @@ void intel_init_pm(struct drm_i915_private *dev_priv) /* For FIFO watermark updates */ if (DISPLAY_VER(dev_priv) >= 9) { skl_setup_wm_latency(dev_priv); - dev_priv->display.compute_global_watermarks = skl_compute_wm; + dev_priv->wm_disp = &skl_wm_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { ilk_setup_wm_latency(dev_priv); @@ -8021,31 +8042,19 @@ void intel_init_pm(struct drm_i915_private *dev_priv) dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) || (DISPLAY_VER(dev_priv) != 5 && dev_priv->wm.pri_latency[0] && dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { - dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm; - dev_priv->display.compute_intermediate_wm = - ilk_compute_intermediate_wm; - dev_priv->display.initial_watermarks = - ilk_initial_watermarks; - dev_priv->display.optimize_watermarks = - ilk_optimize_watermarks; + dev_priv->wm_disp = &ilk_wm_funcs; } else { drm_dbg_kms(&dev_priv->drm, "Failed to read display plane latency. " "Disable CxSR\n"); + dev_priv->wm_disp = &nop_funcs; } } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { vlv_setup_wm_latency(dev_priv); - dev_priv->display.compute_pipe_wm = vlv_compute_pipe_wm; - dev_priv->display.compute_intermediate_wm = vlv_compute_intermediate_wm; - dev_priv->display.initial_watermarks = vlv_initial_watermarks; - dev_priv->display.optimize_watermarks = vlv_optimize_watermarks; - dev_priv->display.atomic_update_watermarks = vlv_atomic_update_fifo; + dev_priv->wm_disp = &vlv_wm_funcs; } else if (IS_G4X(dev_priv)) { g4x_setup_wm_latency(dev_priv); - dev_priv->display.compute_pipe_wm = g4x_compute_pipe_wm; - dev_priv->display.compute_intermediate_wm = g4x_compute_intermediate_wm; - dev_priv->display.initial_watermarks = g4x_initial_watermarks; - dev_priv->display.optimize_watermarks = g4x_optimize_watermarks; + dev_priv->wm_disp = &g4x_wm_funcs; } else if (IS_PINEVIEW(dev_priv)) { if (!intel_get_cxsr_latency(!IS_MOBILE(dev_priv), dev_priv->is_ddr3, @@ -8059,25 +8068,22 @@ void intel_init_pm(struct drm_i915_private *dev_priv) dev_priv->fsb_freq, dev_priv->mem_freq); /* Disable CxSR and never update its watermark again */ intel_set_memory_cxsr(dev_priv, false); - dev_priv->display.update_wm = NULL; + dev_priv->wm_disp = &nop_funcs; } else - dev_priv->display.update_wm = pnv_update_wm; + dev_priv->wm_disp = &pnv_wm_funcs; } else if (DISPLAY_VER(dev_priv) == 4) { - dev_priv->display.update_wm = i965_update_wm; + dev_priv->wm_disp = &i965_wm_funcs; } else if (DISPLAY_VER(dev_priv) == 3) { - dev_priv->display.update_wm = i9xx_update_wm; - dev_priv->display.get_fifo_size = i9xx_get_fifo_size; + dev_priv->wm_disp = &i9xx_wm_funcs; } else if (DISPLAY_VER(dev_priv) == 2) { - if (INTEL_NUM_PIPES(dev_priv) == 1) { - dev_priv->display.update_wm = i845_update_wm; - dev_priv->display.get_fifo_size = i845_get_fifo_size; - } else { - dev_priv->display.update_wm = i9xx_update_wm; - dev_priv->display.get_fifo_size = i830_get_fifo_size; - } + if (INTEL_NUM_PIPES(dev_priv) == 1) + dev_priv->wm_disp = &i845_wm_funcs; + else + dev_priv->wm_disp = &i9xx_wm_funcs; } else { drm_err(&dev_priv->drm, "unexpected fall-through in %s\n", __func__); + dev_priv->wm_disp = &nop_funcs; } } diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h index 941b3ae555c8..990cdcaf85ce 100644 --- a/drivers/gpu/drm/i915/intel_pm.h +++ b/drivers/gpu/drm/i915/intel_pm.h @@ -29,7 +29,6 @@ struct skl_wm_level; void intel_init_clock_gating(struct drm_i915_private *dev_priv); void intel_suspend_hw(struct drm_i915_private *dev_priv); int ilk_wm_max_level(const struct drm_i915_private *dev_priv); -void intel_update_watermarks(struct intel_crtc *crtc); void intel_init_pm(struct drm_i915_private *dev_priv); void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv); void intel_pm_setup(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_sbi.c b/drivers/gpu/drm/i915/intel_sbi.c new file mode 100644 index 000000000000..5ba8490a31e6 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_sbi.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2013-2021 Intel Corporation + * + * LPT/WPT IOSF sideband. + */ + +#include "i915_drv.h" +#include "intel_sbi.h" + +/* SBI access */ +static int intel_sbi_rw(struct drm_i915_private *i915, u16 reg, + enum intel_sbi_destination destination, + u32 *val, bool is_read) +{ + struct intel_uncore *uncore = &i915->uncore; + u32 cmd; + + lockdep_assert_held(&i915->sb_lock); + + if (intel_wait_for_register_fw(uncore, + SBI_CTL_STAT, SBI_BUSY, 0, + 100)) { + drm_err(&i915->drm, + "timeout waiting for SBI to become ready\n"); + return -EBUSY; + } + + intel_uncore_write_fw(uncore, SBI_ADDR, (u32)reg << 16); + intel_uncore_write_fw(uncore, SBI_DATA, is_read ? 0 : *val); + + if (destination == SBI_ICLK) + cmd = SBI_CTL_DEST_ICLK | SBI_CTL_OP_CRRD; + else + cmd = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IORD; + if (!is_read) + cmd |= BIT(8); + intel_uncore_write_fw(uncore, SBI_CTL_STAT, cmd | SBI_BUSY); + + if (__intel_wait_for_register_fw(uncore, + SBI_CTL_STAT, SBI_BUSY, 0, + 100, 100, &cmd)) { + drm_err(&i915->drm, + "timeout waiting for SBI to complete read\n"); + return -ETIMEDOUT; + } + + if (cmd & SBI_RESPONSE_FAIL) { + drm_err(&i915->drm, "error during SBI read of reg %x\n", reg); + return -ENXIO; + } + + if (is_read) + *val = intel_uncore_read_fw(uncore, SBI_DATA); + + return 0; +} + +u32 intel_sbi_read(struct drm_i915_private *i915, u16 reg, + enum intel_sbi_destination destination) +{ + u32 result = 0; + + intel_sbi_rw(i915, reg, destination, &result, true); + + return result; +} + +void intel_sbi_write(struct drm_i915_private *i915, u16 reg, u32 value, + enum intel_sbi_destination destination) +{ + intel_sbi_rw(i915, reg, destination, &value, false); +} diff --git a/drivers/gpu/drm/i915/intel_sbi.h b/drivers/gpu/drm/i915/intel_sbi.h new file mode 100644 index 000000000000..f5a862210454 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_sbi.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2013-2021 Intel Corporation + */ + +#ifndef _INTEL_SBI_H_ +#define _INTEL_SBI_H_ + +#include + +struct drm_i915_private; + +enum intel_sbi_destination { + SBI_ICLK, + SBI_MPHY, +}; + +u32 intel_sbi_read(struct drm_i915_private *i915, u16 reg, + enum intel_sbi_destination destination); +void intel_sbi_write(struct drm_i915_private *i915, u16 reg, u32 value, + enum intel_sbi_destination destination); + +#endif /* _INTEL_SBI_H_ */ diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c deleted file mode 100644 index e304bf44e1ff..000000000000 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ /dev/null @@ -1,577 +0,0 @@ -/* - * Copyright © 2013 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * - */ - -#include - -#include "i915_drv.h" -#include "intel_sideband.h" - -/* - * IOSF sideband, see VLV2_SidebandMsg_HAS.docx and - * VLV_VLV2_PUNIT_HAS_0.8.docx - */ - -/* Standard MMIO read, non-posted */ -#define SB_MRD_NP 0x00 -/* Standard MMIO write, non-posted */ -#define SB_MWR_NP 0x01 -/* Private register read, double-word addressing, non-posted */ -#define SB_CRRDDA_NP 0x06 -/* Private register write, double-word addressing, non-posted */ -#define SB_CRWRDA_NP 0x07 - -static void ping(void *info) -{ -} - -static void __vlv_punit_get(struct drm_i915_private *i915) -{ - iosf_mbi_punit_acquire(); - - /* - * Prevent the cpu from sleeping while we use this sideband, otherwise - * the punit may cause a machine hang. The issue appears to be isolated - * with changing the power state of the CPU package while changing - * the power state via the punit, and we have only observed it - * reliably on 4-core Baytail systems suggesting the issue is in the - * power delivery mechanism and likely to be be board/function - * specific. Hence we presume the workaround needs only be applied - * to the Valleyview P-unit and not all sideband communications. - */ - if (IS_VALLEYVIEW(i915)) { - cpu_latency_qos_update_request(&i915->sb_qos, 0); - on_each_cpu(ping, NULL, 1); - } -} - -static void __vlv_punit_put(struct drm_i915_private *i915) -{ - if (IS_VALLEYVIEW(i915)) - cpu_latency_qos_update_request(&i915->sb_qos, - PM_QOS_DEFAULT_VALUE); - - iosf_mbi_punit_release(); -} - -void vlv_iosf_sb_get(struct drm_i915_private *i915, unsigned long ports) -{ - if (ports & BIT(VLV_IOSF_SB_PUNIT)) - __vlv_punit_get(i915); - - mutex_lock(&i915->sb_lock); -} - -void vlv_iosf_sb_put(struct drm_i915_private *i915, unsigned long ports) -{ - mutex_unlock(&i915->sb_lock); - - if (ports & BIT(VLV_IOSF_SB_PUNIT)) - __vlv_punit_put(i915); -} - -static int vlv_sideband_rw(struct drm_i915_private *i915, - u32 devfn, u32 port, u32 opcode, - u32 addr, u32 *val) -{ - struct intel_uncore *uncore = &i915->uncore; - const bool is_read = (opcode == SB_MRD_NP || opcode == SB_CRRDDA_NP); - int err; - - lockdep_assert_held(&i915->sb_lock); - if (port == IOSF_PORT_PUNIT) - iosf_mbi_assert_punit_acquired(); - - /* Flush the previous comms, just in case it failed last time. */ - if (intel_wait_for_register(uncore, - VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0, - 5)) { - drm_dbg(&i915->drm, "IOSF sideband idle wait (%s) timed out\n", - is_read ? "read" : "write"); - return -EAGAIN; - } - - preempt_disable(); - - intel_uncore_write_fw(uncore, VLV_IOSF_ADDR, addr); - intel_uncore_write_fw(uncore, VLV_IOSF_DATA, is_read ? 0 : *val); - intel_uncore_write_fw(uncore, VLV_IOSF_DOORBELL_REQ, - (devfn << IOSF_DEVFN_SHIFT) | - (opcode << IOSF_OPCODE_SHIFT) | - (port << IOSF_PORT_SHIFT) | - (0xf << IOSF_BYTE_ENABLES_SHIFT) | - (0 << IOSF_BAR_SHIFT) | - IOSF_SB_BUSY); - - if (__intel_wait_for_register_fw(uncore, - VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0, - 10000, 0, NULL) == 0) { - if (is_read) - *val = intel_uncore_read_fw(uncore, VLV_IOSF_DATA); - err = 0; - } else { - drm_dbg(&i915->drm, "IOSF sideband finish wait (%s) timed out\n", - is_read ? "read" : "write"); - err = -ETIMEDOUT; - } - - preempt_enable(); - - return err; -} - -u32 vlv_punit_read(struct drm_i915_private *i915, u32 addr) -{ - u32 val = 0; - - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT, - SB_CRRDDA_NP, addr, &val); - - return val; -} - -int vlv_punit_write(struct drm_i915_private *i915, u32 addr, u32 val) -{ - return vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT, - SB_CRWRDA_NP, addr, &val); -} - -u32 vlv_bunit_read(struct drm_i915_private *i915, u32 reg) -{ - u32 val = 0; - - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT, - SB_CRRDDA_NP, reg, &val); - - return val; -} - -void vlv_bunit_write(struct drm_i915_private *i915, u32 reg, u32 val) -{ - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT, - SB_CRWRDA_NP, reg, &val); -} - -u32 vlv_nc_read(struct drm_i915_private *i915, u8 addr) -{ - u32 val = 0; - - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_NC, - SB_CRRDDA_NP, addr, &val); - - return val; -} - -u32 vlv_iosf_sb_read(struct drm_i915_private *i915, u8 port, u32 reg) -{ - u32 val = 0; - - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), port, - SB_CRRDDA_NP, reg, &val); - - return val; -} - -void vlv_iosf_sb_write(struct drm_i915_private *i915, - u8 port, u32 reg, u32 val) -{ - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), port, - SB_CRWRDA_NP, reg, &val); -} - -u32 vlv_cck_read(struct drm_i915_private *i915, u32 reg) -{ - u32 val = 0; - - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCK, - SB_CRRDDA_NP, reg, &val); - - return val; -} - -void vlv_cck_write(struct drm_i915_private *i915, u32 reg, u32 val) -{ - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCK, - SB_CRWRDA_NP, reg, &val); -} - -u32 vlv_ccu_read(struct drm_i915_private *i915, u32 reg) -{ - u32 val = 0; - - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCU, - SB_CRRDDA_NP, reg, &val); - - return val; -} - -void vlv_ccu_write(struct drm_i915_private *i915, u32 reg, u32 val) -{ - vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCU, - SB_CRWRDA_NP, reg, &val); -} - -static u32 vlv_dpio_phy_iosf_port(struct drm_i915_private *i915, enum dpio_phy phy) -{ - /* - * IOSF_PORT_DPIO: VLV x2 PHY (DP/HDMI B and C), CHV x1 PHY (DP/HDMI D) - * IOSF_PORT_DPIO_2: CHV x2 PHY (DP/HDMI B and C) - */ - if (IS_CHERRYVIEW(i915)) - return phy == DPIO_PHY0 ? IOSF_PORT_DPIO_2 : IOSF_PORT_DPIO; - else - return IOSF_PORT_DPIO; -} - -u32 vlv_dpio_read(struct drm_i915_private *i915, enum pipe pipe, int reg) -{ - u32 port = vlv_dpio_phy_iosf_port(i915, DPIO_PHY(pipe)); - u32 val = 0; - - vlv_sideband_rw(i915, DPIO_DEVFN, port, SB_MRD_NP, reg, &val); - - /* - * FIXME: There might be some registers where all 1's is a valid value, - * so ideally we should check the register offset instead... - */ - drm_WARN(&i915->drm, val == 0xffffffff, - "DPIO read pipe %c reg 0x%x == 0x%x\n", - pipe_name(pipe), reg, val); - - return val; -} - -void vlv_dpio_write(struct drm_i915_private *i915, - enum pipe pipe, int reg, u32 val) -{ - u32 port = vlv_dpio_phy_iosf_port(i915, DPIO_PHY(pipe)); - - vlv_sideband_rw(i915, DPIO_DEVFN, port, SB_MWR_NP, reg, &val); -} - -u32 vlv_flisdsi_read(struct drm_i915_private *i915, u32 reg) -{ - u32 val = 0; - - vlv_sideband_rw(i915, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRRDDA_NP, - reg, &val); - return val; -} - -void vlv_flisdsi_write(struct drm_i915_private *i915, u32 reg, u32 val) -{ - vlv_sideband_rw(i915, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRWRDA_NP, - reg, &val); -} - -/* SBI access */ -static int intel_sbi_rw(struct drm_i915_private *i915, u16 reg, - enum intel_sbi_destination destination, - u32 *val, bool is_read) -{ - struct intel_uncore *uncore = &i915->uncore; - u32 cmd; - - lockdep_assert_held(&i915->sb_lock); - - if (intel_wait_for_register_fw(uncore, - SBI_CTL_STAT, SBI_BUSY, 0, - 100)) { - drm_err(&i915->drm, - "timeout waiting for SBI to become ready\n"); - return -EBUSY; - } - - intel_uncore_write_fw(uncore, SBI_ADDR, (u32)reg << 16); - intel_uncore_write_fw(uncore, SBI_DATA, is_read ? 0 : *val); - - if (destination == SBI_ICLK) - cmd = SBI_CTL_DEST_ICLK | SBI_CTL_OP_CRRD; - else - cmd = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IORD; - if (!is_read) - cmd |= BIT(8); - intel_uncore_write_fw(uncore, SBI_CTL_STAT, cmd | SBI_BUSY); - - if (__intel_wait_for_register_fw(uncore, - SBI_CTL_STAT, SBI_BUSY, 0, - 100, 100, &cmd)) { - drm_err(&i915->drm, - "timeout waiting for SBI to complete read\n"); - return -ETIMEDOUT; - } - - if (cmd & SBI_RESPONSE_FAIL) { - drm_err(&i915->drm, "error during SBI read of reg %x\n", reg); - return -ENXIO; - } - - if (is_read) - *val = intel_uncore_read_fw(uncore, SBI_DATA); - - return 0; -} - -u32 intel_sbi_read(struct drm_i915_private *i915, u16 reg, - enum intel_sbi_destination destination) -{ - u32 result = 0; - - intel_sbi_rw(i915, reg, destination, &result, true); - - return result; -} - -void intel_sbi_write(struct drm_i915_private *i915, u16 reg, u32 value, - enum intel_sbi_destination destination) -{ - intel_sbi_rw(i915, reg, destination, &value, false); -} - -static int gen6_check_mailbox_status(u32 mbox) -{ - switch (mbox & GEN6_PCODE_ERROR_MASK) { - case GEN6_PCODE_SUCCESS: - return 0; - case GEN6_PCODE_UNIMPLEMENTED_CMD: - return -ENODEV; - case GEN6_PCODE_ILLEGAL_CMD: - return -ENXIO; - case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: - case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: - return -EOVERFLOW; - case GEN6_PCODE_TIMEOUT: - return -ETIMEDOUT; - default: - MISSING_CASE(mbox & GEN6_PCODE_ERROR_MASK); - return 0; - } -} - -static int gen7_check_mailbox_status(u32 mbox) -{ - switch (mbox & GEN6_PCODE_ERROR_MASK) { - case GEN6_PCODE_SUCCESS: - return 0; - case GEN6_PCODE_ILLEGAL_CMD: - return -ENXIO; - case GEN7_PCODE_TIMEOUT: - return -ETIMEDOUT; - case GEN7_PCODE_ILLEGAL_DATA: - return -EINVAL; - case GEN11_PCODE_ILLEGAL_SUBCOMMAND: - return -ENXIO; - case GEN11_PCODE_LOCKED: - return -EBUSY; - case GEN11_PCODE_REJECTED: - return -EACCES; - case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: - return -EOVERFLOW; - default: - MISSING_CASE(mbox & GEN6_PCODE_ERROR_MASK); - return 0; - } -} - -static int __sandybridge_pcode_rw(struct drm_i915_private *i915, - u32 mbox, u32 *val, u32 *val1, - int fast_timeout_us, - int slow_timeout_ms, - bool is_read) -{ - struct intel_uncore *uncore = &i915->uncore; - - lockdep_assert_held(&i915->sb_lock); - - /* - * GEN6_PCODE_* are outside of the forcewake domain, we can use - * intel_uncore_read/write_fw variants to reduce the amount of work - * required when reading/writing. - */ - - if (intel_uncore_read_fw(uncore, GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) - return -EAGAIN; - - intel_uncore_write_fw(uncore, GEN6_PCODE_DATA, *val); - intel_uncore_write_fw(uncore, GEN6_PCODE_DATA1, val1 ? *val1 : 0); - intel_uncore_write_fw(uncore, - GEN6_PCODE_MAILBOX, GEN6_PCODE_READY | mbox); - - if (__intel_wait_for_register_fw(uncore, - GEN6_PCODE_MAILBOX, - GEN6_PCODE_READY, 0, - fast_timeout_us, - slow_timeout_ms, - &mbox)) - return -ETIMEDOUT; - - if (is_read) - *val = intel_uncore_read_fw(uncore, GEN6_PCODE_DATA); - if (is_read && val1) - *val1 = intel_uncore_read_fw(uncore, GEN6_PCODE_DATA1); - - if (GRAPHICS_VER(i915) > 6) - return gen7_check_mailbox_status(mbox); - else - return gen6_check_mailbox_status(mbox); -} - -int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox, - u32 *val, u32 *val1) -{ - int err; - - mutex_lock(&i915->sb_lock); - err = __sandybridge_pcode_rw(i915, mbox, val, val1, - 500, 20, - true); - mutex_unlock(&i915->sb_lock); - - if (err) { - drm_dbg(&i915->drm, - "warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n", - mbox, __builtin_return_address(0), err); - } - - return err; -} - -int sandybridge_pcode_write_timeout(struct drm_i915_private *i915, - u32 mbox, u32 val, - int fast_timeout_us, - int slow_timeout_ms) -{ - int err; - - mutex_lock(&i915->sb_lock); - err = __sandybridge_pcode_rw(i915, mbox, &val, NULL, - fast_timeout_us, slow_timeout_ms, - false); - mutex_unlock(&i915->sb_lock); - - if (err) { - drm_dbg(&i915->drm, - "warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n", - val, mbox, __builtin_return_address(0), err); - } - - return err; -} - -static bool skl_pcode_try_request(struct drm_i915_private *i915, u32 mbox, - u32 request, u32 reply_mask, u32 reply, - u32 *status) -{ - *status = __sandybridge_pcode_rw(i915, mbox, &request, NULL, - 500, 0, - true); - - return *status || ((request & reply_mask) == reply); -} - -/** - * skl_pcode_request - send PCODE request until acknowledgment - * @i915: device private - * @mbox: PCODE mailbox ID the request is targeted for - * @request: request ID - * @reply_mask: mask used to check for request acknowledgment - * @reply: value used to check for request acknowledgment - * @timeout_base_ms: timeout for polling with preemption enabled - * - * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE - * reports an error or an overall timeout of @timeout_base_ms+50 ms expires. - * The request is acknowledged once the PCODE reply dword equals @reply after - * applying @reply_mask. Polling is first attempted with preemption enabled - * for @timeout_base_ms and if this times out for another 50 ms with - * preemption disabled. - * - * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some - * other error as reported by PCODE. - */ -int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request, - u32 reply_mask, u32 reply, int timeout_base_ms) -{ - u32 status; - int ret; - - mutex_lock(&i915->sb_lock); - -#define COND \ - skl_pcode_try_request(i915, mbox, request, reply_mask, reply, &status) - - /* - * Prime the PCODE by doing a request first. Normally it guarantees - * that a subsequent request, at most @timeout_base_ms later, succeeds. - * _wait_for() doesn't guarantee when its passed condition is evaluated - * first, so send the first request explicitly. - */ - if (COND) { - ret = 0; - goto out; - } - ret = _wait_for(COND, timeout_base_ms * 1000, 10, 10); - if (!ret) - goto out; - - /* - * The above can time out if the number of requests was low (2 in the - * worst case) _and_ PCODE was busy for some reason even after a - * (queued) request and @timeout_base_ms delay. As a workaround retry - * the poll with preemption disabled to maximize the number of - * requests. Increase the timeout from @timeout_base_ms to 50ms to - * account for interrupts that could reduce the number of these - * requests, and for any quirks of the PCODE firmware that delays - * the request completion. - */ - drm_dbg_kms(&i915->drm, - "PCODE timeout, retrying with preemption disabled\n"); - drm_WARN_ON_ONCE(&i915->drm, timeout_base_ms > 3); - preempt_disable(); - ret = wait_for_atomic(COND, 50); - preempt_enable(); - -out: - mutex_unlock(&i915->sb_lock); - return ret ? ret : status; -#undef COND -} - -int intel_pcode_init(struct drm_i915_private *i915) -{ - int ret = 0; - - if (!IS_DGFX(i915)) - return ret; - - ret = skl_pcode_request(i915, DG1_PCODE_STATUS, - DG1_UNCORE_GET_INIT_STATUS, - DG1_UNCORE_INIT_STATUS_COMPLETE, - DG1_UNCORE_INIT_STATUS_COMPLETE, 180000); - - drm_dbg(&i915->drm, "PCODE init status %d\n", ret); - - if (ret) - drm_err(&i915->drm, "Pcode did not report uncore initialization completion!\n"); - - return ret; -} diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index f9767054dbdf..e072054adac5 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -36,6 +36,12 @@ #define __raw_posting_read(...) ((void)__raw_uncore_read32(__VA_ARGS__)) +static void +fw_domains_get(struct intel_uncore *uncore, enum forcewake_domains fw_domains) +{ + uncore->fw_get_funcs->force_wake_get(uncore, fw_domains); +} + void intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug) { @@ -248,7 +254,7 @@ fw_domain_put(const struct intel_uncore_forcewake_domain *d) } static void -fw_domains_get(struct intel_uncore *uncore, enum forcewake_domains fw_domains) +fw_domains_get_normal(struct intel_uncore *uncore, enum forcewake_domains fw_domains) { struct intel_uncore_forcewake_domain *d; unsigned int tmp; @@ -340,7 +346,7 @@ static void __gen6_gt_wait_for_thread_c0(struct intel_uncore *uncore) static void fw_domains_get_with_thread_status(struct intel_uncore *uncore, enum forcewake_domains fw_domains) { - fw_domains_get(uncore, fw_domains); + fw_domains_get_normal(uncore, fw_domains); /* WaRsForcewakeWaitTC0:snb,ivb,hsw,bdw,vlv */ __gen6_gt_wait_for_thread_c0(uncore); @@ -396,7 +402,7 @@ intel_uncore_fw_release_timer(struct hrtimer *timer) GEM_BUG_ON(!domain->wake_count); if (--domain->wake_count == 0) - uncore->funcs.force_wake_put(uncore, domain->mask); + fw_domains_put(uncore, domain->mask); spin_unlock_irqrestore(&uncore->lock, irqflags); @@ -454,7 +460,7 @@ intel_uncore_forcewake_reset(struct intel_uncore *uncore) fw = uncore->fw_domains_active; if (fw) - uncore->funcs.force_wake_put(uncore, fw); + fw_domains_put(uncore, fw); fw_domains_reset(uncore, uncore->fw_domains); assert_forcewakes_inactive(uncore); @@ -562,7 +568,7 @@ static void forcewake_early_sanitize(struct intel_uncore *uncore, intel_uncore_forcewake_reset(uncore); if (restore_forcewake) { spin_lock_irq(&uncore->lock); - uncore->funcs.force_wake_get(uncore, restore_forcewake); + fw_domains_get(uncore, restore_forcewake); if (intel_uncore_has_fifo(uncore)) uncore->fifo_count = fifo_free_entries(uncore); @@ -623,7 +629,7 @@ static void __intel_uncore_forcewake_get(struct intel_uncore *uncore, } if (fw_domains) - uncore->funcs.force_wake_get(uncore, fw_domains); + fw_domains_get(uncore, fw_domains); } /** @@ -644,7 +650,7 @@ void intel_uncore_forcewake_get(struct intel_uncore *uncore, { unsigned long irqflags; - if (!uncore->funcs.force_wake_get) + if (!uncore->fw_get_funcs) return; assert_rpm_wakelock_held(uncore->rpm); @@ -711,7 +717,7 @@ void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore, { lockdep_assert_held(&uncore->lock); - if (!uncore->funcs.force_wake_get) + if (!uncore->fw_get_funcs) return; __intel_uncore_forcewake_get(uncore, fw_domains); @@ -733,7 +739,7 @@ static void __intel_uncore_forcewake_put(struct intel_uncore *uncore, continue; } - uncore->funcs.force_wake_put(uncore, domain->mask); + fw_domains_put(uncore, domain->mask); } } @@ -750,7 +756,7 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore, { unsigned long irqflags; - if (!uncore->funcs.force_wake_put) + if (!uncore->fw_get_funcs) return; spin_lock_irqsave(&uncore->lock, irqflags); @@ -769,7 +775,7 @@ void intel_uncore_forcewake_flush(struct intel_uncore *uncore, struct intel_uncore_forcewake_domain *domain; unsigned int tmp; - if (!uncore->funcs.force_wake_put) + if (!uncore->fw_get_funcs) return; fw_domains &= uncore->fw_domains; @@ -793,7 +799,7 @@ void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore, { lockdep_assert_held(&uncore->lock); - if (!uncore->funcs.force_wake_put) + if (!uncore->fw_get_funcs) return; __intel_uncore_forcewake_put(uncore, fw_domains); @@ -801,7 +807,7 @@ void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore, void assert_forcewakes_inactive(struct intel_uncore *uncore) { - if (!uncore->funcs.force_wake_get) + if (!uncore->fw_get_funcs) return; drm_WARN(&uncore->i915->drm, uncore->fw_domains_active, @@ -818,7 +824,7 @@ void assert_forcewakes_active(struct intel_uncore *uncore, if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)) return; - if (!uncore->funcs.force_wake_get) + if (!uncore->fw_get_funcs) return; spin_lock_irq(&uncore->lock); @@ -851,16 +857,9 @@ void assert_forcewakes_active(struct intel_uncore *uncore, } /* We give fast paths for the really cool registers */ -#define NEEDS_FORCE_WAKE(reg) ((reg) < 0x40000) - -#define __gen6_reg_read_fw_domains(uncore, offset) \ -({ \ - enum forcewake_domains __fwd; \ - if (NEEDS_FORCE_WAKE(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else \ - __fwd = 0; \ - __fwd; \ +#define NEEDS_FORCE_WAKE(reg) ({ \ + u32 __reg = (reg); \ + __reg < 0x40000 || __reg >= GEN11_BSD_RING_BASE; \ }) static int fw_range_cmp(u32 offset, const struct intel_forcewake_range *entry) @@ -942,9 +941,6 @@ static const struct intel_forcewake_range __vlv_fw_ranges[] = { __fwd; \ }) -#define __gen11_fwtable_reg_read_fw_domains(uncore, offset) \ - find_fw_domain(uncore, offset) - /* *Must* be sorted by offset! See intel_shadow_table_check(). */ static const struct i915_range gen8_shadowed_regs[] = { { .start = 0x2030, .end = 0x2030 }, @@ -1026,6 +1022,45 @@ static const struct i915_range gen12_shadowed_regs[] = { { .start = 0x1F8510, .end = 0x1F8550 }, }; +static const struct i915_range dg2_shadowed_regs[] = { + { .start = 0x2030, .end = 0x2030 }, + { .start = 0x2510, .end = 0x2550 }, + { .start = 0xA008, .end = 0xA00C }, + { .start = 0xA188, .end = 0xA188 }, + { .start = 0xA278, .end = 0xA278 }, + { .start = 0xA540, .end = 0xA56C }, + { .start = 0xC4C8, .end = 0xC4C8 }, + { .start = 0xC4E0, .end = 0xC4E0 }, + { .start = 0xC600, .end = 0xC600 }, + { .start = 0xC658, .end = 0xC658 }, + { .start = 0x22030, .end = 0x22030 }, + { .start = 0x22510, .end = 0x22550 }, + { .start = 0x1C0030, .end = 0x1C0030 }, + { .start = 0x1C0510, .end = 0x1C0550 }, + { .start = 0x1C4030, .end = 0x1C4030 }, + { .start = 0x1C4510, .end = 0x1C4550 }, + { .start = 0x1C8030, .end = 0x1C8030 }, + { .start = 0x1C8510, .end = 0x1C8550 }, + { .start = 0x1D0030, .end = 0x1D0030 }, + { .start = 0x1D0510, .end = 0x1D0550 }, + { .start = 0x1D4030, .end = 0x1D4030 }, + { .start = 0x1D4510, .end = 0x1D4550 }, + { .start = 0x1D8030, .end = 0x1D8030 }, + { .start = 0x1D8510, .end = 0x1D8550 }, + { .start = 0x1E0030, .end = 0x1E0030 }, + { .start = 0x1E0510, .end = 0x1E0550 }, + { .start = 0x1E4030, .end = 0x1E4030 }, + { .start = 0x1E4510, .end = 0x1E4550 }, + { .start = 0x1E8030, .end = 0x1E8030 }, + { .start = 0x1E8510, .end = 0x1E8550 }, + { .start = 0x1F0030, .end = 0x1F0030 }, + { .start = 0x1F0510, .end = 0x1F0550 }, + { .start = 0x1F4030, .end = 0x1F4030 }, + { .start = 0x1F4510, .end = 0x1F4550 }, + { .start = 0x1F8030, .end = 0x1F8030 }, + { .start = 0x1F8510, .end = 0x1F8550 }, +}; + static int mmio_range_cmp(u32 key, const struct i915_range *range) { if (key < range->start) @@ -1036,17 +1071,16 @@ static int mmio_range_cmp(u32 key, const struct i915_range *range) return 0; } -#define __is_X_shadowed(x) \ -static bool is_##x##_shadowed(u32 offset) \ -{ \ - const struct i915_range *regs = x##_shadowed_regs; \ - return BSEARCH(offset, regs, ARRAY_SIZE(x##_shadowed_regs), \ - mmio_range_cmp); \ -} +static bool is_shadowed(struct intel_uncore *uncore, u32 offset) +{ + if (drm_WARN_ON(&uncore->i915->drm, !uncore->shadowed_reg_table)) + return false; -__is_X_shadowed(gen8) -__is_X_shadowed(gen11) -__is_X_shadowed(gen12) + return BSEARCH(offset, + uncore->shadowed_reg_table, + uncore->shadowed_reg_table_entries, + mmio_range_cmp); +} static enum forcewake_domains gen6_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg) @@ -1054,15 +1088,9 @@ gen6_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg) return FORCEWAKE_RENDER; } -#define __gen8_reg_write_fw_domains(uncore, offset) \ -({ \ - enum forcewake_domains __fwd; \ - if (NEEDS_FORCE_WAKE(offset) && !is_gen8_shadowed(offset)) \ - __fwd = FORCEWAKE_RENDER; \ - else \ - __fwd = 0; \ - __fwd; \ -}) +static const struct intel_forcewake_range __gen6_fw_ranges[] = { + GEN_FW_RANGE(0x0, 0x3ffff, FORCEWAKE_RENDER), +}; /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */ static const struct intel_forcewake_range __chv_fw_ranges[] = { @@ -1085,27 +1113,10 @@ static const struct intel_forcewake_range __chv_fw_ranges[] = { }; #define __fwtable_reg_write_fw_domains(uncore, offset) \ -({ \ - enum forcewake_domains __fwd = 0; \ - if (NEEDS_FORCE_WAKE((offset)) && !is_gen8_shadowed(offset)) \ - __fwd = find_fw_domain(uncore, offset); \ - __fwd; \ -}) - -#define __gen11_fwtable_reg_write_fw_domains(uncore, offset) \ ({ \ enum forcewake_domains __fwd = 0; \ const u32 __offset = (offset); \ - if (!is_gen11_shadowed(__offset)) \ - __fwd = find_fw_domain(uncore, __offset); \ - __fwd; \ -}) - -#define __gen12_fwtable_reg_write_fw_domains(uncore, offset) \ -({ \ - enum forcewake_domains __fwd = 0; \ - const u32 __offset = (offset); \ - if (!is_gen12_shadowed(__offset)) \ + if (NEEDS_FORCE_WAKE((__offset)) && !is_shadowed(uncore, __offset)) \ __fwd = find_fw_domain(uncore, __offset); \ __fwd; \ }) @@ -1582,7 +1593,7 @@ static noinline void ___force_wake_auto(struct intel_uncore *uncore, for_each_fw_domain_masked(domain, fw_domains, uncore, tmp) fw_domain_arm_timer(domain); - uncore->funcs.force_wake_get(uncore, fw_domains); + fw_domains_get(uncore, fw_domains); } static inline void __force_wake_auto(struct intel_uncore *uncore, @@ -1598,34 +1609,30 @@ static inline void __force_wake_auto(struct intel_uncore *uncore, ___force_wake_auto(uncore, fw_domains); } -#define __gen_read(func, x) \ +#define __gen_fwtable_read(x) \ static u##x \ -func##_read##x(struct intel_uncore *uncore, i915_reg_t reg, bool trace) { \ +fwtable_read##x(struct intel_uncore *uncore, i915_reg_t reg, bool trace) \ +{ \ enum forcewake_domains fw_engine; \ GEN6_READ_HEADER(x); \ - fw_engine = __##func##_reg_read_fw_domains(uncore, offset); \ + fw_engine = __fwtable_reg_read_fw_domains(uncore, offset); \ if (fw_engine) \ __force_wake_auto(uncore, fw_engine); \ val = __raw_uncore_read##x(uncore, reg); \ GEN6_READ_FOOTER; \ } -#define __gen_reg_read_funcs(func) \ -static enum forcewake_domains \ -func##_reg_read_fw_domains(struct intel_uncore *uncore, i915_reg_t reg) { \ - return __##func##_reg_read_fw_domains(uncore, i915_mmio_reg_offset(reg)); \ -} \ -\ -__gen_read(func, 8) \ -__gen_read(func, 16) \ -__gen_read(func, 32) \ -__gen_read(func, 64) +static enum forcewake_domains +fwtable_reg_read_fw_domains(struct intel_uncore *uncore, i915_reg_t reg) { + return __fwtable_reg_read_fw_domains(uncore, i915_mmio_reg_offset(reg)); +} -__gen_reg_read_funcs(gen11_fwtable); -__gen_reg_read_funcs(fwtable); -__gen_reg_read_funcs(gen6); +__gen_fwtable_read(8) +__gen_fwtable_read(16) +__gen_fwtable_read(32) +__gen_fwtable_read(64) -#undef __gen_reg_read_funcs +#undef __gen_fwtable_read #undef GEN6_READ_FOOTER #undef GEN6_READ_HEADER @@ -1690,34 +1697,29 @@ __gen6_write(8) __gen6_write(16) __gen6_write(32) -#define __gen_write(func, x) \ +#define __gen_fwtable_write(x) \ static void \ -func##_write##x(struct intel_uncore *uncore, i915_reg_t reg, u##x val, bool trace) { \ +fwtable_write##x(struct intel_uncore *uncore, i915_reg_t reg, u##x val, bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_WRITE_HEADER; \ - fw_engine = __##func##_reg_write_fw_domains(uncore, offset); \ + fw_engine = __fwtable_reg_write_fw_domains(uncore, offset); \ if (fw_engine) \ __force_wake_auto(uncore, fw_engine); \ __raw_uncore_write##x(uncore, reg, val); \ GEN6_WRITE_FOOTER; \ } -#define __gen_reg_write_funcs(func) \ -static enum forcewake_domains \ -func##_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg) { \ - return __##func##_reg_write_fw_domains(uncore, i915_mmio_reg_offset(reg)); \ -} \ -\ -__gen_write(func, 8) \ -__gen_write(func, 16) \ -__gen_write(func, 32) +static enum forcewake_domains +fwtable_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg) +{ + return __fwtable_reg_write_fw_domains(uncore, i915_mmio_reg_offset(reg)); +} -__gen_reg_write_funcs(gen12_fwtable); -__gen_reg_write_funcs(gen11_fwtable); -__gen_reg_write_funcs(fwtable); -__gen_reg_write_funcs(gen8); +__gen_fwtable_write(8) +__gen_fwtable_write(16) +__gen_fwtable_write(32) -#undef __gen_reg_write_funcs +#undef __gen_fwtable_write #undef GEN6_WRITE_FOOTER #undef GEN6_WRITE_HEADER @@ -1841,6 +1843,18 @@ static void intel_uncore_fw_domains_fini(struct intel_uncore *uncore) fw_domain_fini(uncore, d->id); } +static const struct intel_uncore_fw_get uncore_get_fallback = { + .force_wake_get = fw_domains_get_with_fallback +}; + +static const struct intel_uncore_fw_get uncore_get_normal = { + .force_wake_get = fw_domains_get_normal, +}; + +static const struct intel_uncore_fw_get uncore_get_thread_status = { + .force_wake_get = fw_domains_get_with_thread_status +}; + static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) { struct drm_i915_private *i915 = uncore->i915; @@ -1856,8 +1870,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) intel_engine_mask_t emask = INTEL_INFO(i915)->platform_engine_mask; int i; - uncore->funcs.force_wake_get = fw_domains_get_with_fallback; - uncore->funcs.force_wake_put = fw_domains_put; + uncore->fw_get_funcs = &uncore_get_fallback; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, FORCEWAKE_RENDER_GEN9, FORCEWAKE_ACK_RENDER_GEN9); @@ -1882,8 +1895,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(i)); } } else if (IS_GRAPHICS_VER(i915, 9, 10)) { - uncore->funcs.force_wake_get = fw_domains_get_with_fallback; - uncore->funcs.force_wake_put = fw_domains_put; + uncore->fw_get_funcs = &uncore_get_fallback; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, FORCEWAKE_RENDER_GEN9, FORCEWAKE_ACK_RENDER_GEN9); @@ -1893,16 +1905,13 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) fw_domain_init(uncore, FW_DOMAIN_ID_MEDIA, FORCEWAKE_MEDIA_GEN9, FORCEWAKE_ACK_MEDIA_GEN9); } else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { - uncore->funcs.force_wake_get = fw_domains_get; - uncore->funcs.force_wake_put = fw_domains_put; + uncore->fw_get_funcs = &uncore_get_normal; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, FORCEWAKE_VLV, FORCEWAKE_ACK_VLV); fw_domain_init(uncore, FW_DOMAIN_ID_MEDIA, FORCEWAKE_MEDIA_VLV, FORCEWAKE_ACK_MEDIA_VLV); } else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) { - uncore->funcs.force_wake_get = - fw_domains_get_with_thread_status; - uncore->funcs.force_wake_put = fw_domains_put; + uncore->fw_get_funcs = &uncore_get_thread_status; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_ACK_HSW); } else if (IS_IVYBRIDGE(i915)) { @@ -1917,9 +1926,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) * (correctly) interpreted by the test below as MT * forcewake being disabled. */ - uncore->funcs.force_wake_get = - fw_domains_get_with_thread_status; - uncore->funcs.force_wake_put = fw_domains_put; + uncore->fw_get_funcs = &uncore_get_thread_status; /* We need to init first for ECOBUS access and then * determine later if we want to reinit, in case of MT access is @@ -1950,9 +1957,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) FORCEWAKE, FORCEWAKE_ACK); } } else if (GRAPHICS_VER(i915) == 6) { - uncore->funcs.force_wake_get = - fw_domains_get_with_thread_status; - uncore->funcs.force_wake_put = fw_domains_put; + uncore->fw_get_funcs = &uncore_get_thread_status; fw_domain_init(uncore, FW_DOMAIN_ID_RENDER, FORCEWAKE, FORCEWAKE_ACK); } @@ -1976,6 +1981,12 @@ out: (uncore)->fw_domains_table_entries = ARRAY_SIZE((d)); \ } +#define ASSIGN_SHADOW_TABLE(uncore, d) \ +{ \ + (uncore)->shadowed_reg_table = d; \ + (uncore)->shadowed_reg_table_entries = ARRAY_SIZE((d)); \ +} + static int i915_pmic_bus_access_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -2086,40 +2097,42 @@ static int uncore_forcewake_init(struct intel_uncore *uncore) return ret; forcewake_early_sanitize(uncore, 0); + ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable); + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __dg2_fw_ranges); - ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable); - ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable); + ASSIGN_SHADOW_TABLE(uncore, dg2_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); } else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __xehp_fw_ranges); - ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable); - ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable); + ASSIGN_SHADOW_TABLE(uncore, gen12_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); } else if (GRAPHICS_VER(i915) >= 12) { ASSIGN_FW_DOMAINS_TABLE(uncore, __gen12_fw_ranges); - ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable); - ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable); + ASSIGN_SHADOW_TABLE(uncore, gen12_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); } else if (GRAPHICS_VER(i915) == 11) { ASSIGN_FW_DOMAINS_TABLE(uncore, __gen11_fw_ranges); - ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen11_fwtable); - ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable); + ASSIGN_SHADOW_TABLE(uncore, gen11_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); } else if (IS_GRAPHICS_VER(i915, 9, 10)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __gen9_fw_ranges); + ASSIGN_SHADOW_TABLE(uncore, gen8_shadowed_regs); ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); - ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable); } else if (IS_CHERRYVIEW(i915)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __chv_fw_ranges); + ASSIGN_SHADOW_TABLE(uncore, gen8_shadowed_regs); ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); - ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable); } else if (GRAPHICS_VER(i915) == 8) { - ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen8); - ASSIGN_READ_MMIO_VFUNCS(uncore, gen6); + ASSIGN_FW_DOMAINS_TABLE(uncore, __gen6_fw_ranges); + ASSIGN_SHADOW_TABLE(uncore, gen8_shadowed_regs); + ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable); } else if (IS_VALLEYVIEW(i915)) { ASSIGN_FW_DOMAINS_TABLE(uncore, __vlv_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen6); - ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable); } else if (IS_GRAPHICS_VER(i915, 6, 7)) { + ASSIGN_FW_DOMAINS_TABLE(uncore, __gen6_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen6); - ASSIGN_READ_MMIO_VFUNCS(uncore, gen6); } uncore->pmic_bus_access_nb.notifier_call = i915_pmic_bus_access_notifier; @@ -2161,8 +2174,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore) } /* make sure fw funcs are set if and only if we have fw*/ - GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->funcs.force_wake_get); - GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->funcs.force_wake_put); + GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->fw_get_funcs); GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->funcs.read_fw_domains); GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->funcs.write_fw_domains); diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 531665b08039..3248e4e2c540 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -84,12 +84,12 @@ enum forcewake_domains { FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1, }; -struct intel_uncore_funcs { +struct intel_uncore_fw_get { void (*force_wake_get)(struct intel_uncore *uncore, enum forcewake_domains domains); - void (*force_wake_put)(struct intel_uncore *uncore, - enum forcewake_domains domains); +}; +struct intel_uncore_funcs { enum forcewake_domains (*read_fw_domains)(struct intel_uncore *uncore, i915_reg_t r); enum forcewake_domains (*write_fw_domains)(struct intel_uncore *uncore, @@ -142,7 +142,15 @@ struct intel_uncore { const struct intel_forcewake_range *fw_domains_table; unsigned int fw_domains_table_entries; + /* + * Shadowed registers are special cases where we can safely write + * to the register *without* grabbing forcewake. + */ + const struct i915_range *shadowed_reg_table; + unsigned int shadowed_reg_table_entries; + struct notifier_block pmic_bus_access_nb; + const struct intel_uncore_fw_get *fw_get_funcs; struct intel_uncore_funcs funcs; unsigned int fifo_count; diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h index 545c8f277c46..4f4c2e15e736 100644 --- a/drivers/gpu/drm/i915/intel_wakeref.h +++ b/drivers/gpu/drm/i915/intel_wakeref.h @@ -123,6 +123,12 @@ enum { __INTEL_WAKEREF_PUT_LAST_BIT__ }; +static inline void +intel_wakeref_might_get(struct intel_wakeref *wf) +{ + might_lock(&wf->mutex); +} + /** * intel_wakeref_put_flags: Release the wakeref * @wf: the wakeref @@ -170,6 +176,12 @@ intel_wakeref_put_delay(struct intel_wakeref *wf, unsigned long delay) FIELD_PREP(INTEL_WAKEREF_PUT_DELAY, delay)); } +static inline void +intel_wakeref_might_put(struct intel_wakeref *wf) +{ + might_lock(&wf->mutex); +} + /** * intel_wakeref_lock: Lock the wakeref (mutex) * @wf: the wakeref diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c new file mode 100644 index 000000000000..e2314ad9546d --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -0,0 +1,299 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020 Intel Corporation. + */ +#include +#include "intel_pxp.h" +#include "intel_pxp_irq.h" +#include "intel_pxp_session.h" +#include "intel_pxp_tee.h" +#include "gem/i915_gem_context.h" +#include "gt/intel_context.h" +#include "i915_drv.h" + +/** + * DOC: PXP + * + * PXP (Protected Xe Path) is a feature available in Gen12 and newer platforms. + * It allows execution and flip to display of protected (i.e. encrypted) + * objects. The SW support is enabled via the CONFIG_DRM_I915_PXP kconfig. + * + * Objects can opt-in to PXP encryption at creation time via the + * I915_GEM_CREATE_EXT_PROTECTED_CONTENT create_ext flag. For objects to be + * correctly protected they must be used in conjunction with a context created + * with the I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. See the documentation + * of those two uapi flags for details and restrictions. + * + * Protected objects are tied to a pxp session; currently we only support one + * session, which i915 manages and whose index is available in the uapi + * (I915_PROTECTED_CONTENT_DEFAULT_SESSION) for use in instructions targeting + * protected objects. + * The session is invalidated by the HW when certain events occur (e.g. + * suspend/resume). When this happens, all the objects that were used with the + * session are marked as invalid and all contexts marked as using protected + * content are banned. Any further attempt at using them in an execbuf call is + * rejected, while flips are converted to black frames. + * + * Some of the PXP setup operations are performed by the Management Engine, + * which is handled by the mei driver; communication between i915 and mei is + * performed via the mei_pxp component module. + */ + +struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp) +{ + return container_of(pxp, struct intel_gt, pxp); +} + +bool intel_pxp_is_active(const struct intel_pxp *pxp) +{ + return pxp->arb_is_valid; +} + +/* KCR register definitions */ +#define KCR_INIT _MMIO(0x320f0) +/* Setting KCR Init bit is required after system boot */ +#define KCR_INIT_ALLOW_DISPLAY_ME_WRITES REG_BIT(14) + +static void kcr_pxp_enable(struct intel_gt *gt) +{ + intel_uncore_write(gt->uncore, KCR_INIT, + _MASKED_BIT_ENABLE(KCR_INIT_ALLOW_DISPLAY_ME_WRITES)); +} + +static void kcr_pxp_disable(struct intel_gt *gt) +{ + intel_uncore_write(gt->uncore, KCR_INIT, + _MASKED_BIT_DISABLE(KCR_INIT_ALLOW_DISPLAY_ME_WRITES)); +} + +static int create_vcs_context(struct intel_pxp *pxp) +{ + static struct lock_class_key pxp_lock; + struct intel_gt *gt = pxp_to_gt(pxp); + struct intel_engine_cs *engine; + struct intel_context *ce; + int i; + + /* + * Find the first VCS engine present. We're guaranteed there is one + * if we're in this function due to the check in has_pxp + */ + for (i = 0, engine = NULL; !engine; i++) + engine = gt->engine_class[VIDEO_DECODE_CLASS][i]; + + GEM_BUG_ON(!engine || engine->class != VIDEO_DECODE_CLASS); + + ce = intel_engine_create_pinned_context(engine, engine->gt->vm, SZ_4K, + I915_GEM_HWS_PXP_ADDR, + &pxp_lock, "pxp_context"); + if (IS_ERR(ce)) { + drm_err(>->i915->drm, "failed to create VCS ctx for PXP\n"); + return PTR_ERR(ce); + } + + pxp->ce = ce; + + return 0; +} + +static void destroy_vcs_context(struct intel_pxp *pxp) +{ + intel_engine_destroy_pinned_context(fetch_and_zero(&pxp->ce)); +} + +void intel_pxp_init(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + int ret; + + if (!HAS_PXP(gt->i915)) + return; + + mutex_init(&pxp->tee_mutex); + + /* + * we'll use the completion to check if there is a termination pending, + * so we start it as completed and we reinit it when a termination + * is triggered. + */ + init_completion(&pxp->termination); + complete_all(&pxp->termination); + + mutex_init(&pxp->arb_mutex); + INIT_WORK(&pxp->session_work, intel_pxp_session_work); + + ret = create_vcs_context(pxp); + if (ret) + return; + + ret = intel_pxp_tee_component_init(pxp); + if (ret) + goto out_context; + + drm_info(>->i915->drm, "Protected Xe Path (PXP) protected content support initialized\n"); + + return; + +out_context: + destroy_vcs_context(pxp); +} + +void intel_pxp_fini(struct intel_pxp *pxp) +{ + if (!intel_pxp_is_enabled(pxp)) + return; + + pxp->arb_is_valid = false; + + intel_pxp_tee_component_fini(pxp); + + destroy_vcs_context(pxp); +} + +void intel_pxp_mark_termination_in_progress(struct intel_pxp *pxp) +{ + pxp->arb_is_valid = false; + reinit_completion(&pxp->termination); +} + +static void pxp_queue_termination(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + + /* + * We want to get the same effect as if we received a termination + * interrupt, so just pretend that we did. + */ + spin_lock_irq(>->irq_lock); + intel_pxp_mark_termination_in_progress(pxp); + pxp->session_events |= PXP_TERMINATION_REQUEST; + queue_work(system_unbound_wq, &pxp->session_work); + spin_unlock_irq(>->irq_lock); +} + +/* + * the arb session is restarted from the irq work when we receive the + * termination completion interrupt + */ +int intel_pxp_start(struct intel_pxp *pxp) +{ + int ret = 0; + + if (!intel_pxp_is_enabled(pxp)) + return -ENODEV; + + mutex_lock(&pxp->arb_mutex); + + if (pxp->arb_is_valid) + goto unlock; + + pxp_queue_termination(pxp); + + if (!wait_for_completion_timeout(&pxp->termination, + msecs_to_jiffies(250))) { + ret = -ETIMEDOUT; + goto unlock; + } + + /* make sure the compiler doesn't optimize the double access */ + barrier(); + + if (!pxp->arb_is_valid) + ret = -EIO; + +unlock: + mutex_unlock(&pxp->arb_mutex); + return ret; +} + +void intel_pxp_init_hw(struct intel_pxp *pxp) +{ + kcr_pxp_enable(pxp_to_gt(pxp)); + intel_pxp_irq_enable(pxp); +} + +void intel_pxp_fini_hw(struct intel_pxp *pxp) +{ + kcr_pxp_disable(pxp_to_gt(pxp)); + + intel_pxp_irq_disable(pxp); +} + +int intel_pxp_key_check(struct intel_pxp *pxp, + struct drm_i915_gem_object *obj, + bool assign) +{ + if (!intel_pxp_is_active(pxp)) + return -ENODEV; + + if (!i915_gem_object_is_protected(obj)) + return -EINVAL; + + GEM_BUG_ON(!pxp->key_instance); + + /* + * If this is the first time we're using this object, it's not + * encrypted yet; it will be encrypted with the current key, so mark it + * as such. If the object is already encrypted, check instead if the + * used key is still valid. + */ + if (!obj->pxp_key_instance && assign) + obj->pxp_key_instance = pxp->key_instance; + + if (obj->pxp_key_instance != pxp->key_instance) + return -ENOEXEC; + + return 0; +} + +void intel_pxp_invalidate(struct intel_pxp *pxp) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_gem_context *ctx, *cn; + + /* ban all contexts marked as protected */ + spin_lock_irq(&i915->gem.contexts.lock); + list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) { + struct i915_gem_engines_iter it; + struct intel_context *ce; + + if (!kref_get_unless_zero(&ctx->ref)) + continue; + + if (likely(!i915_gem_context_uses_protected_content(ctx))) { + i915_gem_context_put(ctx); + continue; + } + + spin_unlock_irq(&i915->gem.contexts.lock); + + /* + * By the time we get here we are either going to suspend with + * quiesced execution or the HW keys are already long gone and + * in this case it is worthless to attempt to close the context + * and wait for its execution. It will hang the GPU if it has + * not already. So, as a fast mitigation, we can ban the + * context as quick as we can. That might race with the + * execbuffer, but currently this is the best that can be done. + */ + for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) + intel_context_ban(ce, NULL); + i915_gem_context_unlock_engines(ctx); + + /* + * The context has been banned, no need to keep the wakeref. + * This is safe from races because the only other place this + * is touched is context_release and we're holding a ctx ref + */ + if (ctx->pxp_wakeref) { + intel_runtime_pm_put(&i915->runtime_pm, + ctx->pxp_wakeref); + ctx->pxp_wakeref = 0; + } + + spin_lock_irq(&i915->gem.contexts.lock); + list_safe_reset_next(ctx, cn, link); + i915_gem_context_put(ctx); + } + spin_unlock_irq(&i915->gem.contexts.lock); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.h b/drivers/gpu/drm/i915/pxp/intel_pxp.h new file mode 100644 index 000000000000..aa262258d4d4 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_H__ +#define __INTEL_PXP_H__ + +#include "intel_pxp_types.h" + +struct drm_i915_gem_object; + +static inline bool intel_pxp_is_enabled(const struct intel_pxp *pxp) +{ + return pxp->ce; +} + +#ifdef CONFIG_DRM_I915_PXP +struct intel_gt *pxp_to_gt(const struct intel_pxp *pxp); +bool intel_pxp_is_active(const struct intel_pxp *pxp); + +void intel_pxp_init(struct intel_pxp *pxp); +void intel_pxp_fini(struct intel_pxp *pxp); + +void intel_pxp_init_hw(struct intel_pxp *pxp); +void intel_pxp_fini_hw(struct intel_pxp *pxp); + +void intel_pxp_mark_termination_in_progress(struct intel_pxp *pxp); + +int intel_pxp_start(struct intel_pxp *pxp); + +int intel_pxp_key_check(struct intel_pxp *pxp, + struct drm_i915_gem_object *obj, + bool assign); + +void intel_pxp_invalidate(struct intel_pxp *pxp); +#else +static inline void intel_pxp_init(struct intel_pxp *pxp) +{ +} + +static inline void intel_pxp_fini(struct intel_pxp *pxp) +{ +} + +static inline int intel_pxp_start(struct intel_pxp *pxp) +{ + return -ENODEV; +} + +static inline bool intel_pxp_is_active(const struct intel_pxp *pxp) +{ + return false; +} + +static inline int intel_pxp_key_check(struct intel_pxp *pxp, + struct drm_i915_gem_object *obj, + bool assign) +{ + return -ENODEV; +} +#endif + +#endif /* __INTEL_PXP_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd.c b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd.c new file mode 100644 index 000000000000..f41e45763d0d --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#include "intel_pxp.h" +#include "intel_pxp_cmd.h" +#include "intel_pxp_session.h" +#include "gt/intel_context.h" +#include "gt/intel_engine_pm.h" +#include "gt/intel_gpu_commands.h" +#include "gt/intel_ring.h" + +#include "i915_trace.h" + +/* stall until prior PXP and MFX/HCP/HUC objects are cmopleted */ +#define MFX_WAIT_PXP (MFX_WAIT | \ + MFX_WAIT_DW0_PXP_SYNC_CONTROL_FLAG | \ + MFX_WAIT_DW0_MFX_SYNC_CONTROL_FLAG) + +static u32 *pxp_emit_session_selection(u32 *cs, u32 idx) +{ + *cs++ = MFX_WAIT_PXP; + + /* pxp off */ + *cs++ = MI_FLUSH_DW; + *cs++ = 0; + *cs++ = 0; + + /* select session */ + *cs++ = MI_SET_APPID | MI_SET_APPID_SESSION_ID(idx); + + *cs++ = MFX_WAIT_PXP; + + /* pxp on */ + *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_PROTECTED_MEM_EN | + MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX; + *cs++ = I915_GEM_HWS_PXP_ADDR | MI_FLUSH_DW_USE_GTT; + *cs++ = 0; + + *cs++ = MFX_WAIT_PXP; + + return cs; +} + +static u32 *pxp_emit_inline_termination(u32 *cs) +{ + /* session inline termination */ + *cs++ = CRYPTO_KEY_EXCHANGE; + *cs++ = 0; + + return cs; +} + +static u32 *pxp_emit_session_termination(u32 *cs, u32 idx) +{ + cs = pxp_emit_session_selection(cs, idx); + cs = pxp_emit_inline_termination(cs); + + return cs; +} + +static u32 *pxp_emit_wait(u32 *cs) +{ + /* wait for cmds to go through */ + *cs++ = MFX_WAIT_PXP; + *cs++ = 0; + + return cs; +} + +/* + * if we ever need to terminate more than one session, we can submit multiple + * selections and terminations back-to-back with a single wait at the end + */ +#define SELECTION_LEN 10 +#define TERMINATION_LEN 2 +#define SESSION_TERMINATION_LEN(x) ((SELECTION_LEN + TERMINATION_LEN) * (x)) +#define WAIT_LEN 2 + +static void pxp_request_commit(struct i915_request *rq) +{ + struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX }; + struct intel_timeline * const tl = i915_request_timeline(rq); + + lockdep_unpin_lock(&tl->mutex, rq->cookie); + + trace_i915_request_add(rq); + __i915_request_commit(rq); + __i915_request_queue(rq, &attr); + + mutex_unlock(&tl->mutex); +} + +int intel_pxp_terminate_session(struct intel_pxp *pxp, u32 id) +{ + struct i915_request *rq; + struct intel_context *ce = pxp->ce; + u32 *cs; + int err = 0; + + if (!intel_pxp_is_enabled(pxp)) + return 0; + + rq = i915_request_create(ce); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + if (ce->engine->emit_init_breadcrumb) { + err = ce->engine->emit_init_breadcrumb(rq); + if (err) + goto out_rq; + } + + cs = intel_ring_begin(rq, SESSION_TERMINATION_LEN(1) + WAIT_LEN); + if (IS_ERR(cs)) { + err = PTR_ERR(cs); + goto out_rq; + } + + cs = pxp_emit_session_termination(cs, id); + cs = pxp_emit_wait(cs); + + intel_ring_advance(rq, cs); + +out_rq: + i915_request_get(rq); + + if (unlikely(err)) + i915_request_set_error_once(rq, err); + + pxp_request_commit(rq); + + if (!err && i915_request_wait(rq, 0, HZ / 5) < 0) + err = -ETIME; + + i915_request_put(rq); + + return err; +} + diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd.h new file mode 100644 index 000000000000..6d6299543578 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_CMD_H__ +#define __INTEL_PXP_CMD_H__ + +#include + +struct intel_pxp; + +int intel_pxp_terminate_session(struct intel_pxp *pxp, u32 idx); + +#endif /* __INTEL_PXP_CMD_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c new file mode 100644 index 000000000000..10e1e45471f1 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include +#include + +#include "gt/intel_gt_debugfs.h" +#include "pxp/intel_pxp.h" +#include "pxp/intel_pxp_irq.h" +#include "i915_drv.h" + +static int pxp_info_show(struct seq_file *m, void *data) +{ + struct intel_pxp *pxp = m->private; + struct drm_printer p = drm_seq_file_printer(m); + bool enabled = intel_pxp_is_enabled(pxp); + + if (!enabled) { + drm_printf(&p, "pxp disabled\n"); + return 0; + } + + drm_printf(&p, "active: %s\n", yesno(intel_pxp_is_active(pxp))); + drm_printf(&p, "instance counter: %u\n", pxp->key_instance); + + return 0; +} +DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(pxp_info); + +static int pxp_terminate_get(void *data, u64 *val) +{ + /* nothing to read */ + return -EPERM; +} + +static int pxp_terminate_set(void *data, u64 val) +{ + struct intel_pxp *pxp = data; + struct intel_gt *gt = pxp_to_gt(pxp); + + if (!intel_pxp_is_active(pxp)) + return -ENODEV; + + /* simulate a termination interrupt */ + spin_lock_irq(>->irq_lock); + intel_pxp_irq_handler(pxp, GEN12_DISPLAY_PXP_STATE_TERMINATED_INTERRUPT); + spin_unlock_irq(>->irq_lock); + + if (!wait_for_completion_timeout(&pxp->termination, + msecs_to_jiffies(100))) + return -ETIMEDOUT; + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(pxp_terminate_fops, pxp_terminate_get, pxp_terminate_set, "%llx\n"); +void intel_pxp_debugfs_register(struct intel_pxp *pxp, struct dentry *gt_root) +{ + static const struct intel_gt_debugfs_file files[] = { + { "info", &pxp_info_fops, NULL }, + { "terminate_state", &pxp_terminate_fops, NULL }, + }; + struct dentry *root; + + if (!gt_root) + return; + + if (!HAS_PXP((pxp_to_gt(pxp)->i915))) + return; + + root = debugfs_create_dir("pxp", gt_root); + if (IS_ERR(root)) + return; + + intel_gt_debugfs_register_files(root, files, ARRAY_SIZE(files), pxp); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.h new file mode 100644 index 000000000000..7e0c3d2f5d7e --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __INTEL_PXP_DEBUGFS_H__ +#define __INTEL_PXP_DEBUGFS_H__ + +struct intel_pxp; +struct dentry; + +#ifdef CONFIG_DRM_I915_PXP +void intel_pxp_debugfs_register(struct intel_pxp *pxp, struct dentry *root); +#else +static inline void +intel_pxp_debugfs_register(struct intel_pxp *pxp, struct dentry *root) +{ +} +#endif + +#endif /* __INTEL_PXP_DEBUGFS_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c new file mode 100644 index 000000000000..8d5553772ded --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020 Intel Corporation. + */ +#include +#include "intel_pxp.h" +#include "intel_pxp_irq.h" +#include "intel_pxp_session.h" +#include "gt/intel_gt_irq.h" +#include "gt/intel_gt_types.h" +#include "i915_irq.h" +#include "i915_reg.h" +#include "intel_runtime_pm.h" + +/** + * intel_pxp_irq_handler - Handles PXP interrupts. + * @pxp: pointer to pxp struct + * @iir: interrupt vector + */ +void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + + if (GEM_WARN_ON(!intel_pxp_is_enabled(pxp))) + return; + + lockdep_assert_held(>->irq_lock); + + if (unlikely(!iir)) + return; + + if (iir & (GEN12_DISPLAY_PXP_STATE_TERMINATED_INTERRUPT | + GEN12_DISPLAY_APP_TERMINATED_PER_FW_REQ_INTERRUPT)) { + /* immediately mark PXP as inactive on termination */ + intel_pxp_mark_termination_in_progress(pxp); + pxp->session_events |= PXP_TERMINATION_REQUEST | PXP_INVAL_REQUIRED; + } + + if (iir & GEN12_DISPLAY_STATE_RESET_COMPLETE_INTERRUPT) + pxp->session_events |= PXP_TERMINATION_COMPLETE; + + if (pxp->session_events) + queue_work(system_unbound_wq, &pxp->session_work); +} + +static inline void __pxp_set_interrupts(struct intel_gt *gt, u32 interrupts) +{ + struct intel_uncore *uncore = gt->uncore; + const u32 mask = interrupts << 16; + + intel_uncore_write(uncore, GEN11_CRYPTO_RSVD_INTR_ENABLE, mask); + intel_uncore_write(uncore, GEN11_CRYPTO_RSVD_INTR_MASK, ~mask); +} + +static inline void pxp_irq_reset(struct intel_gt *gt) +{ + spin_lock_irq(>->irq_lock); + gen11_gt_reset_one_iir(gt, 0, GEN11_KCR); + spin_unlock_irq(>->irq_lock); +} + +void intel_pxp_irq_enable(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + + spin_lock_irq(>->irq_lock); + + if (!pxp->irq_enabled) + WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_KCR)); + + __pxp_set_interrupts(gt, GEN12_PXP_INTERRUPTS); + pxp->irq_enabled = true; + + spin_unlock_irq(>->irq_lock); +} + +void intel_pxp_irq_disable(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + + /* + * We always need to submit a global termination when we re-enable the + * interrupts, so there is no need to make sure that the session state + * makes sense at the end of this function. Just make sure this is not + * called in a path were the driver consider the session as valid and + * doesn't call a termination on restart. + */ + GEM_WARN_ON(intel_pxp_is_active(pxp)); + + spin_lock_irq(>->irq_lock); + + pxp->irq_enabled = false; + __pxp_set_interrupts(gt, 0); + + spin_unlock_irq(>->irq_lock); + intel_synchronize_irq(gt->i915); + + pxp_irq_reset(gt); + + flush_work(&pxp->session_work); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h new file mode 100644 index 000000000000..8b5793654844 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_IRQ_H__ +#define __INTEL_PXP_IRQ_H__ + +#include + +struct intel_pxp; + +#define GEN12_DISPLAY_PXP_STATE_TERMINATED_INTERRUPT BIT(1) +#define GEN12_DISPLAY_APP_TERMINATED_PER_FW_REQ_INTERRUPT BIT(2) +#define GEN12_DISPLAY_STATE_RESET_COMPLETE_INTERRUPT BIT(3) + +#define GEN12_PXP_INTERRUPTS \ + (GEN12_DISPLAY_PXP_STATE_TERMINATED_INTERRUPT | \ + GEN12_DISPLAY_APP_TERMINATED_PER_FW_REQ_INTERRUPT | \ + GEN12_DISPLAY_STATE_RESET_COMPLETE_INTERRUPT) + +#ifdef CONFIG_DRM_I915_PXP +void intel_pxp_irq_enable(struct intel_pxp *pxp); +void intel_pxp_irq_disable(struct intel_pxp *pxp); +void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir); +#else +static inline void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir) +{ +} +#endif + +#endif /* __INTEL_PXP_IRQ_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c new file mode 100644 index 000000000000..23fd86de5a24 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020 Intel Corporation. + */ + +#include "intel_pxp.h" +#include "intel_pxp_irq.h" +#include "intel_pxp_pm.h" +#include "intel_pxp_session.h" + +void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime) +{ + if (!intel_pxp_is_enabled(pxp)) + return; + + pxp->arb_is_valid = false; + + /* + * Contexts using protected objects keep a runtime PM reference, so we + * can only runtime suspend when all of them have been either closed + * or banned. Therefore, there is no need to invalidate in that + * scenario. + */ + if (!runtime) + intel_pxp_invalidate(pxp); + + intel_pxp_fini_hw(pxp); + + pxp->hw_state_invalidated = false; +} + +void intel_pxp_resume(struct intel_pxp *pxp) +{ + if (!intel_pxp_is_enabled(pxp)) + return; + + /* + * The PXP component gets automatically unbound when we go into S3 and + * re-bound after we come out, so in that scenario we can defer the + * hw init to the bind call. + */ + if (!pxp->pxp_component) + return; + + intel_pxp_init_hw(pxp); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h new file mode 100644 index 000000000000..c89e97a0c3d0 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_PM_H__ +#define __INTEL_PXP_PM_H__ + +#include "intel_pxp_types.h" + +#ifdef CONFIG_DRM_I915_PXP +void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime); +void intel_pxp_resume(struct intel_pxp *pxp); +#else +static inline void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime) +{ +} + +static inline void intel_pxp_resume(struct intel_pxp *pxp) +{ +} +#endif + +#endif /* __INTEL_PXP_PM_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c new file mode 100644 index 000000000000..d02732f04757 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#include "drm/i915_drm.h" +#include "i915_drv.h" + +#include "intel_pxp.h" +#include "intel_pxp_cmd.h" +#include "intel_pxp_session.h" +#include "intel_pxp_tee.h" +#include "intel_pxp_types.h" + +#define ARB_SESSION I915_PROTECTED_CONTENT_DEFAULT_SESSION /* shorter define */ + +#define GEN12_KCR_SIP _MMIO(0x32260) /* KCR hwdrm session in play 0-31 */ + +/* PXP global terminate register for session termination */ +#define PXP_GLOBAL_TERMINATE _MMIO(0x320f8) + +static bool intel_pxp_session_is_in_play(struct intel_pxp *pxp, u32 id) +{ + struct intel_uncore *uncore = pxp_to_gt(pxp)->uncore; + intel_wakeref_t wakeref; + u32 sip = 0; + + /* if we're suspended the session is considered off */ + with_intel_runtime_pm_if_in_use(uncore->rpm, wakeref) + sip = intel_uncore_read(uncore, GEN12_KCR_SIP); + + return sip & BIT(id); +} + +static int pxp_wait_for_session_state(struct intel_pxp *pxp, u32 id, bool in_play) +{ + struct intel_uncore *uncore = pxp_to_gt(pxp)->uncore; + intel_wakeref_t wakeref; + u32 mask = BIT(id); + int ret; + + /* if we're suspended the session is considered off */ + wakeref = intel_runtime_pm_get_if_in_use(uncore->rpm); + if (!wakeref) + return in_play ? -ENODEV : 0; + + ret = intel_wait_for_register(uncore, + GEN12_KCR_SIP, + mask, + in_play ? mask : 0, + 100); + + intel_runtime_pm_put(uncore->rpm, wakeref); + + return ret; +} + +static int pxp_create_arb_session(struct intel_pxp *pxp) +{ + struct intel_gt *gt = pxp_to_gt(pxp); + int ret; + + pxp->arb_is_valid = false; + + if (intel_pxp_session_is_in_play(pxp, ARB_SESSION)) { + drm_err(>->i915->drm, "arb session already in play at creation time\n"); + return -EEXIST; + } + + ret = intel_pxp_tee_cmd_create_arb_session(pxp, ARB_SESSION); + if (ret) { + drm_err(>->i915->drm, "tee cmd for arb session creation failed\n"); + return ret; + } + + ret = pxp_wait_for_session_state(pxp, ARB_SESSION, true); + if (ret) { + drm_err(>->i915->drm, "arb session failed to go in play\n"); + return ret; + } + + if (!++pxp->key_instance) + ++pxp->key_instance; + + pxp->arb_is_valid = true; + + return 0; +} + +static int pxp_terminate_arb_session_and_global(struct intel_pxp *pxp) +{ + int ret; + struct intel_gt *gt = pxp_to_gt(pxp); + + /* must mark termination in progress calling this function */ + GEM_WARN_ON(pxp->arb_is_valid); + + /* terminate the hw sessions */ + ret = intel_pxp_terminate_session(pxp, ARB_SESSION); + if (ret) { + drm_err(>->i915->drm, "Failed to submit session termination\n"); + return ret; + } + + ret = pxp_wait_for_session_state(pxp, ARB_SESSION, false); + if (ret) { + drm_err(>->i915->drm, "Session state did not clear\n"); + return ret; + } + + intel_uncore_write(gt->uncore, PXP_GLOBAL_TERMINATE, 1); + + return ret; +} + +static void pxp_terminate(struct intel_pxp *pxp) +{ + int ret; + + pxp->hw_state_invalidated = true; + + /* + * if we fail to submit the termination there is no point in waiting for + * it to complete. PXP will be marked as non-active until the next + * termination is issued. + */ + ret = pxp_terminate_arb_session_and_global(pxp); + if (ret) + complete_all(&pxp->termination); +} + +static void pxp_terminate_complete(struct intel_pxp *pxp) +{ + /* Re-create the arb session after teardown handle complete */ + if (fetch_and_zero(&pxp->hw_state_invalidated)) + pxp_create_arb_session(pxp); + + complete_all(&pxp->termination); +} + +void intel_pxp_session_work(struct work_struct *work) +{ + struct intel_pxp *pxp = container_of(work, typeof(*pxp), session_work); + struct intel_gt *gt = pxp_to_gt(pxp); + intel_wakeref_t wakeref; + u32 events = 0; + + spin_lock_irq(>->irq_lock); + events = fetch_and_zero(&pxp->session_events); + spin_unlock_irq(>->irq_lock); + + if (!events) + return; + + if (events & PXP_INVAL_REQUIRED) + intel_pxp_invalidate(pxp); + + /* + * If we're processing an event while suspending then don't bother, + * we're going to re-init everything on resume anyway. + */ + wakeref = intel_runtime_pm_get_if_in_use(gt->uncore->rpm); + if (!wakeref) + return; + + if (events & PXP_TERMINATION_REQUEST) { + events &= ~PXP_TERMINATION_COMPLETE; + pxp_terminate(pxp); + } + + if (events & PXP_TERMINATION_COMPLETE) + pxp_terminate_complete(pxp); + + intel_runtime_pm_put(gt->uncore->rpm, wakeref); +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.h b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h new file mode 100644 index 000000000000..ba4c9d2b94b7 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_SESSION_H__ +#define __INTEL_PXP_SESSION_H__ + +#include + +struct work_struct; + +void intel_pxp_session_work(struct work_struct *work); + +#endif /* __INTEL_PXP_SESSION_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c new file mode 100644 index 000000000000..49508f31dcb7 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright(c) 2020 Intel Corporation. + */ + +#include +#include "drm/i915_pxp_tee_interface.h" +#include "drm/i915_component.h" +#include "i915_drv.h" +#include "intel_pxp.h" +#include "intel_pxp_session.h" +#include "intel_pxp_tee.h" +#include "intel_pxp_tee_interface.h" + +static inline struct intel_pxp *i915_dev_to_pxp(struct device *i915_kdev) +{ + return &kdev_to_i915(i915_kdev)->gt.pxp; +} + +static int intel_pxp_tee_io_message(struct intel_pxp *pxp, + void *msg_in, u32 msg_in_size, + void *msg_out, u32 msg_out_max_size, + u32 *msg_out_rcv_size) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct i915_pxp_component *pxp_component = pxp->pxp_component; + int ret = 0; + + mutex_lock(&pxp->tee_mutex); + + /* + * The binding of the component is asynchronous from i915 probe, so we + * can't be sure it has happened. + */ + if (!pxp_component) { + ret = -ENODEV; + goto unlock; + } + + ret = pxp_component->ops->send(pxp_component->tee_dev, msg_in, msg_in_size); + if (ret) { + drm_err(&i915->drm, "Failed to send PXP TEE message\n"); + goto unlock; + } + + ret = pxp_component->ops->recv(pxp_component->tee_dev, msg_out, msg_out_max_size); + if (ret < 0) { + drm_err(&i915->drm, "Failed to receive PXP TEE message\n"); + goto unlock; + } + + if (ret > msg_out_max_size) { + drm_err(&i915->drm, + "Failed to receive PXP TEE message due to unexpected output size\n"); + ret = -ENOSPC; + goto unlock; + } + + if (msg_out_rcv_size) + *msg_out_rcv_size = ret; + + ret = 0; +unlock: + mutex_unlock(&pxp->tee_mutex); + return ret; +} + +/** + * i915_pxp_tee_component_bind - bind function to pass the function pointers to pxp_tee + * @i915_kdev: pointer to i915 kernel device + * @tee_kdev: pointer to tee kernel device + * @data: pointer to pxp_tee_master containing the function pointers + * + * This bind function is called during the system boot or resume from system sleep. + * + * Return: return 0 if successful. + */ +static int i915_pxp_tee_component_bind(struct device *i915_kdev, + struct device *tee_kdev, void *data) +{ + struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); + struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev); + intel_wakeref_t wakeref; + + mutex_lock(&pxp->tee_mutex); + pxp->pxp_component = data; + pxp->pxp_component->tee_dev = tee_kdev; + mutex_unlock(&pxp->tee_mutex); + + /* if we are suspended, the HW will be re-initialized on resume */ + wakeref = intel_runtime_pm_get_if_in_use(&i915->runtime_pm); + if (!wakeref) + return 0; + + /* the component is required to fully start the PXP HW */ + intel_pxp_init_hw(pxp); + + intel_runtime_pm_put(&i915->runtime_pm, wakeref); + + return 0; +} + +static void i915_pxp_tee_component_unbind(struct device *i915_kdev, + struct device *tee_kdev, void *data) +{ + struct intel_pxp *pxp = i915_dev_to_pxp(i915_kdev); + + intel_pxp_fini_hw(pxp); + + mutex_lock(&pxp->tee_mutex); + pxp->pxp_component = NULL; + mutex_unlock(&pxp->tee_mutex); +} + +static const struct component_ops i915_pxp_tee_component_ops = { + .bind = i915_pxp_tee_component_bind, + .unbind = i915_pxp_tee_component_unbind, +}; + +int intel_pxp_tee_component_init(struct intel_pxp *pxp) +{ + int ret; + struct intel_gt *gt = pxp_to_gt(pxp); + struct drm_i915_private *i915 = gt->i915; + + ret = component_add_typed(i915->drm.dev, &i915_pxp_tee_component_ops, + I915_COMPONENT_PXP); + if (ret < 0) { + drm_err(&i915->drm, "Failed to add PXP component (%d)\n", ret); + return ret; + } + + pxp->pxp_component_added = true; + + return 0; +} + +void intel_pxp_tee_component_fini(struct intel_pxp *pxp) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + + if (!pxp->pxp_component_added) + return; + + component_del(i915->drm.dev, &i915_pxp_tee_component_ops); + pxp->pxp_component_added = false; +} + +int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, + int arb_session_id) +{ + struct drm_i915_private *i915 = pxp_to_gt(pxp)->i915; + struct pxp_tee_create_arb_in msg_in = {0}; + struct pxp_tee_create_arb_out msg_out = {0}; + int ret; + + msg_in.header.api_version = PXP_TEE_APIVER; + msg_in.header.command_id = PXP_TEE_ARB_CMDID; + msg_in.header.buffer_len = sizeof(msg_in) - sizeof(msg_in.header); + msg_in.protection_mode = PXP_TEE_ARB_PROTECTION_MODE; + msg_in.session_id = arb_session_id; + + ret = intel_pxp_tee_io_message(pxp, + &msg_in, sizeof(msg_in), + &msg_out, sizeof(msg_out), + NULL); + + if (ret) + drm_err(&i915->drm, "Failed to send tee msg ret=[%d]\n", ret); + + return ret; +} diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h new file mode 100644 index 000000000000..c136053ce340 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_TEE_H__ +#define __INTEL_PXP_TEE_H__ + +#include "intel_pxp.h" + +int intel_pxp_tee_component_init(struct intel_pxp *pxp); +void intel_pxp_tee_component_fini(struct intel_pxp *pxp); + +int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp, + int arb_session_id); + +#endif /* __INTEL_PXP_TEE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h new file mode 100644 index 000000000000..36e9b0868f5c --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee_interface.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_TEE_INTERFACE_H__ +#define __INTEL_PXP_TEE_INTERFACE_H__ + +#include + +#define PXP_TEE_APIVER 0x40002 +#define PXP_TEE_ARB_CMDID 0x1e +#define PXP_TEE_ARB_PROTECTION_MODE 0x2 + +/* PXP TEE message header */ +struct pxp_tee_cmd_header { + u32 api_version; + u32 command_id; + u32 status; + /* Length of the message (excluding the header) */ + u32 buffer_len; +} __packed; + +/* PXP TEE message input to create a arbitrary session */ +struct pxp_tee_create_arb_in { + struct pxp_tee_cmd_header header; + u32 protection_mode; + u32 session_id; +} __packed; + +/* PXP TEE message output to create a arbitrary session */ +struct pxp_tee_create_arb_out { + struct pxp_tee_cmd_header header; +} __packed; + +#endif /* __INTEL_PXP_TEE_INTERFACE_H__ */ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_types.h b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h new file mode 100644 index 000000000000..73ef7d1754e1 --- /dev/null +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_types.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright(c) 2020, Intel Corporation. All rights reserved. + */ + +#ifndef __INTEL_PXP_TYPES_H__ +#define __INTEL_PXP_TYPES_H__ + +#include +#include +#include +#include +#include +#include + +struct intel_context; +struct i915_pxp_component; + +/** + * struct intel_pxp - pxp state + */ +struct intel_pxp { + /** + * @pxp_component: i915_pxp_component struct of the bound mei_pxp + * module. Only set and cleared inside component bind/unbind functions, + * which are protected by &tee_mutex. + */ + struct i915_pxp_component *pxp_component; + /** + * @pxp_component_added: track if the pxp component has been added. + * Set and cleared in tee init and fini functions respectively. + */ + bool pxp_component_added; + + /** @ce: kernel-owned context used for PXP operations */ + struct intel_context *ce; + + /** @arb_mutex: protects arb session start */ + struct mutex arb_mutex; + /** + * @arb_is_valid: tracks arb session status. + * After a teardown, the arb session can still be in play on the HW + * even if the keys are gone, so we can't rely on the HW state of the + * session to know if it's valid and need to track the status in SW. + */ + bool arb_is_valid; + + /** + * @key_instance: tracks which key instance we're on, so we can use it + * to determine if an object was created using the current key or a + * previous one. + */ + u32 key_instance; + + /** @tee_mutex: protects the tee channel binding and messaging. */ + struct mutex tee_mutex; + + /** + * @hw_state_invalidated: if the HW perceives an attack on the integrity + * of the encryption it will invalidate the keys and expect SW to + * re-initialize the session. We keep track of this state to make sure + * we only re-start the arb session when required. + */ + bool hw_state_invalidated; + + /** @irq_enabled: tracks the status of the kcr irqs */ + bool irq_enabled; + /** + * @termination: tracks the status of a pending termination. Only + * re-initialized under gt->irq_lock and completed in &session_work. + */ + struct completion termination; + + /** @session_work: worker that manages session events. */ + struct work_struct session_work; + /** @session_events: pending session events, protected with gt->irq_lock. */ + u32 session_events; +#define PXP_TERMINATION_REQUEST BIT(0) +#define PXP_TERMINATION_COMPLETE BIT(1) +#define PXP_INVAL_REQUIRED BIT(2) +}; + +#endif /* __INTEL_PXP_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 2d60a5a5b065..46f4236039a9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -155,7 +155,7 @@ static int igt_ppgtt_alloc(void *arg) if (!HAS_PPGTT(dev_priv)) return 0; - ppgtt = i915_ppgtt_create(&dev_priv->gt); + ppgtt = i915_ppgtt_create(&dev_priv->gt, 0); if (IS_ERR(ppgtt)) return PTR_ERR(ppgtt); @@ -1053,7 +1053,7 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv, if (IS_ERR(file)) return PTR_ERR(file); - ppgtt = i915_ppgtt_create(&dev_priv->gt); + ppgtt = i915_ppgtt_create(&dev_priv->gt, 0); if (IS_ERR(ppgtt)) { err = PTR_ERR(ppgtt); goto out_free; diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h index 3cf6758931f9..bdd290f2bf3c 100644 --- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h @@ -48,5 +48,6 @@ selftest(ring_submission, intel_ring_submission_live_selftests) selftest(perf, i915_perf_live_selftests) selftest(slpc, intel_slpc_live_selftests) selftest(guc, intel_guc_live_selftests) +selftest(guc_multi_lrc, intel_guc_multi_lrc_live_selftests) /* Here be dragons: keep last to run last! */ selftest(late_gt_pm, intel_gt_pm_late_selftests) diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c index 22ef2c87df1a..bc8128170a99 100644 --- a/drivers/gpu/drm/i915/selftests/intel_uncore.c +++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c @@ -68,6 +68,7 @@ static int intel_shadow_table_check(void) { gen8_shadowed_regs, ARRAY_SIZE(gen8_shadowed_regs) }, { gen11_shadowed_regs, ARRAY_SIZE(gen11_shadowed_regs) }, { gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) }, + { dg2_shadowed_regs, ARRAY_SIZE(dg2_shadowed_regs) }, }; const struct i915_range *range; unsigned int i, j; diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index efa86dffe3c6..75793008c4ef 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -6,8 +6,6 @@ #include #include -#include - #include "gem/i915_gem_region.h" #include "intel_memory_region.h" #include "intel_region_ttm.h" diff --git a/drivers/gpu/drm/i915/vlv_sideband.c b/drivers/gpu/drm/i915/vlv_sideband.c new file mode 100644 index 000000000000..35380738a951 --- /dev/null +++ b/drivers/gpu/drm/i915/vlv_sideband.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2013-2021 Intel Corporation + */ + +#include + +#include "i915_drv.h" +#include "vlv_sideband.h" + +/* + * IOSF sideband, see VLV2_SidebandMsg_HAS.docx and + * VLV_VLV2_PUNIT_HAS_0.8.docx + */ + +/* Standard MMIO read, non-posted */ +#define SB_MRD_NP 0x00 +/* Standard MMIO write, non-posted */ +#define SB_MWR_NP 0x01 +/* Private register read, double-word addressing, non-posted */ +#define SB_CRRDDA_NP 0x06 +/* Private register write, double-word addressing, non-posted */ +#define SB_CRWRDA_NP 0x07 + +static void ping(void *info) +{ +} + +static void __vlv_punit_get(struct drm_i915_private *i915) +{ + iosf_mbi_punit_acquire(); + + /* + * Prevent the cpu from sleeping while we use this sideband, otherwise + * the punit may cause a machine hang. The issue appears to be isolated + * with changing the power state of the CPU package while changing + * the power state via the punit, and we have only observed it + * reliably on 4-core Baytail systems suggesting the issue is in the + * power delivery mechanism and likely to be board/function + * specific. Hence we presume the workaround needs only be applied + * to the Valleyview P-unit and not all sideband communications. + */ + if (IS_VALLEYVIEW(i915)) { + cpu_latency_qos_update_request(&i915->sb_qos, 0); + on_each_cpu(ping, NULL, 1); + } +} + +static void __vlv_punit_put(struct drm_i915_private *i915) +{ + if (IS_VALLEYVIEW(i915)) + cpu_latency_qos_update_request(&i915->sb_qos, + PM_QOS_DEFAULT_VALUE); + + iosf_mbi_punit_release(); +} + +void vlv_iosf_sb_get(struct drm_i915_private *i915, unsigned long ports) +{ + if (ports & BIT(VLV_IOSF_SB_PUNIT)) + __vlv_punit_get(i915); + + mutex_lock(&i915->sb_lock); +} + +void vlv_iosf_sb_put(struct drm_i915_private *i915, unsigned long ports) +{ + mutex_unlock(&i915->sb_lock); + + if (ports & BIT(VLV_IOSF_SB_PUNIT)) + __vlv_punit_put(i915); +} + +static int vlv_sideband_rw(struct drm_i915_private *i915, + u32 devfn, u32 port, u32 opcode, + u32 addr, u32 *val) +{ + struct intel_uncore *uncore = &i915->uncore; + const bool is_read = (opcode == SB_MRD_NP || opcode == SB_CRRDDA_NP); + int err; + + lockdep_assert_held(&i915->sb_lock); + if (port == IOSF_PORT_PUNIT) + iosf_mbi_assert_punit_acquired(); + + /* Flush the previous comms, just in case it failed last time. */ + if (intel_wait_for_register(uncore, + VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0, + 5)) { + drm_dbg(&i915->drm, "IOSF sideband idle wait (%s) timed out\n", + is_read ? "read" : "write"); + return -EAGAIN; + } + + preempt_disable(); + + intel_uncore_write_fw(uncore, VLV_IOSF_ADDR, addr); + intel_uncore_write_fw(uncore, VLV_IOSF_DATA, is_read ? 0 : *val); + intel_uncore_write_fw(uncore, VLV_IOSF_DOORBELL_REQ, + (devfn << IOSF_DEVFN_SHIFT) | + (opcode << IOSF_OPCODE_SHIFT) | + (port << IOSF_PORT_SHIFT) | + (0xf << IOSF_BYTE_ENABLES_SHIFT) | + (0 << IOSF_BAR_SHIFT) | + IOSF_SB_BUSY); + + if (__intel_wait_for_register_fw(uncore, + VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0, + 10000, 0, NULL) == 0) { + if (is_read) + *val = intel_uncore_read_fw(uncore, VLV_IOSF_DATA); + err = 0; + } else { + drm_dbg(&i915->drm, "IOSF sideband finish wait (%s) timed out\n", + is_read ? "read" : "write"); + err = -ETIMEDOUT; + } + + preempt_enable(); + + return err; +} + +u32 vlv_punit_read(struct drm_i915_private *i915, u32 addr) +{ + u32 val = 0; + + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT, + SB_CRRDDA_NP, addr, &val); + + return val; +} + +int vlv_punit_write(struct drm_i915_private *i915, u32 addr, u32 val) +{ + return vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_PUNIT, + SB_CRWRDA_NP, addr, &val); +} + +u32 vlv_bunit_read(struct drm_i915_private *i915, u32 reg) +{ + u32 val = 0; + + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT, + SB_CRRDDA_NP, reg, &val); + + return val; +} + +void vlv_bunit_write(struct drm_i915_private *i915, u32 reg, u32 val) +{ + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_BUNIT, + SB_CRWRDA_NP, reg, &val); +} + +u32 vlv_nc_read(struct drm_i915_private *i915, u8 addr) +{ + u32 val = 0; + + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_NC, + SB_CRRDDA_NP, addr, &val); + + return val; +} + +u32 vlv_iosf_sb_read(struct drm_i915_private *i915, u8 port, u32 reg) +{ + u32 val = 0; + + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), port, + SB_CRRDDA_NP, reg, &val); + + return val; +} + +void vlv_iosf_sb_write(struct drm_i915_private *i915, + u8 port, u32 reg, u32 val) +{ + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), port, + SB_CRWRDA_NP, reg, &val); +} + +u32 vlv_cck_read(struct drm_i915_private *i915, u32 reg) +{ + u32 val = 0; + + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCK, + SB_CRRDDA_NP, reg, &val); + + return val; +} + +void vlv_cck_write(struct drm_i915_private *i915, u32 reg, u32 val) +{ + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCK, + SB_CRWRDA_NP, reg, &val); +} + +u32 vlv_ccu_read(struct drm_i915_private *i915, u32 reg) +{ + u32 val = 0; + + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCU, + SB_CRRDDA_NP, reg, &val); + + return val; +} + +void vlv_ccu_write(struct drm_i915_private *i915, u32 reg, u32 val) +{ + vlv_sideband_rw(i915, PCI_DEVFN(0, 0), IOSF_PORT_CCU, + SB_CRWRDA_NP, reg, &val); +} + +static u32 vlv_dpio_phy_iosf_port(struct drm_i915_private *i915, enum dpio_phy phy) +{ + /* + * IOSF_PORT_DPIO: VLV x2 PHY (DP/HDMI B and C), CHV x1 PHY (DP/HDMI D) + * IOSF_PORT_DPIO_2: CHV x2 PHY (DP/HDMI B and C) + */ + if (IS_CHERRYVIEW(i915)) + return phy == DPIO_PHY0 ? IOSF_PORT_DPIO_2 : IOSF_PORT_DPIO; + else + return IOSF_PORT_DPIO; +} + +u32 vlv_dpio_read(struct drm_i915_private *i915, enum pipe pipe, int reg) +{ + u32 port = vlv_dpio_phy_iosf_port(i915, DPIO_PHY(pipe)); + u32 val = 0; + + vlv_sideband_rw(i915, DPIO_DEVFN, port, SB_MRD_NP, reg, &val); + + /* + * FIXME: There might be some registers where all 1's is a valid value, + * so ideally we should check the register offset instead... + */ + drm_WARN(&i915->drm, val == 0xffffffff, + "DPIO read pipe %c reg 0x%x == 0x%x\n", + pipe_name(pipe), reg, val); + + return val; +} + +void vlv_dpio_write(struct drm_i915_private *i915, + enum pipe pipe, int reg, u32 val) +{ + u32 port = vlv_dpio_phy_iosf_port(i915, DPIO_PHY(pipe)); + + vlv_sideband_rw(i915, DPIO_DEVFN, port, SB_MWR_NP, reg, &val); +} + +u32 vlv_flisdsi_read(struct drm_i915_private *i915, u32 reg) +{ + u32 val = 0; + + vlv_sideband_rw(i915, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRRDDA_NP, + reg, &val); + return val; +} + +void vlv_flisdsi_write(struct drm_i915_private *i915, u32 reg, u32 val) +{ + vlv_sideband_rw(i915, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRWRDA_NP, + reg, &val); +} diff --git a/drivers/gpu/drm/i915/intel_sideband.h b/drivers/gpu/drm/i915/vlv_sideband.h similarity index 77% rename from drivers/gpu/drm/i915/intel_sideband.h rename to drivers/gpu/drm/i915/vlv_sideband.h index d1d14bcb8f56..d7732f612e7f 100644 --- a/drivers/gpu/drm/i915/intel_sideband.h +++ b/drivers/gpu/drm/i915/vlv_sideband.h @@ -1,18 +1,16 @@ /* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2013-2021 Intel Corporation + */ -#ifndef _INTEL_SIDEBAND_H_ -#define _INTEL_SIDEBAND_H_ +#ifndef _VLV_SIDEBAND_H_ +#define _VLV_SIDEBAND_H_ #include #include -struct drm_i915_private; enum pipe; - -enum intel_sbi_destination { - SBI_ICLK, - SBI_MPHY, -}; +struct drm_i915_private; enum { VLV_IOSF_SB_BUNIT, @@ -122,22 +120,4 @@ static inline void vlv_punit_put(struct drm_i915_private *i915) vlv_iosf_sb_put(i915, BIT(VLV_IOSF_SB_PUNIT)); } -u32 intel_sbi_read(struct drm_i915_private *i915, u16 reg, - enum intel_sbi_destination destination); -void intel_sbi_write(struct drm_i915_private *i915, u16 reg, u32 value, - enum intel_sbi_destination destination); - -int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox, - u32 *val, u32 *val1); -int sandybridge_pcode_write_timeout(struct drm_i915_private *i915, u32 mbox, - u32 val, int fast_timeout_us, - int slow_timeout_ms); -#define sandybridge_pcode_write(i915, mbox, val) \ - sandybridge_pcode_write_timeout(i915, mbox, val, 500, 0) - -int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request, - u32 reply_mask, u32 reply, int timeout_base_ms); - -int intel_pcode_init(struct drm_i915_private *i915); - -#endif /* _INTEL_SIDEBAND_H */ +#endif /* _VLV_SIDEBAND_H_ */ diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index f5107b6ded7b..ae11061727ff 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -14,6 +14,8 @@ config DRM_MSM select REGULATOR select DRM_KMS_HELPER select DRM_PANEL + select DRM_BRIDGE + select DRM_PANEL_BRIDGE select DRM_SCHED select SHMEM select TMPFS diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 904535eda0c4..40577f8856d8 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -51,7 +51,6 @@ msm-y := \ disp/mdp5/mdp5_mixer.o \ disp/mdp5/mdp5_plane.o \ disp/mdp5/mdp5_smp.o \ - disp/dpu1/dpu_core_irq.o \ disp/dpu1/dpu_core_perf.o \ disp/dpu1/dpu_crtc.o \ disp/dpu1/dpu_encoder.o \ diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c index c9d11d57aed6..dd593ec2bc56 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c @@ -138,7 +138,7 @@ reset_set(void *data, u64 val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(reset_fops, NULL, reset_set, "%llx\n"); +DEFINE_DEBUGFS_ATTRIBUTE(reset_fops, NULL, reset_set, "%llx\n"); void a5xx_debugfs_init(struct msm_gpu *gpu, struct drm_minor *minor) @@ -154,6 +154,6 @@ void a5xx_debugfs_init(struct msm_gpu *gpu, struct drm_minor *minor) ARRAY_SIZE(a5xx_debugfs_list), minor->debugfs_root, minor); - debugfs_create_file("reset", S_IWUGO, minor->debugfs_root, dev, - &reset_fops); + debugfs_create_file_unsafe("reset", S_IWUGO, minor->debugfs_root, dev, + &reset_fops); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 8b73f70766a4..71e52b2b2025 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -516,11 +516,11 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct platform_device *pdev = to_platform_device(gmu->dev); void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc"); - void __iomem *seqptr; + void __iomem *seqptr = NULL; uint32_t pdc_address_offset; bool pdc_in_aop = false; - if (!pdcptr) + if (IS_ERR(pdcptr)) goto err; if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu)) @@ -532,7 +532,7 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) if (!pdc_in_aop) { seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq"); - if (!seqptr) + if (IS_ERR(seqptr)) goto err; } @@ -891,7 +891,7 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index]; gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true); - if (IS_ERR_OR_NULL(gpu_opp)) + if (IS_ERR(gpu_opp)) return; gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */ @@ -905,7 +905,7 @@ static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu) unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index]; gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true); - if (IS_ERR_OR_NULL(gpu_opp)) + if (IS_ERR(gpu_opp)) return; dev_pm_opp_set_opp(&gpu->pdev->dev, gpu_opp); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index e8f65cd8eca6..7501849ed15d 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -180,7 +180,7 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, msm_readl((ptr) + ((offset) << 2)) /* read a value from the CX debug bus */ -static int cx_debugbus_read(void *__iomem cxdbg, u32 block, u32 offset, +static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset, u32 *data) { u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c deleted file mode 100644 index d2457490930b..000000000000 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c +++ /dev/null @@ -1,256 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - */ - -#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ - -#include -#include -#include -#include - -#include "dpu_core_irq.h" -#include "dpu_trace.h" - -/** - * dpu_core_irq_callback_handler - dispatch core interrupts - * @arg: private data of callback handler - * @irq_idx: interrupt index - */ -static void dpu_core_irq_callback_handler(void *arg, int irq_idx) -{ - struct dpu_kms *dpu_kms = arg; - struct dpu_irq *irq_obj = &dpu_kms->irq_obj; - struct dpu_irq_callback *cb; - - VERB("irq_idx=%d\n", irq_idx); - - if (list_empty(&irq_obj->irq_cb_tbl[irq_idx])) - DRM_ERROR("no registered cb, idx:%d\n", irq_idx); - - atomic_inc(&irq_obj->irq_counts[irq_idx]); - - /* - * Perform registered function callback - */ - list_for_each_entry(cb, &irq_obj->irq_cb_tbl[irq_idx], list) - if (cb->func) - cb->func(cb->arg, irq_idx); -} - -u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear) -{ - if (!dpu_kms->hw_intr || - !dpu_kms->hw_intr->ops.get_interrupt_status) - return 0; - - if (irq_idx < 0) { - DPU_ERROR("[%pS] invalid irq_idx=%d\n", - __builtin_return_address(0), irq_idx); - return 0; - } - - return dpu_kms->hw_intr->ops.get_interrupt_status(dpu_kms->hw_intr, - irq_idx, clear); -} - -int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx, - struct dpu_irq_callback *register_irq_cb) -{ - unsigned long irq_flags; - - if (!dpu_kms->irq_obj.irq_cb_tbl) { - DPU_ERROR("invalid params\n"); - return -EINVAL; - } - - if (!register_irq_cb || !register_irq_cb->func) { - DPU_ERROR("invalid irq_cb:%d func:%d\n", - register_irq_cb != NULL, - register_irq_cb ? - register_irq_cb->func != NULL : -1); - return -EINVAL; - } - - if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) { - DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); - return -EINVAL; - } - - VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); - - irq_flags = dpu_kms->hw_intr->ops.lock(dpu_kms->hw_intr); - trace_dpu_core_irq_register_callback(irq_idx, register_irq_cb); - list_del_init(®ister_irq_cb->list); - list_add_tail(®ister_irq_cb->list, - &dpu_kms->irq_obj.irq_cb_tbl[irq_idx]); - if (list_is_first(®ister_irq_cb->list, - &dpu_kms->irq_obj.irq_cb_tbl[irq_idx])) { - int ret = dpu_kms->hw_intr->ops.enable_irq_locked( - dpu_kms->hw_intr, - irq_idx); - if (ret) - DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n", - irq_idx); - } - dpu_kms->hw_intr->ops.unlock(dpu_kms->hw_intr, irq_flags); - - return 0; -} - -int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx, - struct dpu_irq_callback *register_irq_cb) -{ - unsigned long irq_flags; - - if (!dpu_kms->irq_obj.irq_cb_tbl) { - DPU_ERROR("invalid params\n"); - return -EINVAL; - } - - if (!register_irq_cb || !register_irq_cb->func) { - DPU_ERROR("invalid irq_cb:%d func:%d\n", - register_irq_cb != NULL, - register_irq_cb ? - register_irq_cb->func != NULL : -1); - return -EINVAL; - } - - if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) { - DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); - return -EINVAL; - } - - VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); - - irq_flags = dpu_kms->hw_intr->ops.lock(dpu_kms->hw_intr); - trace_dpu_core_irq_unregister_callback(irq_idx, register_irq_cb); - list_del_init(®ister_irq_cb->list); - /* empty callback list but interrupt is still enabled */ - if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx])) { - int ret = dpu_kms->hw_intr->ops.disable_irq_locked( - dpu_kms->hw_intr, - irq_idx); - if (ret) - DPU_ERROR("Fail to disable IRQ for irq_idx:%d\n", - irq_idx); - VERB("irq_idx=%d ret=%d\n", irq_idx, ret); - } - dpu_kms->hw_intr->ops.unlock(dpu_kms->hw_intr, irq_flags); - - return 0; -} - -static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms) -{ - if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.clear_all_irqs) - return; - - dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr); -} - -static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms) -{ - if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.disable_all_irqs) - return; - - dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr); -} - -#ifdef CONFIG_DEBUG_FS -static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v) -{ - struct dpu_kms *dpu_kms = s->private; - struct dpu_irq *irq_obj = &dpu_kms->irq_obj; - struct dpu_irq_callback *cb; - unsigned long irq_flags; - int i, irq_count, cb_count; - - if (WARN_ON(!irq_obj->irq_cb_tbl)) - return 0; - - for (i = 0; i < irq_obj->total_irqs; i++) { - irq_flags = dpu_kms->hw_intr->ops.lock(dpu_kms->hw_intr); - cb_count = 0; - irq_count = atomic_read(&irq_obj->irq_counts[i]); - list_for_each_entry(cb, &irq_obj->irq_cb_tbl[i], list) - cb_count++; - dpu_kms->hw_intr->ops.unlock(dpu_kms->hw_intr, irq_flags); - - if (irq_count || cb_count) - seq_printf(s, "idx:%d irq:%d cb:%d\n", - i, irq_count, cb_count); - } - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_core_irq); - -void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, - struct dentry *parent) -{ - debugfs_create_file("core_irq", 0600, parent, dpu_kms, - &dpu_debugfs_core_irq_fops); -} -#endif - -void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms) -{ - int i; - - pm_runtime_get_sync(&dpu_kms->pdev->dev); - dpu_clear_all_irqs(dpu_kms); - dpu_disable_all_irqs(dpu_kms); - pm_runtime_put_sync(&dpu_kms->pdev->dev); - - /* Create irq callbacks for all possible irq_idx */ - dpu_kms->irq_obj.total_irqs = dpu_kms->hw_intr->total_irqs; - dpu_kms->irq_obj.irq_cb_tbl = kcalloc(dpu_kms->irq_obj.total_irqs, - sizeof(struct list_head), GFP_KERNEL); - dpu_kms->irq_obj.irq_counts = kcalloc(dpu_kms->irq_obj.total_irqs, - sizeof(atomic_t), GFP_KERNEL); - for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) { - INIT_LIST_HEAD(&dpu_kms->irq_obj.irq_cb_tbl[i]); - atomic_set(&dpu_kms->irq_obj.irq_counts[i], 0); - } -} - -void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms) -{ - int i; - - pm_runtime_get_sync(&dpu_kms->pdev->dev); - for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) - if (!list_empty(&dpu_kms->irq_obj.irq_cb_tbl[i])) - DPU_ERROR("irq_idx=%d still enabled/registered\n", i); - - dpu_clear_all_irqs(dpu_kms); - dpu_disable_all_irqs(dpu_kms); - pm_runtime_put_sync(&dpu_kms->pdev->dev); - - kfree(dpu_kms->irq_obj.irq_cb_tbl); - kfree(dpu_kms->irq_obj.irq_counts); - dpu_kms->irq_obj.irq_cb_tbl = NULL; - dpu_kms->irq_obj.irq_counts = NULL; - dpu_kms->irq_obj.total_irqs = 0; -} - -irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms) -{ - /* - * Dispatch to HW driver to handle interrupt lookup that is being - * fired. When matching interrupt is located, HW driver will call to - * dpu_core_irq_callback_handler with the irq_idx from the lookup table. - * dpu_core_irq_callback_handler will perform the registered function - * callback, and do the interrupt status clearing once the registered - * callback is finished. - * Function will also clear the interrupt status after reading. - */ - dpu_kms->hw_intr->ops.dispatch_irqs( - dpu_kms->hw_intr, - dpu_core_irq_callback_handler, - dpu_kms); - - return IRQ_HANDLED; -} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 768012243b44..967245b8cc02 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2014-2018 The Linux Foundation. All rights reserved. + * Copyright (c) 2014-2021 The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark */ @@ -70,17 +70,147 @@ static struct drm_encoder *get_encoder_from_crtc(struct drm_crtc *crtc) return NULL; } -static u32 dpu_crtc_get_vblank_counter(struct drm_crtc *crtc) +static enum dpu_crtc_crc_source dpu_crtc_parse_crc_source(const char *src_name) { - struct drm_encoder *encoder; + if (!src_name || + !strcmp(src_name, "none")) + return DPU_CRTC_CRC_SOURCE_NONE; + if (!strcmp(src_name, "auto") || + !strcmp(src_name, "lm")) + return DPU_CRTC_CRC_SOURCE_LAYER_MIXER; - encoder = get_encoder_from_crtc(crtc); - if (!encoder) { - DRM_ERROR("no encoder found for crtc %d\n", crtc->index); - return false; + return DPU_CRTC_CRC_SOURCE_INVALID; +} + +static int dpu_crtc_verify_crc_source(struct drm_crtc *crtc, + const char *src_name, size_t *values_cnt) +{ + enum dpu_crtc_crc_source source = dpu_crtc_parse_crc_source(src_name); + struct dpu_crtc_state *crtc_state = to_dpu_crtc_state(crtc->state); + + if (source < 0) { + DRM_DEBUG_DRIVER("Invalid source %s for CRTC%d\n", src_name, crtc->index); + return -EINVAL; } - return dpu_encoder_get_frame_count(encoder); + if (source == DPU_CRTC_CRC_SOURCE_LAYER_MIXER) + *values_cnt = crtc_state->num_mixers; + + return 0; +} + +static int dpu_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) +{ + enum dpu_crtc_crc_source source = dpu_crtc_parse_crc_source(src_name); + enum dpu_crtc_crc_source current_source; + struct dpu_crtc_state *crtc_state; + struct drm_device *drm_dev = crtc->dev; + struct dpu_crtc_mixer *m; + + bool was_enabled; + bool enable = false; + int i, ret = 0; + + if (source < 0) { + DRM_DEBUG_DRIVER("Invalid CRC source %s for CRTC%d\n", src_name, crtc->index); + return -EINVAL; + } + + ret = drm_modeset_lock(&crtc->mutex, NULL); + + if (ret) + return ret; + + enable = (source != DPU_CRTC_CRC_SOURCE_NONE); + crtc_state = to_dpu_crtc_state(crtc->state); + + spin_lock_irq(&drm_dev->event_lock); + current_source = crtc_state->crc_source; + spin_unlock_irq(&drm_dev->event_lock); + + was_enabled = (current_source != DPU_CRTC_CRC_SOURCE_NONE); + + if (!was_enabled && enable) { + ret = drm_crtc_vblank_get(crtc); + + if (ret) + goto cleanup; + + } else if (was_enabled && !enable) { + drm_crtc_vblank_put(crtc); + } + + spin_lock_irq(&drm_dev->event_lock); + crtc_state->crc_source = source; + spin_unlock_irq(&drm_dev->event_lock); + + crtc_state->crc_frame_skip_count = 0; + + for (i = 0; i < crtc_state->num_mixers; ++i) { + m = &crtc_state->mixers[i]; + + if (!m->hw_lm || !m->hw_lm->ops.setup_misr) + continue; + + /* Calculate MISR over 1 frame */ + m->hw_lm->ops.setup_misr(m->hw_lm, true, 1); + } + + +cleanup: + drm_modeset_unlock(&crtc->mutex); + + return ret; +} + +static u32 dpu_crtc_get_vblank_counter(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder = get_encoder_from_crtc(crtc); + if (!encoder) { + DRM_ERROR("no encoder found for crtc %d\n", crtc->index); + return 0; + } + + return dpu_encoder_get_vsync_count(encoder); +} + + +static int dpu_crtc_get_crc(struct drm_crtc *crtc) +{ + struct dpu_crtc_state *crtc_state; + struct dpu_crtc_mixer *m; + u32 crcs[CRTC_DUAL_MIXERS]; + + int i = 0; + int rc = 0; + + crtc_state = to_dpu_crtc_state(crtc->state); + + BUILD_BUG_ON(ARRAY_SIZE(crcs) != ARRAY_SIZE(crtc_state->mixers)); + + /* Skip first 2 frames in case of "uncooked" CRCs */ + if (crtc_state->crc_frame_skip_count < 2) { + crtc_state->crc_frame_skip_count++; + return 0; + } + + for (i = 0; i < crtc_state->num_mixers; ++i) { + + m = &crtc_state->mixers[i]; + + if (!m->hw_lm || !m->hw_lm->ops.collect_misr) + continue; + + rc = m->hw_lm->ops.collect_misr(m->hw_lm, &crcs[i]); + + if (rc) { + DRM_DEBUG_DRIVER("MISR read failed\n"); + return rc; + } + } + + return drm_crtc_add_crc_entry(crtc, true, + drm_crtc_accurate_vblank_count(crtc), crcs); } static bool dpu_crtc_get_scanout_position(struct drm_crtc *crtc, @@ -389,6 +519,9 @@ void dpu_crtc_vblank_callback(struct drm_crtc *crtc) dpu_crtc->vblank_cb_time = ktime_get(); else dpu_crtc->vblank_cb_count++; + + dpu_crtc_get_crc(crtc); + drm_crtc_handle_vblank(crtc); trace_dpu_crtc_vblank_cb(DRMID(crtc)); } @@ -1332,6 +1465,8 @@ static const struct drm_crtc_funcs dpu_crtc_funcs = { .atomic_destroy_state = dpu_crtc_destroy_state, .late_register = dpu_crtc_late_register, .early_unregister = dpu_crtc_early_unregister, + .verify_crc_source = dpu_crtc_verify_crc_source, + .set_crc_source = dpu_crtc_set_crc_source, .enable_vblank = msm_crtc_enable_vblank, .disable_vblank = msm_crtc_disable_vblank, .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index cec3474340e8..ae9546ca1359 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. + * Copyright (c) 2015-2021 The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark */ @@ -69,6 +69,19 @@ struct dpu_crtc_smmu_state_data { uint32_t transition_error; }; +/** + * enum dpu_crtc_crc_source: CRC source + * @DPU_CRTC_CRC_SOURCE_NONE: no source set + * @DPU_CRTC_CRC_SOURCE_LAYER_MIXER: CRC in layer mixer + * @DPU_CRTC_CRC_SOURCE_INVALID: Invalid source + */ +enum dpu_crtc_crc_source { + DPU_CRTC_CRC_SOURCE_NONE = 0, + DPU_CRTC_CRC_SOURCE_LAYER_MIXER, + DPU_CRTC_CRC_SOURCE_MAX, + DPU_CRTC_CRC_SOURCE_INVALID = -1 +}; + /** * struct dpu_crtc_mixer: stores the map for each virtual pipeline in the CRTC * @hw_lm: LM HW Driver context @@ -139,6 +152,7 @@ struct dpu_crtc_frame_event { * @event_lock : Spinlock around event handling code * @phandle: Pointer to power handler * @cur_perf : current performance committed to clock/bandwidth driver + * @crc_source : CRC source */ struct dpu_crtc { struct drm_crtc base; @@ -210,6 +224,9 @@ struct dpu_crtc_state { u32 num_ctls; struct dpu_hw_ctl *hw_ctls[CRTC_DUAL_MIXERS]; + + enum dpu_crtc_crc_source crc_source; + int crc_frame_skip_count; }; #define to_dpu_crtc_state(x) \ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 0e9d3fa1544b..e7ee4cfb8461 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -168,6 +168,7 @@ enum dpu_enc_rc_states { * @vsync_event_work: worker to handle vsync event for autorefresh * @topology: topology of the display * @idle_timeout: idle timeout duration in milliseconds + * @dp: msm_dp pointer, for DP encoders */ struct dpu_encoder_virt { struct drm_encoder base; @@ -206,6 +207,8 @@ struct dpu_encoder_virt { struct msm_display_topology topology; u32 idle_timeout; + + struct msm_dp *dp; }; #define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base) @@ -395,19 +398,11 @@ int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc, return 0; } -int dpu_encoder_get_frame_count(struct drm_encoder *drm_enc) +int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc) { - struct dpu_encoder_virt *dpu_enc; - struct dpu_encoder_phys *phys; - int framecount = 0; - - dpu_enc = to_dpu_encoder_virt(drm_enc); - phys = dpu_enc ? dpu_enc->cur_master : NULL; - - if (phys && phys->ops.get_frame_count) - framecount = phys->ops.get_frame_count(phys); - - return framecount; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + struct dpu_encoder_phys *phys = dpu_enc ? dpu_enc->cur_master : NULL; + return phys ? atomic_read(&phys->vsync_cnt) : 0; } int dpu_encoder_get_linecount(struct drm_encoder *drm_enc) @@ -1000,8 +995,8 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, trace_dpu_enc_mode_set(DRMID(drm_enc)); - if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) - msm_dp_display_mode_set(priv->dp, drm_enc, mode, adj_mode); + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS) + msm_dp_display_mode_set(dpu_enc->dp, drm_enc, mode, adj_mode); list_for_each_entry(conn_iter, connector_list, head) if (conn_iter->encoder == drm_enc) @@ -1182,9 +1177,8 @@ static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc) _dpu_encoder_virt_enable_helper(drm_enc); - if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) { - ret = msm_dp_display_enable(priv->dp, - drm_enc); + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS) { + ret = msm_dp_display_enable(dpu_enc->dp, drm_enc); if (ret) { DPU_ERROR_ENC(dpu_enc, "dp display enable failed: %d\n", ret); @@ -1224,8 +1218,8 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) /* wait for idle */ dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE); - if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) { - if (msm_dp_display_pre_disable(priv->dp, drm_enc)) + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS) { + if (msm_dp_display_pre_disable(dpu_enc->dp, drm_enc)) DPU_ERROR_ENC(dpu_enc, "dp display push idle failed\n"); } @@ -1253,8 +1247,8 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); - if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS && priv->dp) { - if (msm_dp_display_disable(priv->dp, drm_enc)) + if (drm_enc->encoder_type == DRM_MODE_ENCODER_TMDS) { + if (msm_dp_display_disable(dpu_enc->dp, drm_enc)) DPU_ERROR_ENC(dpu_enc, "dp display disable failed\n"); } @@ -2170,7 +2164,8 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, timer_setup(&dpu_enc->vsync_event_timer, dpu_encoder_vsync_event_handler, 0); - + else if (disp_info->intf_type == DRM_MODE_ENCODER_TMDS) + dpu_enc->dp = priv->dp[disp_info->h_tile_instance[0]]; INIT_DELAYED_WORK(&dpu_enc->delayed_off_work, dpu_encoder_off_work); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 99a5d73c9b88..e241914a9677 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -163,9 +163,9 @@ void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc, int dpu_encoder_get_linecount(struct drm_encoder *drm_enc); /** - * dpu_encoder_get_frame_count - get interface frame count for the encoder. + * dpu_encoder_get_vsync_count - get vsync count for the encoder. * @drm_enc: Pointer to previously created drm encoder structure */ -int dpu_encoder_get_frame_count(struct drm_encoder *drm_enc); +int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc); #endif /* __DPU_ENCODER_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index aa01698d6b25..34a6940d12c5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -42,7 +42,7 @@ static bool dpu_encoder_phys_cmd_is_master(struct dpu_encoder_phys *phys_enc) { - return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false; + return (phys_enc->split_role != ENC_ROLE_SLAVE); } static bool dpu_encoder_phys_cmd_mode_fixup( diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 700d65e39feb..ce6f32a919e5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -844,7 +844,7 @@ static const struct dpu_intf_cfg sdm845_intf[] = { }; static const struct dpu_intf_cfg sc7180_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, MSM_DP_CONTROLLER_0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 24, 25), INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK, MDP_SSPP_TOP0_INTR, 26, 27), }; @@ -958,12 +958,6 @@ static const struct dpu_perf_cfg sdm845_perf_data = { .min_core_ib = 2400000, .min_llcc_ib = 800000, .min_dram_ib = 800000, - .core_ib_ff = "6.0", - .core_clk_ff = "1.0", - .comp_ratio_rt = - "NV12/5/1/1.23 AB24/5/1/1.23 XB24/5/1/1.23", - .comp_ratio_nrt = - "NV12/5/1/1.25 AB24/5/1/1.25 XB24/5/1/1.25", .undersized_prefill_lines = 2, .xtra_prefill_lines = 2, .dest_scale_prefill_lines = 3, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index d2a945a27cfa..4ade44bbd37e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -676,10 +676,6 @@ struct dpu_perf_cdp_cfg { * @min_core_ib minimum mnoc ib vote in kbps * @min_llcc_ib minimum llcc ib vote in kbps * @min_dram_ib minimum dram ib vote in kbps - * @core_ib_ff core instantaneous bandwidth fudge factor - * @core_clk_ff core clock fudge factor - * @comp_ratio_rt string of 0 or more of /// - * @comp_ratio_nrt string of 0 or more of /// * @undersized_prefill_lines undersized prefill in lines * @xtra_prefill_lines extra prefill latency in lines * @dest_scale_prefill_lines destination scaler latency in lines @@ -702,10 +698,6 @@ struct dpu_perf_cfg { u32 min_core_ib; u32 min_llcc_ib; u32 min_dram_ib; - const char *core_ib_ff; - const char *core_clk_ff; - const char *comp_ratio_rt; - const char *comp_ratio_nrt; u32 undersized_prefill_lines; u32 xtra_prefill_lines; u32 dest_scale_prefill_lines; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 2e816f232e85..d2b6dca487e3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -3,12 +3,15 @@ */ #include +#include #include +#include "dpu_core_irq.h" #include "dpu_kms.h" #include "dpu_hw_interrupts.h" #include "dpu_hw_util.h" #include "dpu_hw_mdss.h" +#include "dpu_trace.h" /** * Register offsets in MDSS register file for the interrupt registers @@ -117,25 +120,33 @@ static const struct dpu_intr_reg dpu_intr_set[] = { #define DPU_IRQ_REG(irq_idx) (irq_idx / 32) #define DPU_IRQ_MASK(irq_idx) (BIT(irq_idx % 32)) -static void dpu_hw_intr_clear_intr_status_nolock(struct dpu_hw_intr *intr, - int irq_idx) +/** + * dpu_core_irq_callback_handler - dispatch core interrupts + * @arg: private data of callback handler + * @irq_idx: interrupt index + */ +static void dpu_core_irq_callback_handler(struct dpu_kms *dpu_kms, int irq_idx) { - int reg_idx; + struct dpu_irq_callback *cb; - if (!intr) - return; + VERB("irq_idx=%d\n", irq_idx); - reg_idx = DPU_IRQ_REG(irq_idx); - DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off, DPU_IRQ_MASK(irq_idx)); + if (list_empty(&dpu_kms->hw_intr->irq_cb_tbl[irq_idx])) + DRM_ERROR("no registered cb, idx:%d\n", irq_idx); - /* ensure register writes go through */ - wmb(); + atomic_inc(&dpu_kms->hw_intr->irq_counts[irq_idx]); + + /* + * Perform registered function callback + */ + list_for_each_entry(cb, &dpu_kms->hw_intr->irq_cb_tbl[irq_idx], list) + if (cb->func) + cb->func(cb->arg, irq_idx); } -static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, - void (*cbfunc)(void *, int), - void *arg) +irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms) { + struct dpu_hw_intr *intr = dpu_kms->hw_intr; int reg_idx; int irq_idx; u32 irq_status; @@ -144,13 +155,8 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, unsigned long irq_flags; if (!intr) - return; + return IRQ_NONE; - /* - * The dispatcher will save the IRQ status before calling here. - * Now need to go through each IRQ status and find matching - * irq lookup index. - */ spin_lock_irqsave(&intr->irq_lock, irq_flags); for (reg_idx = 0; reg_idx < ARRAY_SIZE(dpu_intr_set); reg_idx++) { if (!test_bit(reg_idx, &intr->irq_mask)) @@ -178,17 +184,8 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, */ while ((bit = ffs(irq_status)) != 0) { irq_idx = DPU_IRQ_IDX(reg_idx, bit - 1); - /* - * Once a match on irq mask, perform a callback - * to the given cbfunc. cbfunc will take care - * the interrupt status clearing. If cbfunc is - * not provided, then the interrupt clearing - * is here. - */ - if (cbfunc) - cbfunc(arg, irq_idx); - dpu_hw_intr_clear_intr_status_nolock(intr, irq_idx); + dpu_core_irq_callback_handler(dpu_kms, irq_idx); /* * When callback finish, clear the irq_status @@ -203,6 +200,8 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, wmb(); spin_unlock_irqrestore(&intr->irq_lock, irq_flags); + + return IRQ_HANDLED; } static int dpu_hw_intr_enable_irq_locked(struct dpu_hw_intr *intr, int irq_idx) @@ -303,12 +302,13 @@ static int dpu_hw_intr_disable_irq_locked(struct dpu_hw_intr *intr, int irq_idx) return 0; } -static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr) +static void dpu_clear_irqs(struct dpu_kms *dpu_kms) { + struct dpu_hw_intr *intr = dpu_kms->hw_intr; int i; if (!intr) - return -EINVAL; + return; for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) { if (test_bit(i, &intr->irq_mask)) @@ -318,16 +318,15 @@ static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr) /* ensure register writes go through */ wmb(); - - return 0; } -static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr) +static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms) { + struct dpu_hw_intr *intr = dpu_kms->hw_intr; int i; if (!intr) - return -EINVAL; + return; for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) { if (test_bit(i, &intr->irq_mask)) @@ -337,13 +336,11 @@ static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr) /* ensure register writes go through */ wmb(); - - return 0; } -static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr, - int irq_idx, bool clear) +u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear) { + struct dpu_hw_intr *intr = dpu_kms->hw_intr; int reg_idx; unsigned long irq_flags; u32 intr_status; @@ -351,6 +348,12 @@ static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr, if (!intr) return 0; + if (irq_idx < 0) { + DPU_ERROR("[%pS] invalid irq_idx=%d\n", + __builtin_return_address(0), irq_idx); + return 0; + } + if (irq_idx < 0 || irq_idx >= intr->total_irqs) { pr_err("invalid IRQ index: [%d]\n", irq_idx); return 0; @@ -374,32 +377,6 @@ static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr, return intr_status; } -static unsigned long dpu_hw_intr_lock(struct dpu_hw_intr *intr) -{ - unsigned long irq_flags; - - spin_lock_irqsave(&intr->irq_lock, irq_flags); - - return irq_flags; -} - -static void dpu_hw_intr_unlock(struct dpu_hw_intr *intr, unsigned long irq_flags) -{ - spin_unlock_irqrestore(&intr->irq_lock, irq_flags); -} - -static void __setup_intr_ops(struct dpu_hw_intr_ops *ops) -{ - ops->enable_irq_locked = dpu_hw_intr_enable_irq_locked; - ops->disable_irq_locked = dpu_hw_intr_disable_irq_locked; - ops->dispatch_irqs = dpu_hw_intr_dispatch_irq; - ops->clear_all_irqs = dpu_hw_intr_clear_irqs; - ops->disable_all_irqs = dpu_hw_intr_disable_irqs; - ops->get_interrupt_status = dpu_hw_intr_get_interrupt_status; - ops->lock = dpu_hw_intr_lock; - ops->unlock = dpu_hw_intr_unlock; -} - static void __intr_offset(struct dpu_mdss_cfg *m, void __iomem *addr, struct dpu_hw_blk_reg_map *hw) { @@ -421,7 +398,6 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr, return ERR_PTR(-ENOMEM); __intr_offset(m, addr, &intr->hw); - __setup_intr_ops(&intr->ops); intr->total_irqs = ARRAY_SIZE(dpu_intr_set) * 32; @@ -443,7 +419,168 @@ void dpu_hw_intr_destroy(struct dpu_hw_intr *intr) { if (intr) { kfree(intr->cache_irq_mask); + + kfree(intr->irq_cb_tbl); + kfree(intr->irq_counts); + kfree(intr); } } +int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx, + struct dpu_irq_callback *register_irq_cb) +{ + unsigned long irq_flags; + + if (!dpu_kms->hw_intr->irq_cb_tbl) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + if (!register_irq_cb || !register_irq_cb->func) { + DPU_ERROR("invalid irq_cb:%d func:%d\n", + register_irq_cb != NULL, + register_irq_cb ? + register_irq_cb->func != NULL : -1); + return -EINVAL; + } + + if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) { + DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); + + spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags); + trace_dpu_core_irq_register_callback(irq_idx, register_irq_cb); + list_del_init(®ister_irq_cb->list); + list_add_tail(®ister_irq_cb->list, + &dpu_kms->hw_intr->irq_cb_tbl[irq_idx]); + if (list_is_first(®ister_irq_cb->list, + &dpu_kms->hw_intr->irq_cb_tbl[irq_idx])) { + int ret = dpu_hw_intr_enable_irq_locked( + dpu_kms->hw_intr, + irq_idx); + if (ret) + DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n", + irq_idx); + } + spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); + + return 0; +} + +int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx, + struct dpu_irq_callback *register_irq_cb) +{ + unsigned long irq_flags; + + if (!dpu_kms->hw_intr->irq_cb_tbl) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + if (!register_irq_cb || !register_irq_cb->func) { + DPU_ERROR("invalid irq_cb:%d func:%d\n", + register_irq_cb != NULL, + register_irq_cb ? + register_irq_cb->func != NULL : -1); + return -EINVAL; + } + + if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->total_irqs) { + DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + VERB("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); + + spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags); + trace_dpu_core_irq_unregister_callback(irq_idx, register_irq_cb); + list_del_init(®ister_irq_cb->list); + /* empty callback list but interrupt is still enabled */ + if (list_empty(&dpu_kms->hw_intr->irq_cb_tbl[irq_idx])) { + int ret = dpu_hw_intr_disable_irq_locked( + dpu_kms->hw_intr, + irq_idx); + if (ret) + DPU_ERROR("Fail to disable IRQ for irq_idx:%d\n", + irq_idx); + VERB("irq_idx=%d ret=%d\n", irq_idx, ret); + } + spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); + + return 0; +} + +#ifdef CONFIG_DEBUG_FS +static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v) +{ + struct dpu_kms *dpu_kms = s->private; + struct dpu_irq_callback *cb; + unsigned long irq_flags; + int i, irq_count, cb_count; + + if (WARN_ON(!dpu_kms->hw_intr->irq_cb_tbl)) + return 0; + + for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) { + spin_lock_irqsave(&dpu_kms->hw_intr->irq_lock, irq_flags); + cb_count = 0; + irq_count = atomic_read(&dpu_kms->hw_intr->irq_counts[i]); + list_for_each_entry(cb, &dpu_kms->hw_intr->irq_cb_tbl[i], list) + cb_count++; + spin_unlock_irqrestore(&dpu_kms->hw_intr->irq_lock, irq_flags); + + if (irq_count || cb_count) + seq_printf(s, "idx:%d irq:%d cb:%d\n", + i, irq_count, cb_count); + } + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(dpu_debugfs_core_irq); + +void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, + struct dentry *parent) +{ + debugfs_create_file("core_irq", 0600, parent, dpu_kms, + &dpu_debugfs_core_irq_fops); +} +#endif + +void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms) +{ + int i; + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + dpu_clear_irqs(dpu_kms); + dpu_disable_all_irqs(dpu_kms); + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + /* Create irq callbacks for all possible irq_idx */ + dpu_kms->hw_intr->irq_cb_tbl = kcalloc(dpu_kms->hw_intr->total_irqs, + sizeof(struct list_head), GFP_KERNEL); + dpu_kms->hw_intr->irq_counts = kcalloc(dpu_kms->hw_intr->total_irqs, + sizeof(atomic_t), GFP_KERNEL); + for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) { + INIT_LIST_HEAD(&dpu_kms->hw_intr->irq_cb_tbl[i]); + atomic_set(&dpu_kms->hw_intr->irq_counts[i], 0); + } +} + +void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms) +{ + int i; + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + for (i = 0; i < dpu_kms->hw_intr->total_irqs; i++) + if (!list_empty(&dpu_kms->hw_intr->irq_cb_tbl[i])) + DPU_ERROR("irq_idx=%d still enabled/registered\n", i); + + dpu_clear_irqs(dpu_kms); + dpu_disable_all_irqs(dpu_kms); + pm_runtime_put_sync(&dpu_kms->pdev->dev); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h index ac83c1159815..d50e78c9f148 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h @@ -32,92 +32,6 @@ enum dpu_hw_intr_reg { #define DPU_IRQ_IDX(reg_idx, offset) (reg_idx * 32 + offset) -struct dpu_hw_intr; - -/** - * Interrupt operations. - */ -struct dpu_hw_intr_ops { - - /** - * enable_irq - Enable IRQ based on lookup IRQ index - * @intr: HW interrupt handle - * @irq_idx: Lookup irq index return from irq_idx_lookup - * @return: 0 for success, otherwise failure - */ - int (*enable_irq_locked)( - struct dpu_hw_intr *intr, - int irq_idx); - - /** - * disable_irq - Disable IRQ based on lookup IRQ index - * @intr: HW interrupt handle - * @irq_idx: Lookup irq index return from irq_idx_lookup - * @return: 0 for success, otherwise failure - */ - int (*disable_irq_locked)( - struct dpu_hw_intr *intr, - int irq_idx); - - /** - * clear_all_irqs - Clears all the interrupts (i.e. acknowledges - * any asserted IRQs). Useful during reset. - * @intr: HW interrupt handle - * @return: 0 for success, otherwise failure - */ - int (*clear_all_irqs)( - struct dpu_hw_intr *intr); - - /** - * disable_all_irqs - Disables all the interrupts. Useful during reset. - * @intr: HW interrupt handle - * @return: 0 for success, otherwise failure - */ - int (*disable_all_irqs)( - struct dpu_hw_intr *intr); - - /** - * dispatch_irqs - IRQ dispatcher will call the given callback - * function when a matching interrupt status bit is - * found in the irq mapping table. - * @intr: HW interrupt handle - * @cbfunc: Callback function pointer - * @arg: Argument to pass back during callback - */ - void (*dispatch_irqs)( - struct dpu_hw_intr *intr, - void (*cbfunc)(void *arg, int irq_idx), - void *arg); - - /** - * get_interrupt_status - Gets HW interrupt status, and clear if set, - * based on given lookup IRQ index. - * @intr: HW interrupt handle - * @irq_idx: Lookup irq index return from irq_idx_lookup - * @clear: True to clear irq after read - */ - u32 (*get_interrupt_status)( - struct dpu_hw_intr *intr, - int irq_idx, - bool clear); - - /** - * lock - take the IRQ lock - * @intr: HW interrupt handle - * @return: irq_flags for the taken spinlock - */ - unsigned long (*lock)( - struct dpu_hw_intr *intr); - - /** - * unlock - take the IRQ lock - * @intr: HW interrupt handle - * @irq_flags: the irq_flags returned from lock - */ - void (*unlock)( - struct dpu_hw_intr *intr, unsigned long irq_flags); -}; - /** * struct dpu_hw_intr: hw interrupts handling data structure * @hw: virtual address mapping @@ -126,15 +40,19 @@ struct dpu_hw_intr_ops { * @save_irq_status: array of IRQ status reg storage created during init * @total_irqs: total number of irq_idx mapped in the hw_interrupts * @irq_lock: spinlock for accessing IRQ resources + * @irq_cb_tbl: array of IRQ callbacks lists + * @irq_counts: array of IRQ counts */ struct dpu_hw_intr { struct dpu_hw_blk_reg_map hw; - struct dpu_hw_intr_ops ops; u32 *cache_irq_mask; u32 *save_irq_status; u32 total_irqs; spinlock_t irq_lock; unsigned long irq_mask; + + struct list_head *irq_cb_tbl; + atomic_t *irq_counts; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c index cb6bb7a22c15..86363c0ec834 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. +/* + * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ #include "dpu_kms.h" @@ -24,6 +25,15 @@ #define LM_BLEND0_FG_ALPHA 0x04 #define LM_BLEND0_BG_ALPHA 0x08 +#define LM_MISR_CTRL 0x310 +#define LM_MISR_SIGNATURE 0x314 +#define LM_MISR_FRAME_COUNT_MASK 0xFF +#define LM_MISR_CTRL_ENABLE BIT(8) +#define LM_MISR_CTRL_STATUS BIT(9) +#define LM_MISR_CTRL_STATUS_CLEAR BIT(10) +#define LM_MISR_CTRL_FREE_RUN_MASK BIT(31) + + static const struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer, const struct dpu_mdss_cfg *m, void __iomem *addr, @@ -96,6 +106,48 @@ static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx, } } +static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx, bool enable, u32 frame_count) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 config = 0; + + DPU_REG_WRITE(c, LM_MISR_CTRL, LM_MISR_CTRL_STATUS_CLEAR); + + /* Clear old MISR value (in case it's read before a new value is calculated)*/ + wmb(); + + if (enable) { + config = (frame_count & LM_MISR_FRAME_COUNT_MASK) | + LM_MISR_CTRL_ENABLE | LM_MISR_CTRL_FREE_RUN_MASK; + + DPU_REG_WRITE(c, LM_MISR_CTRL, config); + } else { + DPU_REG_WRITE(c, LM_MISR_CTRL, 0); + } + +} + +static int dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx, u32 *misr_value) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 ctrl = 0; + + if (!misr_value) + return -EINVAL; + + ctrl = DPU_REG_READ(c, LM_MISR_CTRL); + + if (!(ctrl & LM_MISR_CTRL_ENABLE)) + return -EINVAL; + + if (!(ctrl & LM_MISR_CTRL_STATUS)) + return -EINVAL; + + *misr_value = DPU_REG_READ(c, LM_MISR_SIGNATURE); + + return 0; +} + static void dpu_hw_lm_setup_blend_config_sdm845(struct dpu_hw_mixer *ctx, u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op) { @@ -158,6 +210,8 @@ static void _setup_mixer_ops(const struct dpu_mdss_cfg *m, ops->setup_blend_config = dpu_hw_lm_setup_blend_config; ops->setup_alpha_out = dpu_hw_lm_setup_color3; ops->setup_border_color = dpu_hw_lm_setup_border_color; + ops->setup_misr = dpu_hw_lm_setup_misr; + ops->collect_misr = dpu_hw_lm_collect_misr; } struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h index 4a6b2de19ef6..d8052fb2d5da 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. +/* + * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ #ifndef _DPU_HW_LM_H @@ -53,6 +54,16 @@ struct dpu_hw_lm_ops { void (*setup_border_color)(struct dpu_hw_mixer *ctx, struct dpu_mdss_color *color, u8 border_en); + + /** + * setup_misr: Enable/disable MISR + */ + void (*setup_misr)(struct dpu_hw_mixer *ctx, bool enable, u32 frame_count); + + /** + * collect_misr: Read MISR signature + */ + int (*collect_misr)(struct dpu_hw_mixer *ctx, u32 *misr_value); }; struct dpu_hw_mixer { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c index 69eed7932486..f9460672176a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c @@ -138,11 +138,13 @@ static int _sspp_subblk_offset(struct dpu_hw_pipe *ctx, u32 *idx) { int rc = 0; - const struct dpu_sspp_sub_blks *sblk = ctx->cap->sblk; + const struct dpu_sspp_sub_blks *sblk; - if (!ctx) + if (!ctx || !ctx->cap || !ctx->cap->sblk) return -EINVAL; + sblk = ctx->cap->sblk; + switch (s_id) { case DPU_SSPP_SRC: *idx = sblk->src_blk.base; @@ -419,7 +421,7 @@ static void _dpu_hw_sspp_setup_scaler3(struct dpu_hw_pipe *ctx, (void)pe; if (_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx) || !sspp - || !scaler3_cfg || !ctx || !ctx->cap || !ctx->cap->sblk) + || !scaler3_cfg) return; dpu_hw_setup_scaler3(&ctx->hw, scaler3_cfg, idx, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h index ff3cffde84cd..6d4911957e33 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. +/* + * Copyright (c) 2015-2021, The Linux Foundation. All rights reserved. */ #ifndef _DPU_HW_UTIL_H diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index ae48f41821cf..a15b26428280 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -188,6 +188,7 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) struct dentry *entry; struct drm_device *dev; struct msm_drm_private *priv; + int i; if (!p) return -EINVAL; @@ -203,8 +204,10 @@ static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) dpu_debugfs_vbif_init(dpu_kms, entry); dpu_debugfs_core_irq_init(dpu_kms, entry); - if (priv->dp) - msm_dp_debugfs_init(priv->dp, minor); + for (i = 0; i < ARRAY_SIZE(priv->dp); i++) { + if (priv->dp[i]) + msm_dp_debugfs_init(priv->dp[i], minor); + } return dpu_core_perf_debugfs_init(dpu_kms, entry); } @@ -544,35 +547,42 @@ static int _dpu_kms_initialize_displayport(struct drm_device *dev, { struct drm_encoder *encoder = NULL; struct msm_display_info info; - int rc = 0; + int rc; + int i; - if (!priv->dp) - return rc; + for (i = 0; i < ARRAY_SIZE(priv->dp); i++) { + if (!priv->dp[i]) + continue; - encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_TMDS); - if (IS_ERR(encoder)) { - DPU_ERROR("encoder init failed for dsi display\n"); - return PTR_ERR(encoder); + encoder = dpu_encoder_init(dev, DRM_MODE_ENCODER_TMDS); + if (IS_ERR(encoder)) { + DPU_ERROR("encoder init failed for dsi display\n"); + return PTR_ERR(encoder); + } + + memset(&info, 0, sizeof(info)); + rc = msm_dp_modeset_init(priv->dp[i], dev, encoder); + if (rc) { + DPU_ERROR("modeset_init failed for DP, rc = %d\n", rc); + drm_encoder_cleanup(encoder); + return rc; + } + + priv->encoders[priv->num_encoders++] = encoder; + + info.num_of_h_tiles = 1; + info.h_tile_instance[0] = i; + info.capabilities = MSM_DISPLAY_CAP_VID_MODE; + info.intf_type = encoder->encoder_type; + rc = dpu_encoder_setup(dev, encoder, &info); + if (rc) { + DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n", + encoder->base.id, rc); + return rc; + } } - memset(&info, 0, sizeof(info)); - rc = msm_dp_modeset_init(priv->dp, dev, encoder); - if (rc) { - DPU_ERROR("modeset_init failed for DP, rc = %d\n", rc); - drm_encoder_cleanup(encoder); - return rc; - } - - priv->encoders[priv->num_encoders++] = encoder; - - info.num_of_h_tiles = 1; - info.capabilities = MSM_DISPLAY_CAP_VID_MODE; - info.intf_type = encoder->encoder_type; - rc = dpu_encoder_setup(dev, encoder, &info); - if (rc) - DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n", - encoder->base.id, rc); - return rc; + return 0; } /** @@ -792,6 +802,7 @@ static int dpu_irq_postinstall(struct msm_kms *kms) { struct msm_drm_private *priv; struct dpu_kms *dpu_kms = to_dpu_kms(kms); + int i; if (!dpu_kms || !dpu_kms->dev) return -EINVAL; @@ -800,7 +811,8 @@ static int dpu_irq_postinstall(struct msm_kms *kms) if (!priv) return -EINVAL; - msm_dp_irq_postinstall(priv->dp); + for (i = 0; i < ARRAY_SIZE(priv->dp); i++) + msm_dp_irq_postinstall(priv->dp[i]); return 0; } @@ -908,6 +920,10 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms) return 0; mmu = msm_iommu_new(dpu_kms->dev->dev, domain); + if (IS_ERR(mmu)) { + iommu_domain_free(domain); + return PTR_ERR(mmu); + } aspace = msm_gem_address_space_create(mmu, "dpu1", 0x1000, 0x100000000 - 0x1000); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 323a6bce9e64..775bcbda860f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -78,18 +78,6 @@ struct dpu_irq_callback { void *arg; }; -/** - * struct dpu_irq: IRQ structure contains callback registration info - * @total_irq: total number of irq_idx obtained from HW interrupts mapping - * @irq_cb_tbl: array of IRQ callbacks setting - * @debugfs_file: debugfs file for irq statistics - */ -struct dpu_irq { - u32 total_irqs; - struct list_head *irq_cb_tbl; - atomic_t *irq_counts; -}; - struct dpu_kms { struct msm_kms base; struct drm_device *dev; @@ -104,7 +92,6 @@ struct dpu_kms { struct regulator *venus; struct dpu_hw_intr *hw_intr; - struct dpu_irq irq_obj; struct dpu_core_perf perf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index c989621209aa..a3e3b9d1b82e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -1193,7 +1193,7 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane) if (DPU_FORMAT_IS_YUV(fmt)) _dpu_plane_setup_csc(pdpu); else - pdpu->csc_ptr = 0; + pdpu->csc_ptr = NULL; } _dpu_plane_set_qos_lut(plane, fb); @@ -1330,7 +1330,7 @@ static void dpu_plane_reset(struct drm_plane *plane) /* remove previous state, if present */ if (plane->state) { dpu_plane_destroy_state(plane, plane->state); - plane->state = 0; + plane->state = NULL; } pstate = kzalloc(sizeof(*pstate), GFP_KERNEL); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index cdcaf470f148..5a33bb148e9e 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -173,12 +173,9 @@ int mdp4_disable(struct mdp4_kms *mdp4_kms) DBG(""); clk_disable_unprepare(mdp4_kms->clk); - if (mdp4_kms->pclk) - clk_disable_unprepare(mdp4_kms->pclk); - if (mdp4_kms->lut_clk) - clk_disable_unprepare(mdp4_kms->lut_clk); - if (mdp4_kms->axi_clk) - clk_disable_unprepare(mdp4_kms->axi_clk); + clk_disable_unprepare(mdp4_kms->pclk); + clk_disable_unprepare(mdp4_kms->lut_clk); + clk_disable_unprepare(mdp4_kms->axi_clk); return 0; } @@ -188,12 +185,9 @@ int mdp4_enable(struct mdp4_kms *mdp4_kms) DBG(""); clk_prepare_enable(mdp4_kms->clk); - if (mdp4_kms->pclk) - clk_prepare_enable(mdp4_kms->pclk); - if (mdp4_kms->lut_clk) - clk_prepare_enable(mdp4_kms->lut_clk); - if (mdp4_kms->axi_clk) - clk_prepare_enable(mdp4_kms->axi_clk); + clk_prepare_enable(mdp4_kms->pclk); + clk_prepare_enable(mdp4_kms->lut_clk); + clk_prepare_enable(mdp4_kms->axi_clk); return 0; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c index 9741544ffc35..1bf9ff5dbabc 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c @@ -752,6 +752,94 @@ const struct mdp5_cfg_hw msm8x76_config = { .max_clk = 360000000, }; +static const struct mdp5_cfg_hw msm8x53_config = { + .name = "msm8x53", + .mdp = { + .count = 1, + .caps = MDP_CAP_CDM | + MDP_CAP_SRC_SPLIT, + }, + .ctl = { + .count = 3, + .base = { 0x01000, 0x01200, 0x01400 }, + .flush_hw_mask = 0xffffffff, + }, + .pipe_vig = { + .count = 1, + .base = { 0x04000 }, + .caps = MDP_PIPE_CAP_HFLIP | + MDP_PIPE_CAP_VFLIP | + MDP_PIPE_CAP_SCALE | + MDP_PIPE_CAP_CSC | + MDP_PIPE_CAP_DECIMATION | + MDP_PIPE_CAP_SW_PIX_EXT | + 0, + }, + .pipe_rgb = { + .count = 2, + .base = { 0x14000, 0x16000 }, + .caps = MDP_PIPE_CAP_HFLIP | + MDP_PIPE_CAP_VFLIP | + MDP_PIPE_CAP_DECIMATION | + MDP_PIPE_CAP_SW_PIX_EXT | + 0, + }, + .pipe_dma = { + .count = 1, + .base = { 0x24000 }, + .caps = MDP_PIPE_CAP_HFLIP | + MDP_PIPE_CAP_VFLIP | + MDP_PIPE_CAP_SW_PIX_EXT | + 0, + }, + .pipe_cursor = { + .count = 1, + .base = { 0x34000 }, + .caps = MDP_PIPE_CAP_HFLIP | + MDP_PIPE_CAP_VFLIP | + MDP_PIPE_CAP_SW_PIX_EXT | + MDP_PIPE_CAP_CURSOR | + 0, + }, + + .lm = { + .count = 3, + .base = { 0x44000, 0x45000 }, + .instances = { + { .id = 0, .pp = 0, .dspp = 0, + .caps = MDP_LM_CAP_DISPLAY | + MDP_LM_CAP_PAIR }, + { .id = 1, .pp = 1, .dspp = -1, + .caps = MDP_LM_CAP_DISPLAY }, + }, + .nb_stages = 5, + .max_width = 2048, + .max_height = 0xFFFF, + }, + .dspp = { + .count = 1, + .base = { 0x54000 }, + + }, + .pp = { + .count = 2, + .base = { 0x70000, 0x70800 }, + }, + .cdm = { + .count = 1, + .base = { 0x79200 }, + }, + .intf = { + .base = { 0x6a000, 0x6a800, 0x6b000 }, + .connect = { + [0] = INTF_DISABLED, + [1] = INTF_DSI, + [2] = INTF_DSI, + }, + }, + .max_clk = 400000000, +}; + static const struct mdp5_cfg_hw msm8917_config = { .name = "msm8917", .mdp = { @@ -1151,6 +1239,7 @@ static const struct mdp5_cfg_handler cfg_handlers_v1[] = { { .revision = 7, .config = { .hw = &msm8x96_config } }, { .revision = 11, .config = { .hw = &msm8x76_config } }, { .revision = 15, .config = { .hw = &msm8917_config } }, + { .revision = 16, .config = { .hw = &msm8x53_config } }, }; static const struct mdp5_cfg_handler cfg_handlers_v3[] = { diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index b3b42672b2d4..7b242246d4e7 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -295,15 +295,12 @@ static int mdp5_disable(struct mdp5_kms *mdp5_kms) mdp5_kms->enable_count--; WARN_ON(mdp5_kms->enable_count < 0); - if (mdp5_kms->tbu_rt_clk) - clk_disable_unprepare(mdp5_kms->tbu_rt_clk); - if (mdp5_kms->tbu_clk) - clk_disable_unprepare(mdp5_kms->tbu_clk); + clk_disable_unprepare(mdp5_kms->tbu_rt_clk); + clk_disable_unprepare(mdp5_kms->tbu_clk); clk_disable_unprepare(mdp5_kms->ahb_clk); clk_disable_unprepare(mdp5_kms->axi_clk); clk_disable_unprepare(mdp5_kms->core_clk); - if (mdp5_kms->lut_clk) - clk_disable_unprepare(mdp5_kms->lut_clk); + clk_disable_unprepare(mdp5_kms->lut_clk); return 0; } @@ -317,12 +314,9 @@ static int mdp5_enable(struct mdp5_kms *mdp5_kms) clk_prepare_enable(mdp5_kms->ahb_clk); clk_prepare_enable(mdp5_kms->axi_clk); clk_prepare_enable(mdp5_kms->core_clk); - if (mdp5_kms->lut_clk) - clk_prepare_enable(mdp5_kms->lut_clk); - if (mdp5_kms->tbu_clk) - clk_prepare_enable(mdp5_kms->tbu_clk); - if (mdp5_kms->tbu_rt_clk) - clk_prepare_enable(mdp5_kms->tbu_rt_clk); + clk_prepare_enable(mdp5_kms->lut_clk); + clk_prepare_enable(mdp5_kms->tbu_clk); + clk_prepare_enable(mdp5_kms->tbu_rt_clk); return 0; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c index 2f4895bcb0b0..0ea53420bc40 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c @@ -136,10 +136,8 @@ static int mdp5_mdss_enable(struct msm_mdss *mdss) DBG(""); clk_prepare_enable(mdp5_mdss->ahb_clk); - if (mdp5_mdss->axi_clk) - clk_prepare_enable(mdp5_mdss->axi_clk); - if (mdp5_mdss->vsync_clk) - clk_prepare_enable(mdp5_mdss->vsync_clk); + clk_prepare_enable(mdp5_mdss->axi_clk); + clk_prepare_enable(mdp5_mdss->vsync_clk); return 0; } @@ -149,10 +147,8 @@ static int mdp5_mdss_disable(struct msm_mdss *mdss) struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss); DBG(""); - if (mdp5_mdss->vsync_clk) - clk_disable_unprepare(mdp5_mdss->vsync_clk); - if (mdp5_mdss->axi_clk) - clk_disable_unprepare(mdp5_mdss->axi_clk); + clk_disable_unprepare(mdp5_mdss->vsync_clk); + clk_disable_unprepare(mdp5_mdss->axi_clk); clk_disable_unprepare(mdp5_mdss->ahb_clk); return 0; diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index cabe15190ec1..2e1acb1bc390 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -126,8 +126,12 @@ void msm_disp_snapshot_capture_state(struct msm_disp_state *disp_state) priv = drm_dev->dev_private; kms = priv->kms; - if (priv->dp) - msm_dp_snapshot(disp_state, priv->dp); + for (i = 0; i < ARRAY_SIZE(priv->dp); i++) { + if (!priv->dp[i]) + continue; + + msm_dp_snapshot(disp_state, priv->dp[i]); + } for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) { if (!priv->dsi[i]) diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index cc2bb8295329..6ae9b29044b6 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -24,15 +24,6 @@ #define DP_INTERRUPT_STATUS_ACK_SHIFT 1 #define DP_INTERRUPT_STATUS_MASK_SHIFT 2 -#define MSM_DP_CONTROLLER_AHB_OFFSET 0x0000 -#define MSM_DP_CONTROLLER_AHB_SIZE 0x0200 -#define MSM_DP_CONTROLLER_AUX_OFFSET 0x0200 -#define MSM_DP_CONTROLLER_AUX_SIZE 0x0200 -#define MSM_DP_CONTROLLER_LINK_OFFSET 0x0400 -#define MSM_DP_CONTROLLER_LINK_SIZE 0x0C00 -#define MSM_DP_CONTROLLER_P0_OFFSET 0x1000 -#define MSM_DP_CONTROLLER_P0_SIZE 0x0400 - #define DP_INTERRUPT_STATUS1 \ (DP_INTR_AUX_I2C_DONE| \ DP_INTR_WRONG_ADDR | DP_INTR_TIMEOUT | \ @@ -66,82 +57,77 @@ void dp_catalog_snapshot(struct dp_catalog *dp_catalog, struct msm_disp_state *d { struct dp_catalog_private *catalog = container_of(dp_catalog, struct dp_catalog_private, dp_catalog); + struct dss_io_data *dss = &catalog->io->dp_controller; - msm_disp_snapshot_add_block(disp_state, catalog->io->dp_controller.len, - catalog->io->dp_controller.base, "dp_ctrl"); + msm_disp_snapshot_add_block(disp_state, dss->ahb.len, dss->ahb.base, "dp_ahb"); + msm_disp_snapshot_add_block(disp_state, dss->aux.len, dss->aux.base, "dp_aux"); + msm_disp_snapshot_add_block(disp_state, dss->link.len, dss->link.base, "dp_link"); + msm_disp_snapshot_add_block(disp_state, dss->p0.len, dss->p0.base, "dp_p0"); } static inline u32 dp_read_aux(struct dp_catalog_private *catalog, u32 offset) { - offset += MSM_DP_CONTROLLER_AUX_OFFSET; - return readl_relaxed(catalog->io->dp_controller.base + offset); + return readl_relaxed(catalog->io->dp_controller.aux.base + offset); } static inline void dp_write_aux(struct dp_catalog_private *catalog, u32 offset, u32 data) { - offset += MSM_DP_CONTROLLER_AUX_OFFSET; /* * To make sure aux reg writes happens before any other operation, * this function uses writel() instread of writel_relaxed() */ - writel(data, catalog->io->dp_controller.base + offset); + writel(data, catalog->io->dp_controller.aux.base + offset); } static inline u32 dp_read_ahb(struct dp_catalog_private *catalog, u32 offset) { - offset += MSM_DP_CONTROLLER_AHB_OFFSET; - return readl_relaxed(catalog->io->dp_controller.base + offset); + return readl_relaxed(catalog->io->dp_controller.ahb.base + offset); } static inline void dp_write_ahb(struct dp_catalog_private *catalog, u32 offset, u32 data) { - offset += MSM_DP_CONTROLLER_AHB_OFFSET; /* * To make sure phy reg writes happens before any other operation, * this function uses writel() instread of writel_relaxed() */ - writel(data, catalog->io->dp_controller.base + offset); + writel(data, catalog->io->dp_controller.ahb.base + offset); } static inline void dp_write_p0(struct dp_catalog_private *catalog, u32 offset, u32 data) { - offset += MSM_DP_CONTROLLER_P0_OFFSET; /* * To make sure interface reg writes happens before any other operation, * this function uses writel() instread of writel_relaxed() */ - writel(data, catalog->io->dp_controller.base + offset); + writel(data, catalog->io->dp_controller.p0.base + offset); } static inline u32 dp_read_p0(struct dp_catalog_private *catalog, u32 offset) { - offset += MSM_DP_CONTROLLER_P0_OFFSET; /* * To make sure interface reg writes happens before any other operation, * this function uses writel() instread of writel_relaxed() */ - return readl_relaxed(catalog->io->dp_controller.base + offset); + return readl_relaxed(catalog->io->dp_controller.p0.base + offset); } static inline u32 dp_read_link(struct dp_catalog_private *catalog, u32 offset) { - offset += MSM_DP_CONTROLLER_LINK_OFFSET; - return readl_relaxed(catalog->io->dp_controller.base + offset); + return readl_relaxed(catalog->io->dp_controller.link.base + offset); } static inline void dp_write_link(struct dp_catalog_private *catalog, u32 offset, u32 data) { - offset += MSM_DP_CONTROLLER_LINK_OFFSET; /* * To make sure link reg writes happens before any other operation, * this function uses writel() instread of writel_relaxed() */ - writel(data, catalog->io->dp_controller.base + offset); + writel(data, catalog->io->dp_controller.link.base + offset); } /* aux related catalog functions */ @@ -276,29 +262,21 @@ static void dump_regs(void __iomem *base, int len) void dp_catalog_dump_regs(struct dp_catalog *dp_catalog) { - u32 offset, len; struct dp_catalog_private *catalog = container_of(dp_catalog, struct dp_catalog_private, dp_catalog); + struct dss_io_data *io = &catalog->io->dp_controller; pr_info("AHB regs\n"); - offset = MSM_DP_CONTROLLER_AHB_OFFSET; - len = MSM_DP_CONTROLLER_AHB_SIZE; - dump_regs(catalog->io->dp_controller.base + offset, len); + dump_regs(io->ahb.base, io->ahb.len); pr_info("AUXCLK regs\n"); - offset = MSM_DP_CONTROLLER_AUX_OFFSET; - len = MSM_DP_CONTROLLER_AUX_SIZE; - dump_regs(catalog->io->dp_controller.base + offset, len); + dump_regs(io->aux.base, io->aux.len); pr_info("LCLK regs\n"); - offset = MSM_DP_CONTROLLER_LINK_OFFSET; - len = MSM_DP_CONTROLLER_LINK_SIZE; - dump_regs(catalog->io->dp_controller.base + offset, len); + dump_regs(io->link.base, io->link.len); pr_info("P0CLK regs\n"); - offset = MSM_DP_CONTROLLER_P0_OFFSET; - len = MSM_DP_CONTROLLER_P0_SIZE; - dump_regs(catalog->io->dp_controller.base + offset, len); + dump_regs(io->p0.base, io->p0.len); } u32 dp_catalog_aux_get_irq(struct dp_catalog *dp_catalog) @@ -493,8 +471,7 @@ int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog, bit = BIT(pattern - 1) << DP_MAINLINK_READY_LINK_TRAINING_SHIFT; /* Poll for mainlink ready status */ - ret = readx_poll_timeout(readl, catalog->io->dp_controller.base + - MSM_DP_CONTROLLER_LINK_OFFSET + + ret = readx_poll_timeout(readl, catalog->io->dp_controller.link.base + REG_DP_MAINLINK_READY, data, data & bit, POLLING_SLEEP_US, POLLING_TIMEOUT_US); @@ -541,8 +518,7 @@ bool dp_catalog_ctrl_mainlink_ready(struct dp_catalog *dp_catalog) struct dp_catalog_private, dp_catalog); /* Poll for mainlink ready status */ - ret = readl_poll_timeout(catalog->io->dp_controller.base + - MSM_DP_CONTROLLER_LINK_OFFSET + + ret = readl_poll_timeout(catalog->io->dp_controller.link.base + REG_DP_MAINLINK_READY, data, data & DP_MAINLINK_READY_FOR_VIDEO, POLLING_SLEEP_US, POLLING_TIMEOUT_US); diff --git a/drivers/gpu/drm/msm/dp/dp_debug.c b/drivers/gpu/drm/msm/dp/dp_debug.c index 2f6247e80e9d..da4323556ef3 100644 --- a/drivers/gpu/drm/msm/dp/dp_debug.c +++ b/drivers/gpu/drm/msm/dp/dp_debug.c @@ -24,240 +24,108 @@ struct dp_debug_private { struct dp_usbpd *usbpd; struct dp_link *link; struct dp_panel *panel; - struct drm_connector **connector; + struct drm_connector *connector; struct device *dev; struct drm_device *drm_dev; struct dp_debug dp_debug; }; -static int dp_debug_check_buffer_overflow(int rc, int *max_size, int *len) +static int dp_debug_show(struct seq_file *seq, void *p) { - if (rc >= *max_size) { - DRM_ERROR("buffer overflow\n"); - return -EINVAL; - } - *len += rc; - *max_size = SZ_4K - *len; - - return 0; -} - -static ssize_t dp_debug_read_info(struct file *file, char __user *user_buff, - size_t count, loff_t *ppos) -{ - struct dp_debug_private *debug = file->private_data; - char *buf; - u32 len = 0, rc = 0; + struct dp_debug_private *debug = seq->private; u64 lclk = 0; - u32 max_size = SZ_4K; u32 link_params_rate; - struct drm_display_mode *drm_mode; + const struct drm_display_mode *drm_mode; if (!debug) return -ENODEV; - if (*ppos) - return 0; - - buf = kzalloc(SZ_4K, GFP_KERNEL); - if (!buf) - return -ENOMEM; - drm_mode = &debug->panel->dp_mode.drm_mode; - rc = snprintf(buf + len, max_size, "\tname = %s\n", DEBUG_NAME); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\tdp_panel\n\t\tmax_pclk_khz = %d\n", + seq_printf(seq, "\tname = %s\n", DEBUG_NAME); + seq_printf(seq, "\tdp_panel\n\t\tmax_pclk_khz = %d\n", debug->panel->max_pclk_khz); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\tdrm_dp_link\n\t\trate = %u\n", + seq_printf(seq, "\tdrm_dp_link\n\t\trate = %u\n", debug->panel->link_info.rate); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tnum_lanes = %u\n", + seq_printf(seq, "\t\tnum_lanes = %u\n", debug->panel->link_info.num_lanes); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tcapabilities = %lu\n", + seq_printf(seq, "\t\tcapabilities = %lu\n", debug->panel->link_info.capabilities); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\tdp_panel_info:\n\t\tactive = %dx%d\n", + seq_printf(seq, "\tdp_panel_info:\n\t\tactive = %dx%d\n", drm_mode->hdisplay, drm_mode->vdisplay); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tback_porch = %dx%d\n", + seq_printf(seq, "\t\tback_porch = %dx%d\n", drm_mode->htotal - drm_mode->hsync_end, drm_mode->vtotal - drm_mode->vsync_end); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tfront_porch = %dx%d\n", + seq_printf(seq, "\t\tfront_porch = %dx%d\n", drm_mode->hsync_start - drm_mode->hdisplay, drm_mode->vsync_start - drm_mode->vdisplay); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tsync_width = %dx%d\n", + seq_printf(seq, "\t\tsync_width = %dx%d\n", drm_mode->hsync_end - drm_mode->hsync_start, drm_mode->vsync_end - drm_mode->vsync_start); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tactive_low = %dx%d\n", + seq_printf(seq, "\t\tactive_low = %dx%d\n", debug->panel->dp_mode.h_active_low, debug->panel->dp_mode.v_active_low); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\th_skew = %d\n", + seq_printf(seq, "\t\th_skew = %d\n", drm_mode->hskew); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\trefresh rate = %d\n", + seq_printf(seq, "\t\trefresh rate = %d\n", drm_mode_vrefresh(drm_mode)); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tpixel clock khz = %d\n", + seq_printf(seq, "\t\tpixel clock khz = %d\n", drm_mode->clock); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tbpp = %d\n", + seq_printf(seq, "\t\tbpp = %d\n", debug->panel->dp_mode.bpp); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; /* Link Information */ - rc = snprintf(buf + len, max_size, - "\tdp_link:\n\t\ttest_requested = %d\n", + seq_printf(seq, "\tdp_link:\n\t\ttest_requested = %d\n", debug->link->sink_request); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tnum_lanes = %d\n", + seq_printf(seq, "\t\tnum_lanes = %d\n", debug->link->link_params.num_lanes); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - link_params_rate = debug->link->link_params.rate; - rc = snprintf(buf + len, max_size, - "\t\tbw_code = %d\n", + seq_printf(seq, "\t\tbw_code = %d\n", drm_dp_link_rate_to_bw_code(link_params_rate)); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - lclk = debug->link->link_params.rate * 1000; - rc = snprintf(buf + len, max_size, - "\t\tlclk = %lld\n", lclk); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tv_level = %d\n", + seq_printf(seq, "\t\tlclk = %lld\n", lclk); + seq_printf(seq, "\t\tv_level = %d\n", debug->link->phy_params.v_level); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - - rc = snprintf(buf + len, max_size, - "\t\tp_level = %d\n", + seq_printf(seq, "\t\tp_level = %d\n", debug->link->phy_params.p_level); - if (dp_debug_check_buffer_overflow(rc, &max_size, &len)) - goto error; - if (copy_to_user(user_buff, buf, len)) - goto error; - - *ppos += len; - - kfree(buf); - return len; - error: - kfree(buf); - return -EINVAL; + return 0; } +DEFINE_SHOW_ATTRIBUTE(dp_debug); static int dp_test_data_show(struct seq_file *m, void *data) { - struct drm_device *dev; - struct dp_debug_private *debug; - struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; + const struct dp_debug_private *debug = m->private; + const struct drm_connector *connector = debug->connector; u32 bpc; - debug = m->private; - dev = debug->drm_dev; - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - - if (connector->connector_type != - DRM_MODE_CONNECTOR_DisplayPort) - continue; - - if (connector->status == connector_status_connected) { - bpc = debug->link->test_video.test_bit_depth; - seq_printf(m, "hdisplay: %d\n", - debug->link->test_video.test_h_width); - seq_printf(m, "vdisplay: %d\n", - debug->link->test_video.test_v_height); - seq_printf(m, "bpc: %u\n", - dp_link_bit_depth_to_bpc(bpc)); - } else - seq_puts(m, "0"); + if (connector->status == connector_status_connected) { + bpc = debug->link->test_video.test_bit_depth; + seq_printf(m, "hdisplay: %d\n", + debug->link->test_video.test_h_width); + seq_printf(m, "vdisplay: %d\n", + debug->link->test_video.test_v_height); + seq_printf(m, "bpc: %u\n", + dp_link_bit_depth_to_bpc(bpc)); + } else { + seq_puts(m, "0"); } - drm_connector_list_iter_end(&conn_iter); - return 0; } DEFINE_SHOW_ATTRIBUTE(dp_test_data); static int dp_test_type_show(struct seq_file *m, void *data) { - struct dp_debug_private *debug = m->private; - struct drm_device *dev = debug->drm_dev; - struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; + const struct dp_debug_private *debug = m->private; + const struct drm_connector *connector = debug->connector; - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - - if (connector->connector_type != - DRM_MODE_CONNECTOR_DisplayPort) - continue; - - if (connector->status == connector_status_connected) - seq_printf(m, "%02x", DP_TEST_LINK_VIDEO_PATTERN); - else - seq_puts(m, "0"); - } - drm_connector_list_iter_end(&conn_iter); + if (connector->status == connector_status_connected) + seq_printf(m, "%02x", DP_TEST_LINK_VIDEO_PATTERN); + else + seq_puts(m, "0"); return 0; } @@ -269,14 +137,12 @@ static ssize_t dp_test_active_write(struct file *file, { char *input_buffer; int status = 0; - struct dp_debug_private *debug; - struct drm_device *dev; - struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; + const struct dp_debug_private *debug; + const struct drm_connector *connector; int val = 0; debug = ((struct seq_file *)file->private_data)->private; - dev = debug->drm_dev; + connector = debug->connector; if (len == 0) return 0; @@ -287,30 +153,22 @@ static ssize_t dp_test_active_write(struct file *file, DRM_DEBUG_DRIVER("Copied %d bytes from user\n", (unsigned int)len); - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - if (connector->connector_type != - DRM_MODE_CONNECTOR_DisplayPort) - continue; - - if (connector->status == connector_status_connected) { - status = kstrtoint(input_buffer, 10, &val); - if (status < 0) - break; - DRM_DEBUG_DRIVER("Got %d for test active\n", val); - /* To prevent erroneous activation of the compliance - * testing code, only accept an actual value of 1 here - */ - if (val == 1) - debug->panel->video_test = true; - else - debug->panel->video_test = false; + if (connector->status == connector_status_connected) { + status = kstrtoint(input_buffer, 10, &val); + if (status < 0) { + kfree(input_buffer); + return status; } + DRM_DEBUG_DRIVER("Got %d for test active\n", val); + /* To prevent erroneous activation of the compliance + * testing code, only accept an actual value of 1 here + */ + if (val == 1) + debug->panel->video_test = true; + else + debug->panel->video_test = false; } - drm_connector_list_iter_end(&conn_iter); kfree(input_buffer); - if (status < 0) - return status; *offp += len; return len; @@ -319,25 +177,16 @@ static ssize_t dp_test_active_write(struct file *file, static int dp_test_active_show(struct seq_file *m, void *data) { struct dp_debug_private *debug = m->private; - struct drm_device *dev = debug->drm_dev; - struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; + struct drm_connector *connector = debug->connector; - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - if (connector->connector_type != - DRM_MODE_CONNECTOR_DisplayPort) - continue; - - if (connector->status == connector_status_connected) { - if (debug->panel->video_test) - seq_puts(m, "1"); - else - seq_puts(m, "0"); - } else + if (connector->status == connector_status_connected) { + if (debug->panel->video_test) + seq_puts(m, "1"); + else seq_puts(m, "0"); + } else { + seq_puts(m, "0"); } - drm_connector_list_iter_end(&conn_iter); return 0; } @@ -349,11 +198,6 @@ static int dp_test_active_open(struct inode *inode, inode->i_private); } -static const struct file_operations dp_debug_fops = { - .open = simple_open, - .read = dp_debug_read_info, -}; - static const struct file_operations test_active_fops = { .owner = THIS_MODULE, .open = dp_test_active_open, @@ -391,7 +235,7 @@ static int dp_debug_init(struct dp_debug *dp_debug, struct drm_minor *minor) struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, struct dp_usbpd *usbpd, struct dp_link *link, - struct drm_connector **connector, struct drm_minor *minor) + struct drm_connector *connector, struct drm_minor *minor) { int rc = 0; struct dp_debug_private *debug; diff --git a/drivers/gpu/drm/msm/dp/dp_debug.h b/drivers/gpu/drm/msm/dp/dp_debug.h index 7eaedfbb149c..8c0d0b5178fd 100644 --- a/drivers/gpu/drm/msm/dp/dp_debug.h +++ b/drivers/gpu/drm/msm/dp/dp_debug.h @@ -43,7 +43,7 @@ struct dp_debug { */ struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, struct dp_usbpd *usbpd, struct dp_link *link, - struct drm_connector **connector, + struct drm_connector *connector, struct drm_minor *minor); /** @@ -60,7 +60,7 @@ void dp_debug_put(struct dp_debug *dp_debug); static inline struct dp_debug *dp_debug_get(struct device *dev, struct dp_panel *panel, struct dp_usbpd *usbpd, struct dp_link *link, - struct drm_connector **connector, struct drm_minor *minor) + struct drm_connector *connector, struct drm_minor *minor) { return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index a0392e4d8134..aba8aa47ed76 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "msm_drv.h" #include "msm_kms.h" @@ -27,7 +28,6 @@ #include "dp_audio.h" #include "dp_debug.h" -static struct msm_dp *g_dp_display; #define HPD_STRING_SIZE 30 enum { @@ -79,6 +79,8 @@ struct dp_display_private { char *name; int irq; + unsigned int id; + /* state variables */ bool core_initialized; bool hpd_irq_on; @@ -116,11 +118,35 @@ struct dp_display_private { struct dp_audio *audio; }; +struct msm_dp_desc { + phys_addr_t io_start; + unsigned int connector_type; +}; + +struct msm_dp_config { + const struct msm_dp_desc *descs; + size_t num_descs; +}; + +static const struct msm_dp_config sc7180_dp_cfg = { + .descs = (const struct msm_dp_desc[]) { + [MSM_DP_CONTROLLER_0] = { .io_start = 0x0ae90000, .connector_type = DRM_MODE_CONNECTOR_DisplayPort }, + }, + .num_descs = 1, +}; + static const struct of_device_id dp_dt_match[] = { - {.compatible = "qcom,sc7180-dp"}, + { .compatible = "qcom,sc7180-dp", .data = &sc7180_dp_cfg }, {} }; +static struct dp_display_private *dev_get_dp_display_private(struct device *dev) +{ + struct msm_dp *dp = dev_get_drvdata(dev); + + return container_of(dp, struct dp_display_private, dp_display); +} + static int dp_add_event(struct dp_display_private *dp_priv, u32 event, u32 data, u32 delay) { @@ -197,25 +223,24 @@ static int dp_display_bind(struct device *dev, struct device *master, void *data) { int rc = 0; - struct dp_display_private *dp; - struct drm_device *drm; + struct dp_display_private *dp = dev_get_dp_display_private(dev); struct msm_drm_private *priv; + struct drm_device *drm; drm = dev_get_drvdata(master); - dp = container_of(g_dp_display, - struct dp_display_private, dp_display); - dp->dp_display.drm_dev = drm; priv = drm->dev_private; - priv->dp = &(dp->dp_display); + priv->dp[dp->id] = &dp->dp_display; - rc = dp->parser->parse(dp->parser); + rc = dp->parser->parse(dp->parser, dp->dp_display.connector_type); if (rc) { DRM_ERROR("device tree parsing failed\n"); goto end; } + dp->dp_display.panel_bridge = dp->parser->panel_bridge; + dp->aux->drm_dev = drm; rc = dp_aux_register(dp->aux); if (rc) { @@ -240,16 +265,13 @@ end: static void dp_display_unbind(struct device *dev, struct device *master, void *data) { - struct dp_display_private *dp; + struct dp_display_private *dp = dev_get_dp_display_private(dev); struct drm_device *drm = dev_get_drvdata(master); struct msm_drm_private *priv = drm->dev_private; - dp = container_of(g_dp_display, - struct dp_display_private, dp_display); - dp_power_client_deinit(dp->power); dp_aux_unregister(dp->aux); - priv->dp = NULL; + priv->dp[dp->id] = NULL; } static const struct component_ops dp_display_comp_ops = { @@ -379,38 +401,17 @@ static void dp_display_host_deinit(struct dp_display_private *dp) static int dp_display_usbpd_configure_cb(struct device *dev) { - int rc = 0; - struct dp_display_private *dp; - - if (!dev) { - DRM_ERROR("invalid dev\n"); - rc = -EINVAL; - goto end; - } - - dp = container_of(g_dp_display, - struct dp_display_private, dp_display); + struct dp_display_private *dp = dev_get_dp_display_private(dev); dp_display_host_init(dp, false); - rc = dp_display_process_hpd_high(dp); -end: - return rc; + return dp_display_process_hpd_high(dp); } static int dp_display_usbpd_disconnect_cb(struct device *dev) { int rc = 0; - struct dp_display_private *dp; - - if (!dev) { - DRM_ERROR("invalid dev\n"); - rc = -EINVAL; - return rc; - } - - dp = container_of(g_dp_display, - struct dp_display_private, dp_display); + struct dp_display_private *dp = dev_get_dp_display_private(dev); dp_add_event(dp, EV_USER_NOTIFICATION, false, 0); @@ -472,15 +473,7 @@ static int dp_display_usbpd_attention_cb(struct device *dev) { int rc = 0; u32 sink_request; - struct dp_display_private *dp; - - if (!dev) { - DRM_ERROR("invalid dev\n"); - return -EINVAL; - } - - dp = container_of(g_dp_display, - struct dp_display_private, dp_display); + struct dp_display_private *dp = dev_get_dp_display_private(dev); /* check for any test request issued by sink */ rc = dp_link_process_request(dp->link); @@ -647,7 +640,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) DRM_DEBUG_DP("hpd_state=%d\n", state); /* signal the disconnect event early to ensure proper teardown */ - dp_display_handle_plugged_change(g_dp_display, false); + dp_display_handle_plugged_change(&dp->dp_display, false); /* enable HDP plug interrupt to prepare for next plugin */ dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK, true); @@ -834,7 +827,7 @@ static int dp_display_set_mode(struct msm_dp *dp_display, return 0; } -static int dp_display_prepare(struct msm_dp *dp) +static int dp_display_prepare(struct msm_dp *dp_display) { return 0; } @@ -842,9 +835,7 @@ static int dp_display_prepare(struct msm_dp *dp) static int dp_display_enable(struct dp_display_private *dp, u32 data) { int rc = 0; - struct msm_dp *dp_display; - - dp_display = g_dp_display; + struct msm_dp *dp_display = &dp->dp_display; DRM_DEBUG_DP("sink_count=%d\n", dp->link->sink_count); if (dp_display->power_on) { @@ -880,9 +871,7 @@ static int dp_display_post_enable(struct msm_dp *dp_display) static int dp_display_disable(struct dp_display_private *dp, u32 data) { - struct msm_dp *dp_display; - - dp_display = g_dp_display; + struct msm_dp *dp_display = &dp->dp_display; if (!dp_display->power_on) return 0; @@ -912,7 +901,7 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data) return 0; } -static int dp_display_unprepare(struct msm_dp *dp) +static int dp_display_unprepare(struct msm_dp *dp_display) { return 0; } @@ -1213,10 +1202,33 @@ int dp_display_request_irq(struct msm_dp *dp_display) return 0; } +static const struct msm_dp_desc *dp_display_get_desc(struct platform_device *pdev, + unsigned int *id) +{ + const struct msm_dp_config *cfg = of_device_get_match_data(&pdev->dev); + struct resource *res; + int i; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return NULL; + + for (i = 0; i < cfg->num_descs; i++) { + if (cfg->descs[i].io_start == res->start) { + *id = i; + return &cfg->descs[i]; + } + } + + dev_err(&pdev->dev, "unknown displayport instance\n"); + return NULL; +} + static int dp_display_probe(struct platform_device *pdev) { int rc = 0; struct dp_display_private *dp; + const struct msm_dp_desc *desc; if (!pdev || !pdev->dev.of_node) { DRM_ERROR("pdev not found\n"); @@ -1227,8 +1239,13 @@ static int dp_display_probe(struct platform_device *pdev) if (!dp) return -ENOMEM; + desc = dp_display_get_desc(pdev, &dp->id); + if (!desc) + return -EINVAL; + dp->pdev = pdev; dp->name = "drm_dp"; + dp->dp_display.connector_type = desc->connector_type; rc = dp_init_sub_modules(dp); if (rc) { @@ -1237,14 +1254,13 @@ static int dp_display_probe(struct platform_device *pdev) } mutex_init(&dp->event_mutex); - g_dp_display = &dp->dp_display; /* Store DP audio handle inside DP display */ - g_dp_display->dp_audio = dp->audio; + dp->dp_display.dp_audio = dp->audio; init_completion(&dp->audio_comp); - platform_set_drvdata(pdev, g_dp_display); + platform_set_drvdata(pdev, &dp->dp_display); rc = component_add(&pdev->dev, &dp_display_comp_ops); if (rc) { @@ -1257,10 +1273,7 @@ static int dp_display_probe(struct platform_device *pdev) static int dp_display_remove(struct platform_device *pdev) { - struct dp_display_private *dp; - - dp = container_of(g_dp_display, - struct dp_display_private, dp_display); + struct dp_display_private *dp = dev_get_dp_display_private(&pdev->dev); dp_display_deinit_sub_modules(dp); @@ -1315,7 +1328,7 @@ static int dp_pm_resume(struct device *dev) dp->dp_display.is_connected = true; } else { dp->dp_display.is_connected = false; - dp_display_handle_plugged_change(g_dp_display, false); + dp_display_handle_plugged_change(dp_display, false); } DRM_DEBUG_DP("After, sink_count=%d is_connected=%d core_inited=%d power_on=%d\n", @@ -1429,7 +1442,7 @@ void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor) dev = &dp->pdev->dev; dp->debug = dp_debug_get(dev, dp->panel, dp->usbpd, - dp->link, &dp->dp_display.connector, + dp->link, dp->dp_display.connector, minor); if (IS_ERR(dp->debug)) { rc = PTR_ERR(dp->debug); diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h index 8b47cdabb67e..8e80e3bac394 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.h +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -15,9 +15,11 @@ struct msm_dp { struct device *codec_dev; struct drm_connector *connector; struct drm_encoder *encoder; + struct drm_bridge *panel_bridge; bool is_connected; bool audio_enabled; bool power_on; + unsigned int connector_type; hdmi_codec_plugged_cb plugged_cb; diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index 764f4b81017e..76856c4ee1d6 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "msm_drv.h" @@ -147,7 +148,7 @@ struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display) ret = drm_connector_init(dp_display->drm_dev, connector, &dp_connector_funcs, - DRM_MODE_CONNECTOR_DisplayPort); + dp_display->connector_type); if (ret) return ERR_PTR(ret); @@ -160,5 +161,15 @@ struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display) drm_connector_attach_encoder(connector, dp_display->encoder); + if (dp_display->panel_bridge) { + ret = drm_bridge_attach(dp_display->encoder, + dp_display->panel_bridge, NULL, + DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (ret < 0) { + DRM_ERROR("failed to attach panel bridge: %d\n", ret); + return ERR_PTR(ret); + } + } + return connector; } diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 2181b60e1d1d..71db10c0f262 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -234,7 +234,7 @@ u32 dp_panel_get_mode_bpp(struct dp_panel *dp_panel, u32 mode_edid_bpp, u32 mode_pclk_khz) { struct dp_panel_private *panel; - u32 bpp = mode_edid_bpp; + u32 bpp; if (!dp_panel || !mode_edid_bpp || !mode_pclk_khz) { DRM_ERROR("invalid input\n"); diff --git a/drivers/gpu/drm/msm/dp/dp_parser.c b/drivers/gpu/drm/msm/dp/dp_parser.c index 0519dd3ac3c3..a7acc23f742b 100644 --- a/drivers/gpu/drm/msm/dp/dp_parser.c +++ b/drivers/gpu/drm/msm/dp/dp_parser.c @@ -6,11 +6,22 @@ #include #include +#include #include +#include #include "dp_parser.h" #include "dp_reg.h" +#define DP_DEFAULT_AHB_OFFSET 0x0000 +#define DP_DEFAULT_AHB_SIZE 0x0200 +#define DP_DEFAULT_AUX_OFFSET 0x0200 +#define DP_DEFAULT_AUX_SIZE 0x0200 +#define DP_DEFAULT_LINK_OFFSET 0x0400 +#define DP_DEFAULT_LINK_SIZE 0x0C00 +#define DP_DEFAULT_P0_OFFSET 0x1000 +#define DP_DEFAULT_P0_SIZE 0x0400 + static const struct dp_regulator_cfg sdm845_dp_reg_cfg = { .num = 2, .regs = { @@ -19,67 +30,73 @@ static const struct dp_regulator_cfg sdm845_dp_reg_cfg = { }, }; -static int msm_dss_ioremap(struct platform_device *pdev, - struct dss_io_data *io_data) +static void __iomem *dp_ioremap(struct platform_device *pdev, int idx, size_t *len) { - struct resource *res = NULL; + struct resource *res; + void __iomem *base; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - DRM_ERROR("%pS->%s: msm_dss_get_res failed\n", - __builtin_return_address(0), __func__); - return -ENODEV; - } + base = devm_platform_get_and_ioremap_resource(pdev, idx, &res); + if (!IS_ERR(base)) + *len = resource_size(res); - io_data->len = (u32)resource_size(res); - io_data->base = ioremap(res->start, io_data->len); - if (!io_data->base) { - DRM_ERROR("%pS->%s: ioremap failed\n", - __builtin_return_address(0), __func__); - return -EIO; - } - - return 0; -} - -static void msm_dss_iounmap(struct dss_io_data *io_data) -{ - if (io_data->base) { - iounmap(io_data->base); - io_data->base = NULL; - } - io_data->len = 0; -} - -static void dp_parser_unmap_io_resources(struct dp_parser *parser) -{ - struct dp_io *io = &parser->io; - - msm_dss_iounmap(&io->dp_controller); + return base; } static int dp_parser_ctrl_res(struct dp_parser *parser) { - int rc = 0; struct platform_device *pdev = parser->pdev; struct dp_io *io = &parser->io; + struct dss_io_data *dss = &io->dp_controller; - rc = msm_dss_ioremap(pdev, &io->dp_controller); - if (rc) { - DRM_ERROR("unable to remap dp io resources, rc=%d\n", rc); - goto err; + dss->ahb.base = dp_ioremap(pdev, 0, &dss->ahb.len); + if (IS_ERR(dss->ahb.base)) + return PTR_ERR(dss->ahb.base); + + dss->aux.base = dp_ioremap(pdev, 1, &dss->aux.len); + if (IS_ERR(dss->aux.base)) { + /* + * The initial binding had a single reg, but in order to + * support variation in the sub-region sizes this was split. + * dp_ioremap() will fail with -EINVAL here if only a single + * reg is specified, so fill in the sub-region offsets and + * lengths based on this single region. + */ + if (PTR_ERR(dss->aux.base) == -EINVAL) { + if (dss->ahb.len < DP_DEFAULT_P0_OFFSET + DP_DEFAULT_P0_SIZE) { + DRM_ERROR("legacy memory region not large enough\n"); + return -EINVAL; + } + + dss->ahb.len = DP_DEFAULT_AHB_SIZE; + dss->aux.base = dss->ahb.base + DP_DEFAULT_AUX_OFFSET; + dss->aux.len = DP_DEFAULT_AUX_SIZE; + dss->link.base = dss->ahb.base + DP_DEFAULT_LINK_OFFSET; + dss->link.len = DP_DEFAULT_LINK_SIZE; + dss->p0.base = dss->ahb.base + DP_DEFAULT_P0_OFFSET; + dss->p0.len = DP_DEFAULT_P0_SIZE; + } else { + DRM_ERROR("unable to remap aux region: %pe\n", dss->aux.base); + return PTR_ERR(dss->aux.base); + } + } else { + dss->link.base = dp_ioremap(pdev, 2, &dss->link.len); + if (IS_ERR(dss->link.base)) { + DRM_ERROR("unable to remap link region: %pe\n", dss->link.base); + return PTR_ERR(dss->link.base); + } + + dss->p0.base = dp_ioremap(pdev, 3, &dss->p0.len); + if (IS_ERR(dss->p0.base)) { + DRM_ERROR("unable to remap p0 region: %pe\n", dss->p0.base); + return PTR_ERR(dss->p0.base); + } } io->phy = devm_phy_get(&pdev->dev, "dp"); - if (IS_ERR(io->phy)) { - rc = PTR_ERR(io->phy); - goto err; - } + if (IS_ERR(io->phy)) + return PTR_ERR(io->phy); return 0; -err: - dp_parser_unmap_io_resources(parser); - return rc; } static int dp_parser_misc(struct dp_parser *parser) @@ -248,7 +265,28 @@ static int dp_parser_clock(struct dp_parser *parser) return 0; } -static int dp_parser_parse(struct dp_parser *parser) +static int dp_parser_find_panel(struct dp_parser *parser) +{ + struct device *dev = &parser->pdev->dev; + struct drm_panel *panel; + int rc; + + rc = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); + if (rc) { + DRM_ERROR("failed to acquire DRM panel: %d\n", rc); + return rc; + } + + parser->panel_bridge = devm_drm_panel_bridge_add(dev, panel); + if (IS_ERR(parser->panel_bridge)) { + DRM_ERROR("failed to create panel bridge\n"); + return PTR_ERR(parser->panel_bridge); + } + + return 0; +} + +static int dp_parser_parse(struct dp_parser *parser, int connector_type) { int rc = 0; @@ -269,6 +307,12 @@ static int dp_parser_parse(struct dp_parser *parser) if (rc) return rc; + if (connector_type == DRM_MODE_CONNECTOR_eDP) { + rc = dp_parser_find_panel(parser); + if (rc) + return rc; + } + /* Map the corresponding regulator information according to * version. Currently, since we only have one supported platform, * mapping the regulator directly. diff --git a/drivers/gpu/drm/msm/dp/dp_parser.h b/drivers/gpu/drm/msm/dp/dp_parser.h index 34b49628bbaf..3172da089421 100644 --- a/drivers/gpu/drm/msm/dp/dp_parser.h +++ b/drivers/gpu/drm/msm/dp/dp_parser.h @@ -25,11 +25,18 @@ enum dp_pm_type { DP_MAX_PM }; -struct dss_io_data { - u32 len; +struct dss_io_region { + size_t len; void __iomem *base; }; +struct dss_io_data { + struct dss_io_region ahb; + struct dss_io_region aux; + struct dss_io_region link; + struct dss_io_region p0; +}; + static inline const char *dp_parser_pm_name(enum dp_pm_type module) { switch (module) { @@ -116,8 +123,9 @@ struct dp_parser { struct dp_display_data disp_data; const struct dp_regulator_cfg *regulator_cfg; u32 max_dp_lanes; + struct drm_bridge *panel_bridge; - int (*parse)(struct dp_parser *parser); + int (*parse)(struct dp_parser *parser, int connector_type); }; /** diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index b50db91cb8a7..569c8ff062ba 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -107,6 +107,8 @@ void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host, u32 dma_base, u32 len); int msm_dsi_host_enable(struct mipi_dsi_host *host); int msm_dsi_host_disable(struct mipi_dsi_host *host); +void msm_dsi_host_enable_irq(struct mipi_dsi_host *host); +void msm_dsi_host_disable_irq(struct mipi_dsi_host *host); int msm_dsi_host_power_on(struct mipi_dsi_host *host, struct msm_dsi_phy_shared_timings *phy_shared_timings, bool is_bonded_dsi, struct msm_dsi_phy *phy); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index c86b5090fae6..f69a125f9559 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -106,7 +106,8 @@ struct msm_dsi_host { phys_addr_t ctrl_size; struct regulator_bulk_data supplies[DSI_DEV_REGULATOR_MAX]; - struct clk *bus_clks[DSI_BUS_CLK_MAX]; + int num_bus_clks; + struct clk_bulk_data bus_clks[DSI_BUS_CLK_MAX]; struct clk *byte_clk; struct clk *esc_clk; @@ -115,16 +116,16 @@ struct msm_dsi_host { struct clk *pixel_clk_src; struct clk *byte_intf_clk; - u32 byte_clk_rate; - u32 pixel_clk_rate; - u32 esc_clk_rate; + unsigned long byte_clk_rate; + unsigned long pixel_clk_rate; + unsigned long esc_clk_rate; /* DSI v2 specific clocks */ struct clk *src_clk; struct clk *esc_clk_src; struct clk *dsi_clk_src; - u32 src_clk_rate; + unsigned long src_clk_rate; struct gpio_desc *disp_en_gpio; struct gpio_desc *te_gpio; @@ -374,15 +375,14 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) int i, ret = 0; /* get bus clocks */ - for (i = 0; i < cfg->num_bus_clks; i++) { - msm_host->bus_clks[i] = msm_clk_get(pdev, - cfg->bus_clk_names[i]); - if (IS_ERR(msm_host->bus_clks[i])) { - ret = PTR_ERR(msm_host->bus_clks[i]); - pr_err("%s: Unable to get %s clock, ret = %d\n", - __func__, cfg->bus_clk_names[i], ret); - goto exit; - } + for (i = 0; i < cfg->num_bus_clks; i++) + msm_host->bus_clks[i].id = cfg->bus_clk_names[i]; + msm_host->num_bus_clks = cfg->num_bus_clks; + + ret = devm_clk_bulk_get(&pdev->dev, msm_host->num_bus_clks, msm_host->bus_clks); + if (ret < 0) { + dev_err(&pdev->dev, "Unable to get clocks, ret = %d\n", ret); + goto exit; } /* get link and source clocks */ @@ -433,41 +433,6 @@ exit: return ret; } -static int dsi_bus_clk_enable(struct msm_dsi_host *msm_host) -{ - const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg; - int i, ret; - - DBG("id=%d", msm_host->id); - - for (i = 0; i < cfg->num_bus_clks; i++) { - ret = clk_prepare_enable(msm_host->bus_clks[i]); - if (ret) { - pr_err("%s: failed to enable bus clock %d ret %d\n", - __func__, i, ret); - goto err; - } - } - - return 0; -err: - while (--i >= 0) - clk_disable_unprepare(msm_host->bus_clks[i]); - - return ret; -} - -static void dsi_bus_clk_disable(struct msm_dsi_host *msm_host) -{ - const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg; - int i; - - DBG(""); - - for (i = cfg->num_bus_clks - 1; i >= 0; i--) - clk_disable_unprepare(msm_host->bus_clks[i]); -} - int msm_dsi_runtime_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -478,7 +443,7 @@ int msm_dsi_runtime_suspend(struct device *dev) if (!msm_host->cfg_hnd) return 0; - dsi_bus_clk_disable(msm_host); + clk_bulk_disable_unprepare(msm_host->num_bus_clks, msm_host->bus_clks); return 0; } @@ -493,15 +458,15 @@ int msm_dsi_runtime_resume(struct device *dev) if (!msm_host->cfg_hnd) return 0; - return dsi_bus_clk_enable(msm_host); + return clk_bulk_prepare_enable(msm_host->num_bus_clks, msm_host->bus_clks); } int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host) { - u32 byte_intf_rate; + unsigned long byte_intf_rate; int ret; - DBG("Set clk rates: pclk=%d, byteclk=%d", + DBG("Set clk rates: pclk=%d, byteclk=%lu", msm_host->mode->clock, msm_host->byte_clk_rate); ret = dev_pm_opp_set_rate(&msm_host->pdev->dev, @@ -558,13 +523,11 @@ int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) goto pixel_clk_err; } - if (msm_host->byte_intf_clk) { - ret = clk_prepare_enable(msm_host->byte_intf_clk); - if (ret) { - pr_err("%s: Failed to enable byte intf clk\n", - __func__); - goto byte_intf_clk_err; - } + ret = clk_prepare_enable(msm_host->byte_intf_clk); + if (ret) { + pr_err("%s: Failed to enable byte intf clk\n", + __func__); + goto byte_intf_clk_err; } return 0; @@ -583,7 +546,7 @@ int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host) { int ret; - DBG("Set clk rates: pclk=%d, byteclk=%d, esc_clk=%d, dsi_src_clk=%d", + DBG("Set clk rates: pclk=%d, byteclk=%lu, esc_clk=%lu, dsi_src_clk=%lu", msm_host->mode->clock, msm_host->byte_clk_rate, msm_host->esc_clk_rate, msm_host->src_clk_rate); @@ -660,8 +623,7 @@ void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host) dev_pm_opp_set_rate(&msm_host->pdev->dev, 0); clk_disable_unprepare(msm_host->esc_clk); clk_disable_unprepare(msm_host->pixel_clk); - if (msm_host->byte_intf_clk) - clk_disable_unprepare(msm_host->byte_intf_clk); + clk_disable_unprepare(msm_host->byte_intf_clk); clk_disable_unprepare(msm_host->byte_clk); } @@ -673,10 +635,10 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host) clk_disable_unprepare(msm_host->byte_clk); } -static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_bonded_dsi) +static unsigned long dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_bonded_dsi) { struct drm_display_mode *mode = msm_host->mode; - u32 pclk_rate; + unsigned long pclk_rate; pclk_rate = mode->clock * 1000; @@ -696,7 +658,7 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi) { u8 lanes = msm_host->lanes; u32 bpp = dsi_get_bpp(msm_host->format); - u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_bonded_dsi); + unsigned long pclk_rate = dsi_get_pclk_rate(msm_host, is_bonded_dsi); u64 pclk_bpp = (u64)pclk_rate * bpp; if (lanes == 0) { @@ -713,7 +675,7 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi) msm_host->pixel_clk_rate = pclk_rate; msm_host->byte_clk_rate = pclk_bpp; - DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate, + DBG("pclk=%lu, bclk=%lu", msm_host->pixel_clk_rate, msm_host->byte_clk_rate); } @@ -772,7 +734,7 @@ int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_bonded_dsi) msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div; - DBG("esc=%d, src=%d", msm_host->esc_clk_rate, + DBG("esc=%lu, src=%lu", msm_host->esc_clk_rate, msm_host->src_clk_rate); return 0; @@ -1898,6 +1860,23 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) return ret; } + msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); + if (msm_host->irq < 0) { + ret = msm_host->irq; + dev_err(&pdev->dev, "failed to get irq: %d\n", ret); + return ret; + } + + /* do not autoenable, will be enabled later */ + ret = devm_request_irq(&pdev->dev, msm_host->irq, dsi_host_irq, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT | IRQF_NO_AUTOEN, + "dsi_isr", msm_host); + if (ret < 0) { + dev_err(&pdev->dev, "failed to request IRQ%u: %d\n", + msm_host->irq, ret); + return ret; + } + init_completion(&msm_host->dma_comp); init_completion(&msm_host->video_comp); mutex_init(&msm_host->dev_mutex); @@ -1925,7 +1904,6 @@ void msm_dsi_host_destroy(struct mipi_dsi_host *host) DBG(""); dsi_tx_buf_free(msm_host); if (msm_host->workqueue) { - flush_workqueue(msm_host->workqueue); destroy_workqueue(msm_host->workqueue); msm_host->workqueue = NULL; } @@ -1941,25 +1919,8 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host, { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; - struct platform_device *pdev = msm_host->pdev; int ret; - msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (msm_host->irq < 0) { - ret = msm_host->irq; - DRM_DEV_ERROR(dev->dev, "failed to get irq: %d\n", ret); - return ret; - } - - ret = devm_request_irq(&pdev->dev, msm_host->irq, - dsi_host_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT, - "dsi_isr", msm_host); - if (ret < 0) { - DRM_DEV_ERROR(&pdev->dev, "failed to request IRQ%u: %d\n", - msm_host->irq, ret); - return ret; - } - msm_host->dev = dev; ret = cfg_hnd->ops->tx_buf_alloc(msm_host, SZ_4K); if (ret) { @@ -2315,6 +2276,20 @@ void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host, clk_req->escclk_rate = msm_host->esc_clk_rate; } +void msm_dsi_host_enable_irq(struct mipi_dsi_host *host) +{ + struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + + enable_irq(msm_host->irq); +} + +void msm_dsi_host_disable_irq(struct mipi_dsi_host *host) +{ + struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + + disable_irq(msm_host->irq); +} + int msm_dsi_host_enable(struct mipi_dsi_host *host) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index c41d39f5b7cf..20c4d650fd80 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -3,6 +3,8 @@ * Copyright (c) 2015, The Linux Foundation. All rights reserved. */ +#include "drm/drm_bridge_connector.h" + #include "msm_kms.h" #include "dsi.h" @@ -377,6 +379,14 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) } } + /* + * Enable before preparing the panel, disable after unpreparing, so + * that the panel can communicate over the DSI link. + */ + msm_dsi_host_enable_irq(host); + if (is_bonded_dsi && msm_dsi1) + msm_dsi_host_enable_irq(msm_dsi1->host); + /* Always call panel functions once, because even for dual panels, * there is only one drm_panel instance. */ @@ -411,6 +421,10 @@ host_en_fail: if (panel) drm_panel_unprepare(panel); panel_prep_fail: + msm_dsi_host_disable_irq(host); + if (is_bonded_dsi && msm_dsi1) + msm_dsi_host_disable_irq(msm_dsi1->host); + if (is_bonded_dsi && msm_dsi1) msm_dsi_host_power_off(msm_dsi1->host); host1_on_fail: @@ -523,6 +537,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) id, ret); } + msm_dsi_host_disable_irq(host); + if (is_bonded_dsi && msm_dsi1) + msm_dsi_host_disable_irq(msm_dsi1->host); + /* Save PHY status if it is a clock source */ msm_dsi_phy_pll_save_state(msm_dsi->phy); @@ -688,10 +706,10 @@ struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id) { struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct drm_device *dev = msm_dsi->dev; + struct drm_connector *connector; struct drm_encoder *encoder; struct drm_bridge *int_bridge, *ext_bridge; - struct drm_connector *connector; - struct list_head *connector_list; + int ret; int_bridge = msm_dsi->bridge; ext_bridge = msm_dsi->external_bridge = @@ -699,22 +717,44 @@ struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id) encoder = msm_dsi->encoder; - /* link the internal dsi bridge to the external bridge */ - drm_bridge_attach(encoder, ext_bridge, int_bridge, 0); - /* - * we need the drm_connector created by the external bridge - * driver (or someone else) to feed it to our driver's - * priv->connector[] list, mainly for msm_fbdev_init() + * Try first to create the bridge without it creating its own + * connector.. currently some bridges support this, and others + * do not (and some support both modes) */ - connector_list = &dev->mode_config.connector_list; + ret = drm_bridge_attach(encoder, ext_bridge, int_bridge, + DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (ret == -EINVAL) { + struct drm_connector *connector; + struct list_head *connector_list; - list_for_each_entry(connector, connector_list, head) { - if (drm_connector_has_possible_encoder(connector, encoder)) - return connector; + /* link the internal dsi bridge to the external bridge */ + drm_bridge_attach(encoder, ext_bridge, int_bridge, 0); + + /* + * we need the drm_connector created by the external bridge + * driver (or someone else) to feed it to our driver's + * priv->connector[] list, mainly for msm_fbdev_init() + */ + connector_list = &dev->mode_config.connector_list; + + list_for_each_entry(connector, connector_list, head) { + if (drm_connector_has_possible_encoder(connector, encoder)) + return connector; + } + + return ERR_PTR(-ENODEV); } - return ERR_PTR(-ENODEV); + connector = drm_bridge_connector_init(dev, encoder); + if (IS_ERR(connector)) { + DRM_ERROR("Unable to create bridge connector\n"); + return ERR_CAST(connector); + } + + drm_connector_attach_encoder(connector, encoder); + + return connector; } void msm_dsi_manager_bridge_destroy(struct drm_bridge *bridge) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 8c65ef6968ca..9842e04b5858 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -627,6 +627,8 @@ static const struct of_device_id dsi_phy_dt_match[] = { .data = &dsi_phy_14nm_cfgs }, { .compatible = "qcom,dsi-phy-14nm-660", .data = &dsi_phy_14nm_660_cfgs }, + { .compatible = "qcom,dsi-phy-14nm-8953", + .data = &dsi_phy_14nm_8953_cfgs }, #endif #ifdef CONFIG_DRM_MSM_DSI_10NM_PHY { .compatible = "qcom,dsi-phy-10nm", diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index b91303ada74f..4c8257581bfc 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -48,6 +48,7 @@ extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 5b4e991f220d..7414966f198e 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -213,9 +213,7 @@ static void pll_14nm_dec_frac_calc(struct dsi_pll_14nm *pll, struct dsi_pll_conf DBG("vco_clk_rate=%lld ref_clk_rate=%lld", vco_clk_rate, fref); dec_start_multiple = div_u64(vco_clk_rate * multiplier, fref); - div_u64_rem(dec_start_multiple, multiplier, &div_frac_start); - - dec_start = div_u64(dec_start_multiple, multiplier); + dec_start = div_u64_rem(dec_start_multiple, multiplier, &div_frac_start); pconf->dec_start = (u32)dec_start; pconf->div_frac_start = div_frac_start; @@ -1065,3 +1063,24 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = { .io_start = { 0xc994400, 0xc996000 }, .num_dsi_phy = 2, }; + +const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs = { + .has_phy_lane = true, + .reg_cfg = { + .num = 1, + .regs = { + {"vcca", 17000, 32}, + }, + }, + .ops = { + .enable = dsi_14nm_phy_enable, + .disable = dsi_14nm_phy_disable, + .pll_init = dsi_pll_14nm_init, + .save_pll_state = dsi_14nm_pll_save_state, + .restore_pll_state = dsi_14nm_pll_restore_state, + }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, + .io_start = { 0x1a94400, 0x1a96400 }, + .num_dsi_phy = 2, +}; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index cb297b08458e..079613d2aaa9 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -114,9 +114,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config multiplier = 1 << FRAC_BITS; dec_multiple = div_u64(pll_freq * multiplier, divider); - div_u64_rem(dec_multiple, multiplier, &frac); - - dec = div_u64(dec_multiple, multiplier); + dec = div_u64_rem(dec_multiple, multiplier, &frac); if (!(pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1)) config->pll_clock_inverters = 0x28; diff --git a/drivers/gpu/drm/msm/edp/edp_ctrl.c b/drivers/gpu/drm/msm/edp/edp_ctrl.c index fe1366b4c49f..a68a4a1867c1 100644 --- a/drivers/gpu/drm/msm/edp/edp_ctrl.c +++ b/drivers/gpu/drm/msm/edp/edp_ctrl.c @@ -1190,7 +1190,6 @@ void msm_edp_ctrl_destroy(struct edp_ctrl *ctrl) return; if (ctrl->workqueue) { - flush_workqueue(ctrl->workqueue); destroy_workqueue(ctrl->workqueue); ctrl->workqueue = NULL; } @@ -1243,8 +1242,6 @@ bool msm_edp_ctrl_panel_connected(struct edp_ctrl *ctrl) int msm_edp_ctrl_get_panel_info(struct edp_ctrl *ctrl, struct drm_connector *connector, struct edid **edid) { - int ret = 0; - mutex_lock(&ctrl->dev_mutex); if (ctrl->edid) { @@ -1279,7 +1276,7 @@ disable_ret: } unlock_ret: mutex_unlock(&ctrl->dev_mutex); - return ret; + return 0; } int msm_edp_ctrl_timing_cfg(struct edp_ctrl *ctrl, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 737453b6e596..75b64e6ae035 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -61,10 +61,8 @@ static void msm_hdmi_destroy(struct hdmi *hdmi) * at this point, hpd has been disabled, * after flush workq, it's safe to deinit hdcp */ - if (hdmi->workq) { - flush_workqueue(hdmi->workq); + if (hdmi->workq) destroy_workqueue(hdmi->workq); - } msm_hdmi_hdcp_destroy(hdmi); if (hdmi->phy_dev) { @@ -154,19 +152,13 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) ret = -ENOMEM; goto fail; } - for (i = 0; i < config->hpd_reg_cnt; i++) { - struct regulator *reg; + for (i = 0; i < config->hpd_reg_cnt; i++) + hdmi->hpd_regs[i].supply = config->hpd_reg_names[i]; - reg = devm_regulator_get(&pdev->dev, - config->hpd_reg_names[i]); - if (IS_ERR(reg)) { - ret = PTR_ERR(reg); - DRM_DEV_ERROR(&pdev->dev, "failed to get hpd regulator: %s (%d)\n", - config->hpd_reg_names[i], ret); - goto fail; - } - - hdmi->hpd_regs[i] = reg; + ret = devm_regulator_bulk_get(&pdev->dev, config->hpd_reg_cnt, hdmi->hpd_regs); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to get hpd regulator: %d\n", ret); + goto fail; } hdmi->pwr_regs = devm_kcalloc(&pdev->dev, @@ -177,19 +169,11 @@ static struct hdmi *msm_hdmi_init(struct platform_device *pdev) ret = -ENOMEM; goto fail; } - for (i = 0; i < config->pwr_reg_cnt; i++) { - struct regulator *reg; - reg = devm_regulator_get(&pdev->dev, - config->pwr_reg_names[i]); - if (IS_ERR(reg)) { - ret = PTR_ERR(reg); - DRM_DEV_ERROR(&pdev->dev, "failed to get pwr regulator: %s (%d)\n", - config->pwr_reg_names[i], ret); - goto fail; - } - - hdmi->pwr_regs[i] = reg; + ret = devm_regulator_bulk_get(&pdev->dev, config->pwr_reg_cnt, hdmi->pwr_regs); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to get pwr regulator: %d\n", ret); + goto fail; } hdmi->hpd_clks = devm_kcalloc(&pdev->dev, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index d0b84f0abee1..82261078c6b1 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -56,8 +56,8 @@ struct hdmi { void __iomem *qfprom_mmio; phys_addr_t mmio_phy_addr; - struct regulator **hpd_regs; - struct regulator **pwr_regs; + struct regulator_bulk_data *hpd_regs; + struct regulator_bulk_data *pwr_regs; struct clk **hpd_clks; struct clk **pwr_clks; @@ -163,7 +163,7 @@ struct hdmi_phy { void __iomem *mmio; struct hdmi_phy_cfg *cfg; const struct hdmi_phy_funcs *funcs; - struct regulator **regs; + struct regulator_bulk_data *regs; struct clk **clks; }; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 6e380db9287b..f04eb4a70f0d 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -28,13 +28,9 @@ static void msm_hdmi_power_on(struct drm_bridge *bridge) pm_runtime_get_sync(&hdmi->pdev->dev); - for (i = 0; i < config->pwr_reg_cnt; i++) { - ret = regulator_enable(hdmi->pwr_regs[i]); - if (ret) { - DRM_DEV_ERROR(dev->dev, "failed to enable pwr regulator: %s (%d)\n", - config->pwr_reg_names[i], ret); - } - } + ret = regulator_bulk_enable(config->pwr_reg_cnt, hdmi->pwr_regs); + if (ret) + DRM_DEV_ERROR(dev->dev, "failed to enable pwr regulator: %d\n", ret); if (config->pwr_clk_cnt > 0) { DBG("pixclock: %lu", hdmi->pixclock); @@ -70,13 +66,9 @@ static void power_off(struct drm_bridge *bridge) for (i = 0; i < config->pwr_clk_cnt; i++) clk_disable_unprepare(hdmi->pwr_clks[i]); - for (i = 0; i < config->pwr_reg_cnt; i++) { - ret = regulator_disable(hdmi->pwr_regs[i]); - if (ret) { - DRM_DEV_ERROR(dev->dev, "failed to disable pwr regulator: %s (%d)\n", - config->pwr_reg_names[i], ret); - } - } + ret = regulator_bulk_disable(config->pwr_reg_cnt, hdmi->pwr_regs); + if (ret) + DRM_DEV_ERROR(dev->dev, "failed to disable pwr regulator: %d\n", ret); pm_runtime_put_autosuspend(&hdmi->pdev->dev); } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c index 58707a1f3878..a7f729cdec7b 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c @@ -146,16 +146,13 @@ int msm_hdmi_hpd_enable(struct drm_connector *connector) const struct hdmi_platform_config *config = hdmi->config; struct device *dev = &hdmi->pdev->dev; uint32_t hpd_ctrl; - int i, ret; + int ret; unsigned long flags; - for (i = 0; i < config->hpd_reg_cnt; i++) { - ret = regulator_enable(hdmi->hpd_regs[i]); - if (ret) { - DRM_DEV_ERROR(dev, "failed to enable hpd regulator: %s (%d)\n", - config->hpd_reg_names[i], ret); - goto fail; - } + ret = regulator_bulk_enable(config->hpd_reg_cnt, hdmi->hpd_regs); + if (ret) { + DRM_DEV_ERROR(dev, "failed to enable hpd regulators: %d\n", ret); + goto fail; } ret = pinctrl_pm_select_default_state(dev); @@ -207,7 +204,7 @@ static void hdp_disable(struct hdmi_connector *hdmi_connector) struct hdmi *hdmi = hdmi_connector->hdmi; const struct hdmi_platform_config *config = hdmi->config; struct device *dev = &hdmi->pdev->dev; - int i, ret = 0; + int ret; /* Disable HPD interrupt */ hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL, 0); @@ -225,12 +222,9 @@ static void hdp_disable(struct hdmi_connector *hdmi_connector) if (ret) dev_warn(dev, "pinctrl state chg failed: %d\n", ret); - for (i = 0; i < config->hpd_reg_cnt; i++) { - ret = regulator_disable(hdmi->hpd_regs[i]); - if (ret) - dev_warn(dev, "failed to disable hpd regulator: %s (%d)\n", - config->hpd_reg_names[i], ret); - } + ret = regulator_bulk_disable(config->hpd_reg_cnt, hdmi->hpd_regs); + if (ret) + dev_warn(dev, "failed to disable hpd regulator: %d\n", ret); } static void diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c index 8a38d4b95102..16b0e8836d27 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c @@ -23,22 +23,15 @@ static int msm_hdmi_phy_resource_init(struct hdmi_phy *phy) if (!phy->clks) return -ENOMEM; - for (i = 0; i < cfg->num_regs; i++) { - struct regulator *reg; + for (i = 0; i < cfg->num_regs; i++) + phy->regs[i].supply = cfg->reg_names[i]; - reg = devm_regulator_get(dev, cfg->reg_names[i]); - if (IS_ERR(reg)) { - ret = PTR_ERR(reg); - if (ret != -EPROBE_DEFER) { - DRM_DEV_ERROR(dev, - "failed to get phy regulator: %s (%d)\n", - cfg->reg_names[i], ret); - } + ret = devm_regulator_bulk_get(dev, cfg->num_regs, phy->regs); + if (ret) { + if (ret != -EPROBE_DEFER) + DRM_DEV_ERROR(dev, "failed to get phy regulators: %d\n", ret); - return ret; - } - - phy->regs[i] = reg; + return ret; } for (i = 0; i < cfg->num_clks; i++) { @@ -66,11 +59,10 @@ int msm_hdmi_phy_resource_enable(struct hdmi_phy *phy) pm_runtime_get_sync(dev); - for (i = 0; i < cfg->num_regs; i++) { - ret = regulator_enable(phy->regs[i]); - if (ret) - DRM_DEV_ERROR(dev, "failed to enable regulator: %s (%d)\n", - cfg->reg_names[i], ret); + ret = regulator_bulk_enable(cfg->num_regs, phy->regs); + if (ret) { + DRM_DEV_ERROR(dev, "failed to enable regulators: (%d)\n", ret); + return ret; } for (i = 0; i < cfg->num_clks; i++) { @@ -92,8 +84,7 @@ void msm_hdmi_phy_resource_disable(struct hdmi_phy *phy) for (i = cfg->num_clks - 1; i >= 0; i--) clk_disable_unprepare(phy->clks[i]); - for (i = cfg->num_regs - 1; i >= 0; i--) - regulator_disable(phy->regs[i]); + regulator_bulk_disable(cfg->num_regs, phy->regs); pm_runtime_put_sync(dev); } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c index a8f3b2cbfdc5..99c7853353fd 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c @@ -682,7 +682,7 @@ static int hdmi_8996_pll_is_enabled(struct clk_hw *hw) return pll_locked; } -static struct clk_ops hdmi_8996_pll_ops = { +static const struct clk_ops hdmi_8996_pll_ops = { .set_rate = hdmi_8996_pll_set_clk_rate, .round_rate = hdmi_8996_pll_round_rate, .recalc_rate = hdmi_8996_pll_recalc_rate, @@ -695,7 +695,7 @@ static const char * const hdmi_pll_parents[] = { "xo", }; -static struct clk_init_data pll_init = { +static const struct clk_init_data pll_init = { .name = "hdmipll", .ops = &hdmi_8996_pll_ops, .parent_names = hdmi_pll_parents, diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index fab09e7c6efc..27c9ae563f2f 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -116,20 +116,10 @@ out: trace_msm_atomic_async_commit_finish(crtc_mask); } -static enum hrtimer_restart msm_atomic_pending_timer(struct hrtimer *t) -{ - struct msm_pending_timer *timer = container_of(t, - struct msm_pending_timer, timer); - - kthread_queue_work(timer->worker, &timer->work); - - return HRTIMER_NORESTART; -} - static void msm_atomic_pending_work(struct kthread_work *work) { struct msm_pending_timer *timer = container_of(work, - struct msm_pending_timer, work); + struct msm_pending_timer, work.work); msm_atomic_async_commit(timer->kms, timer->crtc_idx); } @@ -139,8 +129,6 @@ int msm_atomic_init_pending_timer(struct msm_pending_timer *timer, { timer->kms = kms; timer->crtc_idx = crtc_idx; - hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - timer->timer.function = msm_atomic_pending_timer; timer->worker = kthread_create_worker(0, "atomic-worker-%d", crtc_idx); if (IS_ERR(timer->worker)) { @@ -149,7 +137,10 @@ int msm_atomic_init_pending_timer(struct msm_pending_timer *timer, return ret; } sched_set_fifo(timer->worker->task); - kthread_init_work(&timer->work, msm_atomic_pending_work); + + msm_hrtimer_work_init(&timer->work, timer->worker, + msm_atomic_pending_work, + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); return 0; } @@ -258,7 +249,7 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) vsync_time = kms->funcs->vsync_time(kms, async_crtc); wakeup_time = ktime_sub(vsync_time, ms_to_ktime(1)); - hrtimer_start(&timer->timer, wakeup_time, + msm_hrtimer_queue_work(&timer->work, wakeup_time, HRTIMER_MODE_ABS); } diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index d4e09703a87d..7936e8d498dd 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -58,7 +58,7 @@ static const struct drm_mode_config_helper_funcs mode_config_helper_funcs = { }; #ifdef CONFIG_DRM_MSM_REGISTER_LOGGING -static bool reglog = false; +static bool reglog; MODULE_PARM_DESC(reglog, "Enable register read/write logging"); module_param(reglog, bool, 0600); #else @@ -75,7 +75,7 @@ static char *vram = "16m"; MODULE_PARM_DESC(vram, "Configure VRAM size (for devices without IOMMU/GPUMMU)"); module_param(vram, charp, 0); -bool dumpstate = false; +bool dumpstate; MODULE_PARM_DESC(dumpstate, "Dump KMS state on errors"); module_param(dumpstate, bool, 0600); @@ -200,6 +200,35 @@ void msm_rmw(void __iomem *addr, u32 mask, u32 or) msm_writel(val | or, addr); } +static enum hrtimer_restart msm_hrtimer_worktimer(struct hrtimer *t) +{ + struct msm_hrtimer_work *work = container_of(t, + struct msm_hrtimer_work, timer); + + kthread_queue_work(work->worker, &work->work); + + return HRTIMER_NORESTART; +} + +void msm_hrtimer_queue_work(struct msm_hrtimer_work *work, + ktime_t wakeup_time, + enum hrtimer_mode mode) +{ + hrtimer_start(&work->timer, wakeup_time, mode); +} + +void msm_hrtimer_work_init(struct msm_hrtimer_work *work, + struct kthread_worker *worker, + kthread_work_func_t fn, + clockid_t clock_id, + enum hrtimer_mode mode) +{ + hrtimer_init(&work->timer, clock_id, mode); + work->timer.function = msm_hrtimer_worktimer; + work->worker = worker; + kthread_init_work(&work->work, fn); +} + static irqreturn_t msm_irq(int irq, void *arg) { struct drm_device *dev = arg; diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index c552f0c3890c..69952b239384 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -60,6 +60,13 @@ enum msm_mdp_plane_property { PLANE_PROP_MAX_NUM }; +enum msm_dp_controller { + MSM_DP_CONTROLLER_0, + MSM_DP_CONTROLLER_1, + MSM_DP_CONTROLLER_2, + MSM_DP_CONTROLLER_COUNT, +}; + #define MSM_GPU_MAX_RINGS 4 #define MAX_H_TILES_PER_DISPLAY 2 @@ -153,7 +160,7 @@ struct msm_drm_private { /* DSI is shared by mdp4 and mdp5 */ struct msm_dsi *dsi[2]; - struct msm_dp *dp; + struct msm_dp *dp[MSM_DP_CONTROLLER_COUNT]; /* when we have more than one 'msm_gpu' these need to be an array: */ struct msm_gpu *gpu; @@ -480,6 +487,28 @@ void msm_writel(u32 data, void __iomem *addr); u32 msm_readl(const void __iomem *addr); void msm_rmw(void __iomem *addr, u32 mask, u32 or); +/** + * struct msm_hrtimer_work - a helper to combine an hrtimer with kthread_work + * + * @timer: hrtimer to control when the kthread work is triggered + * @work: the kthread work + * @worker: the kthread worker the work will be scheduled on + */ +struct msm_hrtimer_work { + struct hrtimer timer; + struct kthread_work work; + struct kthread_worker *worker; +}; + +void msm_hrtimer_queue_work(struct msm_hrtimer_work *work, + ktime_t wakeup_time, + enum hrtimer_mode mode); +void msm_hrtimer_work_init(struct msm_hrtimer_work *work, + struct kthread_worker *worker, + kthread_work_func_t fn, + clockid_t clock_id, + enum hrtimer_mode mode); + #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 40a9863f5951..104fdfc14027 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include @@ -1132,6 +1133,7 @@ static int msm_gem_new_impl(struct drm_device *dev, msm_obj->flags = flags; msm_obj->madv = MSM_MADV_WILLNEED; + INIT_LIST_HEAD(&msm_obj->node); INIT_LIST_HEAD(&msm_obj->vmas); *obj = &msm_obj->base; @@ -1166,7 +1168,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32 ret = msm_gem_new_impl(dev, size, flags, &obj); if (ret) - goto fail; + return ERR_PTR(ret); msm_obj = to_msm_bo(obj); @@ -1250,7 +1252,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, ret = msm_gem_new_impl(dev, size, MSM_BO_WC, &obj); if (ret) - goto fail; + return ERR_PTR(ret); drm_gem_private_object_init(dev, obj, size); diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 0f1b29ee04a9..4a1420b05e97 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -4,6 +4,8 @@ * Author: Rob Clark */ +#include + #include "msm_drv.h" #include "msm_gem.h" #include "msm_gpu.h" diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 8a3a592da3a4..2c46cd968ac4 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -296,7 +296,7 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, state->bos = kcalloc(nr, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); - for (i = 0; i < submit->nr_bos; i++) { + for (i = 0; state->bos && i < submit->nr_bos; i++) { if (should_dump(submit, i)) { msm_gpu_crashstate_get_bo(state, submit->bos[i].obj, submit->bos[i].iova, submit->bos[i].flags); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index ee25d556c8a1..59cdd00b69d0 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -112,6 +112,13 @@ struct msm_gpu_devfreq { * it is inactive. */ unsigned long idle_freq; + + /** + * idle_work: + * + * Used to delay clamping to idle freq on active->idle transition. + */ + struct msm_hrtimer_work idle_work; }; struct msm_gpu { diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 20006d060b5b..8b7473f69cb8 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -88,8 +88,12 @@ static struct devfreq_dev_profile msm_devfreq_profile = { .get_cur_freq = msm_devfreq_get_cur_freq, }; +static void msm_devfreq_idle_work(struct kthread_work *work); + void msm_devfreq_init(struct msm_gpu *gpu) { + struct msm_gpu_devfreq *df = &gpu->devfreq; + /* We need target support to do devfreq */ if (!gpu->funcs->gpu_busy) return; @@ -105,25 +109,27 @@ void msm_devfreq_init(struct msm_gpu *gpu) msm_devfreq_profile.freq_table = NULL; msm_devfreq_profile.max_state = 0; - gpu->devfreq.devfreq = devm_devfreq_add_device(&gpu->pdev->dev, + df->devfreq = devm_devfreq_add_device(&gpu->pdev->dev, &msm_devfreq_profile, DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL); - if (IS_ERR(gpu->devfreq.devfreq)) { + if (IS_ERR(df->devfreq)) { DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n"); - gpu->devfreq.devfreq = NULL; + df->devfreq = NULL; return; } - devfreq_suspend_device(gpu->devfreq.devfreq); + devfreq_suspend_device(df->devfreq); - gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node, - gpu->devfreq.devfreq); + gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node, df->devfreq); if (IS_ERR(gpu->cooling)) { DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't register GPU cooling device\n"); gpu->cooling = NULL; } + + msm_hrtimer_work_init(&df->idle_work, gpu->worker, msm_devfreq_idle_work, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); } void msm_devfreq_cleanup(struct msm_gpu *gpu) @@ -154,6 +160,11 @@ void msm_devfreq_active(struct msm_gpu *gpu) if (!df->devfreq) return; + /* + * Cancel any pending transition to idle frequency: + */ + hrtimer_cancel(&df->idle_work.timer); + /* * Hold devfreq lock to synchronize with get_dev_status()/ * target() callbacks @@ -184,9 +195,12 @@ void msm_devfreq_active(struct msm_gpu *gpu) mutex_unlock(&df->devfreq->lock); } -void msm_devfreq_idle(struct msm_gpu *gpu) + +static void msm_devfreq_idle_work(struct kthread_work *work) { - struct msm_gpu_devfreq *df = &gpu->devfreq; + struct msm_gpu_devfreq *df = container_of(work, + struct msm_gpu_devfreq, idle_work.work); + struct msm_gpu *gpu = container_of(df, struct msm_gpu, devfreq); unsigned long idle_freq, target_freq = 0; if (!df->devfreq) @@ -208,3 +222,11 @@ void msm_devfreq_idle(struct msm_gpu *gpu) mutex_unlock(&df->devfreq->lock); } + +void msm_devfreq_idle(struct msm_gpu *gpu) +{ + struct msm_gpu_devfreq *df = &gpu->devfreq; + + msm_hrtimer_queue_work(&df->idle_work, ms_to_ktime(1), + HRTIMER_MODE_ABS); +} diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index de2bc3467bb5..6a42b819abc4 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -136,8 +136,7 @@ struct msm_kms; * shortly before vblank to flush pending async updates. */ struct msm_pending_timer { - struct hrtimer timer; - struct kthread_work work; + struct msm_hrtimer_work work; struct kthread_worker *worker; struct msm_kms *kms; unsigned crtc_idx; diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index b8621c6e0554..7cb158bcbcf6 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -101,6 +101,7 @@ get_sched_entity(struct msm_file_private *ctx, struct msm_ringbuffer *ring, ret = drm_sched_entity_init(entity, sched_prio, &sched, 1, NULL); if (ret) { + mutex_unlock(&entity_lock); kfree(entity); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index d7b9f7f8c9e3..8e28403ea9b1 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1414,7 +1414,7 @@ nv50_mstm_prepare(struct nv50_mstm *mstm) int ret; NV_ATOMIC(drm, "%s: mstm prepare\n", mstm->outp->base.base.name); - ret = drm_dp_update_payload_part1(&mstm->mgr); + ret = drm_dp_update_payload_part1(&mstm->mgr, 1); drm_for_each_encoder(encoder, mstm->outp->base.base.dev) { if (encoder->encoder_type == DRM_MODE_ENCODER_DPMST) { diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index d3b21d318b42..12b107acb6ee 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1250,7 +1250,7 @@ nouveau_ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm_dma = (void *)ttm; struct nouveau_drm *drm; struct device *dev; - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (ttm_tt_is_populated(ttm)) return 0; @@ -1273,7 +1273,7 @@ nouveau_ttm_tt_unpopulate(struct ttm_device *bdev, { struct nouveau_drm *drm; struct device *dev; - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (slave) return; diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index ec867fa880a4..751c2c075e09 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -423,7 +423,7 @@ radeon_mst_encoder_dpms(struct drm_encoder *encoder, int mode) drm_dp_mst_allocate_vcpi(&radeon_connector->mst_port->mst_mgr, radeon_connector->port, mst_enc->pbn, slots); - drm_dp_update_payload_part1(&radeon_connector->mst_port->mst_mgr); + drm_dp_update_payload_part1(&radeon_connector->mst_port->mst_mgr, 1); radeon_dp_mst_set_be_cntl(primary, mst_enc, radeon_connector->mst_port->hpd.hpd, true); @@ -452,7 +452,7 @@ radeon_mst_encoder_dpms(struct drm_encoder *encoder, int mode) return; drm_dp_mst_reset_vcpi_slots(&radeon_connector->mst_port->mst_mgr, mst_enc->port); - drm_dp_update_payload_part1(&radeon_connector->mst_port->mst_mgr); + drm_dp_update_payload_part1(&radeon_connector->mst_port->mst_mgr, 1); drm_dp_check_act_status(&radeon_connector->mst_port->mst_mgr); /* and this can also fail */ diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 7793249bc549..11b21d605584 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -545,14 +545,14 @@ static int radeon_ttm_tt_populate(struct ttm_device *bdev, { struct radeon_device *rdev = radeon_get_rdev(bdev); struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm); - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); if (gtt && gtt->userptr) { ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL); if (!ttm->sg) return -ENOMEM; - ttm->page_flags |= TTM_PAGE_FLAG_SG; + ttm->page_flags |= TTM_TT_FLAG_EXTERNAL; return 0; } @@ -569,13 +569,13 @@ static void radeon_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm { struct radeon_device *rdev = radeon_get_rdev(bdev); struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(rdev, ttm); - bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG); + bool slave = !!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL); radeon_ttm_tt_unbind(bdev, ttm); if (gtt && gtt->userptr) { kfree(ttm->sg); - ttm->page_flags &= ~TTM_PAGE_FLAG_SG; + ttm->page_flags &= ~TTM_TT_FLAG_EXTERNAL; return; } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 6b03f89a98d4..3ddb7c710a3d 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -186,10 +186,8 @@ static void tilcdc_fini(struct drm_device *dev) if (priv->mmio) iounmap(priv->mmio); - if (priv->wq) { - flush_workqueue(priv->wq); + if (priv->wq) destroy_workqueue(priv->wq); - } dev->dev_private = NULL; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3b22c0013dbf..d62b2013c367 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1115,8 +1115,8 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, return -EBUSY; if (!bo->ttm || !ttm_tt_is_populated(bo->ttm) || - bo->ttm->page_flags & TTM_PAGE_FLAG_SG || - bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED || + bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL || + bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED || !ttm_bo_get_unless_zero(bo)) { if (locked) dma_resv_unlock(bo->base.resv); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index c1a6fff4135b..72a94301bc95 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -147,7 +147,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, bool clear; int ret = 0; - if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) || + if (ttm && ((ttm->page_flags & TTM_TT_FLAG_SWAPPED) || dst_man->use_tt)) { ret = ttm_tt_populate(bdev, ttm, ctx); if (ret) @@ -169,7 +169,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, } clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm)); - if (!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC))) + if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC))) ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter); if (!src_iter->ops->maps_tt) diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index f56be5bc0861..33680c94127c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -162,9 +162,11 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, * Refuse to fault imported pages. This should be handled * (if at all) by redirecting mmap to the exporter. */ - if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) { - dma_resv_unlock(bo->base.resv); - return VM_FAULT_SIGBUS; + if (bo->ttm && (bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { + if (!(bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)) { + dma_resv_unlock(bo->base.resv); + return VM_FAULT_SIGBUS; + } } return 0; @@ -346,8 +348,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, } else if (unlikely(!page)) { break; } - page->index = drm_vma_node_start(&bo->base.vma_node) + - page_offset; pfn = page_to_pfn(page); } @@ -519,11 +519,6 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, switch (bo->resource->mem_type) { case TTM_PL_SYSTEM: - if (unlikely(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) { - ret = ttm_tt_swapin(bo->ttm); - if (unlikely(ret != 0)) - return ret; - } fallthrough; case TTM_PL_TT: ret = ttm_bo_vm_access_kmap(bo, offset, buf, len, write); diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index c961a788b519..1bba0a0ed3f9 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -371,7 +371,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, WARN_ON(!num_pages || ttm_tt_is_populated(tt)); WARN_ON(dma_addr && !pool->dev); - if (tt->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC) + if (tt->page_flags & TTM_TT_FLAG_ZERO_ALLOC) gfp_flags |= __GFP_ZERO; if (ctx->gfp_retry_mayfail) diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index dae52433beeb..7e83c00a3f48 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -68,12 +68,12 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) switch (bo->type) { case ttm_bo_type_device: if (zero_alloc) - page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + page_flags |= TTM_TT_FLAG_ZERO_ALLOC; break; case ttm_bo_type_kernel: break; case ttm_bo_type_sg: - page_flags |= TTM_PAGE_FLAG_SG; + page_flags |= TTM_TT_FLAG_EXTERNAL; break; default: pr_err("Illegal buffer object type\n"); @@ -84,6 +84,9 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) if (unlikely(bo->ttm == NULL)) return -ENOMEM; + WARN_ON(bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE && + !(bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL)); + return 0; } @@ -156,7 +159,7 @@ EXPORT_SYMBOL(ttm_tt_init); void ttm_tt_fini(struct ttm_tt *ttm) { - WARN_ON(ttm->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED); + WARN_ON(ttm->page_flags & TTM_TT_FLAG_PRIV_POPULATED); if (ttm->swap_storage) fput(ttm->swap_storage); @@ -178,7 +181,7 @@ int ttm_sg_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, ttm_tt_init_fields(ttm, bo, page_flags, caching); - if (page_flags & TTM_PAGE_FLAG_SG) + if (page_flags & TTM_TT_FLAG_EXTERNAL) ret = ttm_sg_tt_alloc_page_directory(ttm); else ret = ttm_dma_tt_alloc_page_directory(ttm); @@ -224,7 +227,7 @@ int ttm_tt_swapin(struct ttm_tt *ttm) fput(swap_storage); ttm->swap_storage = NULL; - ttm->page_flags &= ~TTM_PAGE_FLAG_SWAPPED; + ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED; return 0; @@ -279,7 +282,7 @@ int ttm_tt_swapout(struct ttm_device *bdev, struct ttm_tt *ttm, ttm_tt_unpopulate(bdev, ttm); ttm->swap_storage = swap_storage; - ttm->page_flags |= TTM_PAGE_FLAG_SWAPPED; + ttm->page_flags |= TTM_TT_FLAG_SWAPPED; return ttm->num_pages; @@ -289,17 +292,6 @@ out_err: return ret; } -static void ttm_tt_add_mapping(struct ttm_device *bdev, struct ttm_tt *ttm) -{ - pgoff_t i; - - if (ttm->page_flags & TTM_PAGE_FLAG_SG) - return; - - for (i = 0; i < ttm->num_pages; ++i) - ttm->pages[i]->mapping = bdev->dev_mapping; -} - int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) { @@ -311,7 +303,7 @@ int ttm_tt_populate(struct ttm_device *bdev, if (ttm_tt_is_populated(ttm)) return 0; - if (!(ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { atomic_long_add(ttm->num_pages, &ttm_pages_allocated); if (bdev->pool.use_dma32) atomic_long_add(ttm->num_pages, @@ -336,9 +328,8 @@ int ttm_tt_populate(struct ttm_device *bdev, if (ret) goto error; - ttm_tt_add_mapping(bdev, ttm); - ttm->page_flags |= TTM_PAGE_FLAG_PRIV_POPULATED; - if (unlikely(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) { + ttm->page_flags |= TTM_TT_FLAG_PRIV_POPULATED; + if (unlikely(ttm->page_flags & TTM_TT_FLAG_SWAPPED)) { ret = ttm_tt_swapin(ttm); if (unlikely(ret != 0)) { ttm_tt_unpopulate(bdev, ttm); @@ -349,7 +340,7 @@ int ttm_tt_populate(struct ttm_device *bdev, return 0; error: - if (!(ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { atomic_long_sub(ttm->num_pages, &ttm_pages_allocated); if (bdev->pool.use_dma32) atomic_long_sub(ttm->num_pages, @@ -359,39 +350,24 @@ error: } EXPORT_SYMBOL(ttm_tt_populate); -static void ttm_tt_clear_mapping(struct ttm_tt *ttm) -{ - pgoff_t i; - struct page **page = ttm->pages; - - if (ttm->page_flags & TTM_PAGE_FLAG_SG) - return; - - for (i = 0; i < ttm->num_pages; ++i) { - (*page)->mapping = NULL; - (*page++)->index = 0; - } -} - void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) { if (!ttm_tt_is_populated(ttm)) return; - ttm_tt_clear_mapping(ttm); if (bdev->funcs->ttm_tt_unpopulate) bdev->funcs->ttm_tt_unpopulate(bdev, ttm); else ttm_pool_free(&bdev->pool, ttm); - if (!(ttm->page_flags & TTM_PAGE_FLAG_SG)) { + if (!(ttm->page_flags & TTM_TT_FLAG_EXTERNAL)) { atomic_long_sub(ttm->num_pages, &ttm_pages_allocated); if (bdev->pool.use_dma32) atomic_long_sub(ttm->num_pages, &ttm_dma32_pages_allocated); } - ttm->page_flags &= ~TTM_PAGE_FLAG_PRIV_POPULATED; + ttm->page_flags &= ~TTM_TT_FLAG_PRIV_POPULATED; } #ifdef CONFIG_DEBUG_FS diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index c1deab2cf38d..bd46396a1ae0 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -83,7 +83,6 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, return 0; } - switch (args->param) { case DRM_V3D_PARAM_SUPPORTS_TFU: args->value = 1; @@ -97,6 +96,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, case DRM_V3D_PARAM_SUPPORTS_PERFMON: args->value = (v3d->ver >= 40); return 0; + case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT: + args->value = 1; + return 0; default: DRM_DEBUG("Unknown parameter %d\n", args->param); return -EINVAL; @@ -136,9 +138,8 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) struct v3d_file_priv *v3d_priv = file->driver_priv; enum v3d_queue q; - for (q = 0; q < V3D_MAX_QUEUES; q++) { + for (q = 0; q < V3D_MAX_QUEUES; q++) drm_sched_entity_destroy(&v3d_priv->sched_entity[q]); - } v3d_perfmon_close_file(v3d_priv); kfree(v3d_priv); @@ -147,7 +148,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file) DEFINE_DRM_GEM_FOPS(v3d_drm_fops); /* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP - * protection between clients. Note that render nodes would be be + * protection between clients. Note that render nodes would be * able to submit CLs that could access BOs from clients authenticated * with the master node. The TFU doesn't use the GMP, so it would * need to stay DRM_AUTH until we do buffer size/offset validation. @@ -219,7 +220,6 @@ static int v3d_platform_drm_probe(struct platform_device *pdev) u32 mmu_debug; u32 ident1; - v3d = devm_drm_dev_alloc(dev, &v3d_drm_driver, struct v3d_dev, drm); if (IS_ERR(v3d)) return PTR_ERR(v3d); diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index b900a050d5e2..b74b1351bfc8 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -19,15 +19,6 @@ struct reset_control; #define GMP_GRANULARITY (128 * 1024) -/* Enum for each of the V3D queues. */ -enum v3d_queue { - V3D_BIN, - V3D_RENDER, - V3D_TFU, - V3D_CSD, - V3D_CACHE_CLEAN, -}; - #define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1) struct v3d_queue_state { @@ -294,6 +285,21 @@ struct v3d_csd_job { struct drm_v3d_submit_csd args; }; +struct v3d_submit_outsync { + struct drm_syncobj *syncobj; +}; + +struct v3d_submit_ext { + u32 flags; + u32 wait_stage; + + u32 in_sync_count; + u64 in_syncs; + + u32 out_sync_count; + struct v3d_submit_outsync *out_syncs; +}; + /** * __wait_for - magic wait macro * diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index ead0be8d48a7..6a000d77c568 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -392,6 +392,9 @@ v3d_render_job_free(struct kref *ref) void v3d_job_cleanup(struct v3d_job *job) { + if (!job) + return; + drm_sched_job_cleanup(&job->base); v3d_job_put(job); } @@ -416,7 +419,7 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, return -EINVAL; ret = drm_gem_dma_resv_wait(file_priv, args->handle, - true, timeout_jiffies); + true, timeout_jiffies); /* Decrement the user's timeout, in case we got interrupted * such that the ioctl will be restarted. @@ -435,41 +438,83 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, } static int -v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, - struct v3d_job *job, void (*free)(struct kref *ref), - u32 in_sync, enum v3d_queue queue) +v3d_job_add_deps(struct drm_file *file_priv, struct v3d_job *job, + u32 in_sync, u32 point) { struct dma_fence *in_fence = NULL; - struct v3d_file_priv *v3d_priv = file_priv->driver_priv; int ret; + ret = drm_syncobj_find_fence(file_priv, in_sync, point, 0, &in_fence); + if (ret == -EINVAL) + return ret; + + return drm_sched_job_add_dependency(&job->base, in_fence); +} + +static int +v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, + void **container, size_t size, void (*free)(struct kref *ref), + u32 in_sync, struct v3d_submit_ext *se, enum v3d_queue queue) +{ + struct v3d_file_priv *v3d_priv = file_priv->driver_priv; + struct v3d_job *job; + bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); + int ret, i; + + *container = kcalloc(1, size, GFP_KERNEL); + if (!*container) { + DRM_ERROR("Cannot allocate memory for v3d job."); + return -ENOMEM; + } + + job = *container; job->v3d = v3d; job->free = free; ret = pm_runtime_get_sync(v3d->drm.dev); if (ret < 0) - return ret; + goto fail; ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue], v3d_priv); if (ret) - goto fail; - - ret = drm_syncobj_find_fence(file_priv, in_sync, 0, 0, &in_fence); - if (ret == -EINVAL) goto fail_job; - ret = drm_sched_job_add_dependency(&job->base, in_fence); - if (ret) - goto fail_job; + if (has_multisync) { + if (se->in_sync_count && se->wait_stage == queue) { + struct drm_v3d_sem __user *handle = u64_to_user_ptr(se->in_syncs); + + for (i = 0; i < se->in_sync_count; i++) { + struct drm_v3d_sem in; + + ret = copy_from_user(&in, handle++, sizeof(in)); + if (ret) { + DRM_DEBUG("Failed to copy wait dep handle.\n"); + goto fail_deps; + } + ret = v3d_job_add_deps(file_priv, job, in.handle, 0); + if (ret) + goto fail_deps; + } + } + } else { + ret = v3d_job_add_deps(file_priv, job, in_sync, 0); + if (ret) + goto fail_deps; + } kref_init(&job->refcount); return 0; -fail_job: + +fail_deps: drm_sched_job_cleanup(&job->base); -fail: +fail_job: pm_runtime_put_autosuspend(v3d->drm.dev); +fail: + kfree(*container); + *container = NULL; + return ret; } @@ -491,25 +536,171 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, struct v3d_job *job, struct ww_acquire_ctx *acquire_ctx, u32 out_sync, + struct v3d_submit_ext *se, struct dma_fence *done_fence) { struct drm_syncobj *sync_out; + bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC); int i; for (i = 0; i < job->bo_count; i++) { /* XXX: Use shared fences for read-only objects. */ dma_resv_add_excl_fence(job->bo[i]->resv, - job->done_fence); + job->done_fence); } drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); /* Update the return sync object for the job */ - sync_out = drm_syncobj_find(file_priv, out_sync); - if (sync_out) { - drm_syncobj_replace_fence(sync_out, done_fence); - drm_syncobj_put(sync_out); + /* If it only supports a single signal semaphore*/ + if (!has_multisync) { + sync_out = drm_syncobj_find(file_priv, out_sync); + if (sync_out) { + drm_syncobj_replace_fence(sync_out, done_fence); + drm_syncobj_put(sync_out); + } + return; } + + /* If multiple semaphores extension is supported */ + if (se->out_sync_count) { + for (i = 0; i < se->out_sync_count; i++) { + drm_syncobj_replace_fence(se->out_syncs[i].syncobj, + done_fence); + drm_syncobj_put(se->out_syncs[i].syncobj); + } + kvfree(se->out_syncs); + } +} + +static void +v3d_put_multisync_post_deps(struct v3d_submit_ext *se) +{ + unsigned int i; + + if (!(se && se->out_sync_count)) + return; + + for (i = 0; i < se->out_sync_count; i++) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); +} + +static int +v3d_get_multisync_post_deps(struct drm_file *file_priv, + struct v3d_submit_ext *se, + u32 count, u64 handles) +{ + struct drm_v3d_sem __user *post_deps; + int i, ret; + + if (!count) + return 0; + + se->out_syncs = (struct v3d_submit_outsync *) + kvmalloc_array(count, + sizeof(struct v3d_submit_outsync), + GFP_KERNEL); + if (!se->out_syncs) + return -ENOMEM; + + post_deps = u64_to_user_ptr(handles); + + for (i = 0; i < count; i++) { + struct drm_v3d_sem out; + + ret = copy_from_user(&out, post_deps++, sizeof(out)); + if (ret) { + DRM_DEBUG("Failed to copy post dep handles\n"); + goto fail; + } + + se->out_syncs[i].syncobj = drm_syncobj_find(file_priv, + out.handle); + if (!se->out_syncs[i].syncobj) { + ret = -EINVAL; + goto fail; + } + } + se->out_sync_count = count; + + return 0; + +fail: + for (i--; i >= 0; i--) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); + + return ret; +} + +/* Get data for multiple binary semaphores synchronization. Parse syncobj + * to be signaled when job completes (out_sync). + */ +static int +v3d_get_multisync_submit_deps(struct drm_file *file_priv, + struct drm_v3d_extension __user *ext, + void *data) +{ + struct drm_v3d_multi_sync multisync; + struct v3d_submit_ext *se = data; + int ret; + + ret = copy_from_user(&multisync, ext, sizeof(multisync)); + if (ret) + return ret; + + if (multisync.pad) + return -EINVAL; + + ret = v3d_get_multisync_post_deps(file_priv, data, multisync.out_sync_count, + multisync.out_syncs); + if (ret) + return ret; + + se->in_sync_count = multisync.in_sync_count; + se->in_syncs = multisync.in_syncs; + se->flags |= DRM_V3D_EXT_ID_MULTI_SYNC; + se->wait_stage = multisync.wait_stage; + + return 0; +} + +/* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data + * according to the extension id (name). + */ +static int +v3d_get_extensions(struct drm_file *file_priv, + u64 ext_handles, + void *data) +{ + struct drm_v3d_extension __user *user_ext; + int ret; + + user_ext = u64_to_user_ptr(ext_handles); + while (user_ext) { + struct drm_v3d_extension ext; + + if (copy_from_user(&ext, user_ext, sizeof(ext))) { + DRM_DEBUG("Failed to copy submit extension\n"); + return -EFAULT; + } + + switch (ext.id) { + case DRM_V3D_EXT_ID_MULTI_SYNC: + ret = v3d_get_multisync_submit_deps(file_priv, user_ext, data); + if (ret) + return ret; + break; + default: + DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); + return -EINVAL; + } + + user_ext = u64_to_user_ptr(ext.next); + } + + return 0; } /** @@ -531,8 +722,9 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_cl *args = data; + struct v3d_submit_ext se = {0}; struct v3d_bin_job *bin = NULL; - struct v3d_render_job *render; + struct v3d_render_job *render = NULL; struct v3d_job *clean_job = NULL; struct v3d_job *last_job; struct ww_acquire_ctx acquire_ctx; @@ -540,44 +732,38 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end); - if (args->pad != 0) + if (args->pad) return -EINVAL; - if (args->flags != 0 && - args->flags != DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { + if (args->flags && + args->flags & ~(DRM_V3D_SUBMIT_CL_FLUSH_CACHE | + DRM_V3D_SUBMIT_EXTENSION)) { DRM_INFO("invalid flags: %d\n", args->flags); return -EINVAL; } - render = kcalloc(1, sizeof(*render), GFP_KERNEL); - if (!render) - return -ENOMEM; + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions, &se); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + + ret = v3d_job_init(v3d, file_priv, (void *)&render, sizeof(*render), + v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER); + if (ret) + goto fail; render->start = args->rcl_start; render->end = args->rcl_end; INIT_LIST_HEAD(&render->unref_list); - ret = v3d_job_init(v3d, file_priv, &render->base, - v3d_render_job_free, args->in_sync_rcl, V3D_RENDER); - if (ret) { - kfree(render); - return ret; - } - if (args->bcl_start != args->bcl_end) { - bin = kcalloc(1, sizeof(*bin), GFP_KERNEL); - if (!bin) { - v3d_job_cleanup(&render->base); - return -ENOMEM; - } - - ret = v3d_job_init(v3d, file_priv, &bin->base, - v3d_job_free, args->in_sync_bcl, V3D_BIN); - if (ret) { - v3d_job_cleanup(&render->base); - kfree(bin); - return ret; - } + ret = v3d_job_init(v3d, file_priv, (void *)&bin, sizeof(*bin), + v3d_job_free, args->in_sync_bcl, &se, V3D_BIN); + if (ret) + goto fail; bin->start = args->bcl_start; bin->end = args->bcl_end; @@ -588,18 +774,10 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) { - clean_job = kcalloc(1, sizeof(*clean_job), GFP_KERNEL); - if (!clean_job) { - ret = -ENOMEM; + ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job), + v3d_job_free, 0, 0, V3D_CACHE_CLEAN); + if (ret) goto fail; - } - - ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0, V3D_CACHE_CLEAN); - if (ret) { - kfree(clean_job); - clean_job = NULL; - goto fail; - } last_job = clean_job; } else { @@ -657,6 +835,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, last_job, &acquire_ctx, args->out_sync, + &se, last_job->done_fence); if (bin) @@ -672,11 +851,10 @@ fail_unreserve: drm_gem_unlock_reservations(last_job->bo, last_job->bo_count, &acquire_ctx); fail: - if (bin) - v3d_job_cleanup(&bin->base); - v3d_job_cleanup(&render->base); - if (clean_job) - v3d_job_cleanup(clean_job); + v3d_job_cleanup((void *)bin); + v3d_job_cleanup((void *)render); + v3d_job_cleanup(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -696,28 +874,36 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, { struct v3d_dev *v3d = to_v3d_dev(dev); struct drm_v3d_submit_tfu *args = data; - struct v3d_tfu_job *job; + struct v3d_submit_ext se = {0}; + struct v3d_tfu_job *job = NULL; struct ww_acquire_ctx acquire_ctx; int ret = 0; trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia); - job = kcalloc(1, sizeof(*job), GFP_KERNEL); - if (!job) - return -ENOMEM; - - ret = v3d_job_init(v3d, file_priv, &job->base, - v3d_job_free, args->in_sync, V3D_TFU); - if (ret) { - kfree(job); - return ret; + if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { + DRM_DEBUG("invalid flags: %d\n", args->flags); + return -EINVAL; } + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions, &se); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } + } + + ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), + v3d_job_free, args->in_sync, &se, V3D_TFU); + if (ret) + goto fail; + job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles), sizeof(*job->base.bo), GFP_KERNEL); if (!job->base.bo) { - v3d_job_cleanup(&job->base); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } job->args = *args; @@ -757,6 +943,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, v3d_attach_fences_and_unlock_reservation(file_priv, &job->base, &acquire_ctx, args->out_sync, + &se, job->base.done_fence); v3d_job_put(&job->base); @@ -764,7 +951,8 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, return 0; fail: - v3d_job_cleanup(&job->base); + v3d_job_cleanup((void *)job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -785,41 +973,44 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_csd *args = data; - struct v3d_csd_job *job; - struct v3d_job *clean_job; + struct v3d_submit_ext se = {0}; + struct v3d_csd_job *job = NULL; + struct v3d_job *clean_job = NULL; struct ww_acquire_ctx acquire_ctx; int ret; trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]); + if (args->pad) + return -EINVAL; + if (!v3d_has_csd(v3d)) { DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n"); return -EINVAL; } - job = kcalloc(1, sizeof(*job), GFP_KERNEL); - if (!job) - return -ENOMEM; - - ret = v3d_job_init(v3d, file_priv, &job->base, - v3d_job_free, args->in_sync, V3D_CSD); - if (ret) { - kfree(job); - return ret; + if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) { + DRM_INFO("invalid flags: %d\n", args->flags); + return -EINVAL; } - clean_job = kcalloc(1, sizeof(*clean_job), GFP_KERNEL); - if (!clean_job) { - v3d_job_cleanup(&job->base); - return -ENOMEM; + if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { + ret = v3d_get_extensions(file_priv, args->extensions, &se); + if (ret) { + DRM_DEBUG("Failed to get extensions.\n"); + return ret; + } } - ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0, V3D_CACHE_CLEAN); - if (ret) { - v3d_job_cleanup(&job->base); - kfree(clean_job); - return ret; - } + ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job), + v3d_job_free, args->in_sync, &se, V3D_CSD); + if (ret) + goto fail; + + ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job), + v3d_job_free, 0, 0, V3D_CACHE_CLEAN); + if (ret) + goto fail; job->args = *args; @@ -856,6 +1047,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, clean_job, &acquire_ctx, args->out_sync, + &se, clean_job->done_fence); v3d_job_put(&job->base); @@ -868,8 +1060,9 @@ fail_unreserve: drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count, &acquire_ctx); fail: - v3d_job_cleanup(&job->base); + v3d_job_cleanup((void *)job); v3d_job_cleanup(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -903,8 +1096,7 @@ v3d_gem_init(struct drm_device *dev) if (!v3d->pt) { drm_mm_takedown(&v3d->mm); dev_err(v3d->drm.dev, - "Failed to allocate page tables. " - "Please ensure you have CMA enabled.\n"); + "Failed to allocate page tables. Please ensure you have CMA enabled.\n"); return -ENOMEM; } diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 9d963f1fda8f..749db18dcfa2 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -29,6 +29,8 @@ #include #include #include +#include +#include #include #include @@ -155,6 +157,35 @@ static void virtio_gpu_config_changed(struct virtio_device *vdev) schedule_work(&vgdev->config_changed_work); } +static __poll_t virtio_gpu_poll(struct file *filp, + struct poll_table_struct *wait) +{ + struct drm_file *drm_file = filp->private_data; + struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv; + struct drm_device *dev = drm_file->minor->dev; + struct drm_pending_event *e = NULL; + __poll_t mask = 0; + + if (!vfpriv->ring_idx_mask) + return drm_poll(filp, wait); + + poll_wait(filp, &drm_file->event_wait, wait); + + if (!list_empty(&drm_file->event_list)) { + spin_lock_irq(&dev->event_lock); + e = list_first_entry(&drm_file->event_list, + struct drm_pending_event, link); + drm_file->event_space += e->event->length; + list_del(&e->link); + spin_unlock_irq(&dev->event_lock); + + kfree(e); + mask |= EPOLLIN | EPOLLRDNORM; + } + + return mask; +} + static struct virtio_device_id id_table[] = { { VIRTIO_ID_GPU, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -194,7 +225,17 @@ MODULE_AUTHOR("Dave Airlie "); MODULE_AUTHOR("Gerd Hoffmann "); MODULE_AUTHOR("Alon Levy"); -DEFINE_DRM_GEM_FOPS(virtio_gpu_driver_fops); +static const struct file_operations virtio_gpu_driver_fops = { + .owner = THIS_MODULE, + .open = drm_open, + .release = drm_release, + .unlocked_ioctl = drm_ioctl, + .compat_ioctl = drm_compat_ioctl, + .poll = virtio_gpu_poll, + .read = drm_read, + .llseek = noop_llseek, + .mmap = drm_gem_mmap +}; static const struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index cb60d52c2bd1..e0265fe74aa5 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -138,11 +138,18 @@ struct virtio_gpu_fence_driver { spinlock_t lock; }; +#define VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL 0x10000000 +struct virtio_gpu_fence_event { + struct drm_pending_event base; + struct drm_event event; +}; + struct virtio_gpu_fence { struct dma_fence f; uint32_t ring_idx; uint64_t fence_id; bool emit_fence_info; + struct virtio_gpu_fence_event *e; struct virtio_gpu_fence_driver *drv; struct list_head node; }; diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c index 98a00c1e654d..f28357dbde35 100644 --- a/drivers/gpu/drm/virtio/virtgpu_fence.c +++ b/drivers/gpu/drm/virtio/virtgpu_fence.c @@ -152,11 +152,21 @@ void virtio_gpu_fence_event_process(struct virtio_gpu_device *vgdev, continue; dma_fence_signal_locked(&curr->f); + if (curr->e) { + drm_send_event(vgdev->ddev, &curr->e->base); + curr->e = NULL; + } + list_del(&curr->node); dma_fence_put(&curr->f); } dma_fence_signal_locked(&signaled->f); + if (signaled->e) { + drm_send_event(vgdev->ddev, &signaled->e->base); + signaled->e = NULL; + } + list_del(&signaled->node); dma_fence_put(&signaled->f); break; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index be7b22a03884..5618a1d5879c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -38,6 +38,36 @@ VIRTGPU_BLOB_FLAG_USE_SHAREABLE | \ VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE) +static int virtio_gpu_fence_event_create(struct drm_device *dev, + struct drm_file *file, + struct virtio_gpu_fence *fence, + uint32_t ring_idx) +{ + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct virtio_gpu_fence_event *e = NULL; + int ret; + + if (!(vfpriv->ring_idx_mask & (1 << ring_idx))) + return 0; + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return -ENOMEM; + + e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL; + e->event.length = sizeof(e->event); + + ret = drm_event_reserve_init(dev, file, &e->base, &e->event); + if (ret) + goto free; + + fence->e = e; + return 0; +free: + kfree(e); + return ret; +} + /* Must be called with &virtio_gpu_fpriv.struct_mutex held. */ static void virtio_gpu_create_context_locked(struct virtio_gpu_device *vgdev, struct virtio_gpu_fpriv *vfpriv) @@ -195,6 +225,10 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, goto out_unresv; } + ret = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx); + if (ret) + goto out_unresv; + if (out_fence_fd >= 0) { sync_file = sync_file_create(&out_fence->f); if (!sync_file) { @@ -252,6 +286,12 @@ static int virtio_gpu_getparam_ioctl(struct drm_device *dev, void *data, case VIRTGPU_PARAM_CROSS_DEVICE: value = vgdev->has_resource_assign_uuid ? 1 : 0; break; + case VIRTGPU_PARAM_CONTEXT_INIT: + value = vgdev->has_context_init ? 1 : 0; + break; + case VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs: + value = vgdev->capset_id_mask; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/vmwgfx/ttm_memory.c b/drivers/gpu/drm/vmwgfx/ttm_memory.c index edd17c30d5a5..7f7fe35fc21d 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_memory.c +++ b/drivers/gpu/drm/vmwgfx/ttm_memory.c @@ -468,7 +468,6 @@ void ttm_mem_global_release(struct ttm_mem_global *glob) struct ttm_mem_zone *zone; unsigned int i; - flush_workqueue(glob->swap_queue); destroy_workqueue(glob->swap_queue); glob->swap_queue = NULL; for (i = 0; i < glob->num_zones; ++i) { diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index f5fd5b786607..0e0bcd0da852 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -47,3 +47,5 @@ config INTEL_MEI_TXE Intel Bay Trail source "drivers/misc/mei/hdcp/Kconfig" +source "drivers/misc/mei/pxp/Kconfig" + diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile index f1c76f7ee804..d8e5165917f2 100644 --- a/drivers/misc/mei/Makefile +++ b/drivers/misc/mei/Makefile @@ -26,3 +26,4 @@ mei-$(CONFIG_EVENT_TRACING) += mei-trace.o CFLAGS_mei-trace.o = -I$(src) obj-$(CONFIG_INTEL_MEI_HDCP) += hdcp/ +obj-$(CONFIG_INTEL_MEI_PXP) += pxp/ diff --git a/drivers/misc/mei/pxp/Kconfig b/drivers/misc/mei/pxp/Kconfig new file mode 100644 index 000000000000..4029b96afc04 --- /dev/null +++ b/drivers/misc/mei/pxp/Kconfig @@ -0,0 +1,13 @@ + +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2020, Intel Corporation. All rights reserved. +# +config INTEL_MEI_PXP + tristate "Intel PXP services of ME Interface" + select INTEL_MEI_ME + depends on DRM_I915 + help + MEI Support for PXP Services on Intel platforms. + + Enables the ME FW services required for PXP support through + I915 display driver of Intel. diff --git a/drivers/misc/mei/pxp/Makefile b/drivers/misc/mei/pxp/Makefile new file mode 100644 index 000000000000..0329950d5794 --- /dev/null +++ b/drivers/misc/mei/pxp/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2020, Intel Corporation. All rights reserved. +# +# Makefile - PXP client driver for Intel MEI Bus Driver. + +obj-$(CONFIG_INTEL_MEI_PXP) += mei_pxp.o diff --git a/drivers/misc/mei/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c new file mode 100644 index 000000000000..f7380d387bab --- /dev/null +++ b/drivers/misc/mei/pxp/mei_pxp.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2020 - 2021 Intel Corporation + */ + +/** + * DOC: MEI_PXP Client Driver + * + * The mei_pxp driver acts as a translation layer between PXP + * protocol implementer (I915) and ME FW by translating PXP + * negotiation messages to ME FW command payloads and vice versa. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mei_pxp.h" + +/** + * mei_pxp_send_message() - Sends a PXP message to ME FW. + * @dev: device corresponding to the mei_cl_device + * @message: a message buffer to send + * @size: size of the message + * Return: 0 on Success, <0 on Failure + */ +static int +mei_pxp_send_message(struct device *dev, const void *message, size_t size) +{ + struct mei_cl_device *cldev; + ssize_t byte; + + if (!dev || !message) + return -EINVAL; + + cldev = to_mei_cl_device(dev); + + /* temporary drop const qualifier till the API is fixed */ + byte = mei_cldev_send(cldev, (u8 *)message, size); + if (byte < 0) { + dev_dbg(dev, "mei_cldev_send failed. %zd\n", byte); + return byte; + } + + return 0; +} + +/** + * mei_pxp_receive_message() - Receives a PXP message from ME FW. + * @dev: device corresponding to the mei_cl_device + * @buffer: a message buffer to contain the received message + * @size: size of the buffer + * Return: bytes sent on Success, <0 on Failure + */ +static int +mei_pxp_receive_message(struct device *dev, void *buffer, size_t size) +{ + struct mei_cl_device *cldev; + ssize_t byte; + + if (!dev || !buffer) + return -EINVAL; + + cldev = to_mei_cl_device(dev); + + byte = mei_cldev_recv(cldev, buffer, size); + if (byte < 0) { + dev_dbg(dev, "mei_cldev_recv failed. %zd\n", byte); + return byte; + } + + return byte; +} + +static const struct i915_pxp_component_ops mei_pxp_ops = { + .owner = THIS_MODULE, + .send = mei_pxp_send_message, + .recv = mei_pxp_receive_message, +}; + +static int mei_component_master_bind(struct device *dev) +{ + struct mei_cl_device *cldev = to_mei_cl_device(dev); + struct i915_pxp_component *comp_master = mei_cldev_get_drvdata(cldev); + int ret; + + comp_master->ops = &mei_pxp_ops; + comp_master->tee_dev = dev; + ret = component_bind_all(dev, comp_master); + if (ret < 0) + return ret; + + return 0; +} + +static void mei_component_master_unbind(struct device *dev) +{ + struct mei_cl_device *cldev = to_mei_cl_device(dev); + struct i915_pxp_component *comp_master = mei_cldev_get_drvdata(cldev); + + component_unbind_all(dev, comp_master); +} + +static const struct component_master_ops mei_component_master_ops = { + .bind = mei_component_master_bind, + .unbind = mei_component_master_unbind, +}; + +/** + * mei_pxp_component_match - compare function for matching mei pxp. + * + * The function checks if the driver is i915, the subcomponent is PXP + * and the grand parent of pxp and the parent of i915 are the same + * PCH device. + * + * @dev: master device + * @subcomponent: subcomponent to match (I915_COMPONENT_PXP) + * @data: compare data (mei pxp device) + * + * Return: + * * 1 - if components match + * * 0 - otherwise + */ +static int mei_pxp_component_match(struct device *dev, int subcomponent, + void *data) +{ + struct device *base = data; + + if (strcmp(dev->driver->name, "i915") || + subcomponent != I915_COMPONENT_PXP) + return 0; + + base = base->parent; + if (!base) + return 0; + + base = base->parent; + dev = dev->parent; + + return (base && dev && dev == base); +} + +static int mei_pxp_probe(struct mei_cl_device *cldev, + const struct mei_cl_device_id *id) +{ + struct i915_pxp_component *comp_master; + struct component_match *master_match; + int ret; + + ret = mei_cldev_enable(cldev); + if (ret < 0) { + dev_err(&cldev->dev, "mei_cldev_enable Failed. %d\n", ret); + goto enable_err_exit; + } + + comp_master = kzalloc(sizeof(*comp_master), GFP_KERNEL); + if (!comp_master) { + ret = -ENOMEM; + goto err_exit; + } + + master_match = NULL; + component_match_add_typed(&cldev->dev, &master_match, + mei_pxp_component_match, &cldev->dev); + if (IS_ERR_OR_NULL(master_match)) { + ret = -ENOMEM; + goto err_exit; + } + + mei_cldev_set_drvdata(cldev, comp_master); + ret = component_master_add_with_match(&cldev->dev, + &mei_component_master_ops, + master_match); + if (ret < 0) { + dev_err(&cldev->dev, "Master comp add failed %d\n", ret); + goto err_exit; + } + + return 0; + +err_exit: + mei_cldev_set_drvdata(cldev, NULL); + kfree(comp_master); + mei_cldev_disable(cldev); +enable_err_exit: + return ret; +} + +static void mei_pxp_remove(struct mei_cl_device *cldev) +{ + struct i915_pxp_component *comp_master = mei_cldev_get_drvdata(cldev); + int ret; + + component_master_del(&cldev->dev, &mei_component_master_ops); + kfree(comp_master); + mei_cldev_set_drvdata(cldev, NULL); + + ret = mei_cldev_disable(cldev); + if (ret) + dev_warn(&cldev->dev, "mei_cldev_disable() failed\n"); +} + +/* fbf6fcf1-96cf-4e2e-a6a6-1bab8cbe36b1 : PAVP GUID*/ +#define MEI_GUID_PXP GUID_INIT(0xfbf6fcf1, 0x96cf, 0x4e2e, 0xA6, \ + 0xa6, 0x1b, 0xab, 0x8c, 0xbe, 0x36, 0xb1) + +static struct mei_cl_device_id mei_pxp_tbl[] = { + { .uuid = MEI_GUID_PXP, .version = MEI_CL_VERSION_ANY }, + { } +}; +MODULE_DEVICE_TABLE(mei, mei_pxp_tbl); + +static struct mei_cl_driver mei_pxp_driver = { + .id_table = mei_pxp_tbl, + .name = KBUILD_MODNAME, + .probe = mei_pxp_probe, + .remove = mei_pxp_remove, +}; + +module_mei_cl_driver(mei_pxp_driver); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MEI PXP"); diff --git a/drivers/misc/mei/pxp/mei_pxp.h b/drivers/misc/mei/pxp/mei_pxp.h new file mode 100644 index 000000000000..e7b15373fefd --- /dev/null +++ b/drivers/misc/mei/pxp/mei_pxp.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2020 Intel Corporation + * + * Authors: + * Vitaly Lubart + */ + +#ifndef __MEI_PXP_H__ +#define __MEI_PXP_H__ + +/* me_pxp_status: Enumeration of all PXP Status Codes */ +enum me_pxp_status { + ME_PXP_STATUS_SUCCESS = 0x0000, + +}; + +#endif /* __MEI_PXP_H__ */ diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index a445298e1c25..061d87313fac 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -919,9 +919,20 @@ struct drm_bridge *devm_drm_panel_bridge_add(struct device *dev, struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev, struct drm_panel *panel, u32 connector_type); -struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, struct device_node *node, - u32 port, u32 endpoint); struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge); #endif +#if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL_BRIDGE) +struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, struct device_node *node, + u32 port, u32 endpoint); +#else +static inline struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, + struct device_node *node, + u32 port, + u32 endpoint) +{ + return ERR_PTR(-ENODEV); +} +#endif + #endif diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 1d5b3dbb6e56..b52df4db3e8f 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -453,6 +453,7 @@ struct drm_panel; # define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) # define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) # define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ /* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ #define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ @@ -537,6 +538,9 @@ struct drm_panel; #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 #define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 +/* DFP Capability Extension */ +#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ + /* Link Configuration */ #define DP_LINK_BW_SET 0x100 # define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ @@ -688,6 +692,7 @@ struct drm_panel; #define DP_DSC_ENABLE 0x160 /* DP 1.4 */ # define DP_DECOMPRESSION_EN (1 << 0) +#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ #define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ # define DP_PSR_ENABLE BIT(0) @@ -743,6 +748,7 @@ struct drm_panel; # define DP_RECEIVE_PORT_0_STATUS (1 << 0) # define DP_RECEIVE_PORT_1_STATUS (1 << 1) # define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ +# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ #define DP_ADJUST_REQUEST_LANE0_1 0x206 #define DP_ADJUST_REQUEST_LANE2_3 0x207 @@ -865,6 +871,8 @@ struct drm_panel; # define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 # define DP_PHY_TEST_PATTERN_CP2520 0x5 +#define DP_PHY_SQUARE_PATTERN 0x249 + #define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A #define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 #define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 @@ -1109,6 +1117,18 @@ struct drm_panel; #define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f +#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 +#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 + +/* DSC Extended Capability Branch Total DSC Resources */ +#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ +# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) +# define DP_DSC_DECODER_COUNT_SHIFT 5 +#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ +# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 + /* Protocol Converter Extension */ /* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ #define DP_CEC_TUNNELING_CAPABILITY 0x3000 @@ -1319,6 +1339,10 @@ struct drm_panel; #define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ #define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ #define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ +#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ +# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) +/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ +#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ enum drm_dp_phy { DP_PHY_DPRX, @@ -1490,6 +1514,8 @@ u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE], int lane); u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE], int lane); +u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], unsigned int lane); diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index ddb9231d0309..78044ac5b59b 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -554,6 +554,8 @@ struct drm_dp_mst_topology_state { struct drm_private_state base; struct list_head vcpis; struct drm_dp_mst_topology_mgr *mgr; + u8 total_avail_slots; + u8 start_slot; }; #define to_dp_mst_topology_mgr(x) container_of(x, struct drm_dp_mst_topology_mgr, base) @@ -806,6 +808,7 @@ int drm_dp_mst_get_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp void drm_dp_mst_reset_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); +void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_t link_encoding_cap); void drm_dp_mst_deallocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); @@ -815,7 +818,7 @@ int drm_dp_find_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, int pbn); -int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr); +int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr, int start_slot); int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr); diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index 4e0258a61311..e86925cf07b9 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -16,12 +16,16 @@ void drm_fb_memcpy_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vadd struct drm_rect *clip); void drm_fb_swab(void *dst, void *src, struct drm_framebuffer *fb, struct drm_rect *clip, bool cached); +void drm_fb_xrgb8888_to_rgb332(void *dst, void *vaddr, struct drm_framebuffer *fb, + struct drm_rect *clip); void drm_fb_xrgb8888_to_rgb565(void *dst, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip, bool swab); void drm_fb_xrgb8888_to_rgb565_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip, bool swab); +void drm_fb_xrgb8888_to_rgb888(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip); void drm_fb_xrgb8888_to_rgb888_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip); diff --git a/include/drm/gud.h b/include/drm/gud.h index 0b46b54fe56e..c52a8ba4ae4e 100644 --- a/include/drm/gud.h +++ b/include/drm/gud.h @@ -246,10 +246,12 @@ struct gud_state_req { /* Get supported pixel formats as a byte array of GUD_PIXEL_FORMAT_* */ #define GUD_REQ_GET_FORMATS 0x40 #define GUD_FORMATS_MAX_NUM 32 - /* R1 is a 1-bit monochrome transfer format presented to userspace as XRGB8888 */ - #define GUD_PIXEL_FORMAT_R1 0x01 + #define GUD_PIXEL_FORMAT_R1 0x01 /* 1-bit monochrome */ + #define GUD_PIXEL_FORMAT_R8 0x08 /* 8-bit greyscale */ #define GUD_PIXEL_FORMAT_XRGB1111 0x20 + #define GUD_PIXEL_FORMAT_RGB332 0x30 #define GUD_PIXEL_FORMAT_RGB565 0x40 + #define GUD_PIXEL_FORMAT_RGB888 0x50 #define GUD_PIXEL_FORMAT_XRGB8888 0x80 #define GUD_PIXEL_FORMAT_ARGB8888 0x81 diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h index 55c3b123581b..c1e2a43d2d1e 100644 --- a/include/drm/i915_component.h +++ b/include/drm/i915_component.h @@ -29,6 +29,7 @@ enum i915_component_type { I915_COMPONENT_AUDIO = 1, I915_COMPONENT_HDCP, + I915_COMPONENT_PXP }; /* MAX_PORT is the number of port diff --git a/include/drm/i915_pxp_tee_interface.h b/include/drm/i915_pxp_tee_interface.h new file mode 100644 index 000000000000..af593ec64469 --- /dev/null +++ b/include/drm/i915_pxp_tee_interface.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2020 Intel Corporation + */ + +#ifndef _I915_PXP_TEE_INTERFACE_H_ +#define _I915_PXP_TEE_INTERFACE_H_ + +#include +#include + +/** + * struct i915_pxp_component_ops - ops for PXP services. + * @owner: Module providing the ops + * @send: sends data to PXP + * @receive: receives data from PXP + */ +struct i915_pxp_component_ops { + /** + * @owner: owner of the module provding the ops + */ + struct module *owner; + + int (*send)(struct device *dev, const void *message, size_t size); + int (*recv)(struct device *dev, void *buffer, size_t size); +}; + +/** + * struct i915_pxp_component - Used for communication between i915 and TEE + * drivers for the PXP services + * @tee_dev: device that provide the PXP service from TEE Bus. + * @pxp_ops: Ops implemented by TEE driver, used by i915 driver. + */ +struct i915_pxp_component { + struct device *tee_dev; + const struct i915_pxp_component_ops *ops; + + /* To protect the above members. */ + struct mutex mutex; +}; + +#endif /* _I915_TEE_PXP_INTERFACE_H_ */ diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index cbe03d45e883..0a4ddec78d8f 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -65,7 +65,7 @@ struct ttm_device_funcs { * ttm_tt_create * * @bo: The buffer object to create the ttm for. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * * Create a struct ttm_tt to back data with system memory pages. * No pages are actually allocated. diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 89b15d673b22..f20832139815 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -38,36 +38,70 @@ struct ttm_resource; struct ttm_buffer_object; struct ttm_operation_ctx; -#define TTM_PAGE_FLAG_SWAPPED (1 << 4) -#define TTM_PAGE_FLAG_ZERO_ALLOC (1 << 6) -#define TTM_PAGE_FLAG_SG (1 << 8) -#define TTM_PAGE_FLAG_NO_RETRY (1 << 9) - -#define TTM_PAGE_FLAG_PRIV_POPULATED (1 << 31) - /** - * struct ttm_tt - * - * @pages: Array of pages backing the data. - * @page_flags: see TTM_PAGE_FLAG_* - * @num_pages: Number of pages in the page array. - * @sg: for SG objects via dma-buf - * @dma_address: The DMA (bus) addresses of the pages - * @swap_storage: Pointer to shmem struct file for swap storage. - * @pages_list: used by some page allocation backend - * @caching: The current caching state of the pages, see enum ttm_caching. - * - * This is a structure holding the pages, caching- and aperture binding - * status for a buffer object that isn't backed by fixed (VRAM / AGP) + * struct ttm_tt - This is a structure holding the pages, caching- and aperture + * binding status for a buffer object that isn't backed by fixed (VRAM / AGP) * memory. */ struct ttm_tt { + /** @pages: Array of pages backing the data. */ struct page **pages; + /** + * @page_flags: The page flags. + * + * Supported values: + * + * TTM_TT_FLAG_SWAPPED: Set by TTM when the pages have been unpopulated + * and swapped out by TTM. Calling ttm_tt_populate() will then swap the + * pages back in, and unset the flag. Drivers should in general never + * need to touch this. + * + * TTM_TT_FLAG_ZERO_ALLOC: Set if the pages will be zeroed on + * allocation. + * + * TTM_TT_FLAG_EXTERNAL: Set if the underlying pages were allocated + * externally, like with dma-buf or userptr. This effectively disables + * TTM swapping out such pages. Also important is to prevent TTM from + * ever directly mapping these pages. + * + * Note that enum ttm_bo_type.ttm_bo_type_sg objects will always enable + * this flag. + * + * TTM_TT_FLAG_EXTERNAL_MAPPABLE: Same behaviour as + * TTM_TT_FLAG_EXTERNAL, but with the reduced restriction that it is + * still valid to use TTM to map the pages directly. This is useful when + * implementing a ttm_tt backend which still allocates driver owned + * pages underneath(say with shmem). + * + * Note that since this also implies TTM_TT_FLAG_EXTERNAL, the usage + * here should always be: + * + * page_flags = TTM_TT_FLAG_EXTERNAL | + * TTM_TT_FLAG_EXTERNAL_MAPPABLE; + * + * TTM_TT_FLAG_PRIV_POPULATED: TTM internal only. DO NOT USE. This is + * set by TTM after ttm_tt_populate() has successfully returned, and is + * then unset when TTM calls ttm_tt_unpopulate(). + */ +#define TTM_TT_FLAG_SWAPPED (1 << 0) +#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) +#define TTM_TT_FLAG_EXTERNAL (1 << 2) +#define TTM_TT_FLAG_EXTERNAL_MAPPABLE (1 << 3) + +#define TTM_TT_FLAG_PRIV_POPULATED (1 << 31) uint32_t page_flags; + /** @num_pages: Number of pages in the page array. */ uint32_t num_pages; + /** @sg: for SG objects via dma-buf. */ struct sg_table *sg; + /** @dma_address: The DMA (bus) addresses of the pages. */ dma_addr_t *dma_address; + /** @swap_storage: Pointer to shmem struct file for swap storage. */ struct file *swap_storage; + /** + * @caching: The current caching state of the pages, see enum + * ttm_caching. + */ enum ttm_caching caching; }; @@ -85,7 +119,7 @@ struct ttm_kmap_iter_tt { static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { - return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED; + return tt->page_flags & TTM_TT_FLAG_PRIV_POPULATED; } /** @@ -104,7 +138,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * * @ttm: The struct ttm_tt. * @bo: The buffer object we create the ttm for. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * @caching: the desired caching state of the pages * * Create a struct ttm_tt to back data with system memory pages. @@ -179,7 +213,7 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm); */ static inline void ttm_tt_mark_for_clear(struct ttm_tt *ttm) { - ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + ttm->page_flags |= TTM_TT_FLAG_ZERO_ALLOC; } void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages); @@ -195,7 +229,7 @@ struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, * * @bo: Buffer object we allocate the ttm for. * @bridge: The agp bridge this device is sitting on. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * * * Create a TTM backend that uses the indicated AGP bridge as an aperture diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index fa5fc620050b..d03dd2346ad7 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -511,7 +511,7 @@ struct dma_buf { wait_queue_head_t *poll; __poll_t active; - } cb_excl, cb_shared; + } cb_in, cb_out; #ifdef CONFIG_DMABUF_SYSFS_STATS /** * @sysfs_entry: diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 5de7956818a5..8b6c20636a79 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -149,6 +149,101 @@ struct dma_resv { struct dma_resv_list __rcu *fence; }; +/** + * struct dma_resv_iter - current position into the dma_resv fences + * + * Don't touch this directly in the driver, use the accessor function instead. + */ +struct dma_resv_iter { + /** @obj: The dma_resv object we iterate over */ + struct dma_resv *obj; + + /** @all_fences: If all fences should be returned */ + bool all_fences; + + /** @fence: the currently handled fence */ + struct dma_fence *fence; + + /** @seq: sequence number to check for modifications */ + unsigned int seq; + + /** @index: index into the shared fences */ + unsigned int index; + + /** @fences: the shared fences */ + struct dma_resv_list *fences; + + /** @is_restarted: true if this is the first returned fence */ + bool is_restarted; +}; + +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); + +/** + * dma_resv_iter_begin - initialize a dma_resv_iter object + * @cursor: The dma_resv_iter object to initialize + * @obj: The dma_resv object which we want to iterate over + * @all_fences: If all fences should be returned or just the exclusive one + */ +static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, + struct dma_resv *obj, + bool all_fences) +{ + cursor->obj = obj; + cursor->all_fences = all_fences; + cursor->fence = NULL; +} + +/** + * dma_resv_iter_end - cleanup a dma_resv_iter object + * @cursor: the dma_resv_iter object which should be cleaned up + * + * Make sure that the reference to the fence in the cursor is properly + * dropped. + */ +static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) +{ + dma_fence_put(cursor->fence); +} + +/** + * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * @cursor: the cursor of the current position + * + * Returns true if the currently returned fence is the exclusive one. + */ +static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +{ + return cursor->index == 0; +} + +/** + * dma_resv_iter_is_restarted - test if this is the first fence after a restart + * @cursor: the cursor with the current position + * + * Return true if this is the first fence in an iteration after a restart. + */ +static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) +{ + return cursor->is_restarted; +} + +/** + * dma_resv_for_each_fence_unlocked - unlocked fence iterator + * @cursor: a struct dma_resv_iter pointer + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object without holding the + * &dma_resv.lock and using RCU instead. The cursor needs to be initialized + * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside + * the iterator a reference to the dma_fence is held and the RCU lock dropped. + * When the dma_resv is modified the iteration starts over again. + */ +#define dma_resv_for_each_fence_unlocked(cursor, fence) \ + for (fence = dma_resv_iter_first_unlocked(cursor); \ + fence; fence = dma_resv_iter_next_unlocked(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 0cbd1540aeac..26e45fc5eb1a 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -786,13 +786,6 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_VRAM_LOST_COUNTER 0x1F /* query ras mask of enabled features*/ #define AMDGPU_INFO_RAS_ENABLED_FEATURES 0x20 -/* query video encode/decode caps */ -#define AMDGPU_INFO_VIDEO_CAPS 0x21 - /* Subquery id: Decode */ - #define AMDGPU_INFO_VIDEO_CAPS_DECODE 0 - /* Subquery id: Encode */ - #define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1 - /* RAS MASK: UMC (VRAM) */ #define AMDGPU_INFO_RAS_ENABLED_UMC (1 << 0) /* RAS MASK: SDMA */ @@ -821,6 +814,12 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_RAS_ENABLED_MP1 (1 << 12) /* RAS MASK: FUSE */ #define AMDGPU_INFO_RAS_ENABLED_FUSE (1 << 13) +/* query video encode/decode caps */ +#define AMDGPU_INFO_VIDEO_CAPS 0x21 + /* Subquery id: Decode */ + #define AMDGPU_INFO_VIDEO_CAPS_DECODE 0 + /* Subquery id: Encode */ + #define AMDGPU_INFO_VIDEO_CAPS_ENCODE 1 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT 0 #define AMDGPU_INFO_MMR_SE_INDEX_MASK 0xff diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 45a914850be0..7f652c96845b 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -104,6 +104,12 @@ extern "C" { /* 8 bpp Red */ #define DRM_FORMAT_R8 fourcc_code('R', '8', ' ', ' ') /* [7:0] R */ +/* 10 bpp Red */ +#define DRM_FORMAT_R10 fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */ + +/* 12 bpp Red */ +#define DRM_FORMAT_R12 fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */ + /* 16 bpp Red */ #define DRM_FORMAT_R16 fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */ diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index e4a2570a6058..e1e351682872 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -1112,7 +1112,8 @@ struct drm_mode_destroy_blob { * Lease mode resources, creating another drm_master. * * The @object_ids array must reference at least one CRTC, one connector and - * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. Alternatively, + * the lease can be completely empty. */ struct drm_mode_create_lease { /** @object_ids: Pointer to array of object ids (__u32) */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index bde5860b3686..914ebd9290e5 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching { #define I915_TILING_NONE 0 #define I915_TILING_X 1 #define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ #define I915_TILING_LAST I915_TILING_Y #define I915_BIT_6_SWIZZLE_NONE 0 @@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param { * Extensions: * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT) */ #define I915_CONTEXT_PARAM_ENGINES 0xa @@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param { * attempted to use it, never re-use this context param number. */ #define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -2049,6 +2105,135 @@ struct i915_context_engines_bond { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +/** + * struct i915_context_engines_parallel_submit - Configure engine for + * parallel submission. + * + * Setup a slot in the context engine map to allow multiple BBs to be submitted + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU + * in parallel. Multiple hardware contexts are created internally in the i915 to + * run these BBs. Once a slot is configured for N BBs only N BBs can be + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how + * many BBs there are based on the slot's configuration. The N BBs are the last + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. + * + * The default placement behavior is to create implicit bonds between each + * context if each context maps to more than 1 physical engine (e.g. context is + * a virtual engine). Also we only allow contexts of same engine class and these + * contexts must be in logically contiguous order. Examples of the placement + * behavior are described below. Lastly, the default is to not allow BBs to be + * preempted mid-batch. Rather insert coordinated preemption points on all + * hardware contexts between each set of BBs. Flags could be added in the future + * to change both of these default behaviors. + * + * Returns -EINVAL if hardware context placement configuration is invalid or if + * the placement configuration isn't supported on the platform / submission + * interface. + * Returns -ENODEV if extension isn't supported on the platform / submission + * interface. + * + * .. code-block:: none + * + * Examples syntax: + * CS[X] = generic engine of same class, logical instance X + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE + * + * Example 1 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=1, + * engines=CS[0],CS[1]) + * + * Results in the following valid placement: + * CS[0], CS[1] + * + * Example 2 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[2],CS[1],CS[3]) + * + * Results in the following valid placements: + * CS[0], CS[1] + * CS[2], CS[3] + * + * This can be thought of as two virtual engines, each containing two + * engines thereby making a 2D array. However, there are bonds tying the + * entries together and placing restrictions on how they can be scheduled. + * Specifically, the scheduler can choose only vertical columns from the 2D + * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the + * scheduler wants to submit to CS[0], it must also choose CS[1] and vice + * versa. Same for CS[2] requires also using CS[3]. + * VE[0] = CS[0], CS[2] + * VE[1] = CS[1], CS[3] + * + * Example 3 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[1],CS[1],CS[3]) + * + * Results in the following valid and invalid placements: + * CS[0], CS[1] + * CS[1], CS[3] - Not logically contiguous, return -EINVAL + */ +struct i915_context_engines_parallel_submit { + /** + * @base: base user extension. + */ + struct i915_user_extension base; + + /** + * @engine_index: slot for parallel engine + */ + __u16 engine_index; + + /** + * @width: number of contexts per parallel engine or in other words the + * number of batches in each submission + */ + __u16 width; + + /** + * @num_siblings: number of siblings per context or in other words the + * number of possible placements for each submission + */ + __u16 num_siblings; + + /** + * @mbz16: reserved for future use; must be zero + */ + __u16 mbz16; + + /** + * @flags: all undefined flags must be zero, currently not defined flags + */ + __u64 flags; + + /** + * @mbz64: reserved for future use; must be zero + */ + __u64 mbz64[3]; + + /** + * @engines: 2-d array of engine instances to configure parallel engine + * + * length = width (i) * num_siblings (j) + * index = j + i * num_siblings + */ + struct i915_engine_class_instance engines[0]; + +} __packed; + +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 width; \ + __u16 num_siblings; \ + __u16 mbz16; \ + __u64 flags; \ + __u64 mbz64[3]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + /** * DOC: Context Engine Map uAPI * @@ -2108,6 +2293,7 @@ struct i915_context_param_engines { __u64 extensions; /* linked chain of extension blocks, 0 terminates */ #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ +#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ struct i915_engine_class_instance engines[0]; } __attribute__((packed)); @@ -2726,14 +2912,20 @@ struct drm_i915_engine_info { /** @flags: Engine flags. */ __u64 flags; +#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0) /** @capabilities: Capabilities of this engine. */ __u64 capabilities; #define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + /** @logical_instance: Logical instance of engine */ + __u16 logical_instance; + /** @rsvd1: Reserved fields. */ - __u64 rsvd1[4]; + __u16 rsvd1[3]; + /** @rsvd2: Reserved fields. */ + __u64 rsvd2[3]; }; /** @@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 __u64 extensions; }; @@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + #if defined(__cplusplus) } #endif diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 4104f22fb3d3..3dfc0af8756a 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -58,6 +58,67 @@ extern "C" { struct drm_v3d_perfmon_get_values) #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 +#define DRM_V3D_SUBMIT_EXTENSION 0x02 + +/* struct drm_v3d_extension - ioctl extensions + * + * Linked-list of generic extensions where the id identify which struct is + * pointed by ext_data. Therefore, DRM_V3D_EXT_ID_* is used on id to identify + * the extension type. + */ +struct drm_v3d_extension { + __u64 next; + __u32 id; +#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 + __u32 flags; /* mbz */ +}; + +/* struct drm_v3d_sem - wait/signal semaphore + * + * If binary semaphore, it only takes syncobj handle and ignores flags and + * point fields. Point is defined for timeline syncobj feature. + */ +struct drm_v3d_sem { + __u32 handle; /* syncobj */ + /* rsv below, for future uses */ + __u32 flags; + __u64 point; /* for timeline sem support */ + __u64 mbz[2]; /* must be zero, rsv */ +}; + +/* Enum for each of the V3D queues. */ +enum v3d_queue { + V3D_BIN, + V3D_RENDER, + V3D_TFU, + V3D_CSD, + V3D_CACHE_CLEAN, +}; + +/** + * struct drm_v3d_multi_sync - ioctl extension to add support multiples + * syncobjs for commands submission. + * + * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to + * this extension to define wait and signal dependencies, instead of single + * in/out sync entries on submitting commands. The field flags is used to + * determine the stage to set wait dependencies. + */ +struct drm_v3d_multi_sync { + struct drm_v3d_extension base; + /* Array of wait and signal semaphores */ + __u64 in_syncs; + __u64 out_syncs; + + /* Number of entries */ + __u32 in_sync_count; + __u32 out_sync_count; + + /* set the stage (v3d_queue) to sync */ + __u32 wait_stage; + + __u32 pad; /* mbz */ +}; /** * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D @@ -135,12 +196,16 @@ struct drm_v3d_submit_cl { /* Number of BO handles passed in (size is that times 4). */ __u32 bo_handle_count; + /* DRM_V3D_SUBMIT_* properties */ __u32 flags; /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; __u32 pad; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; }; /** @@ -210,6 +275,7 @@ enum drm_v3d_param { DRM_V3D_PARAM_SUPPORTS_CSD, DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH, DRM_V3D_PARAM_SUPPORTS_PERFMON, + DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT, }; struct drm_v3d_get_param { @@ -248,6 +314,11 @@ struct drm_v3d_submit_tfu { __u32 in_sync; /* Sync object to signal when the TFU job is done. */ __u32 out_sync; + + __u32 flags; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; }; /* Submits a compute shader for dispatch. This job will block on any @@ -276,6 +347,13 @@ struct drm_v3d_submit_csd { /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; + + __u32 flags; + + __u32 pad; }; enum {