diff --git a/.mailmap b/.mailmap index 081a14a3bd31..9afff56ad8bc 100644 --- a/.mailmap +++ b/.mailmap @@ -27,6 +27,7 @@ Alan Cox Alan Cox Aleksandar Markovic Aleksey Gorelov +Alex Williamson Alexander Lobakin Alexander Lobakin Alexander Lobakin @@ -206,6 +207,7 @@ Danilo Krummrich David Brownell David Collins David Heidelberg +David Hildenbrand David Rheinsberg David Rheinsberg David Rheinsberg @@ -426,7 +428,7 @@ Kenneth W Chen Kenneth Westfield Kiran Gunda Kirill Tkhai -Kirill A. Shutemov +Kiryl Shutsemau Kishon Vijay Abraham I Konrad Dybcio Konrad Dybcio @@ -605,7 +607,8 @@ Oleksij Rempel Oleksij Rempel Oliver Hartkopp Oliver Hartkopp -Oliver Upton +Oliver Upton +Oliver Upton Ondřej Jirman Oza Pawandeep Pali Rohár @@ -644,6 +647,7 @@ Qais Yousef Quentin Monnet Quentin Monnet Quentin Perret +Rae Moar Rafael J. Wysocki Rajeev Nandan Rajendra Nayak diff --git a/CREDITS b/CREDITS index 903ea238e64f..fa5397f4ebcd 100644 --- a/CREDITS +++ b/CREDITS @@ -2036,6 +2036,10 @@ S: Botanicka' 68a S: 602 00 Brno S: Czech Republic +N: Karsten Keil +E: isdn@linux-pingi.de +D: ISDN subsystem maintainer + N: Jakob Kemi E: jakob.kemi@telia.com D: V4L W9966 Webcam driver diff --git a/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml b/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml index ba644c30dcf4..17d1f97ce8c2 100644 --- a/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml @@ -19,6 +19,7 @@ properties: compatible: enum: - ite,it66121 + - ite,it66122 - ite,it6610 reg: diff --git a/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml b/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml index 9ef587d46506..20c7e0a77802 100644 --- a/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml +++ b/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml @@ -27,7 +27,9 @@ properties: - const: adi,adv7123 - enum: - adi,adv7123 + - asl-tek,cs5263 - dumb-vga-dac + - parade,ps185hdm - radxa,ra620 - realtek,rtd2171 - ti,opa362 diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml index aeb4e4f36044..ebda78db87a6 100644 --- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml +++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml @@ -18,6 +18,7 @@ properties: compatible: oneOf: - enum: + - qcom,glymur-dp - qcom,sa8775p-dp - qcom,sc7180-dp - qcom,sc7280-dp @@ -31,6 +32,11 @@ properties: - qcom,sm8650-dp - qcom,x1e80100-dp + - items: + - enum: + - qcom,qcs8300-dp + - const: qcom,sa8775p-dp + - items: - enum: - qcom,sm6350-dp @@ -53,6 +59,12 @@ properties: - qcom,sm8550-dp - const: qcom,sm8350-dp + - items: + - enum: + - qcom,sm6150-dp + - const: qcom,sm8150-dp + - const: qcom,sm8350-dp + - items: - enum: - qcom,sm8750-dp @@ -195,9 +207,11 @@ allOf: compatible: contains: enum: + - qcom,glymur-dp - qcom,sa8775p-dp - qcom,x1e80100-dp then: + $ref: /schemas/sound/dai-common.yaml# oneOf: - required: - aux-bus @@ -239,6 +253,7 @@ allOf: enum: # these platforms support 2 streams MST on some interfaces, # others are SST only + - qcom,glymur-dp - qcom,sc8280xp-dp - qcom,x1e80100-dp then: @@ -295,7 +310,7 @@ allOf: minItems: 6 maxItems: 8 -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/display/msm/gmu.yaml b/Documentation/devicetree/bindings/display/msm/gmu.yaml index afc187935744..e32056ae0f5d 100644 --- a/Documentation/devicetree/bindings/display/msm/gmu.yaml +++ b/Documentation/devicetree/bindings/display/msm/gmu.yaml @@ -21,7 +21,7 @@ properties: compatible: oneOf: - items: - - pattern: '^qcom,adreno-gmu-[67][0-9][0-9]\.[0-9]$' + - pattern: '^qcom,adreno-gmu-[6-8][0-9][0-9]\.[0-9]$' - const: qcom,adreno-gmu - items: - pattern: '^qcom,adreno-gmu-x[1-9][0-9][0-9]\.[0-9]$' @@ -299,6 +299,64 @@ allOf: required: - qcom,qmp + - if: + properties: + compatible: + contains: + const: qcom,adreno-gmu-840.1 + then: + properties: + reg: + items: + - description: Core GMU registers + reg-names: + items: + - const: gmu + clocks: + items: + - description: GPU AHB clock + - description: GMU clock + - description: GPU CX clock + - description: GPU MEMNOC clock + - description: GMU HUB clock + clock-names: + items: + - const: ahb + - const: gmu + - const: cxo + - const: memnoc + - const: hub + + - if: + properties: + compatible: + contains: + const: qcom,adreno-gmu-x285.1 + then: + properties: + reg: + items: + - description: Core GMU registers + reg-names: + items: + - const: gmu + clocks: + items: + - description: GPU AHB clock + - description: GMU clock + - description: GPU CX clock + - description: GPU MEMNOC clock + - description: GMU HUB clock + - description: GMU RSCC HUB clock + clock-names: + items: + - const: ahb + - const: gmu + - const: cxo + - const: memnoc + - const: hub + - const: rscc + - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml new file mode 100644 index 000000000000..2329ed96e6cb --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml @@ -0,0 +1,264 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/msm/qcom,glymur-mdss.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Glymur Display MDSS + +maintainers: + - Abel Vesa + +description: + Glymur MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like + DPU display controller, DP interfaces, etc. + +$ref: /schemas/display/msm/mdss-common.yaml# + +properties: + compatible: + const: qcom,glymur-mdss + + clocks: + items: + - description: Display AHB + - description: Display hf AXI + - description: Display core + + iommus: + maxItems: 1 + + interconnects: + items: + - description: Interconnect path from mdp0 port to the data bus + - description: Interconnect path from CPU to the reg bus + + interconnect-names: + items: + - const: mdp0-mem + - const: cpu-cfg + +patternProperties: + "^display-controller@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + const: qcom,glymur-dpu + + "^displayport-controller@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + const: qcom,glymur-dp + + "^phy@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + const: qcom,glymur-dp-phy + +required: + - compatible + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + #include + #include + #include + + display-subsystem@ae00000 { + compatible = "qcom,glymur-mdss"; + reg = <0x0ae00000 0x1000>; + reg-names = "mdss"; + + interrupts = ; + + clocks = <&dispcc_ahb_clk>, + <&gcc_disp_hf_axi_clk>, + <&dispcc_mdp_clk>; + clock-names = "bus", "nrt_bus", "core"; + + interconnects = <&mmss_noc MASTER_MDP QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, + <&hsc_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "mdp0-mem", + "cpu-cfg"; + + resets = <&disp_cc_mdss_core_bcr>; + + power-domains = <&mdss_gdsc>; + + iommus = <&apps_smmu 0x1c00 0x2>; + + interrupt-controller; + #interrupt-cells = <1>; + + #address-cells = <1>; + #size-cells = <1>; + ranges; + + display-controller@ae01000 { + compatible = "qcom,glymur-dpu"; + reg = <0x0ae01000 0x8f000>, + <0x0aeb0000 0x2008>; + reg-names = "mdp", "vbif"; + + clocks = <&gcc_axi_clk>, + <&dispcc_ahb_clk>, + <&dispcc_mdp_lut_clk>, + <&dispcc_mdp_clk>, + <&dispcc_mdp_vsync_clk>; + clock-names = "nrt_bus", + "iface", + "lut", + "core", + "vsync"; + + assigned-clocks = <&dispcc_mdp_vsync_clk>; + assigned-clock-rates = <19200000>; + + operating-points-v2 = <&mdp_opp_table>; + power-domains = <&rpmhpd RPMHPD_MMCX>; + + interrupt-parent = <&mdss>; + interrupts = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dpu_intf1_out: endpoint { + remote-endpoint = <&dsi0_in>; + }; + }; + + port@1 { + reg = <1>; + dpu_intf2_out: endpoint { + remote-endpoint = <&dsi1_in>; + }; + }; + }; + + mdp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-200000000 { + opp-hz = /bits/ 64 <200000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-325000000 { + opp-hz = /bits/ 64 <325000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-375000000 { + opp-hz = /bits/ 64 <375000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-514000000 { + opp-hz = /bits/ 64 <514000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + + displayport-controller@ae90000 { + compatible = "qcom,glymur-dp"; + reg = <0xae90000 0x200>, + <0xae90200 0x200>, + <0xae90400 0x600>, + <0xae91000 0x400>, + <0xae91400 0x400>; + + interrupt-parent = <&mdss>; + interrupts = <12>; + + clocks = <&dispcc_mdss_ahb_clk>, + <&dispcc_dptx0_aux_clk>, + <&dispcc_dptx0_link_clk>, + <&dispcc_dptx0_link_intf_clk>, + <&dispcc_dptx0_pixel0_clk>, + <&dispcc_dptx0_pixel1_clk>; + clock-names = "core_iface", + "core_aux", + "ctrl_link", + "ctrl_link_iface", + "stream_pixel", + "stream_1_pixel"; + + assigned-clocks = <&dispcc_mdss_dptx0_link_clk_src>, + <&dispcc_mdss_dptx0_pixel0_clk_src>, + <&dispcc_mdss_dptx0_pixel1_clk_src>; + assigned-clock-parents = <&usb_1_ss0_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_ss0_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>, + <&usb_1_ss0_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + + operating-points-v2 = <&mdss_dp0_opp_table>; + + power-domains = <&rpmhpd RPMHPD_MMCX>; + + phys = <&usb_1_ss0_qmpphy QMP_USB43DP_DP_PHY>; + phy-names = "dp"; + + #sound-dai-cells = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + mdss_dp0_in: endpoint { + remote-endpoint = <&mdss_intf0_out>; + }; + }; + + port@1 { + reg = <1>; + + mdss_dp0_out: endpoint { + }; + }; + }; + + mdss_dp0_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-160000000 { + opp-hz = /bits/ 64 <160000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-270000000 { + opp-hz = /bits/ 64 <270000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-540000000 { + opp-hz = /bits/ 64 <540000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-810000000 { + opp-hz = /bits/ 64 <810000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcs8300-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcs8300-mdss.yaml new file mode 100644 index 000000000000..e96baaae9ba9 --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/qcom,qcs8300-mdss.yaml @@ -0,0 +1,286 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/msm/qcom,qcs8300-mdss.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Technologies, Inc. QCS8300 Display MDSS + +maintainers: + - Yongxing Mou + +description: + QCS8300 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like + DPU display controller, DP interfaces and EDP etc. + +$ref: /schemas/display/msm/mdss-common.yaml# + +properties: + compatible: + const: qcom,qcs8300-mdss + + clocks: + items: + - description: Display AHB + - description: Display hf AXI + - description: Display core + + iommus: + maxItems: 1 + + interconnects: + maxItems: 3 + + interconnect-names: + maxItems: 3 + +patternProperties: + "^display-controller@[0-9a-f]+$": + type: object + additionalProperties: true + + properties: + compatible: + contains: + const: qcom,qcs8300-dpu + + "^displayport-controller@[0-9a-f]+$": + type: object + additionalProperties: true + + properties: + compatible: + contains: + const: qcom,qcs8300-dp + + "^phy@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + contains: + const: qcom,qcs8300-edp-phy + +required: + - compatible + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + #include + #include + #include + #include + + mdss: display-subsystem@ae00000 { + compatible = "qcom,qcs8300-mdss"; + reg = <0x0ae00000 0x1000>; + reg-names = "mdss"; + + interconnects = <&mmss_noc MASTER_MDP0 QCOM_ICC_TAG_ACTIVE_ONLY + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>, + <&mmss_noc MASTER_MDP1 QCOM_ICC_TAG_ACTIVE_ONLY + &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ACTIVE_ONLY>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY + &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ACTIVE_ONLY>; + interconnect-names = "mdp0-mem", + "mdp1-mem", + "cpu-cfg"; + + resets = <&dispcc_core_bcr>; + power-domains = <&dispcc_gdsc>; + + clocks = <&dispcc_ahb_clk>, + <&gcc GCC_DISP_HF_AXI_CLK>, + <&dispcc_mdp_clk>; + + interrupts = ; + interrupt-controller; + #interrupt-cells = <1>; + + iommus = <&apps_smmu 0x1000 0x402>; + + #address-cells = <1>; + #size-cells = <1>; + ranges; + + display-controller@ae01000 { + compatible = "qcom,qcs8300-dpu", "qcom,sa8775p-dpu"; + reg = <0x0ae01000 0x8f000>, + <0x0aeb0000 0x2008>; + reg-names = "mdp", "vbif"; + + clocks = <&gcc GCC_DISP_HF_AXI_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_MDP_LUT_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_MDP_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_VSYNC_CLK>; + clock-names = "nrt_bus", + "iface", + "lut", + "core", + "vsync"; + + assigned-clocks = <&dispcc0 MDSS_DISP_CC_MDSS_VSYNC_CLK>; + assigned-clock-rates = <19200000>; + operating-points-v2 = <&mdp_opp_table>; + power-domains = <&rpmhpd RPMHPD_MMCX>; + + interrupt-parent = <&mdss>; + interrupts = <0>; + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + + dpu_intf0_out: endpoint { + remote-endpoint = <&mdss_dp0_in>; + }; + }; + }; + + mdp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-375000000 { + opp-hz = /bits/ 64 <375000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-500000000 { + opp-hz = /bits/ 64 <500000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + + opp-575000000 { + opp-hz = /bits/ 64 <575000000>; + required-opps = <&rpmhpd_opp_turbo>; + }; + + opp-650000000 { + opp-hz = /bits/ 64 <650000000>; + required-opps = <&rpmhpd_opp_turbo_l1>; + }; + }; + }; + + mdss_dp0_phy: phy@aec2a00 { + compatible = "qcom,qcs8300-edp-phy", "qcom,sa8775p-edp-phy"; + + reg = <0x0aec2a00 0x200>, + <0x0aec2200 0xd0>, + <0x0aec2600 0xd0>, + <0x0aec2000 0x1c8>; + + clocks = <&dispcc MDSS_DISP_CC_MDSS_DPTX0_AUX_CLK>, + <&dispcc MDSS_DISP_CC_MDSS_AHB_CLK>; + clock-names = "aux", + "cfg_ahb"; + + #clock-cells = <1>; + #phy-cells = <0>; + + vdda-phy-supply = <&vreg_l1c>; + vdda-pll-supply = <&vreg_l4a>; + }; + + displayport-controller@af54000 { + compatible = "qcom,qcs8300-dp", "qcom,sa8775p-dp"; + + pinctrl-0 = <&dp_hot_plug_det>; + pinctrl-names = "default"; + + reg = <0xaf54000 0x104>, + <0xaf54200 0x0c0>, + <0xaf55000 0x770>, + <0xaf56000 0x09c>, + <0xaf57000 0x09c>, + <0xaf58000 0x09c>, + <0xaf59000 0x09c>, + <0xaf5a000 0x23c>, + <0xaf5b000 0x23c>; + + interrupt-parent = <&mdss>; + interrupts = <12>; + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_AHB_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_AUX_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_LINK_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_LINK_INTF_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL0_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL1_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL2_CLK>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL3_CLK>; + clock-names = "core_iface", + "core_aux", + "ctrl_link", + "ctrl_link_iface", + "stream_pixel", + "stream_1_pixel", + "stream_2_pixel", + "stream_3_pixel"; + assigned-clocks = <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_LINK_CLK_SRC>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL1_CLK_SRC>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL2_CLK_SRC>, + <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_PIXEL3_CLK_SRC>; + assigned-clock-parents = <&mdss_dp0_phy 0>, + <&mdss_dp0_phy 1>, + <&mdss_dp0_phy 1>, + <&mdss_dp0_phy 1>; + phys = <&mdss_dp0_phy>; + phy-names = "dp"; + operating-points-v2 = <&dp_opp_table>; + power-domains = <&rpmhpd RPMHPD_MMCX>; + + #sound-dai-cells = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + mdss_dp0_in: endpoint { + remote-endpoint = <&dpu_intf0_out>; + }; + }; + + port@1 { + reg = <1>; + + mdss_dp_out: endpoint { }; + }; + }; + + dp_opp_table: opp-table { + compatible = "operating-points-v2"; + + opp-160000000 { + opp-hz = /bits/ 64 <160000000>; + required-opps = <&rpmhpd_opp_low_svs>; + }; + + opp-270000000 { + opp-hz = /bits/ 64 <270000000>; + required-opps = <&rpmhpd_opp_svs>; + }; + + opp-540000000 { + opp-hz = /bits/ 64 <540000000>; + required-opps = <&rpmhpd_opp_svs_l1>; + }; + + opp-810000000 { + opp-hz = /bits/ 64 <810000000>; + required-opps = <&rpmhpd_opp_nom>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml index 9ac24f99d3ad..46e9335f849f 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6150-mdss.yaml @@ -51,6 +51,14 @@ patternProperties: compatible: const: qcom,sm6150-dpu + "^displayport-controller@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + contains: + const: qcom,sm6150-dp + "^dsi@[0-9a-f]+$": type: object additionalProperties: true @@ -130,35 +138,37 @@ examples: #size-cells = <0>; port@0 { - reg = <0>; - dpu_intf0_out: endpoint { - }; + reg = <0>; + + dpu_intf0_out: endpoint { + }; }; port@1 { - reg = <1>; - dpu_intf1_out: endpoint { - remote-endpoint = <&mdss_dsi0_in>; - }; + reg = <1>; + + dpu_intf1_out: endpoint { + remote-endpoint = <&mdss_dsi0_in>; + }; }; }; mdp_opp_table: opp-table { compatible = "operating-points-v2"; - opp-19200000 { - opp-hz = /bits/ 64 <19200000>; - required-opps = <&rpmhpd_opp_low_svs>; + opp-192000000 { + opp-hz = /bits/ 64 <192000000>; + required-opps = <&rpmhpd_opp_low_svs>; }; - opp-25600000 { - opp-hz = /bits/ 64 <25600000>; - required-opps = <&rpmhpd_opp_svs>; + opp-256000000 { + opp-hz = /bits/ 64 <256000000>; + required-opps = <&rpmhpd_opp_svs>; }; opp-307200000 { - opp-hz = /bits/ 64 <307200000>; - required-opps = <&rpmhpd_opp_nom>; + opp-hz = /bits/ 64 <307200000>; + required-opps = <&rpmhpd_opp_nom>; }; }; }; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8650-dpu.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8650-dpu.yaml index 0a46120dd868..fe296e3186d0 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8650-dpu.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8650-dpu.yaml @@ -13,11 +13,17 @@ $ref: /schemas/display/msm/dpu-common.yaml# properties: compatible: - enum: - - qcom,sa8775p-dpu - - qcom,sm8650-dpu - - qcom,sm8750-dpu - - qcom,x1e80100-dpu + oneOf: + - enum: + - qcom,glymur-dpu + - qcom,sa8775p-dpu + - qcom,sm8650-dpu + - qcom,sm8750-dpu + - qcom,x1e80100-dpu + - items: + - enum: + - qcom,qcs8300-dpu + - const: qcom,sa8775p-dpu reg: items: diff --git a/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml b/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml index 34a612705e8c..d979701a00a8 100644 --- a/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml +++ b/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.yaml @@ -24,6 +24,7 @@ properties: - raspberrypi,dsi-7inch - startek,kd050hdfia020 - tdo,tl050hdv35 + - wanchanglong,w552946aaa - wanchanglong,w552946aba - const: ilitek,ili9881c diff --git a/Documentation/devicetree/bindings/display/panel/lg,ld070wx3-sl01.yaml b/Documentation/devicetree/bindings/display/panel/lg,ld070wx3-sl01.yaml new file mode 100644 index 000000000000..0f0b9079f199 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/lg,ld070wx3-sl01.yaml @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/lg,ld070wx3-sl01.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: LG Corporation 7" WXGA TFT LCD panel + +maintainers: + - Svyatoslav Ryhel + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + items: + - const: lg,ld070wx3-sl01 + + reg: + maxItems: 1 + + vdd-supply: true + vcc-supply: true + + backlight: true + port: true + +required: + - compatible + - vdd-supply + - vcc-supply + +additionalProperties: false + +examples: + - | + #include + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "lg,ld070wx3-sl01"; + reg = <0>; + + vdd-supply = <&vdd_3v3_lcd>; + vcc-supply = <&vcc_1v8_lcd>; + + backlight = <&backlight>; + + port { + endpoint { + remote-endpoint = <&dsi0_out>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml b/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml index 4388d5375851..dbc01e640895 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-lvds.yaml @@ -59,6 +59,8 @@ properties: # Jenson Display BL-JT60050-01A 7" WSVGA (1024x600) color TFT LCD LVDS panel - jenson,bl-jt60050-01a - tbs,a711-panel + # Winstar WF70A8SYJHLNGA 7" WSVGA (1024x600) color TFT LCD LVDS panel + - winstar,wf70a8syjhlnga - const: panel-lvds diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml index ac2db8cf5eb7..8d668979b62d 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml @@ -19,6 +19,9 @@ description: | If the panel is more advanced a dedicated binding file is required. +allOf: + - $ref: panel-common.yaml# + properties: compatible: @@ -42,8 +45,6 @@ properties: - kingdisplay,kd097d04 # LG ACX467AKM-7 4.95" 1080×1920 LCD Panel - lg,acx467akm-7 - # LG Corporation 7" WXGA TFT LCD panel - - lg,ld070wx3-sl01 # LG Corporation 5" HD TFT LCD panel - lg,lh500wx1-sd03 # Lincoln LCD197 5" 1080x1920 LCD panel @@ -56,8 +57,6 @@ properties: - panasonic,vvx10f034n00 # Samsung s6e3fa7 1080x2220 based AMS559NK06 AMOLED panel - samsung,s6e3fa7-ams559nk06 - # Samsung sofef00 1080x2280 AMOLED panel - - samsung,sofef00 # Shangai Top Display Optoelectronics 7" TL070WSH30 1024x600 TFT LCD panel - tdo,tl070wsh30 @@ -70,30 +69,12 @@ properties: reset-gpios: true port: true power-supply: true - vddio-supply: true - -allOf: - - $ref: panel-common.yaml# - - if: - properties: - compatible: - enum: - - samsung,sofef00 - then: - properties: - power-supply: false - required: - - vddio-supply - else: - properties: - vddio-supply: false - required: - - power-supply additionalProperties: false required: - compatible + - power-supply - reg examples: diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index 35ba99b76119..24e277b19094 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -270,6 +270,8 @@ properties: - qiaodian,qd43003c0-40 # Shenzhen QiShenglong Industrialist Co., Ltd. Gopher 2b 4.3" 480(RGB)x272 TFT LCD panel - qishenglong,gopher2b-lcd + # Raystar Optronics, Inc. RFF500F-AWH-DNN 5.0" TFT 840x480 + - raystar,rff500f-awh-dnn # Rocktech Displays Ltd. RK101II01D-CT 10.1" TFT 1280x800 - rocktech,rk101ii01d-ct # Rocktech Display Ltd. RK070ER9427 800(RGB)x480 TFT LCD panel @@ -278,6 +280,8 @@ properties: - rocktech,rk043fn48h # Samsung Electronics 10.1" WXGA (1280x800) TFT LCD panel - samsung,ltl101al01 + # Samsung Electronics 10.6" FWXGA (1366x768) TFT LCD panel + - samsung,ltl106al01 # Samsung Electronics 10.1" WSVGA TFT LCD panel - samsung,ltn101nt05 # Satoz SAT050AT40H12R2 5.0" WVGA TFT LCD panel diff --git a/Documentation/devicetree/bindings/display/panel/ronbo,rb070d30.yaml b/Documentation/devicetree/bindings/display/panel/ronbo,rb070d30.yaml index 04f86e0cbac9..694037301583 100644 --- a/Documentation/devicetree/bindings/display/panel/ronbo,rb070d30.yaml +++ b/Documentation/devicetree/bindings/display/panel/ronbo,rb070d30.yaml @@ -9,6 +9,9 @@ title: Ronbo RB070D30 DSI Display Panel maintainers: - Maxime Ripard +allOf: + - $ref: panel-common.yaml# + properties: compatible: const: ronbo,rb070d30 @@ -20,10 +23,6 @@ properties: description: GPIO used for the power pin maxItems: 1 - reset-gpios: - description: GPIO used for the reset pin - maxItems: 1 - shlr-gpios: description: GPIO used for the shlr pin (horizontal flip) maxItems: 1 @@ -35,10 +34,6 @@ properties: vcc-lcd-supply: description: Power regulator - backlight: - description: Backlight used by the panel - $ref: /schemas/types.yaml#/definitions/phandle - required: - compatible - power-gpios @@ -47,5 +42,6 @@ required: - shlr-gpios - updn-gpios - vcc-lcd-supply + - port -additionalProperties: false +unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/panel/samsung,sofef00.yaml b/Documentation/devicetree/bindings/display/panel/samsung,sofef00.yaml new file mode 100644 index 000000000000..eeee3cac72e3 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/samsung,sofef00.yaml @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/samsung,sofef00.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung SOFEF00 AMOLED DDIC + +description: The SOFEF00 is display driver IC with connected panel. + +maintainers: + - David Heidelberg + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + items: + - enum: + # Samsung 6.01 inch, 1080x2160 pixels, 18:9 ratio + - samsung,sofef00-ams601nt22 + # Samsung 6.28 inch, 1080x2280 pixels, 19:9 ratio + - samsung,sofef00-ams628nw01 + - const: samsung,sofef00 + + reg: + maxItems: 1 + + poc-supply: + description: POC regulator + + vci-supply: + description: VCI regulator + + vddio-supply: + description: VDD regulator + +required: + - compatible + - reset-gpios + - poc-supply + - vci-supply + - vddio-supply + +unevaluatedProperties: false + +examples: + - | + #include + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "samsung,sofef00-ams628nw01", "samsung,sofef00"; + reg = <0>; + + vddio-supply = <&vreg_l14a_1p88>; + vci-supply = <&s2dos05_buck1>; + poc-supply = <&s2dos05_ldo1>; + + te-gpios = <&tlmm 10 GPIO_ACTIVE_HIGH>; + reset-gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>; + + pinctrl-0 = <&panel_active>; + pinctrl-1 = <&panel_suspend>; + pinctrl-names = "default", "sleep"; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml index 96b4b088eebe..d649808c59da 100644 --- a/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml +++ b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3588-dw-hdmi-qp.yaml @@ -113,6 +113,14 @@ properties: description: Additional HDMI QP related data is accessed through VO GRF regs. + frl-enable-gpios: + description: + Optional GPIO line to be asserted when operating in HDMI 2.1 FRL mode and + deasserted for HDMI 1.4/2.0 TMDS. It can be used to control external + voltage bias for HDMI data lines. When not present the HDMI encoder will + operate in TMDS mode only. + maxItems: 1 + required: - compatible - reg @@ -132,8 +140,10 @@ unevaluatedProperties: false examples: - | #include + #include #include #include + #include #include #include @@ -164,6 +174,7 @@ examples: rockchip,grf = <&sys_grf>; rockchip,vo-grf = <&vo1_grf>; #sound-dai-cells = <0>; + frl-enable-gpios = <&gpio4 RK_PB1 GPIO_ACTIVE_LOW>; ports { #address-cells = <1>; diff --git a/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml b/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml index 5e3e199fd9a4..96d50d14c071 100644 --- a/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml +++ b/Documentation/devicetree/bindings/gpio/ti,twl4030-gpio.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/ti,twl4030-gpio.yaml# +$id: http://devicetree.org/schemas/gpio/ti,twl4030-gpio.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: TI TWL4030 GPIO controller diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 89495f094d52..c9efdd1a6d1c 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -89,6 +89,8 @@ properties: - description: Qcom Adreno GPUs implementing "qcom,smmu-500" and "arm,mmu-500" items: - enum: + - qcom,glymur-smmu-500 + - qcom,kaanapali-smmu-500 - qcom,milos-smmu-500 - qcom,qcm2290-smmu-500 - qcom,qcs615-smmu-500 diff --git a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml index 5caa3779660d..5491d0775ede 100644 --- a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml +++ b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml @@ -180,9 +180,9 @@ allOf: then: properties: reg: - minItems: 2 + maxItems: 2 reg-names: - minItems: 2 + maxItems: 2 else: properties: reg: diff --git a/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml b/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml index 6a47e08e0e97..f9cffbb2df07 100644 --- a/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml +++ b/Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml @@ -142,7 +142,9 @@ allOf: required: - orientation-switch then: - $ref: /schemas/usb/usb-switch.yaml# + allOf: + - $ref: /schemas/usb/usb-switch.yaml# + - $ref: /schemas/usb/usb-switch-ports.yaml# unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index a58370a6a5d3..fba7b2549dde 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -24,6 +24,10 @@ properties: - enum: - qcom,qcs8300-qmp-ufs-phy - const: qcom,sa8775p-qmp-ufs-phy + - items: + - enum: + - qcom,kaanapali-qmp-ufs-phy + - const: qcom,sm8750-qmp-ufs-phy - enum: - qcom,msm8996-qmp-ufs-phy - qcom,msm8998-qmp-ufs-phy diff --git a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml index e906403208c0..ea1135c91fb7 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml @@ -125,7 +125,9 @@ allOf: contains: const: google,gs101-usb31drd-phy then: - $ref: /schemas/usb/usb-switch.yaml# + allOf: + - $ref: /schemas/usb/usb-switch.yaml# + - $ref: /schemas/usb/usb-switch-ports.yaml# properties: clocks: diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml index e925cd4c3ac8..72483bc3274d 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml @@ -197,6 +197,7 @@ allOf: - renesas,rcar-gen2-scif - renesas,rcar-gen3-scif - renesas,rcar-gen4-scif + - renesas,rcar-gen5-scif then: properties: interrupts: diff --git a/Documentation/devicetree/bindings/sound/qcom,pm4125-sdw.yaml b/Documentation/devicetree/bindings/sound/qcom,pm4125-sdw.yaml index 23624f32ac30..769e4cb5b99b 100644 --- a/Documentation/devicetree/bindings/sound/qcom,pm4125-sdw.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,pm4125-sdw.yaml @@ -32,7 +32,7 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32-array minItems: 2 - maxItems: 2 + maxItems: 4 items: enum: [1, 2, 3, 4] @@ -48,7 +48,7 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32-array minItems: 2 - maxItems: 2 + maxItems: 5 items: enum: [1, 2, 3, 4, 5] diff --git a/Documentation/devicetree/bindings/spi/spi-cadence.yaml b/Documentation/devicetree/bindings/spi/spi-cadence.yaml index 8de96abe9da1..27414b78d61d 100644 --- a/Documentation/devicetree/bindings/spi/spi-cadence.yaml +++ b/Documentation/devicetree/bindings/spi/spi-cadence.yaml @@ -14,9 +14,14 @@ allOf: properties: compatible: - enum: - - cdns,spi-r1p6 - - xlnx,zynq-spi-r1p6 + oneOf: + - enum: + - xlnx,zynq-spi-r1p6 + - items: + - enum: + - xlnx,zynqmp-spi-r1p6 + - xlnx,versal-net-spi-r1p6 + - const: cdns,spi-r1p6 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml index 748faf7f7081..ce6762c92fda 100644 --- a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml +++ b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml @@ -34,6 +34,7 @@ properties: - rockchip,rk3328-spi - rockchip,rk3368-spi - rockchip,rk3399-spi + - rockchip,rk3506-spi - rockchip,rk3528-spi - rockchip,rk3562-spi - rockchip,rk3568-spi diff --git a/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml b/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml index aaa0bbb5bfe1..cea84ab2204f 100644 --- a/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml +++ b/Documentation/devicetree/bindings/ufs/qcom,sm8650-ufshc.yaml @@ -15,6 +15,7 @@ select: compatible: contains: enum: + - qcom,kaanapali-ufshc - qcom,sm8650-ufshc - qcom,sm8750-ufshc required: @@ -24,6 +25,7 @@ properties: compatible: items: - enum: + - qcom,kaanapali-ufshc - qcom,sm8650-ufshc - qcom,sm8750-ufshc - const: qcom,ufshc diff --git a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml index e3a7df91f7f1..89b1fb90aeeb 100644 --- a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml +++ b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml @@ -76,6 +76,7 @@ required: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# additionalProperties: false diff --git a/Documentation/devicetree/bindings/usb/fsl,imx8mp-dwc3.yaml b/Documentation/devicetree/bindings/usb/fsl,imx8mp-dwc3.yaml index baf130669c38..73e7a60a0060 100644 --- a/Documentation/devicetree/bindings/usb/fsl,imx8mp-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/fsl,imx8mp-dwc3.yaml @@ -89,13 +89,21 @@ required: - reg - "#address-cells" - "#size-cells" - - dma-ranges - ranges - clocks - clock-names - interrupts - power-domains +allOf: + - if: + properties: + compatible: + const: fsl,imx8mp-dwc3 + then: + required: + - dma-ranges + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml index e588514fab2d..793662f6f3bf 100644 --- a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml +++ b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml @@ -52,6 +52,7 @@ required: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# - if: required: - mode-switch diff --git a/Documentation/devicetree/bindings/usb/nxp,ptn36502.yaml b/Documentation/devicetree/bindings/usb/nxp,ptn36502.yaml index d805dde80796..4d2fcaa71870 100644 --- a/Documentation/devicetree/bindings/usb/nxp,ptn36502.yaml +++ b/Documentation/devicetree/bindings/usb/nxp,ptn36502.yaml @@ -46,6 +46,7 @@ required: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# additionalProperties: false diff --git a/Documentation/devicetree/bindings/usb/onnn,nb7vpq904m.yaml b/Documentation/devicetree/bindings/usb/onnn,nb7vpq904m.yaml index 589914d22bf2..25fab5fdc2cd 100644 --- a/Documentation/devicetree/bindings/usb/onnn,nb7vpq904m.yaml +++ b/Documentation/devicetree/bindings/usb/onnn,nb7vpq904m.yaml @@ -91,6 +91,7 @@ required: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# additionalProperties: false diff --git a/Documentation/devicetree/bindings/usb/parade,ps8830.yaml b/Documentation/devicetree/bindings/usb/parade,ps8830.yaml index aeb33667818e..eaeab1c01a59 100644 --- a/Documentation/devicetree/bindings/usb/parade,ps8830.yaml +++ b/Documentation/devicetree/bindings/usb/parade,ps8830.yaml @@ -81,6 +81,7 @@ required: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# additionalProperties: false diff --git a/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml index dfd084ed9024..d49a58d5478f 100644 --- a/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,snps-dwc3.yaml @@ -68,6 +68,7 @@ properties: - qcom,sm8550-dwc3 - qcom,sm8650-dwc3 - qcom,x1e80100-dwc3 + - qcom,x1e80100-dwc3-mp - const: qcom,snps-dwc3 reg: @@ -460,8 +461,10 @@ allOf: then: properties: interrupts: + minItems: 4 maxItems: 5 interrupt-names: + minItems: 4 items: - const: dwc_usb3 - const: pwr_event diff --git a/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml b/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml index 96346723f3e9..96dcec9b7620 100644 --- a/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,wcd939x-usbss.yaml @@ -60,6 +60,7 @@ required: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# additionalProperties: false diff --git a/Documentation/devicetree/bindings/usb/ti,tusb1046.yaml b/Documentation/devicetree/bindings/usb/ti,tusb1046.yaml index f713cac4a8ac..e1501ea6b50b 100644 --- a/Documentation/devicetree/bindings/usb/ti,tusb1046.yaml +++ b/Documentation/devicetree/bindings/usb/ti,tusb1046.yaml @@ -11,6 +11,7 @@ maintainers: allOf: - $ref: usb-switch.yaml# + - $ref: usb-switch-ports.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/usb-switch-ports.yaml b/Documentation/devicetree/bindings/usb/usb-switch-ports.yaml new file mode 100644 index 000000000000..6bf0c97e30ae --- /dev/null +++ b/Documentation/devicetree/bindings/usb/usb-switch-ports.yaml @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/usb-switch-ports.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: USB Orientation and Mode Switches Ports Graph Properties + +maintainers: + - Greg Kroah-Hartman + +description: + Ports Graph properties for devices handling USB mode and orientation switching. + +properties: + port: + $ref: /schemas/graph.yaml#/$defs/port-base + description: + A port node to link the device to a TypeC controller for the purpose of + handling altmode muxing and orientation switching. + + properties: + endpoint: + $ref: /schemas/graph.yaml#/$defs/endpoint-base + unevaluatedProperties: false + properties: + data-lanes: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 1 + maxItems: 8 + uniqueItems: true + items: + maximum: 8 + + ports: + $ref: /schemas/graph.yaml#/properties/ports + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: + Super Speed (SS) Output endpoint to the Type-C connector + + port@1: + $ref: /schemas/graph.yaml#/$defs/port-base + description: + Super Speed (SS) Input endpoint from the Super-Speed PHY + unevaluatedProperties: false + + properties: + endpoint: + $ref: /schemas/graph.yaml#/$defs/endpoint-base + unevaluatedProperties: false + properties: + data-lanes: + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 1 + maxItems: 8 + uniqueItems: true + items: + maximum: 8 + +oneOf: + - required: + - port + - required: + - ports + +additionalProperties: true diff --git a/Documentation/devicetree/bindings/usb/usb-switch.yaml b/Documentation/devicetree/bindings/usb/usb-switch.yaml index 896201912630..f77731493dc4 100644 --- a/Documentation/devicetree/bindings/usb/usb-switch.yaml +++ b/Documentation/devicetree/bindings/usb/usb-switch.yaml @@ -25,56 +25,4 @@ properties: description: Possible handler of SuperSpeed signals retiming type: boolean - port: - $ref: /schemas/graph.yaml#/$defs/port-base - description: - A port node to link the device to a TypeC controller for the purpose of - handling altmode muxing and orientation switching. - - properties: - endpoint: - $ref: /schemas/graph.yaml#/$defs/endpoint-base - unevaluatedProperties: false - properties: - data-lanes: - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 1 - maxItems: 8 - uniqueItems: true - items: - maximum: 8 - - ports: - $ref: /schemas/graph.yaml#/properties/ports - properties: - port@0: - $ref: /schemas/graph.yaml#/properties/port - description: - Super Speed (SS) Output endpoint to the Type-C connector - - port@1: - $ref: /schemas/graph.yaml#/$defs/port-base - description: - Super Speed (SS) Input endpoint from the Super-Speed PHY - unevaluatedProperties: false - - properties: - endpoint: - $ref: /schemas/graph.yaml#/$defs/endpoint-base - unevaluatedProperties: false - properties: - data-lanes: - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 1 - maxItems: 8 - uniqueItems: true - items: - maximum: 8 - -oneOf: - - required: - - port - - required: - - ports - additionalProperties: true diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 3451c9ac0add..e73442920f8b 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -176,6 +176,8 @@ patternProperties: description: All Sensors Corporation "^asix,.*": description: ASIX Electronics Corporation + "^asl-tek,.*": + description: ASL Xiamen Technology Co., Ltd. "^aspeed,.*": description: ASPEED Technology Inc. "^asrock,.*": @@ -1325,6 +1327,8 @@ patternProperties: description: Raumfeld GmbH "^raydium,.*": description: Raydium Semiconductor Corp. + "^raystar,.*": + description: Raystar Optronics, Inc. "^rda,.*": description: Unisoc Communications, Inc. "^realtek,.*": diff --git a/Documentation/firmware-guide/acpi/i2c-muxes.rst b/Documentation/firmware-guide/acpi/i2c-muxes.rst index f366539acd79..96ef4012d78f 100644 --- a/Documentation/firmware-guide/acpi/i2c-muxes.rst +++ b/Documentation/firmware-guide/acpi/i2c-muxes.rst @@ -37,8 +37,8 @@ which corresponds to the following ASL (in the scope of \_SB):: Name (_HID, ...) Name (_CRS, ResourceTemplate () { I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED, - AddressingMode7Bit, "\\_SB.SMB1.CH00", 0x00, - ResourceConsumer,,) + AddressingMode7Bit, "\\_SB.SMB1.MUX0.CH00", + 0x00, ResourceConsumer,,) } } } @@ -52,8 +52,8 @@ which corresponds to the following ASL (in the scope of \_SB):: Name (_HID, ...) Name (_CRS, ResourceTemplate () { I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED, - AddressingMode7Bit, "\\_SB.SMB1.CH01", 0x00, - ResourceConsumer,,) + AddressingMode7Bit, "\\_SB.SMB1.MUX0.CH01", + 0x00, ResourceConsumer,,) } } } diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index abfe220764e1..2292e65f044c 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -413,6 +413,21 @@ Plane Panic Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_panic.c :export: +Colorop Abstraction +=================== + +.. kernel-doc:: drivers/gpu/drm/drm_colorop.c + :doc: overview + +Colorop Functions Reference +--------------------------- + +.. kernel-doc:: include/drm/drm_colorop.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_colorop.c + :export: + Display Modes Function Reference ================================ diff --git a/Documentation/gpu/rfc/color_pipeline.rst b/Documentation/gpu/rfc/color_pipeline.rst new file mode 100644 index 000000000000..cd1cc2d0f988 --- /dev/null +++ b/Documentation/gpu/rfc/color_pipeline.rst @@ -0,0 +1,378 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +Linux Color Pipeline API +======================== + +What problem are we solving? +============================ + +We would like to support pre-, and post-blending complex color +transformations in display controller hardware in order to allow for +HW-supported HDR use-cases, as well as to provide support to +color-managed applications, such as video or image editors. + +It is possible to support an HDR output on HW supporting the Colorspace +and HDR Metadata drm_connector properties, but that requires the +compositor or application to render and compose the content into one +final buffer intended for display. Doing so is costly. + +Most modern display HW offers various 1D LUTs, 3D LUTs, matrices, and other +operations to support color transformations. These operations are often +implemented in fixed-function HW and therefore much more power efficient than +performing similar operations via shaders or CPU. + +We would like to make use of this HW functionality to support complex color +transformations with no, or minimal CPU or shader load. The switch between HW +fixed-function blocks and shaders/CPU must be seamless with no visible +difference when fallback to shaders/CPU is neceesary at any time. + + +How are other OSes solving this problem? +======================================== + +The most widely supported use-cases regard HDR content, whether video or +gaming. + +Most OSes will specify the source content format (color gamut, encoding transfer +function, and other metadata, such as max and average light levels) to a driver. +Drivers will then program their fixed-function HW accordingly to map from a +source content buffer's space to a display's space. + +When fixed-function HW is not available the compositor will assemble a shader to +ask the GPU to perform the transformation from the source content format to the +display's format. + +A compositor's mapping function and a driver's mapping function are usually +entirely separate concepts. On OSes where a HW vendor has no insight into +closed-source compositor code such a vendor will tune their color management +code to visually match the compositor's. On other OSes, where both mapping +functions are open to an implementer they will ensure both mappings match. + +This results in mapping algorithm lock-in, meaning that no-one alone can +experiment with or introduce new mapping algorithms and achieve +consistent results regardless of which implementation path is taken. + +Why is Linux different? +======================= + +Unlike other OSes, where there is one compositor for one or more drivers, on +Linux we have a many-to-many relationship. Many compositors; many drivers. +In addition each compositor vendor or community has their own view of how +color management should be done. This is what makes Linux so beautiful. + +This means that a HW vendor can now no longer tune their driver to one +compositor, as tuning it to one could make it look fairly different from +another compositor's color mapping. + +We need a better solution. + + +Descriptive API +=============== + +An API that describes the source and destination colorspaces is a descriptive +API. It describes the input and output color spaces but does not describe +how precisely they should be mapped. Such a mapping includes many minute +design decision that can greatly affect the look of the final result. + +It is not feasible to describe such mapping with enough detail to ensure the +same result from each implementation. In fact, these mappings are a very active +research area. + + +Prescriptive API +================ + +A prescriptive API describes not the source and destination colorspaces. It +instead prescribes a recipe for how to manipulate pixel values to arrive at the +desired outcome. + +This recipe is generally an ordered list of straight-forward operations, +with clear mathematical definitions, such as 1D LUTs, 3D LUTs, matrices, +or other operations that can be described in a precise manner. + + +The Color Pipeline API +====================== + +HW color management pipelines can significantly differ between HW +vendors in terms of availability, ordering, and capabilities of HW +blocks. This makes a common definition of color management blocks and +their ordering nigh impossible. Instead we are defining an API that +allows user space to discover the HW capabilities in a generic manner, +agnostic of specific drivers and hardware. + + +drm_colorop Object +================== + +To support the definition of color pipelines we define the DRM core +object type drm_colorop. Individual drm_colorop objects will be chained +via the NEXT property of a drm_colorop to constitute a color pipeline. +Each drm_colorop object is unique, i.e., even if multiple color +pipelines have the same operation they won't share the same drm_colorop +object to describe that operation. + +Note that drivers are not expected to map drm_colorop objects statically +to specific HW blocks. The mapping of drm_colorop objects is entirely a +driver-internal detail and can be as dynamic or static as a driver needs +it to be. See more in the Driver Implementation Guide section below. + +Each drm_colorop has three core properties: + +TYPE: An enumeration property, defining the type of transformation, such as +* enumerated curve +* custom (uniform) 1D LUT +* 3x3 matrix +* 3x4 matrix +* 3D LUT +* etc. + +Depending on the type of transformation other properties will describe +more details. + +BYPASS: A boolean property that can be used to easily put a block into +bypass mode. The BYPASS property is not mandatory for a colorop, as long +as the entire pipeline can get bypassed by setting the COLOR_PIPELINE on +a plane to '0'. + +NEXT: The ID of the next drm_colorop in a color pipeline, or 0 if this +drm_colorop is the last in the chain. + +An example of a drm_colorop object might look like one of these:: + + /* 1D enumerated curve */ + Color operation 42 + ├─ "TYPE": immutable enum {1D enumerated curve, 1D LUT, 3x3 matrix, 3x4 matrix, 3D LUT, etc.} = 1D enumerated curve + ├─ "BYPASS": bool {true, false} + ├─ "CURVE_1D_TYPE": enum {sRGB EOTF, sRGB inverse EOTF, PQ EOTF, PQ inverse EOTF, …} + └─ "NEXT": immutable color operation ID = 43 + + /* custom 4k entry 1D LUT */ + Color operation 52 + ├─ "TYPE": immutable enum {1D enumerated curve, 1D LUT, 3x3 matrix, 3x4 matrix, 3D LUT, etc.} = 1D LUT + ├─ "BYPASS": bool {true, false} + ├─ "SIZE": immutable range = 4096 + ├─ "DATA": blob + └─ "NEXT": immutable color operation ID = 0 + + /* 17^3 3D LUT */ + Color operation 72 + ├─ "TYPE": immutable enum {1D enumerated curve, 1D LUT, 3x3 matrix, 3x4 matrix, 3D LUT, etc.} = 3D LUT + ├─ "BYPASS": bool {true, false} + ├─ "SIZE": immutable range = 17 + ├─ "DATA": blob + └─ "NEXT": immutable color operation ID = 73 + +drm_colorop extensibility +------------------------- + +Unlike existing DRM core objects, like &drm_plane, drm_colorop is not +extensible. This simplifies implementations and keeps all functionality +for managing &drm_colorop objects in the DRM core. + +If there is a need one may introduce a simple &drm_colorop_funcs +function table in the future, for example to support an IN_FORMATS +property on a &drm_colorop. + +If a driver requires the ability to create a driver-specific colorop +object they will need to add &drm_colorop func table support with +support for the usual functions, like destroy, atomic_duplicate_state, +and atomic_destroy_state. + + +COLOR_PIPELINE Plane Property +============================= + +Color Pipelines are created by a driver and advertised via a new +COLOR_PIPELINE enum property on each plane. Values of the property +always include object id 0, which is the default and means all color +processing is disabled. Additional values will be the object IDs of the +first drm_colorop in a pipeline. A driver can create and advertise none, +one, or more possible color pipelines. A DRM client will select a color +pipeline by setting the COLOR PIPELINE to the respective value. + +NOTE: Many DRM clients will set enumeration properties via the string +value, often hard-coding it. Since this enumeration is generated based +on the colorop object IDs it is important to perform the Color Pipeline +Discovery, described below, instead of hard-coding color pipeline +assignment. Drivers might generate the enum strings dynamically. +Hard-coded strings might only work for specific drivers on a specific +pieces of HW. Color Pipeline Discovery can work universally, as long as +drivers implement the required color operations. + +The COLOR_PIPELINE property is only exposed when the +DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE is set. Drivers shall ignore any +existing pre-blend color operations when this cap is set, such as +COLOR_RANGE and COLOR_ENCODING. If drivers want to support COLOR_RANGE +or COLOR_ENCODING functionality when the color pipeline client cap is +set, they are expected to expose colorops in the pipeline to allow for +the appropriate color transformation. + +Setting of the COLOR_PIPELINE plane property or drm_colorop properties +is only allowed for userspace that sets this client cap. + +An example of a COLOR_PIPELINE property on a plane might look like this:: + + Plane 10 + ├─ "TYPE": immutable enum {Overlay, Primary, Cursor} = Primary + ├─ … + └─ "COLOR_PIPELINE": enum {0, 42, 52} = 0 + + +Color Pipeline Discovery +======================== + +A DRM client wanting color management on a drm_plane will: + +1. Get the COLOR_PIPELINE property of the plane +2. iterate all COLOR_PIPELINE enum values +3. for each enum value walk the color pipeline (via the NEXT pointers) + and see if the available color operations are suitable for the + desired color management operations + +If userspace encounters an unknown or unsuitable color operation during +discovery it does not need to reject the entire color pipeline outright, +as long as the unknown or unsuitable colorop has a "BYPASS" property. +Drivers will ensure that a bypassed block does not have any effect. + +An example of chained properties to define an AMD pre-blending color +pipeline might look like this:: + + Plane 10 + ├─ "TYPE" (immutable) = Primary + └─ "COLOR_PIPELINE": enum {0, 44} = 0 + + Color operation 44 + ├─ "TYPE" (immutable) = 1D enumerated curve + ├─ "BYPASS": bool + ├─ "CURVE_1D_TYPE": enum {sRGB EOTF, PQ EOTF} = sRGB EOTF + └─ "NEXT" (immutable) = 45 + + Color operation 45 + ├─ "TYPE" (immutable) = 3x4 Matrix + ├─ "BYPASS": bool + ├─ "DATA": blob + └─ "NEXT" (immutable) = 46 + + Color operation 46 + ├─ "TYPE" (immutable) = 1D enumerated curve + ├─ "BYPASS": bool + ├─ "CURVE_1D_TYPE": enum {sRGB Inverse EOTF, PQ Inverse EOTF} = sRGB EOTF + └─ "NEXT" (immutable) = 47 + + Color operation 47 + ├─ "TYPE" (immutable) = 1D LUT + ├─ "SIZE": immutable range = 4096 + ├─ "DATA": blob + └─ "NEXT" (immutable) = 48 + + Color operation 48 + ├─ "TYPE" (immutable) = 3D LUT + ├─ "DATA": blob + └─ "NEXT" (immutable) = 49 + + Color operation 49 + ├─ "TYPE" (immutable) = 1D enumerated curve + ├─ "BYPASS": bool + ├─ "CURVE_1D_TYPE": enum {sRGB EOTF, PQ EOTF} = sRGB EOTF + └─ "NEXT" (immutable) = 0 + + +Color Pipeline Programming +========================== + +Once a DRM client has found a suitable pipeline it will: + +1. Set the COLOR_PIPELINE enum value to the one pointing at the first + drm_colorop object of the desired pipeline +2. Set the properties for all drm_colorop objects in the pipeline to the + desired values, setting BYPASS to true for unused drm_colorop blocks, + and false for enabled drm_colorop blocks +3. Perform (TEST_ONLY or not) atomic commit with all the other KMS + states it wishes to change + +To configure the pipeline for an HDR10 PQ plane and blending in linear +space, a compositor might perform an atomic commit with the following +property values:: + + Plane 10 + └─ "COLOR_PIPELINE" = 42 + + Color operation 42 + └─ "BYPASS" = true + + Color operation 44 + └─ "BYPASS" = true + + Color operation 45 + └─ "BYPASS" = true + + Color operation 46 + └─ "BYPASS" = true + + Color operation 47 + ├─ "DATA" = Gamut mapping + tone mapping + night mode + └─ "BYPASS" = false + + Color operation 48 + ├─ "CURVE_1D_TYPE" = PQ EOTF + └─ "BYPASS" = false + + +Driver Implementer's Guide +========================== + +What does this all mean for driver implementations? As noted above the +colorops can map to HW directly but don't need to do so. Here are some +suggestions on how to think about creating your color pipelines: + +- Try to expose pipelines that use already defined colorops, even if + your hardware pipeline is split differently. This allows existing + userspace to immediately take advantage of the hardware. + +- Additionally, try to expose your actual hardware blocks as colorops. + Define new colorop types where you believe it can offer significant + benefits if userspace learns to program them. + +- Avoid defining new colorops for compound operations with very narrow + scope. If you have a hardware block for a special operation that + cannot be split further, you can expose that as a new colorop type. + However, try to not define colorops for "use cases", especially if + they require you to combine multiple hardware blocks. + +- Design new colorops as prescriptive, not descriptive; by the + mathematical formula, not by the assumed input and output. + +A defined colorop type must be deterministic. The exact behavior of the +colorop must be documented entirely, whether via a mathematical formula +or some other description. Its operation can depend only on its +properties and input and nothing else, allowed error tolerance +notwithstanding. + + +Driver Forward/Backward Compatibility +===================================== + +As this is uAPI drivers can't regress color pipelines that have been +introduced for a given HW generation. New HW generations are free to +abandon color pipelines advertised for previous generations. +Nevertheless, it can be beneficial to carry support for existing color +pipelines forward as those will likely already have support in DRM +clients. + +Introducing new colorops to a pipeline is fine, as long as they can be +bypassed or are purely informational. DRM clients implementing support +for the pipeline can always skip unknown properties as long as they can +be confident that doing so will not cause unexpected results. + +If a new colorop doesn't fall into one of the above categories +(bypassable or informational) the modified pipeline would be unusable +for user space. In this case a new pipeline should be defined. + + +References +========== + +1. https://lore.kernel.org/dri-devel/QMers3awXvNCQlyhWdTtsPwkp5ie9bze_hD5nAccFW7a_RXlWjYB7MoUW_8CKLT2bSQwIXVi5H6VULYIxCdgvryZoAoJnC5lZgyK1QWn488=@emersion.fr/ \ No newline at end of file diff --git a/Documentation/gpu/rfc/index.rst b/Documentation/gpu/rfc/index.rst index 396e535377fb..ef19b0ba2a3e 100644 --- a/Documentation/gpu/rfc/index.rst +++ b/Documentation/gpu/rfc/index.rst @@ -35,3 +35,6 @@ host such documentation: .. toctree:: i915_vm_bind.rst + +.. toctree:: + color_pipeline.rst \ No newline at end of file diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index cafb4ec20447..80728f6f9bc8 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -605,6 +605,8 @@ operations: reply: &pin-attrs attributes: - id + - module-name + - clock-id - board-label - panel-label - package-label diff --git a/Documentation/networking/ax25.rst b/Documentation/networking/ax25.rst index 605e72c6c877..89c79dd6c6f9 100644 --- a/Documentation/networking/ax25.rst +++ b/Documentation/networking/ax25.rst @@ -11,6 +11,7 @@ found on https://linux-ax25.in-berlin.de. There is a mailing list for discussing Linux amateur radio matters called linux-hams@vger.kernel.org. To subscribe to it, send a message to -majordomo@vger.kernel.org with the words "subscribe linux-hams" in the body -of the message, the subject field is ignored. You don't need to be -subscribed to post but of course that means you might miss an answer. +linux-hams+subscribe@vger.kernel.org or use the web interface at +https://vger.kernel.org. The subject and body of the message are +ignored. You don't need to be subscribed to post but of course that +means you might miss an answer. diff --git a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst index 289c146a8291..6877a3260582 100644 --- a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst +++ b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst @@ -137,16 +137,20 @@ d. Checksum offload header v5 Checksum offload header fields are in big endian format. +Packet format:: + Bit 0 - 6 7 8-15 16-31 Function Header Type Next Header Checksum Valid Reserved Header Type is to indicate the type of header, this usually is set to CHECKSUM Header types -= ========================================== + += =============== 0 Reserved 1 Reserved 2 checksum header += =============== Checksum Valid is to indicate whether the header checksum is valid. Value of 1 implies that checksum is calculated on this packet and is valid, value of 0 @@ -183,9 +187,11 @@ rmnet in a single linear skb. rmnet will process the individual packets and either ACK the MAP command or deliver the IP packet to the network stack as needed -MAP header|IP Packet|Optional padding|MAP header|IP Packet|Optional padding.... +Packet format:: -MAP header|IP Packet|Optional padding|MAP header|Command Packet|Optional pad... + MAP header|IP Packet|Optional padding|MAP header|IP Packet|Optional padding.... + + MAP header|IP Packet|Optional padding|MAP header|Command Packet|Optional pad... 3. Userspace configuration ========================== diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst index f4e1b4e07adc..2f776e90d318 100644 --- a/Documentation/networking/net_failover.rst +++ b/Documentation/networking/net_failover.rst @@ -96,9 +96,8 @@ needed to these network configuration daemons to make sure that an IP is received only on the 'failover' device. Below is the patch snippet used with 'cloud-ifupdown-helper' script found on -Debian cloud images: +Debian cloud images:: -:: @@ -27,6 +27,8 @@ do_setup() { local working="$cfgdir/.$INTERFACE" local final="$cfgdir/$INTERFACE" @@ -172,9 +171,8 @@ appropriate FDB entry is added. The following script is executed on the destination hypervisor once migration completes, and it reattaches the VF to the VM and brings down the virtio-net -interface. +interface:: -:: # reattach-vf.sh #!/bin/bash diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 59cb9982afe6..2555e75e5cc1 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -19,9 +19,6 @@ Userdata append support by Matthew Wood , Jan 22 2024 Sysdata append support by Breno Leitao , Jan 15 2025 -Please send bug reports to Matt Mackall -Satyam Sharma , and Cong Wang - Introduction: ============= diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst index 57d1964453e1..d5363b08f515 100644 --- a/Documentation/sound/codecs/cs35l56.rst +++ b/Documentation/sound/codecs/cs35l56.rst @@ -105,10 +105,10 @@ In this example the SSID is 10280c63. The format of the firmware file names is: -SoundWire (except CS35L56 Rev B0): +SoundWire: cs35lxx-b0-dsp1-misc-SSID[-spkidX]-l?u? -SoundWire CS35L56 Rev B0: +SoundWire CS35L56 Rev B0 firmware released before kernel version 6.16: cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN Non-SoundWire (HDA and I2S): @@ -127,9 +127,8 @@ Where: * spkidX is an optional part, used for laptops that have firmware configurations for different makes and models of internal speakers. -The CS35L56 Rev B0 continues to use the old filename scheme because a -large number of firmware files have already been published with these -names. +Early firmware for CS35L56 Rev B0 used the ALSA prefix (ampN) as the +filename qualifier. Support for the l?u? qualifier was added in kernel 6.16. Sound Open Firmware and ALSA topology files ------------------------------------------- diff --git a/Documentation/userspace-api/netlink/intro-specs.rst b/Documentation/userspace-api/netlink/intro-specs.rst index a4435ae4628d..e5ebc617754a 100644 --- a/Documentation/userspace-api/netlink/intro-specs.rst +++ b/Documentation/userspace-api/netlink/intro-specs.rst @@ -13,10 +13,10 @@ Simple CLI Kernel comes with a simple CLI tool which should be useful when developing Netlink related code. The tool is implemented in Python and can use a YAML specification to issue Netlink requests -to the kernel. Only Generic Netlink is supported. +to the kernel. The tool is located at ``tools/net/ynl/pyynl/cli.py``. It accepts -a handul of arguments, the most important ones are: +a handful of arguments, the most important ones are: - ``--spec`` - point to the spec file - ``--do $name`` / ``--dump $name`` - issue request ``$name`` diff --git a/MAINTAINERS b/MAINTAINERS index f9eca679d084..5a4aac3206fa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -915,6 +915,7 @@ F: drivers/staging/media/sunxi/cedrus/ ALPHA PORT M: Richard Henderson M: Matt Turner +M: Magnus Lindholm L: linux-alpha@vger.kernel.org S: Odd Fixes F: arch/alpha/ @@ -1997,6 +1998,10 @@ F: include/uapi/linux/if_arcnet.h ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) M: Arnd Bergmann +M: Krzysztof Kozlowski +M: Alexandre Belloni +M: Linus Walleij +R: Drew Fustini L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: soc@lists.linux.dev S: Maintained @@ -3851,6 +3856,7 @@ F: drivers/hwmon/asus-ec-sensors.c ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS M: Corentin Chary M: Luke D. Jones +M: Denis Benato L: platform-driver-x86@vger.kernel.org S: Maintained W: https://asus-linux.org/ @@ -4403,7 +4409,7 @@ BLOCK LAYER M: Jens Axboe L: linux-block@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git F: Documentation/ABI/stable/sysfs-block F: Documentation/block/ F: block/ @@ -4823,6 +4829,7 @@ F: drivers/net/dsa/b53/* F: drivers/net/dsa/bcm_sf2* F: include/linux/dsa/brcm.h F: include/linux/platform_data/b53.h +F: net/dsa/tag_brcm.c BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Florian Fainelli @@ -7880,6 +7887,7 @@ DRM DRIVER for Qualcomm Adreno GPUs M: Rob Clark R: Sean Paul R: Konrad Dybcio +R: Akhil P Oommen L: linux-arm-msm@vger.kernel.org L: dri-devel@lists.freedesktop.org L: freedreno@lists.freedesktop.org @@ -8080,6 +8088,13 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/samsung,s6e3ha8.yaml F: drivers/gpu/drm/panel/panel-samsung-s6e3ha8.c +DRM DRIVER FOR SAMSUNG SOFEF00 DDIC +M: David Heidelberg +M: Casey Connolly +S: Maintained +F: Documentation/devicetree/bindings/display/panel/samsung,sofef00.yaml +F: drivers/gpu/drm/panel/panel-samsung-sofef00.c + DRM DRIVER FOR SHARP MEMORY LCD M: Alex Lanzano S: Maintained @@ -9220,6 +9235,7 @@ R: Yue Hu R: Jeffle Xu R: Sandeep Dhavale R: Hongbo Li +R: Chunhai Guo L: linux-erofs@lists.ozlabs.org S: Maintained W: https://erofs.docs.kernel.org @@ -11538,7 +11554,7 @@ F: include/linux/platform_data/huawei-gaokun-ec.h HUGETLB SUBSYSTEM M: Muchun Song M: Oscar Salvador -R: David Hildenbrand +R: David Hildenbrand L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -12534,6 +12550,7 @@ F: include/linux/avf/virtchnl.h F: include/linux/net/intel/*/ INTEL ETHERNET PROTOCOL DRIVER FOR RDMA +M: Krzysztof Czurylo M: Tatyana Nikolova L: linux-rdma@vger.kernel.org S: Supported @@ -12874,7 +12891,8 @@ F: tools/testing/selftests/sgx/* K: \bSGX_ INTEL SKYLAKE INT3472 ACPI DEVICE DRIVER -M: Daniel Scally +M: Daniel Scally +M: Sakari Ailus S: Maintained F: drivers/platform/x86/intel/int3472/ F: include/linux/platform_data/x86/int3472.h @@ -13129,6 +13147,15 @@ F: include/uapi/linux/io_uring.h F: include/uapi/linux/io_uring/ F: io_uring/ +IO_URING ZCRX +M: Pavel Begunkov +L: io-uring@vger.kernel.org +L: netdev@vger.kernel.org +T: git https://github.com/isilence/linux.git zcrx/for-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git +S: Maintained +F: io_uring/zcrx.* + IPMI SUBSYSTEM M: Corey Minyard L: openipmi-developer@lists.sourceforge.net (moderated for non-subscribers) @@ -13264,10 +13291,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git mast F: drivers/infiniband/ulp/isert ISDN/CMTP OVER BLUETOOTH -M: Karsten Keil -L: isdn4linux@listserv.isdn4linux.de (subscribers-only) L: netdev@vger.kernel.org -S: Odd Fixes +S: Orphan W: http://www.isdn4linux.de F: Documentation/isdn/ F: drivers/isdn/capi/ @@ -13276,10 +13301,8 @@ F: include/uapi/linux/isdn/ F: net/bluetooth/cmtp/ ISDN/mISDN SUBSYSTEM -M: Karsten Keil -L: isdn4linux@listserv.isdn4linux.de (subscribers-only) L: netdev@vger.kernel.org -S: Maintained +S: Orphan W: http://www.isdn4linux.de F: drivers/isdn/Kconfig F: drivers/isdn/Makefile @@ -13433,9 +13456,12 @@ F: mm/kasan/ F: scripts/Makefile.kasan KCONFIG +M: Nathan Chancellor +M: Nicolas Schier L: linux-kbuild@vger.kernel.org -S: Orphan +S: Odd Fixes Q: https://patchwork.kernel.org/project/linux-kbuild/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kbuild/linux.git F: Documentation/kbuild/kconfig* F: scripts/Kconfig.include F: scripts/kconfig/ @@ -13620,7 +13646,7 @@ F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins M: David Gow -R: Rae Moar +R: Rae Moar L: linux-kselftest@vger.kernel.org L: kunit-dev@googlegroups.com S: Maintained @@ -13661,7 +13687,7 @@ F: virt/kvm/* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier -M: Oliver Upton +M: Oliver Upton R: Joey Gouly R: Suzuki K Poulose R: Zenghui Yu @@ -13735,7 +13761,7 @@ KERNEL VIRTUAL MACHINE for s390 (KVM/s390) M: Christian Borntraeger M: Janosch Frank M: Claudio Imbrenda -R: David Hildenbrand +R: David Hildenbrand L: kvm@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git @@ -14412,6 +14438,7 @@ F: tools/memory-model/ LINUX-NEXT TREE M: Stephen Rothwell +M: Mark Brown L: linux-next@vger.kernel.org S: Supported B: mailto:linux-next@vger.kernel.org and the appropriate development tree @@ -16221,7 +16248,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git F: drivers/devfreq/tegra30-devfreq.c MEMORY HOT(UN)PLUG -M: David Hildenbrand +M: David Hildenbrand M: Oscar Salvador L: linux-mm@kvack.org S: Maintained @@ -16246,7 +16273,7 @@ F: tools/mm/ MEMORY MANAGEMENT - CORE M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand R: Lorenzo Stoakes R: Liam R. Howlett R: Vlastimil Babka @@ -16302,7 +16329,7 @@ F: mm/execmem.c MEMORY MANAGEMENT - GUP (GET USER PAGES) M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand R: Jason Gunthorpe R: John Hubbard R: Peter Xu @@ -16318,7 +16345,7 @@ F: tools/testing/selftests/mm/gup_test.c MEMORY MANAGEMENT - KSM (Kernel Samepage Merging) M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand R: Xu Xin R: Chengming Zhou L: linux-mm@kvack.org @@ -16334,7 +16361,7 @@ F: mm/mm_slot.h MEMORY MANAGEMENT - MEMORY POLICY AND MIGRATION M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand R: Zi Yan R: Matthew Brost R: Joshua Hahn @@ -16374,7 +16401,7 @@ F: mm/workingset.c MEMORY MANAGEMENT - MISC M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand R: Lorenzo Stoakes R: Liam R. Howlett R: Vlastimil Babka @@ -16462,7 +16489,7 @@ F: mm/shuffle.h MEMORY MANAGEMENT - RECLAIM M: Andrew Morton M: Johannes Weiner -R: David Hildenbrand +R: David Hildenbrand R: Michal Hocko R: Qi Zheng R: Shakeel Butt @@ -16475,7 +16502,7 @@ F: mm/workingset.c MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand M: Lorenzo Stoakes R: Rik van Riel R: Liam R. Howlett @@ -16499,12 +16526,12 @@ F: mm/secretmem.c MEMORY MANAGEMENT - SWAP M: Andrew Morton +M: Chris Li +M: Kairui Song R: Kemeng Shi -R: Kairui Song R: Nhat Pham R: Baoquan He R: Barry Song -R: Chris Li L: linux-mm@kvack.org S: Maintained F: Documentation/mm/swap-table.rst @@ -16520,7 +16547,7 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton -M: David Hildenbrand +M: David Hildenbrand M: Lorenzo Stoakes R: Zi Yan R: Baolin Wang @@ -16622,7 +16649,7 @@ MEMORY MAPPING - MADVISE (MEMORY ADVICE) M: Andrew Morton M: Liam R. Howlett M: Lorenzo Stoakes -M: David Hildenbrand +M: David Hildenbrand R: Vlastimil Babka R: Jann Horn L: linux-mm@kvack.org @@ -20164,6 +20191,7 @@ R: Alexander Shishkin R: Jiri Olsa R: Ian Rogers R: Adrian Hunter +R: James Clark L: linux-perf-users@vger.kernel.org L: linux-kernel@vger.kernel.org S: Supported @@ -21335,6 +21363,7 @@ F: drivers/media/platform/qcom/venus/ QUALCOMM WCN36XX WIRELESS DRIVER M: Loic Poulain L: wcn36xx@lists.infradead.org +L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx F: drivers/net/wireless/ath/wcn36xx/ @@ -26903,7 +26932,7 @@ S: Maintained F: drivers/vfio/cdx/* VFIO DRIVER -M: Alex Williamson +M: Alex Williamson L: kvm@vger.kernel.org S: Maintained T: git https://github.com/awilliam/linux-vfio.git @@ -27066,7 +27095,7 @@ T: git git://linuxtv.org/media.git F: drivers/media/test-drivers/vimc/* VIRT LIB -M: Alex Williamson +M: Alex Williamson M: Paolo Bonzini L: kvm@vger.kernel.org S: Supported @@ -27087,7 +27116,7 @@ F: net/vmw_vsock/virtio_transport_common.c VIRTIO BALLOON M: "Michael S. Tsirkin" -M: David Hildenbrand +M: David Hildenbrand L: virtualization@lists.linux.dev S: Maintained F: drivers/virtio/virtio_balloon.c @@ -27242,7 +27271,7 @@ F: drivers/iommu/virtio-iommu.c F: include/uapi/linux/virtio_iommu.h VIRTIO MEM DRIVER -M: David Hildenbrand +M: David Hildenbrand L: virtualization@lists.linux.dev S: Maintained W: https://virtio-mem.gitlab.io/ @@ -27848,7 +27877,7 @@ F: arch/x86/kernel/stacktrace.c F: arch/x86/kernel/unwind_*.c X86 TRUST DOMAIN EXTENSIONS (TDX) -M: Kirill A. Shutemov +M: Kiryl Shutsemau R: Dave Hansen R: Rick Edgecombe L: x86@kernel.org diff --git a/Makefile b/Makefile index d14824792227..d763c2c75cdb 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 74ff01133532..61130b88964b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -917,6 +917,13 @@ config ARCH_USES_CFI_TRAPS An architecture should select this option if it requires the .kcfi_traps section for KCFI trap handling. +config ARCH_USES_CFI_GENERIC_LLVM_PASS + bool + help + An architecture should select this option if it uses the generic + KCFIPass in LLVM to expand kCFI bundles instead of architecture-specific + lowering. + config CFI bool "Use Kernel Control Flow Integrity (kCFI)" default CFI_CLANG diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2e3f93b690f4..4fb985b76e97 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -44,6 +44,8 @@ config ARM select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_MEMTEST + # https://github.com/llvm/llvm-project/commit/d130f402642fba3d065aacb506cb061c899558de + select ARCH_USES_CFI_GENERIC_LLVM_PASS if CLANG_VERSION < 220000 select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_IPC_PARSE_VERSION diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi index c78ed064d166..1eb6406449d1 100644 --- a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi @@ -77,6 +77,14 @@ &i2c0 { /delete-property/ pinctrl-0; }; +&pm { + clocks = <&firmware_clocks 5>, + <&clocks BCM2835_CLOCK_PERI_IMAGE>, + <&clocks BCM2835_CLOCK_H264>, + <&clocks BCM2835_CLOCK_ISP>; + clock-names = "v3d", "peri_image", "h264", "isp"; +}; + &rmem { /* * RPi4's co-processor will copy the board's bootloader configuration diff --git a/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi b/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi index 8b3c21d9f333..fa9d784c88b6 100644 --- a/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi +++ b/arch/arm/boot/dts/broadcom/bcm2835-rpi-common.dtsi @@ -13,7 +13,16 @@ &hdmi { clock-names = "pixel", "hdmi"; }; +&pm { + clocks = <&firmware_clocks 5>, + <&clocks BCM2835_CLOCK_PERI_IMAGE>, + <&clocks BCM2835_CLOCK_H264>, + <&clocks BCM2835_CLOCK_ISP>; + clock-names = "v3d", "peri_image", "h264", "isp"; +}; + &v3d { + clocks = <&firmware_clocks 5>; power-domains = <&power RPI_POWER_DOMAIN_V3D>; }; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index e77a66adc22a..205b87f557d6 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -326,6 +326,8 @@ gicv2: interrupt-controller@7fff9000 { <0x7fffe000 0x2000>; interrupt-controller; #address-cells = <0>; + interrupts = ; #interrupt-cells = <3>; }; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 00d97b8a757f..51746005239b 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -26,9 +26,12 @@ void __init apply_alternatives_all(void); bool alternative_is_applied(u16 cpucap); #ifdef CONFIG_MODULES -void apply_alternatives_module(void *start, size_t length); +int apply_alternatives_module(void *start, size_t length); #else -static inline void apply_alternatives_module(void *start, size_t length) { } +static inline int apply_alternatives_module(void *start, size_t length) +{ + return 0; +} #endif void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr, diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h index a81937fae9f6..21dbc9dda747 100644 --- a/arch/arm64/include/asm/kfence.h +++ b/arch/arm64/include/asm/kfence.h @@ -10,8 +10,6 @@ #include -static inline bool arch_kfence_init_pool(void) { return true; } - static inline bool kfence_protect_page(unsigned long addr, bool protect) { set_memory_valid(addr, 1, !protect); @@ -25,6 +23,7 @@ static inline bool arm64_kfence_can_set_direct_map(void) { return !kfence_early_init; } +bool arch_kfence_init_pool(void); #else /* CONFIG_KFENCE */ static inline bool arm64_kfence_can_set_direct_map(void) { return false; } #endif /* CONFIG_KFENCE */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 9abcc8ef3087..b57b2bb00967 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -77,7 +77,7 @@ __percpu_##name##_case_##sz(void *ptr, unsigned long val) \ " stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n" \ " cbnz %w[loop], 1b", \ /* LSE atomics */ \ - #op_lse "\t%" #w "[val], %[ptr]\n" \ + #op_lse "\t%" #w "[val], %" #w "[tmp], %[ptr]\n" \ __nops(3)) \ : [loop] "=&r" (loop), [tmp] "=&r" (tmp), \ [ptr] "+Q"(*(u##sz *)ptr) \ @@ -124,9 +124,16 @@ PERCPU_RW_OPS(8) PERCPU_RW_OPS(16) PERCPU_RW_OPS(32) PERCPU_RW_OPS(64) -PERCPU_OP(add, add, stadd) -PERCPU_OP(andnot, bic, stclr) -PERCPU_OP(or, orr, stset) + +/* + * Use value-returning atomics for CPU-local ops as they are more likely + * to execute "near" to the CPU (e.g. in L1$). + * + * https://lore.kernel.org/r/e7d539ed-ced0-4b96-8ecd-048a5b803b85@paulmck-laptop + */ +PERCPU_OP(add, add, ldadd) +PERCPU_OP(andnot, bic, ldclr) +PERCPU_OP(or, orr, ldset) PERCPU_RET_OP(add, add, ldadd) #undef PERCPU_RW_OPS diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index aa89c2e67ebc..0944e296dd4a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -293,7 +293,8 @@ static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); + if (pte_sw_dirty(pte)) + pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index a76f9b387a26..c59f6324f2bb 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -53,7 +53,7 @@ enum { EDYNSCS_INVALID_CFA_OPCODE = 4, }; -int __pi_scs_patch(const u8 eh_frame[], int size); +int __pi_scs_patch(const u8 eh_frame[], int size, bool skip_dry_run); #endif /* __ASSEMBLY __ */ diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index 8fef12626090..900454aaa292 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -117,6 +117,7 @@ void spectre_bhb_patch_wa3(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void spectre_bhb_patch_clearbhb(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); +void spectre_print_disabled_mitigations(void); #endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 7aca29e1d30b..c022c1acb8c7 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -197,8 +197,6 @@ static int __init acpi_fadt_sanity_check(void) */ void __init acpi_boot_table_init(void) { - int ret; - /* * Enable ACPI instead of device tree unless * - ACPI has been disabled explicitly (acpi=off), or @@ -252,12 +250,8 @@ void __init acpi_boot_table_init(void) * behaviour, use acpi=nospcr to disable console in ACPI SPCR * table as default serial console. */ - ret = acpi_parse_spcr(earlycon_acpi_spcr_enable, + acpi_parse_spcr(earlycon_acpi_spcr_enable, !param_acpi_nospcr); - if (!ret || param_acpi_nospcr || !IS_ENABLED(CONFIG_ACPI_SPCR_TABLE)) - pr_info("Use ACPI SPCR as default console: No\n"); - else - pr_info("Use ACPI SPCR as default console: Yes\n"); if (IS_ENABLED(CONFIG_ACPI_BGRT)) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 8ff6610af496..f5ec7e7c1d3f 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -139,9 +139,9 @@ static noinstr void clean_dcache_range_nopatch(u64 start, u64 end) } while (cur += d_size, cur < end); } -static void __apply_alternatives(const struct alt_region *region, - bool is_module, - unsigned long *cpucap_mask) +static int __apply_alternatives(const struct alt_region *region, + bool is_module, + unsigned long *cpucap_mask) { struct alt_instr *alt; __le32 *origptr, *updptr; @@ -166,10 +166,13 @@ static void __apply_alternatives(const struct alt_region *region, updptr = is_module ? origptr : lm_alias(origptr); nr_inst = alt->orig_len / AARCH64_INSN_SIZE; - if (ALT_HAS_CB(alt)) + if (ALT_HAS_CB(alt)) { alt_cb = ALT_REPL_PTR(alt); - else + if (is_module && !core_kernel_text((unsigned long)alt_cb)) + return -ENOEXEC; + } else { alt_cb = patch_alternative; + } alt_cb(alt, origptr, updptr, nr_inst); @@ -193,6 +196,8 @@ static void __apply_alternatives(const struct alt_region *region, bitmap_and(applied_alternatives, applied_alternatives, system_cpucaps, ARM64_NCAPS); } + + return 0; } static void __init apply_alternatives_vdso(void) @@ -277,7 +282,7 @@ void __init apply_boot_alternatives(void) } #ifdef CONFIG_MODULES -void apply_alternatives_module(void *start, size_t length) +int apply_alternatives_module(void *start, size_t length) { struct alt_region region = { .begin = start, @@ -287,7 +292,7 @@ void apply_alternatives_module(void *start, size_t length) bitmap_fill(all_capabilities, ARM64_NCAPS); - __apply_alternatives(®ion, true, &all_capabilities[0]); + return __apply_alternatives(®ion, true, &all_capabilities[0]); } #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 5ed401ff79e3..e25b0f84a22d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -95,6 +95,7 @@ #include #include +#include /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ static DECLARE_BITMAP(elf_hwcap, MAX_CPU_FEATURES) __read_mostly; @@ -3875,6 +3876,11 @@ static void __init setup_system_capabilities(void) */ if (system_uses_ttbr0_pan()) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); + + /* + * Report Spectre mitigations status. + */ + spectre_print_disabled_mitigations(); } void __init setup_system_features(void) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index d6d443c4a01a..24adb581af0e 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -489,16 +489,29 @@ int module_finalize(const Elf_Ehdr *hdr, int ret; s = find_section(hdr, sechdrs, ".altinstructions"); - if (s) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); + if (s) { + ret = apply_alternatives_module((void *)s->sh_addr, s->sh_size); + if (ret < 0) { + pr_err("module %s: error occurred when applying alternatives\n", me->name); + return ret; + } + } if (scs_is_dynamic()) { s = find_section(hdr, sechdrs, ".init.eh_frame"); if (s) { - ret = __pi_scs_patch((void *)s->sh_addr, s->sh_size); - if (ret) + /* + * Because we can reject modules that are malformed + * so SCS patching fails, skip dry run and try to patch + * it in place. If patching fails, the module would not + * be loaded anyway. + */ + ret = __pi_scs_patch((void *)s->sh_addr, s->sh_size, true); + if (ret) { pr_err("module %s: error occurred during dynamic SCS patching (%d)\n", me->name, ret); + return -ENOEXEC; + } } } diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 43f7a2f39403..32148bf09c1d 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -476,7 +476,8 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, folio = page_folio(page); if (folio_test_hugetlb(folio)) - WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio)); + WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio) && + !is_huge_zero_folio(folio)); else WARN_ON_ONCE(!page_mte_tagged(page) && !is_zero_page(page)); diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index e8ddbde31a83..659297f87cfa 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -104,7 +104,7 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) if (enable_scs) { scs_patch(__eh_frame_start + va_offset, - __eh_frame_end - __eh_frame_start); + __eh_frame_end - __eh_frame_start, false); asm("ic ialluis"); dynamic_scs_is_enabled = true; diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index 55d0cd64ef71..bbe7d30ed12b 100644 --- a/arch/arm64/kernel/pi/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -225,7 +225,7 @@ static int scs_handle_fde_frame(const struct eh_frame *frame, return 0; } -int scs_patch(const u8 eh_frame[], int size) +int scs_patch(const u8 eh_frame[], int size, bool skip_dry_run) { int code_alignment_factor = 1; bool fde_use_sdata8 = false; @@ -277,11 +277,13 @@ int scs_patch(const u8 eh_frame[], int size) } } else { ret = scs_handle_fde_frame(frame, code_alignment_factor, - fde_use_sdata8, true); + fde_use_sdata8, !skip_dry_run); if (ret) return ret; - scs_handle_fde_frame(frame, code_alignment_factor, - fde_use_sdata8, false); + + if (!skip_dry_run) + scs_handle_fde_frame(frame, code_alignment_factor, + fde_use_sdata8, false); } p += sizeof(frame->size) + frame->size; diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h index 08ef9f80456b..aec3172d4003 100644 --- a/arch/arm64/kernel/pi/pi.h +++ b/arch/arm64/kernel/pi/pi.h @@ -27,7 +27,7 @@ extern pgd_t init_pg_dir[], init_pg_end[]; void init_feature_override(u64 boot_status, const void *fdt, int chosen); u64 kaslr_early_init(void *fdt, int chosen); void relocate_kernel(u64 offset); -int scs_patch(const u8 eh_frame[], int size); +int scs_patch(const u8 eh_frame[], int size, bool skip_dry_run); void map_range(phys_addr_t *pte, u64 start, u64 end, phys_addr_t pa, pgprot_t prot, int level, pte_t *tbl, bool may_use_cont, diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 8ab6104a4883..43a0361a8bf0 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -49,7 +49,10 @@ void *alloc_insn_page(void) addr = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE); if (!addr) return NULL; - set_memory_rox((unsigned long)addr, 1); + if (set_memory_rox((unsigned long)addr, 1)) { + execmem_free(addr); + return NULL; + } return addr; } diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index f9a32dfde006..c7d70d04c164 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -91,12 +91,7 @@ early_param("nospectre_v2", parse_spectre_v2_param); static bool spectre_v2_mitigations_off(void) { - bool ret = __nospectre_v2 || cpu_mitigations_off(); - - if (ret) - pr_info_once("spectre-v2 mitigation disabled by command line option\n"); - - return ret; + return __nospectre_v2 || cpu_mitigations_off(); } static const char *get_bhb_affected_string(enum mitigation_state bhb_state) @@ -421,13 +416,8 @@ early_param("ssbd", parse_spectre_v4_param); */ static bool spectre_v4_mitigations_off(void) { - bool ret = cpu_mitigations_off() || - __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED; - - if (ret) - pr_info_once("spectre-v4 mitigation disabled by command-line option\n"); - - return ret; + return cpu_mitigations_off() || + __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED; } /* Do we need to toggle the mitigation state on entry to/exit from the kernel? */ @@ -1042,10 +1032,6 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) { /* No point mitigating Spectre-BHB alone. */ - } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { - pr_info_once("spectre-bhb mitigation disabled by compile time option\n"); - } else if (cpu_mitigations_off() || __nospectre_bhb) { - pr_info_once("spectre-bhb mitigation disabled by command line option\n"); } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; set_bit(BHB_HW, &system_bhb_mitigations); @@ -1199,3 +1185,18 @@ void unpriv_ebpf_notify(int new_state) pr_err("WARNING: %s", EBPF_WARN); } #endif + +void spectre_print_disabled_mitigations(void) +{ + /* Keep a single copy of the common message suffix to avoid duplication. */ + const char *spectre_disabled_suffix = "mitigation disabled by command-line option\n"; + + if (spectre_v2_mitigations_off()) + pr_info("spectre-v2 %s", spectre_disabled_suffix); + + if (spectre_v4_mitigations_off()) + pr_info("spectre-v4 %s", spectre_disabled_suffix); + + if (__nospectre_bhb || cpu_mitigations_off()) + pr_info("spectre-bhb %s", spectre_disabled_suffix); +} diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index 4e16f9b96f63..58b7d0c477d7 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -479,7 +479,7 @@ static void __do_ffa_mem_xfer(const u64 func_id, struct ffa_mem_region_attributes *ep_mem_access; struct ffa_composite_mem_region *reg; struct ffa_mem_region *buf; - u32 offset, nr_ranges; + u32 offset, nr_ranges, checked_offset; int ret = 0; if (addr_mbz || npages_mbz || fraglen > len || @@ -516,7 +516,12 @@ static void __do_ffa_mem_xfer(const u64 func_id, goto out_unlock; } - if (fraglen < offset + sizeof(struct ffa_composite_mem_region)) { + if (check_add_overflow(offset, sizeof(struct ffa_composite_mem_region), &checked_offset)) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + if (fraglen < checked_offset) { ret = FFA_RET_INVALID_PARAMETERS; goto out_unlock; } diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index ddc8beb55eee..49db32f3ddf7 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -367,6 +367,19 @@ static int host_stage2_unmap_dev_all(void) return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr); } +/* + * Ensure the PFN range is contained within PA-range. + * + * This check is also robust to overflows and is therefore a requirement before + * using a pfn/nr_pages pair from an untrusted source. + */ +static bool pfn_range_is_valid(u64 pfn, u64 nr_pages) +{ + u64 limit = BIT(kvm_phys_shift(&host_mmu.arch.mmu) - PAGE_SHIFT); + + return pfn < limit && ((limit - pfn) >= nr_pages); +} + struct kvm_mem_range { u64 start; u64 end; @@ -776,6 +789,9 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) void *virt = __hyp_va(phys); int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); hyp_lock_component(); @@ -804,6 +820,9 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages) u64 virt = (u64)__hyp_va(phys); int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); hyp_lock_component(); @@ -887,6 +906,9 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages) u64 size = PAGE_SIZE * nr_pages; int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); if (!ret) @@ -902,6 +924,9 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages) u64 size = PAGE_SIZE * nr_pages; int ret; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + host_lock_component(); ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); if (!ret) @@ -945,6 +970,9 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu if (prot & ~KVM_PGTABLE_PROT_RWX) return -EINVAL; + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + ret = __guest_check_transition_size(phys, ipa, nr_pages, &size); if (ret) return ret; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e67eb39ddc11..8ae2bca81614 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2595,19 +2595,23 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, .val = 0, \ } -/* sys_reg_desc initialiser for known cpufeature ID registers */ -#define AA32_ID_SANITISED(name) { \ - ID_DESC(name), \ - .visibility = aa32_id_visibility, \ - .val = 0, \ -} - /* sys_reg_desc initialiser for writable ID registers */ #define ID_WRITABLE(name, mask) { \ ID_DESC(name), \ .val = mask, \ } +/* + * 32bit ID regs are fully writable when the guest is 32bit + * capable. Nothing in the KVM code should rely on 32bit features + * anyway, only 64bit, so let the VMM do its worse. + */ +#define AA32_ID_WRITABLE(name) { \ + ID_DESC(name), \ + .visibility = aa32_id_visibility, \ + .val = GENMASK(31, 0), \ +} + /* sys_reg_desc initialiser for cpufeature ID registers that need filtering */ #define ID_FILTERED(sysreg, name, mask) { \ ID_DESC(sysreg), \ @@ -3128,40 +3132,39 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* AArch64 mappings of the AArch32 ID registers */ /* CRm=1 */ - AA32_ID_SANITISED(ID_PFR0_EL1), - AA32_ID_SANITISED(ID_PFR1_EL1), + AA32_ID_WRITABLE(ID_PFR0_EL1), + AA32_ID_WRITABLE(ID_PFR1_EL1), { SYS_DESC(SYS_ID_DFR0_EL1), .access = access_id_reg, .get_user = get_id_reg, .set_user = set_id_dfr0_el1, .visibility = aa32_id_visibility, .reset = read_sanitised_id_dfr0_el1, - .val = ID_DFR0_EL1_PerfMon_MASK | - ID_DFR0_EL1_CopDbg_MASK, }, + .val = GENMASK(31, 0) }, ID_HIDDEN(ID_AFR0_EL1), - AA32_ID_SANITISED(ID_MMFR0_EL1), - AA32_ID_SANITISED(ID_MMFR1_EL1), - AA32_ID_SANITISED(ID_MMFR2_EL1), - AA32_ID_SANITISED(ID_MMFR3_EL1), + AA32_ID_WRITABLE(ID_MMFR0_EL1), + AA32_ID_WRITABLE(ID_MMFR1_EL1), + AA32_ID_WRITABLE(ID_MMFR2_EL1), + AA32_ID_WRITABLE(ID_MMFR3_EL1), /* CRm=2 */ - AA32_ID_SANITISED(ID_ISAR0_EL1), - AA32_ID_SANITISED(ID_ISAR1_EL1), - AA32_ID_SANITISED(ID_ISAR2_EL1), - AA32_ID_SANITISED(ID_ISAR3_EL1), - AA32_ID_SANITISED(ID_ISAR4_EL1), - AA32_ID_SANITISED(ID_ISAR5_EL1), - AA32_ID_SANITISED(ID_MMFR4_EL1), - AA32_ID_SANITISED(ID_ISAR6_EL1), + AA32_ID_WRITABLE(ID_ISAR0_EL1), + AA32_ID_WRITABLE(ID_ISAR1_EL1), + AA32_ID_WRITABLE(ID_ISAR2_EL1), + AA32_ID_WRITABLE(ID_ISAR3_EL1), + AA32_ID_WRITABLE(ID_ISAR4_EL1), + AA32_ID_WRITABLE(ID_ISAR5_EL1), + AA32_ID_WRITABLE(ID_MMFR4_EL1), + AA32_ID_WRITABLE(ID_ISAR6_EL1), /* CRm=3 */ - AA32_ID_SANITISED(MVFR0_EL1), - AA32_ID_SANITISED(MVFR1_EL1), - AA32_ID_SANITISED(MVFR2_EL1), + AA32_ID_WRITABLE(MVFR0_EL1), + AA32_ID_WRITABLE(MVFR1_EL1), + AA32_ID_WRITABLE(MVFR2_EL1), ID_UNALLOCATED(3,3), - AA32_ID_SANITISED(ID_PFR2_EL1), + AA32_ID_WRITABLE(ID_PFR2_EL1), ID_HIDDEN(ID_DFR1_EL1), - AA32_ID_SANITISED(ID_MMFR5_EL1), + AA32_ID_WRITABLE(ID_MMFR5_EL1), ID_UNALLOCATED(3,7), /* AArch64 ID registers */ @@ -5606,11 +5609,13 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) guard(mutex)(&kvm->arch.config_lock); - if (!(static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && - irqchip_in_kernel(kvm) && - kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)) { - kvm->arch.id_regs[IDREG_IDX(SYS_ID_AA64PFR0_EL1)] &= ~ID_AA64PFR0_EL1_GIC_MASK; - kvm->arch.id_regs[IDREG_IDX(SYS_ID_PFR1_EL1)] &= ~ID_PFR1_EL1_GIC_MASK; + if (!irqchip_in_kernel(kvm)) { + u64 val; + + val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val); + val = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, val); } if (vcpu_has_nv(vcpu)) { diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index 4c1209261b65..bb92853d1fd3 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -64,29 +64,37 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) static int iter_mark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long intid, flags; struct vgic_irq *irq; - unsigned long intid; int nr_lpis = 0; + xa_lock_irqsave(&dist->lpi_xa, flags); + xa_for_each(&dist->lpi_xa, intid, irq) { if (!vgic_try_get_irq_ref(irq)) continue; - xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); + __xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); nr_lpis++; } + xa_unlock_irqrestore(&dist->lpi_xa, flags); + return nr_lpis; } static void iter_unmark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long intid, flags; struct vgic_irq *irq; - unsigned long intid; xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) { - xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); + xa_lock_irqsave(&dist->lpi_xa, flags); + __xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); + xa_unlock_irqrestore(&dist->lpi_xa, flags); + + /* vgic_put_irq() expects to be called outside of the xa_lock */ vgic_put_irq(kvm, irq); } } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 1796b1a22a72..da62edbc1205 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -53,7 +53,7 @@ void kvm_vgic_early_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - xa_init(&dist->lpi_xa); + xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ); } /* CREATION */ @@ -71,6 +71,7 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); int kvm_vgic_create(struct kvm *kvm, u32 type) { struct kvm_vcpu *vcpu; + u64 aa64pfr0, pfr1; unsigned long i; int ret; @@ -161,10 +162,19 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) + aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - else + } else { INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); + aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); + pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); + } + + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index ce3e3ed3f29f..3f1c4b10fed9 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -78,6 +78,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq; + unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -88,7 +89,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, if (!irq) return ERR_PTR(-ENOMEM); - ret = xa_reserve(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); + ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); @@ -103,7 +104,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->target_vcpu = vcpu; irq->group = 1; - xa_lock(&dist->lpi_xa); + xa_lock_irqsave(&dist->lpi_xa, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -114,21 +115,18 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; - - goto out_unlock; + } else { + ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); } - ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); + xa_unlock_irqrestore(&dist->lpi_xa, flags); + if (ret) { xa_release(&dist->lpi_xa, intid); kfree(irq); - } -out_unlock: - xa_unlock(&dist->lpi_xa); - - if (ret) return ERR_PTR(ret); + } /* * We "cache" the configuration table entries in our struct vgic_irq's. diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 6fbb4b099855..2f75ef14d339 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -301,7 +301,8 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) return; /* Hide GICv3 sysreg if necessary */ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) { + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2 || + !irqchip_in_kernel(vcpu->kvm)) { vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 | ICH_HCR_EL2_TC); return; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 6dd5a10081e2..8d20c53faef0 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -28,7 +28,7 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->arch.config_lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_dist->lpi_xa.xa_lock + * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled * vgic_cpu->ap_list_lock must be taken with IRQs disabled * vgic_irq->irq_lock must be taken with IRQs disabled * @@ -141,32 +141,39 @@ static __must_check bool vgic_put_irq_norelease(struct kvm *kvm, struct vgic_irq void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long flags; - if (irq->intid >= VGIC_MIN_LPI) - might_lock(&dist->lpi_xa.xa_lock); + /* + * Normally the lock is only taken when the refcount drops to 0. + * Acquire/release it early on lockdep kernels to make locking issues + * in rare release paths a bit more obvious. + */ + if (IS_ENABLED(CONFIG_LOCKDEP) && irq->intid >= VGIC_MIN_LPI) { + guard(spinlock_irqsave)(&dist->lpi_xa.xa_lock); + } if (!__vgic_put_irq(kvm, irq)) return; - xa_lock(&dist->lpi_xa); + xa_lock_irqsave(&dist->lpi_xa, flags); vgic_release_lpi_locked(dist, irq); - xa_unlock(&dist->lpi_xa); + xa_unlock_irqrestore(&dist->lpi_xa, flags); } static void vgic_release_deleted_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - unsigned long intid; + unsigned long flags, intid; struct vgic_irq *irq; - xa_lock(&dist->lpi_xa); + xa_lock_irqsave(&dist->lpi_xa, flags); xa_for_each(&dist->lpi_xa, intid, irq) { if (irq->pending_release) vgic_release_lpi_locked(dist, irq); } - xa_unlock(&dist->lpi_xa); + xa_unlock_irqrestore(&dist->lpi_xa, flags); } void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index a86c897017df..cd5912ba617b 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -35,7 +35,7 @@ void copy_highpage(struct page *to, struct page *from) from != folio_page(src, 0)) return; - WARN_ON_ONCE(!folio_try_hugetlb_mte_tagging(dst)); + folio_try_hugetlb_mte_tagging(dst); /* * Populate tags for all subpages. @@ -51,8 +51,13 @@ void copy_highpage(struct page *to, struct page *from) } folio_set_hugetlb_mte_tagged(dst); } else if (page_mte_tagged(from)) { - /* It's a new page, shouldn't have been tagged yet */ - WARN_ON_ONCE(!try_page_mte_tagging(to)); + /* + * Most of the time it's a new page that shouldn't have been + * tagged yet. However, folio migration can end up reusing the + * same page without untagging it. Ignore the warning if the + * page is already tagged. + */ + try_page_mte_tagging(to); mte_copy_page_tags(kto, kfrom); set_page_mte_tagged(to); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d816ff44faff..125dfa6c613b 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -969,6 +969,16 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, void tag_clear_highpage(struct page *page) { + /* + * Check if MTE is supported and fall back to clear_highpage(). + * get_huge_zero_folio() unconditionally passes __GFP_ZEROTAGS and + * post_alloc_hook() will invoke tag_clear_highpage(). + */ + if (!system_supports_mte()) { + clear_highpage(page); + return; + } + /* Newly allocated page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b8d37eb037fc..2ba01dc8ef82 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -708,6 +708,30 @@ static int split_kernel_leaf_mapping_locked(unsigned long addr) return ret; } +static inline bool force_pte_mapping(void) +{ + const bool bbml2 = system_capabilities_finalized() ? + system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); + + if (debug_pagealloc_enabled()) + return true; + if (bbml2) + return false; + return rodata_full || arm64_kfence_can_set_direct_map() || is_realm_world(); +} + +static inline bool split_leaf_mapping_possible(void) +{ + /* + * !BBML2_NOABORT systems should never run into scenarios where we would + * have to split. So exit early and let calling code detect it and raise + * a warning. + */ + if (!system_supports_bbml2_noabort()) + return false; + return !force_pte_mapping(); +} + static DEFINE_MUTEX(pgtable_split_lock); int split_kernel_leaf_mapping(unsigned long start, unsigned long end) @@ -715,12 +739,11 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end) int ret; /* - * !BBML2_NOABORT systems should not be trying to change permissions on - * anything that is not pte-mapped in the first place. Just return early - * and let the permission change code raise a warning if not already - * pte-mapped. + * Exit early if the region is within a pte-mapped area or if we can't + * split. For the latter case, the permission change code will raise a + * warning if not already pte-mapped. */ - if (!system_supports_bbml2_noabort()) + if (!split_leaf_mapping_possible() || is_kfence_address((void *)start)) return 0; /* @@ -758,30 +781,30 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end) return ret; } -static int __init split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + gfp_t gfp = *(gfp_t *)walk->private; pud_t pud = pudp_get(pudp); int ret = 0; if (pud_leaf(pud)) - ret = split_pud(pudp, pud, GFP_ATOMIC, false); + ret = split_pud(pudp, pud, gfp, false); return ret; } -static int __init split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, + unsigned long next, struct mm_walk *walk) { + gfp_t gfp = *(gfp_t *)walk->private; pmd_t pmd = pmdp_get(pmdp); int ret = 0; if (pmd_leaf(pmd)) { if (pmd_cont(pmd)) split_contpmd(pmdp); - ret = split_pmd(pmdp, pmd, GFP_ATOMIC, false); + ret = split_pmd(pmdp, pmd, gfp, false); /* * We have split the pmd directly to ptes so there is no need to @@ -793,9 +816,8 @@ static int __init split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr, return ret; } -static int __init split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, - unsigned long next, - struct mm_walk *walk) +static int split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, + unsigned long next, struct mm_walk *walk) { pte_t pte = __ptep_get(ptep); @@ -805,12 +827,24 @@ static int __init split_to_ptes_pte_entry(pte_t *ptep, unsigned long addr, return 0; } -static const struct mm_walk_ops split_to_ptes_ops __initconst = { +static const struct mm_walk_ops split_to_ptes_ops = { .pud_entry = split_to_ptes_pud_entry, .pmd_entry = split_to_ptes_pmd_entry, .pte_entry = split_to_ptes_pte_entry, }; +static int range_split_to_ptes(unsigned long start, unsigned long end, gfp_t gfp) +{ + int ret; + + arch_enter_lazy_mmu_mode(); + ret = walk_kernel_page_table_range_lockless(start, end, + &split_to_ptes_ops, NULL, &gfp); + arch_leave_lazy_mmu_mode(); + + return ret; +} + static bool linear_map_requires_bbml2 __initdata; u32 idmap_kpti_bbml2_flag; @@ -847,11 +881,9 @@ static int __init linear_map_split_to_ptes(void *__unused) * PTE. The kernel alias remains static throughout runtime so * can continue to be safely mapped with large mappings. */ - ret = walk_kernel_page_table_range_lockless(lstart, kstart, - &split_to_ptes_ops, NULL, NULL); + ret = range_split_to_ptes(lstart, kstart, GFP_ATOMIC); if (!ret) - ret = walk_kernel_page_table_range_lockless(kend, lend, - &split_to_ptes_ops, NULL, NULL); + ret = range_split_to_ptes(kend, lend, GFP_ATOMIC); if (ret) panic("Failed to split linear map\n"); flush_tlb_kernel_range(lstart, lend); @@ -1002,6 +1034,33 @@ static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); __kfence_pool = phys_to_virt(kfence_pool); } + +bool arch_kfence_init_pool(void) +{ + unsigned long start = (unsigned long)__kfence_pool; + unsigned long end = start + KFENCE_POOL_SIZE; + int ret; + + /* Exit early if we know the linear map is already pte-mapped. */ + if (!split_leaf_mapping_possible()) + return true; + + /* Kfence pool is already pte-mapped for the early init case. */ + if (kfence_early_init) + return true; + + mutex_lock(&pgtable_split_lock); + ret = range_split_to_ptes(start, end, GFP_PGTABLE_KERNEL); + mutex_unlock(&pgtable_split_lock); + + /* + * Since the system supports bbml2_noabort, tlb invalidation is not + * required here; the pgtable mappings have been split to pte but larger + * entries may safely linger in the TLB. + */ + + return !ret; +} #else /* CONFIG_KFENCE */ static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; } @@ -1009,16 +1068,6 @@ static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { #endif /* CONFIG_KFENCE */ -static inline bool force_pte_mapping(void) -{ - bool bbml2 = system_capabilities_finalized() ? - system_supports_bbml2_noabort() : cpu_supports_bbml2_noabort(); - - return (!bbml2 && (rodata_full || arm64_kfence_can_set_direct_map() || - is_realm_world())) || - debug_pagealloc_enabled(); -} - static void __init map_mem(pgd_t *pgdp) { static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index ab83089c3d8f..0c9a50a1e73e 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1213,6 +1213,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, u8 src = bpf2a64[insn->src_reg]; const u8 tmp = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; + const u8 tmp3 = bpf2a64[TMP_REG_3]; const u8 fp = bpf2a64[BPF_REG_FP]; const u8 arena_vm_base = bpf2a64[ARENA_VM_START]; const u8 priv_sp = bpf2a64[PRIVATE_SP]; @@ -1757,8 +1758,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, case BPF_ST | BPF_PROBE_MEM32 | BPF_W: case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) { - emit(A64_ADD(1, tmp2, dst, arena_vm_base), ctx); - dst = tmp2; + emit(A64_ADD(1, tmp3, dst, arena_vm_base), ctx); + dst = tmp3; } if (dst == fp) { dst_adj = ctx->priv_sp_used ? priv_sp : A64_SP; diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c index 876028b1083f..064b0f0f95ca 100644 --- a/arch/csky/abiv2/cacheflush.c +++ b/arch/csky/abiv2/cacheflush.c @@ -21,7 +21,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, folio = page_folio(pfn_to_page(pfn)); - if (test_and_set_bit(PG_dcache_clean, &folio->flags)) + if (test_and_set_bit(PG_dcache_clean, &folio->flags.f)) return; icache_inv_range(address, address + nr*PAGE_SIZE); diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h index 6513ac5d2578..da51a0f02391 100644 --- a/arch/csky/abiv2/inc/abi/cacheflush.h +++ b/arch/csky/abiv2/inc/abi/cacheflush.h @@ -20,8 +20,8 @@ static inline void flush_dcache_folio(struct folio *folio) { - if (test_bit(PG_dcache_clean, &folio->flags)) - clear_bit(PG_dcache_clean, &folio->flags); + if (test_bit(PG_dcache_clean, &folio->flags.f)) + clear_bit(PG_dcache_clean, &folio->flags.f); } #define flush_dcache_folio flush_dcache_folio diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index dc5bd3f1b8d2..96ca1a688984 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -109,7 +109,7 @@ endif ifdef CONFIG_RUSTC_HAS_ANNOTATE_TABLEJUMP KBUILD_RUSTFLAGS += -Cllvm-args=--loongarch-annotate-tablejump else -KBUILD_RUSTFLAGS += -Zno-jump-tables # keep compatibility with older compilers +KBUILD_RUSTFLAGS += $(if $(call rustc-min-version,109300),-Cjump-tables=n,-Zno-jump-tables) # keep compatibility with older compilers endif ifdef CONFIG_LTO_CLANG # The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled. diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index fc83bb32f9f0..bd5f0457ad21 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -67,6 +67,8 @@ #define cpu_has_hypervisor cpu_opt(LOONGARCH_CPU_HYPERVISOR) #define cpu_has_ptw cpu_opt(LOONGARCH_CPU_PTW) #define cpu_has_lspw cpu_opt(LOONGARCH_CPU_LSPW) +#define cpu_has_msgint cpu_opt(LOONGARCH_CPU_MSGINT) #define cpu_has_avecint cpu_opt(LOONGARCH_CPU_AVECINT) +#define cpu_has_redirectint cpu_opt(LOONGARCH_CPU_REDIRECTINT) #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index dfb982fe8701..d4cd4041bee7 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -101,7 +101,9 @@ enum cpu_type_enum { #define CPU_FEATURE_HYPERVISOR 26 /* CPU has hypervisor (running in VM) */ #define CPU_FEATURE_PTW 27 /* CPU has hardware page table walker */ #define CPU_FEATURE_LSPW 28 /* CPU has LSPW (lddir/ldpte instructions) */ -#define CPU_FEATURE_AVECINT 29 /* CPU has AVEC interrupt */ +#define CPU_FEATURE_MSGINT 29 /* CPU has MSG interrupt */ +#define CPU_FEATURE_AVECINT 30 /* CPU has AVEC interrupt */ +#define CPU_FEATURE_REDIRECTINT 31 /* CPU has interrupt remapping */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) @@ -132,6 +134,8 @@ enum cpu_type_enum { #define LOONGARCH_CPU_HYPERVISOR BIT_ULL(CPU_FEATURE_HYPERVISOR) #define LOONGARCH_CPU_PTW BIT_ULL(CPU_FEATURE_PTW) #define LOONGARCH_CPU_LSPW BIT_ULL(CPU_FEATURE_LSPW) +#define LOONGARCH_CPU_MSGINT BIT_ULL(CPU_FEATURE_MSGINT) #define LOONGARCH_CPU_AVECINT BIT_ULL(CPU_FEATURE_AVECINT) +#define LOONGARCH_CPU_REDIRECTINT BIT_ULL(CPU_FEATURE_REDIRECTINT) #endif /* _ASM_CPU_H */ diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 13b2462f3d8c..5faa97a87a9e 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -134,13 +134,13 @@ static inline void hw_breakpoint_thread_switch(struct task_struct *next) /* Determine number of BRP registers available. */ static inline int get_num_brps(void) { - return csr_read64(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; + return csr_read32(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; } /* Determine number of WRP registers available. */ static inline int get_num_wrps(void) { - return csr_read64(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; + return csr_read32(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; } #endif /* __KERNEL__ */ diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index eaff72b38dc8..0130185e0349 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -14,7 +14,7 @@ #include #include -extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size); +extern void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size); extern void __init early_iounmap(void __iomem *addr, unsigned long size); #define early_memremap early_ioremap @@ -25,6 +25,9 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size); static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, pgprot_t prot) { + if (offset > TO_PHYS_MASK) + return NULL; + switch (pgprot_val(prot) & _CACHE_MASK) { case _CACHE_CC: return (void __iomem *)(unsigned long)(CACHE_BASE + offset); diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 09dfd7eb406e..3de03cb864b2 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -128,6 +128,7 @@ #define CPUCFG6_PMNUM GENMASK(7, 4) #define CPUCFG6_PMNUM_SHIFT 4 #define CPUCFG6_PMBITS GENMASK(13, 8) +#define CPUCFG6_PMBITS_SHIFT 8 #define CPUCFG6_UPM BIT(14) #define LOONGARCH_CPUCFG16 0x10 @@ -1137,6 +1138,7 @@ #define IOCSRF_FLATMODE BIT_ULL(10) #define IOCSRF_VM BIT_ULL(11) #define IOCSRF_AVEC BIT_ULL(15) +#define IOCSRF_REDIRECT BIT_ULL(16) #define LOONGARCH_IOCSR_VENDOR 0x10 diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index 1c63a9d9a6d3..08dcc698ec18 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -88,7 +88,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (!ptdesc) return NULL; diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index bd128696e96d..03fb60432fde 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -424,6 +424,9 @@ static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) |= _PAGE_MODIFIED; + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | (pgprot_val(newprot) & ~_PAGE_CHG_MASK)); } @@ -547,9 +550,11 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _HPAGE_CHG_MASK) | - (pgprot_val(newprot) & ~_HPAGE_CHG_MASK); - return pmd; + if (pmd_val(pmd) & _PAGE_DIRTY) + pmd_val(pmd) |= _PAGE_MODIFIED; + + return __pmd((pmd_val(pmd) & _HPAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_HPAGE_CHG_MASK)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index cbfce2872d71..6f943d1391ff 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -157,6 +157,8 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options |= LOONGARCH_CPU_TLB; if (config & CPUCFG1_IOCSR) c->options |= LOONGARCH_CPU_IOCSR; + if (config & CPUCFG1_MSGINT) + c->options |= LOONGARCH_CPU_MSGINT; if (config & CPUCFG1_UAL) { c->options |= LOONGARCH_CPU_UAL; elf_hwcap |= HWCAP_LOONGARCH_UAL; @@ -331,6 +333,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int c->options |= LOONGARCH_CPU_EIODECODE; if (config & IOCSRF_AVEC) c->options |= LOONGARCH_CPU_AVECINT; + if (config & IOCSRF_REDIRECT) + c->options |= LOONGARCH_CPU_REDIRECTINT; if (config & IOCSRF_VM) c->options |= LOONGARCH_CPU_HYPERVISOR; } diff --git a/arch/loongarch/kernel/kexec_efi.c b/arch/loongarch/kernel/kexec_efi.c index 45121b914f8f..5ee78ebb1546 100644 --- a/arch/loongarch/kernel/kexec_efi.c +++ b/arch/loongarch/kernel/kexec_efi.c @@ -42,7 +42,7 @@ static void *efi_kexec_load(struct kimage *image, { int ret; unsigned long text_offset, kernel_segment_number; - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; struct kexec_segment *kernel_segment; struct loongarch_image_header *h; diff --git a/arch/loongarch/kernel/kexec_elf.c b/arch/loongarch/kernel/kexec_elf.c index 97b2f049801a..1b6b64744c7f 100644 --- a/arch/loongarch/kernel/kexec_elf.c +++ b/arch/loongarch/kernel/kexec_elf.c @@ -59,7 +59,7 @@ static void *elf_kexec_load(struct kimage *image, int ret; unsigned long text_offset, kernel_segment_number; struct elfhdr ehdr; - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; struct kexec_elf_info elf_info; struct kexec_segment *kernel_segment; diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c index e4b2bbc47e62..2d64b7c81e5e 100644 --- a/arch/loongarch/kernel/machine_kexec.c +++ b/arch/loongarch/kernel/machine_kexec.c @@ -39,34 +39,12 @@ static unsigned long systable_ptr; static unsigned long start_addr; static unsigned long first_ind_entry; -static void kexec_image_info(const struct kimage *kimage) -{ - unsigned long i; - - pr_debug("kexec kimage info:\n"); - pr_debug("\ttype: %d\n", kimage->type); - pr_debug("\tstart: %lx\n", kimage->start); - pr_debug("\thead: %lx\n", kimage->head); - pr_debug("\tnr_segments: %lu\n", kimage->nr_segments); - - for (i = 0; i < kimage->nr_segments; i++) { - pr_debug("\t segment[%lu]: %016lx - %016lx", i, - kimage->segment[i].mem, - kimage->segment[i].mem + kimage->segment[i].memsz); - pr_debug("\t\t0x%lx bytes, %lu pages\n", - (unsigned long)kimage->segment[i].memsz, - (unsigned long)kimage->segment[i].memsz / PAGE_SIZE); - } -} - int machine_kexec_prepare(struct kimage *kimage) { int i; char *bootloader = "kexec"; void *cmdline_ptr = (void *)KEXEC_CMDLINE_ADDR; - kexec_image_info(kimage); - kimage->arch.efi_boot = fw_arg0; kimage->arch.systable_ptr = fw_arg2; diff --git a/arch/loongarch/kernel/machine_kexec_file.c b/arch/loongarch/kernel/machine_kexec_file.c index dda236b51a88..fb57026f5f25 100644 --- a/arch/loongarch/kernel/machine_kexec_file.c +++ b/arch/loongarch/kernel/machine_kexec_file.c @@ -143,7 +143,7 @@ int load_other_segments(struct kimage *image, unsigned long initrd_load_addr = 0; unsigned long orig_segments = image->nr_segments; char *modified_cmdline = NULL; - struct kexec_buf kbuf; + struct kexec_buf kbuf = {}; kbuf.image = image; /* Don't allocate anything below the kernel */ diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c index aed901c57fb4..8ab1ffedc52c 100644 --- a/arch/loongarch/kernel/mem.c +++ b/arch/loongarch/kernel/mem.c @@ -13,7 +13,7 @@ void __init memblock_init(void) { u32 mem_type; - u64 mem_start, mem_end, mem_size; + u64 mem_start, mem_size; efi_memory_desc_t *md; /* Parse memory information */ @@ -21,7 +21,6 @@ void __init memblock_init(void) mem_type = md->type; mem_start = md->phys_addr; mem_size = md->num_pages << EFI_PAGE_SHIFT; - mem_end = mem_start + mem_size; switch (mem_type) { case EFI_LOADER_CODE: @@ -31,8 +30,6 @@ void __init memblock_init(void) case EFI_PERSISTENT_MEMORY: case EFI_CONVENTIONAL_MEMORY: memblock_add(mem_start, mem_size); - if (max_low_pfn < (mem_end >> PAGE_SHIFT)) - max_low_pfn = mem_end >> PAGE_SHIFT; break; case EFI_PAL_CODE: case EFI_UNUSABLE_MEMORY: @@ -49,6 +46,8 @@ void __init memblock_init(void) } } + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); memblock_set_current_limit(PFN_PHYS(max_low_pfn)); /* Reserve the first 2MB */ diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index d6e73e8f9c0b..ab9c660526a3 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -272,7 +272,8 @@ int __init init_numa_memory(void) node_mem_init(node); node_set_online(node); } - max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); setup_nr_node_ids(); loongson_sysconf.nr_nodes = nr_node_ids; @@ -283,26 +284,6 @@ int __init init_numa_memory(void) #endif -void __init paging_init(void) -{ - unsigned int node; - unsigned long zones_size[MAX_NR_ZONES] = {0, }; - - for_each_online_node(node) { - unsigned long start_pfn, end_pfn; - - get_pfn_range_for_nid(node, &start_pfn, &end_pfn); - - if (end_pfn > max_low_pfn) - max_low_pfn = end_pfn; - } -#ifdef CONFIG_ZONE_DMA32 - zones_size[ZONE_DMA32] = MAX_DMA32_PFN; -#endif - zones_size[ZONE_NORMAL] = max_low_pfn; - free_area_init(zones_size); -} - int pcibus_to_node(struct pci_bus *bus) { return dev_to_node(&bus->dev); diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 8ad098703488..9d257c8519c9 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -845,13 +845,14 @@ static const struct loongarch_perf_event *loongarch_pmu_map_raw_event(u64 config static int __init init_hw_perf_events(void) { - int counters; + int bits, counters; if (!cpu_has_pmp) return -ENODEV; pr_info("Performance counters: "); - counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> 4) + 1; + bits = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMBITS) >> CPUCFG6_PMBITS_SHIFT) + 1; + counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> CPUCFG6_PMNUM_SHIFT) + 1; loongarch_pmu.num_counters = counters; loongarch_pmu.max_period = (1ULL << 63) - 1; @@ -867,7 +868,7 @@ static int __init init_hw_perf_events(void) on_each_cpu(reset_counters, NULL, 1); pr_cont("%s PMU enabled, %d %d-bit counters available to each CPU.\n", - loongarch_pmu.name, counters, 64); + loongarch_pmu.name, counters, bits); perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 69c17d162fff..25a87378e48e 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -294,8 +294,6 @@ static void __init fdt_setup(void) early_init_dt_scan(fdt_pointer, __pa(fdt_pointer)); early_init_fdt_reserve_self(); - - max_low_pfn = PFN_PHYS(memblock_end_of_DRAM()); #endif } @@ -390,7 +388,8 @@ static void __init check_kernel_sections_mem(void) static void __init arch_mem_init(char **cmdline_p) { /* Recalculate max_low_pfn for "mem=xxx" */ - max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = min(PFN_DOWN(HIGHMEM_START), max_pfn); if (usermem) pr_info("User-defined physical RAM map overwrite\n"); diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 3d9be6ca7ec5..da5926fead4a 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -1131,8 +1131,8 @@ static void configure_exception_vector(void) tlbrentry = (unsigned long)exception_handlers + 80*VECSIZE; csr_write64(eentry, LOONGARCH_CSR_EENTRY); - csr_write64(eentry, LOONGARCH_CSR_MERRENTRY); - csr_write64(tlbrentry, LOONGARCH_CSR_TLBRENTRY); + csr_write64(__pa(eentry), LOONGARCH_CSR_MERRENTRY); + csr_write64(__pa(tlbrentry), LOONGARCH_CSR_TLBRENTRY); } void per_cpu_trap_init(int cpu) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index c32333695381..a1cc116b4dac 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -439,7 +439,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, spin_lock_irqsave(&s->lock, flags); switch (type) { case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: - if (val >= EIOINTC_ROUTE_MAX_VCPUS) + if (val > EIOINTC_ROUTE_MAX_VCPUS) ret = -EINVAL; else s->num_cpu = val; diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c index 7c8143e79c12..a7fa458e3360 100644 --- a/arch/loongarch/kvm/mmu.c +++ b/arch/loongarch/kvm/mmu.c @@ -857,7 +857,7 @@ static int kvm_map_page(struct kvm_vcpu *vcpu, unsigned long gpa, bool write) if (writeable) { prot_bits = kvm_pte_mkwriteable(prot_bits); - if (write) + if (write || !kvm_slot_dirty_track_enabled(memslot)) prot_bits = kvm_pte_mkdirty(prot_bits); } diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c index 32dc213374be..29c2aaba63c3 100644 --- a/arch/loongarch/kvm/timer.c +++ b/arch/loongarch/kvm/timer.c @@ -4,6 +4,7 @@ */ #include +#include #include #include @@ -95,6 +96,7 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu) * and set CSR TVAL with -1 */ write_gcsr_timertick(0); + __delay(2); /* Wait cycles until timer interrupt injected */ /* * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index 30e3b089a596..1245a6b35896 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -132,6 +132,9 @@ static void kvm_lose_pmu(struct kvm_vcpu *vcpu) * Clear KVM_LARCH_PMU if the guest is not using PMU CSRs when * exiting the guest, so that the next time trap into the guest. * We don't need to deal with PMU CSRs contexts. + * + * Otherwise set the request bit KVM_REQ_PMU to restore guest PMU + * before entering guest VM */ val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0); val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1); @@ -139,16 +142,12 @@ static void kvm_lose_pmu(struct kvm_vcpu *vcpu) val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); if (!(val & KVM_PMU_EVENT_ENABLED)) vcpu->arch.aux_inuse &= ~KVM_LARCH_PMU; + else + kvm_make_request(KVM_REQ_PMU, vcpu); kvm_restore_host_pmu(vcpu); } -static void kvm_restore_pmu(struct kvm_vcpu *vcpu) -{ - if ((vcpu->arch.aux_inuse & KVM_LARCH_PMU)) - kvm_make_request(KVM_REQ_PMU, vcpu); -} - static void kvm_check_pmu(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_PMU, vcpu)) { @@ -299,7 +298,10 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST; if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) { - kvm_lose_pmu(vcpu); + if (vcpu->arch.aux_inuse & KVM_LARCH_PMU) { + kvm_lose_pmu(vcpu); + kvm_make_request(KVM_REQ_PMU, vcpu); + } /* make sure the vcpu mode has been written */ smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE); local_irq_enable(); @@ -1604,9 +1606,6 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_restore_timer(vcpu); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); - /* Restore hardware PMU CSRs */ - kvm_restore_pmu(vcpu); - /* Don't bother restoring registers multiple times unless necessary */ if (vcpu->arch.aux_inuse & KVM_LARCH_HWCSR_USABLE) return 0; diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index c3e4586a7975..6bfd4b8dad1b 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -60,7 +60,6 @@ int __ref page_is_ram(unsigned long pfn) return memblock_is_memory(addr) && !memblock_is_reserved(addr); } -#ifndef CONFIG_NUMA void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -72,7 +71,6 @@ void __init paging_init(void) free_area_init(max_zone_pfns); } -#endif /* !CONFIG_NUMA */ void __ref free_initmem(void) { diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c index df949a3d0f34..27c336959fe8 100644 --- a/arch/loongarch/mm/ioremap.c +++ b/arch/loongarch/mm/ioremap.c @@ -6,7 +6,7 @@ #include #include -void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size) +void __init __iomem *early_ioremap(phys_addr_t phys_addr, unsigned long size) { return ((void __iomem *)TO_CACHE(phys_addr)); } diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index 3a2836e9d856..816570514c37 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -47,7 +47,7 @@ static struct resource standard_io_resources[] = { .name = "keyboard", .start = 0x60, .end = 0x6f, - .flags = IORESOURCE_IO | IORESOURCE_BUSY + .flags = IORESOURCE_IO }, { .name = "dma page reg", @@ -213,7 +213,7 @@ void __init plat_mem_setup(void) /* Request I/O space for devices used on the Malta board. */ for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++) - request_resource(&ioport_resource, standard_io_resources+i); + insert_resource(&ioport_resource, standard_io_resources + i); /* * Enable DMA channel 4 (cascade channel) in the PIIX4 south bridge. diff --git a/arch/mips/pci/pci-malta.c b/arch/mips/pci/pci-malta.c index 6aefdf20ca05..2e35aeba45bc 100644 --- a/arch/mips/pci/pci-malta.c +++ b/arch/mips/pci/pci-malta.c @@ -230,8 +230,7 @@ void __init mips_pcibios_init(void) } /* PIIX4 ACPI starts at 0x1000 */ - if (controller->io_resource->start < 0x00001000UL) - controller->io_resource->start = 0x00001000UL; + PCIBIOS_MIN_IO = 0x1000; iomem_resource.end &= 0xfffffffffULL; /* 64 GB */ ioport_resource.end = controller->io_resource->end; diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index f7e0fee5ee55..7ac88ff13d3c 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -35,6 +35,8 @@ #define KERNEL_START (KERNEL_BINARY_TEXT_START) +#define ALIGNMENT_OK(ptr, type) (((ptr) & (sizeof(type) - 1)) == 0) + extern struct unwind_table_entry __start___unwind[]; extern struct unwind_table_entry __stop___unwind[]; @@ -257,12 +259,15 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int if (pc_is_kernel_fn(pc, _switch_to) || pc == (unsigned long)&_switch_to_ret) { info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE; - info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); + if (ALIGNMENT_OK(info->prev_sp, long)) + info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET); + else + info->prev_ip = info->prev_sp = 0; return 1; } #ifdef CONFIG_IRQSTACKS - if (pc == (unsigned long)&_call_on_stack) { + if (pc == (unsigned long)&_call_on_stack && ALIGNMENT_OK(info->sp, long)) { info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ); info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET); return 1; @@ -370,8 +375,10 @@ static void unwind_frame_regs(struct unwind_frame_info *info) info->prev_sp = info->sp - frame_size; if (e->Millicode) info->rp = info->r31; - else if (rpoffset) + else if (rpoffset && ALIGNMENT_OK(info->prev_sp, long)) info->rp = *(unsigned long *)(info->prev_sp - rpoffset); + else + info->rp = 0; info->prev_ip = info->rp; info->rp = 0; } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e24f4d88885a..9537a61ebae0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -137,6 +137,7 @@ config PPC select ARCH_HAS_DMA_OPS if PPC64 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE if ARCH_SUPPORTS_HUGETLBFS select ARCH_HAS_KCOV select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC64 && PPC_FPU select ARCH_HAS_MEMBARRIER_CALLBACKS diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 7b527d18aa5e..4c321a8ea896 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -423,7 +423,6 @@ config PPC_64S_HASH_MMU config PPC_RADIX_MMU bool "Radix MMU Support" depends on PPC_BOOK3S_64 - select ARCH_HAS_GIGANTIC_PAGE default y help Enable support for the Power ISA 3.0 Radix style MMU. Currently this diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 22cda9c452d2..fadec20b87a8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -367,7 +367,7 @@ config RISCV_NONSTANDARD_CACHE_OPS systems to handle cache management. config AS_HAS_INSN - def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero) + def_bool $(as-instr,.insn 0x100000f) config AS_HAS_OPTION_ARCH # https://github.com/llvm/llvm-project/commit/9e8ed3403c191ab9c4903e8eeb8f732ff8a43cb4 diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index ecf2fcce2d92..4c6de57f65ef 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -134,21 +134,6 @@ endif CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS) # Default target when executing plain make -boot := arch/riscv/boot -ifeq ($(CONFIG_XIP_KERNEL),y) -KBUILD_IMAGE := $(boot)/xipImage -else -ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN_K210),yy) -KBUILD_IMAGE := $(boot)/loader.bin -else -ifeq ($(CONFIG_EFI_ZBOOT),) -KBUILD_IMAGE := $(boot)/Image.gz -else -KBUILD_IMAGE := $(boot)/vmlinuz.efi -endif -endif -endif - boot := arch/riscv/boot boot-image-y := Image boot-image-$(CONFIG_KERNEL_BZIP2) := Image.bz2 @@ -159,7 +144,7 @@ boot-image-$(CONFIG_KERNEL_LZO) := Image.lzo boot-image-$(CONFIG_KERNEL_ZSTD) := Image.zst boot-image-$(CONFIG_KERNEL_XZ) := Image.xz ifdef CONFIG_RISCV_M_MODE -boot-image-$(CONFIG_ARCH_CANAAN) := loader.bin +boot-image-$(CONFIG_SOC_CANAAN_K210) := loader.bin endif boot-image-$(CONFIG_EFI_ZBOOT) := vmlinuz.efi boot-image-$(CONFIG_XIP_KERNEL) := xipImage diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 8bd2a11382a3..e9e8ba83e632 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -12,6 +12,12 @@ #define __ASM_STR(x) #x #endif +#ifdef CONFIG_AS_HAS_INSN +#define ASM_INSN_I(__x) ".insn " __x +#else +#define ASM_INSN_I(__x) ".4byte " __x +#endif + #if __riscv_xlen == 64 #define __REG_SEL(a, b) __ASM_STR(a) #elif __riscv_xlen == 32 @@ -84,15 +90,9 @@ .endm #ifdef CONFIG_SMP -#ifdef CONFIG_32BIT -#define PER_CPU_OFFSET_SHIFT 2 -#else -#define PER_CPU_OFFSET_SHIFT 3 -#endif - .macro asm_per_cpu dst sym tmp lw \tmp, TASK_TI_CPU_NUM(tp) - slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT + slli \tmp, \tmp, RISCV_LGPTR la \dst, __per_cpu_offset add \dst, \dst, \tmp REG_L \tmp, 0(\dst) diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index fbd0e4306c93..62837fa981e8 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -31,6 +31,8 @@ struct riscv_isainfo { DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); +extern const struct seq_operations cpuinfo_op; + /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 948d2b34e94e..58f8dda73259 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -42,4 +42,11 @@ static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair, return pair->value == other_pair->value; } +#ifdef CONFIG_MMU +void riscv_hwprobe_register_async_probe(void); +void riscv_hwprobe_complete_async_probe(void); +#else +static inline void riscv_hwprobe_register_async_probe(void) {} +static inline void riscv_hwprobe_complete_async_probe(void) {} +#endif #endif diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index c9cfcea52cbb..d29da6ccd3dd 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -256,10 +256,10 @@ INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3), \ SIMM12((offset) & 0xfe0), RS1(base)) -#define RISCV_PAUSE ".4byte 0x100000f" -#define ZAWRS_WRS_NTO ".4byte 0x00d00073" -#define ZAWRS_WRS_STO ".4byte 0x01d00073" -#define RISCV_NOP4 ".4byte 0x00000013" +#define RISCV_PAUSE ASM_INSN_I("0x100000f") +#define ZAWRS_WRS_NTO ASM_INSN_I("0x00d00073") +#define ZAWRS_WRS_STO ASM_INSN_I("0x01d00073") +#define RISCV_NOP4 ASM_INSN_I("0x00000013") #define RISCV_INSN_NOP4 _AC(0x00000013, U) diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 1018d2216901..6e789fa58514 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -69,6 +69,8 @@ typedef struct { #define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t)) +#define MAX_POSSIBLE_PHYSMEM_BITS 56 + /* * rv64 PTE format: * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 29e994a9afb6..5a08eb5fe99f 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -654,6 +654,8 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot) return __pgprot(prot); } +#define pgprot_dmacoherent pgprot_writecombine + /* * Both Svade and Svadu control the hardware behavior when the PTE A/D bits need to be set. By * default the M-mode firmware enables the hardware updating scheme when only Svadu is present in diff --git a/arch/riscv/include/asm/vdso/arch_data.h b/arch/riscv/include/asm/vdso/arch_data.h index da57a3786f7a..88b37af55175 100644 --- a/arch/riscv/include/asm/vdso/arch_data.h +++ b/arch/riscv/include/asm/vdso/arch_data.h @@ -12,6 +12,12 @@ struct vdso_arch_data { /* Boolean indicating all CPUs have the same static hwprobe values. */ __u8 homogeneous_cpus; + + /* + * A gate to check and see if the hwprobe data is actually ready, as + * probing is deferred to avoid boot slowdowns. + */ + __u8 ready; }; #endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */ diff --git a/arch/riscv/include/asm/vendor_extensions/mips.h b/arch/riscv/include/asm/vendor_extensions/mips.h index ea8ca747d691..ffeb12dc17a3 100644 --- a/arch/riscv/include/asm/vendor_extensions/mips.h +++ b/arch/riscv/include/asm/vendor_extensions/mips.h @@ -30,8 +30,8 @@ extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_mips; * allowing any subsequent instructions to fetch. */ -#define MIPS_PAUSE ".4byte 0x00501013\n\t" -#define MIPS_EHB ".4byte 0x00301013\n\t" -#define MIPS_IHB ".4byte 0x00101013\n\t" +#define MIPS_PAUSE ASM_INSN_I("0x00501013\n\t") +#define MIPS_EHB ASM_INSN_I("0x00301013\n\t") +#define MIPS_IHB ASM_INSN_I("0x00101013\n\t") #endif // _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_H diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index f6b13e9f5e6c..3dbc8cc557dd 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -62,10 +62,8 @@ int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned lo return -ENODEV; } - if (!of_device_is_available(node)) { - pr_info("CPU with hartid=%lu is not available\n", *hart); + if (!of_device_is_available(node)) return -ENODEV; - } if (of_property_read_string(node, "riscv,isa-base", &isa)) goto old_interface; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 67b59699357d..72ca768f4e91 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -932,9 +932,9 @@ static int has_thead_homogeneous_vlenb(void) { int cpu; u32 prev_vlenb = 0; - u32 vlenb; + u32 vlenb = 0; - /* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */ + /* Ignore thead,vlenb property if xtheadvector is not enabled in the kernel */ if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) return 0; diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index 9f3db3503dab..15fec5d1e6de 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -265,10 +265,10 @@ void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, { if (!strncmp(remcom_in_buffer, gdb_xfer_read_target, sizeof(gdb_xfer_read_target))) - strcpy(remcom_out_buffer, riscv_gdb_stub_target_desc); + strscpy(remcom_out_buffer, riscv_gdb_stub_target_desc, BUFMAX); else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml, sizeof(gdb_xfer_read_cpuxml))) - strcpy(remcom_out_buffer, riscv_gdb_stub_cpuxml); + strscpy(remcom_out_buffer, riscv_gdb_stub_cpuxml, BUFMAX); } static inline void kgdb_arch_update_addr(struct pt_regs *regs, diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index 75551ac6504c..1675cbad8619 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -119,6 +119,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned int num_plts = 0; unsigned int num_gots = 0; Elf_Rela *scratch = NULL; + Elf_Rela *new_scratch; size_t scratch_size = 0; int i; @@ -168,9 +169,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, scratch_size_needed = (num_scratch_relas + num_relas) * sizeof(*scratch); if (scratch_size_needed > scratch_size) { scratch_size = scratch_size_needed; - scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); - if (!scratch) + new_scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); + if (!new_scratch) { + kvfree(scratch); return -ENOMEM; + } + scratch = new_scratch; } for (size_t j = 0; j < num_relas; j++) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index e650dec44817..5ed5095320e6 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -40,6 +40,17 @@ enum ipi_message_type { IPI_MAX }; +static const char * const ipi_names[] = { + [IPI_RESCHEDULE] = "Rescheduling interrupts", + [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", + [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", + [IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts", +}; + unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = INVALID_HARTID }; @@ -199,7 +210,7 @@ void riscv_ipi_set_virq_range(int virq, int nr) /* Request IPIs */ for (i = 0; i < nr_ipi; i++) { err = request_percpu_irq(ipi_virq_base + i, handle_IPI, - "IPI", &ipi_dummy_dev); + ipi_names[i], &ipi_dummy_dev); WARN_ON(err); ipi_desc[i] = irq_to_desc(ipi_virq_base + i); @@ -210,17 +221,6 @@ void riscv_ipi_set_virq_range(int virq, int nr) riscv_ipi_enable(); } -static const char * const ipi_names[] = { - [IPI_RESCHEDULE] = "Rescheduling interrupts", - [IPI_CALL_FUNC] = "Function call interrupts", - [IPI_CPU_STOP] = "CPU stop interrupts", - [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", - [IPI_IRQ_WORK] = "IRQ work interrupts", - [IPI_TIMER] = "Timer broadcast interrupts", - [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", - [IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts", -}; - void show_ipi_stats(struct seq_file *p, int prec) { unsigned int cpu, i; diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 3fe9e6edef8f..b41b6255751c 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -16,6 +16,22 @@ #ifdef CONFIG_FRAME_POINTER +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + unsigned long addr = x; \ + if ((task) == current) \ + val = READ_ONCE(addr); \ + else \ + val = READ_ONCE_NOCHECK(addr); \ + val; \ +}) + extern asmlinkage void handle_exception(void); extern unsigned long ret_from_exception_end; @@ -69,8 +85,9 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->ra; pc = regs->ra; } else { - fp = frame->fp; - pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, + fp = READ_ONCE_TASK_STACK(task, frame->fp); + pc = READ_ONCE_TASK_STACK(task, frame->ra); + pc = ftrace_graph_ret_addr(current, &graph_idx, pc, &frame->ra); if (pc >= (unsigned long)handle_exception && pc < (unsigned long)&ret_from_exception_end) { diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 000f4451a9d8..199d13f86f31 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -5,6 +5,9 @@ * more details. */ #include +#include +#include +#include #include #include #include @@ -28,6 +31,11 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, bool first = true; int cpu; + if (pair->key != RISCV_HWPROBE_KEY_MVENDORID && + pair->key != RISCV_HWPROBE_KEY_MIMPID && + pair->key != RISCV_HWPROBE_KEY_MARCHID) + goto out; + for_each_cpu(cpu, cpus) { u64 cpu_id; @@ -58,6 +66,7 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, } } +out: pair->value = id; } @@ -454,28 +463,32 @@ static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs, return 0; } -static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, - size_t pair_count, size_t cpusetsize, - unsigned long __user *cpus_user, - unsigned int flags) -{ - if (flags & RISCV_HWPROBE_WHICH_CPUS) - return hwprobe_get_cpus(pairs, pair_count, cpusetsize, - cpus_user, flags); - - return hwprobe_get_values(pairs, pair_count, cpusetsize, - cpus_user, flags); -} - #ifdef CONFIG_MMU -static int __init init_hwprobe_vdso_data(void) +static DECLARE_COMPLETION(boot_probes_done); +static atomic_t pending_boot_probes = ATOMIC_INIT(1); + +void riscv_hwprobe_register_async_probe(void) +{ + atomic_inc(&pending_boot_probes); +} + +void riscv_hwprobe_complete_async_probe(void) +{ + if (atomic_dec_and_test(&pending_boot_probes)) + complete(&boot_probes_done); +} + +static int complete_hwprobe_vdso_data(void) { struct vdso_arch_data *avd = vdso_k_arch_data; u64 id_bitsmash = 0; struct riscv_hwprobe pair; int key; + if (unlikely(!atomic_dec_and_test(&pending_boot_probes))) + wait_for_completion(&boot_probes_done); + /* * Initialize vDSO data with the answers for the "all CPUs" case, to * save a syscall in the common case. @@ -503,13 +516,52 @@ static int __init init_hwprobe_vdso_data(void) * vDSO should defer to the kernel for exotic cpu masks. */ avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1; + + /* + * Make sure all the VDSO values are visible before we look at them. + * This pairs with the implicit "no speculativly visible accesses" + * barrier in the VDSO hwprobe code. + */ + smp_wmb(); + avd->ready = true; + return 0; +} + +static int __init init_hwprobe_vdso_data(void) +{ + struct vdso_arch_data *avd = vdso_k_arch_data; + + /* + * Prevent the vDSO cached values from being used, as they're not ready + * yet. + */ + avd->ready = false; return 0; } arch_initcall_sync(init_hwprobe_vdso_data); +#else + +static int complete_hwprobe_vdso_data(void) { return 0; } + #endif /* CONFIG_MMU */ +static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + DO_ONCE_SLEEPABLE(complete_hwprobe_vdso_data); + + if (flags & RISCV_HWPROBE_WHICH_CPUS) + return hwprobe_get_cpus(pairs, pair_count, cpusetsize, + cpus_user, flags); + + return hwprobe_get_values(pairs, pair_count, cpusetsize, + cpus_user, flags); +} + SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, size_t, pair_count, size_t, cpusetsize, unsigned long __user *, cpus, unsigned int, flags) diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug index 5db4df44279e..40f8dafffa0a 100644 --- a/arch/riscv/kernel/tests/Kconfig.debug +++ b/arch/riscv/kernel/tests/Kconfig.debug @@ -31,7 +31,7 @@ config RISCV_MODULE_LINKING_KUNIT If unsure, say N. config RISCV_KPROBES_KUNIT - bool "KUnit test for riscv kprobes" if !KUNIT_ALL_TESTS + tristate "KUnit test for riscv kprobes" if !KUNIT_ALL_TESTS depends on KUNIT depends on KPROBES default KUNIT_ALL_TESTS diff --git a/arch/riscv/kernel/tests/kprobes/Makefile b/arch/riscv/kernel/tests/kprobes/Makefile index 4cb6c66a98e8..df7256f62313 100644 --- a/arch/riscv/kernel/tests/kprobes/Makefile +++ b/arch/riscv/kernel/tests/kprobes/Makefile @@ -1 +1,3 @@ -obj-y += test-kprobes.o test-kprobes-asm.o +obj-$(CONFIG_RISCV_KPROBES_KUNIT) += kprobes_riscv_kunit.o + +kprobes_riscv_kunit-objs := test-kprobes.o test-kprobes-asm.o diff --git a/arch/riscv/kernel/tests/kprobes/test-kprobes.c b/arch/riscv/kernel/tests/kprobes/test-kprobes.c index 6f6cdfbf5a95..664535ca0a98 100644 --- a/arch/riscv/kernel/tests/kprobes/test-kprobes.c +++ b/arch/riscv/kernel/tests/kprobes/test-kprobes.c @@ -49,8 +49,11 @@ static struct kunit_case kprobes_testcases[] = { }; static struct kunit_suite kprobes_test_suite = { - .name = "kprobes_test_riscv", + .name = "kprobes_riscv", .test_cases = kprobes_testcases, }; kunit_test_suites(&kprobes_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit test for riscv kprobes"); diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index ae2068425fbc..70b5e6927620 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -379,6 +379,7 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) { schedule_on_each_cpu(check_vector_unaligned_access); + riscv_hwprobe_complete_async_probe(); return 0; } @@ -473,8 +474,12 @@ static int __init check_unaligned_access_all_cpus(void) per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; } else if (!check_vector_unaligned_access_emulated_all_cpus() && IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { - kthread_run(vec_check_unaligned_access_speed_all_cpus, - NULL, "vec_check_unaligned_access_speed_all_cpus"); + riscv_hwprobe_register_async_probe(); + if (IS_ERR(kthread_run(vec_check_unaligned_access_speed_all_cpus, + NULL, "vec_check_unaligned_access_speed_all_cpus"))) { + pr_warn("Failed to create vec_unalign_check kthread\n"); + riscv_hwprobe_complete_async_probe(); + } } /* diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index 2ddeba6c68dd..8f45500d0a6e 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -27,7 +27,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count, * homogeneous, then this function can handle requests for arbitrary * masks. */ - if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus)) + if (flags != 0 || (!all_cpus && !avd->homogeneous_cpus) || unlikely(!avd->ready)) return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags); /* This is something we can handle, fill out the pairs. */ diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index fda0346f0ea1..11422cb95a64 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -689,8 +689,20 @@ bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu) */ read_lock_irqsave(&imsic->vsfile_lock, flags); - if (imsic->vsfile_cpu > -1) - ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + if (imsic->vsfile_cpu > -1) { + /* + * This function is typically called from kvm_vcpu_block() via + * kvm_arch_vcpu_runnable() upon WFI trap. The kvm_vcpu_block() + * can be preempted and the blocking VCPU might resume on a + * different CPU. This means it is possible that current CPU + * does not match the imsic->vsfile_cpu hence this function + * must check imsic->vsfile_cpu before accessing HGEIP CSR. + */ + if (imsic->vsfile_cpu != vcpu->cpu) + ret = true; + else + ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + } read_unlock_irqrestore(&imsic->vsfile_lock, flags); return ret; diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 525fb5a330c0..58f5f3536ffd 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -171,7 +171,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change) { hva_t hva, reg_end, size; - gpa_t base_gpa; bool writable; int ret = 0; @@ -190,15 +189,13 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, hva = new->userspace_addr; size = new->npages << PAGE_SHIFT; reg_end = hva + size; - base_gpa = new->base_gfn << PAGE_SHIFT; writable = !(new->flags & KVM_MEM_READONLY); mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and - * any holes between them, so iterate over all of them to find - * out if we can map any of them right now. + * any holes between them, so iterate over all of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ @@ -209,7 +206,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, */ do { struct vm_area_struct *vma; - hva_t vm_start, vm_end; + hva_t vm_end; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) @@ -225,36 +222,18 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } /* Take the intersection of this VMA with the memory region */ - vm_start = max(hva, vma->vm_start); vm_end = min(reg_end, vma->vm_end); if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = base_gpa + (vm_start - hva); - phys_addr_t pa; - - pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; - pa += vm_start - vma->vm_start; - /* IO region dirty page logging not allowed */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } - - ret = kvm_riscv_mmu_ioremap(kvm, gpa, pa, vm_end - vm_start, - writable, false); - if (ret) - break; } hva = vm_end; } while (hva < reg_end); - if (change == KVM_MR_FLAGS_ONLY) - goto out; - - if (ret) - kvm_riscv_mmu_iounmap(kvm, base_gpa, size); - out: mmap_read_unlock(current->mm); return ret; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index bccb919ca615..5ce35aba6069 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -212,7 +212,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) && + return (kvm_riscv_vcpu_has_interrupts(vcpu, -1ULL) && !kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause); } diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 3b51690cc876..34299c2b231f 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -21,7 +21,7 @@ #define pt_dump_seq_puts(m, fmt) \ ({ \ if (m) \ - seq_printf(m, fmt); \ + seq_puts(m, fmt); \ }) /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c4145672ca34..df22b10d9141 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -158,7 +158,6 @@ config S390 select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WANT_KERNEL_PMD_MKWRITE select ARCH_WANT_LD_ORPHAN_WARN - select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_THP_SWAP select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index b31c1df90257..8433f769f7e1 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -101,6 +101,7 @@ CONFIG_SLUB_STATS=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y +CONFIG_PERSISTENT_HUGE_ZERO_FOLIO=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA_DEBUGFS=y CONFIG_CMA_SYSFS=y @@ -123,12 +124,12 @@ CONFIG_TLS_DEVICE=y CONFIG_TLS_TOE=y CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_XDP_SOCKETS=y -CONFIG_XDP_SOCKETS_DIAG=m -CONFIG_DIBS=y -CONFIG_DIBS_LO=y CONFIG_SMC=m CONFIG_SMC_DIAG=m +CONFIG_DIBS=y +CONFIG_DIBS_LO=y +CONFIG_XDP_SOCKETS=y +CONFIG_XDP_SOCKETS_DIAG=m CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -472,6 +473,7 @@ CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y +CONFIG_MD_LLBITMAP=y # CONFIG_MD_BITMAP_FILE is not set CONFIG_MD_LINEAR=m CONFIG_MD_CLUSTER=m @@ -654,9 +656,12 @@ CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y CONFIG_JFS_STATISTICS=y CONFIG_XFS_FS=y +CONFIG_XFS_SUPPORT_V4=y +CONFIG_XFS_SUPPORT_ASCII_CI=y CONFIG_XFS_QUOTA=y CONFIG_XFS_POSIX_ACL=y CONFIG_XFS_RT=y +# CONFIG_XFS_ONLINE_SCRUB is not set CONFIG_XFS_DEBUG=y CONFIG_GFS2_FS=m CONFIG_GFS2_FS_LOCKING_DLM=y @@ -666,7 +671,6 @@ CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_BTRFS_DEBUG=y CONFIG_BTRFS_ASSERT=y CONFIG_NILFS2_FS=m -CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 161dad7ef211..4414dabd04a6 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -94,6 +94,7 @@ CONFIG_SLAB_BUCKETS=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y +CONFIG_PERSISTENT_HUGE_ZERO_FOLIO=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 @@ -114,12 +115,12 @@ CONFIG_TLS_DEVICE=y CONFIG_TLS_TOE=y CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_XDP_SOCKETS=y -CONFIG_XDP_SOCKETS_DIAG=m -CONFIG_DIBS=y -CONFIG_DIBS_LO=y CONFIG_SMC=m CONFIG_SMC_DIAG=m +CONFIG_DIBS=y +CONFIG_DIBS_LO=y +CONFIG_XDP_SOCKETS=y +CONFIG_XDP_SOCKETS_DIAG=m CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -462,6 +463,7 @@ CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y +CONFIG_MD_LLBITMAP=y # CONFIG_MD_BITMAP_FILE is not set CONFIG_MD_LINEAR=m CONFIG_MD_CLUSTER=m @@ -644,16 +646,18 @@ CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y CONFIG_JFS_STATISTICS=y CONFIG_XFS_FS=y +CONFIG_XFS_SUPPORT_V4=y +CONFIG_XFS_SUPPORT_ASCII_CI=y CONFIG_XFS_QUOTA=y CONFIG_XFS_POSIX_ACL=y CONFIG_XFS_RT=y +# CONFIG_XFS_ONLINE_SCRUB is not set CONFIG_GFS2_FS=m CONFIG_GFS2_FS_LOCKING_DLM=y CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m -CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index ed0b137353ad..b5478267d6a7 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -33,7 +33,6 @@ CONFIG_NET=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_SAFE=y CONFIG_BLK_DEV_RAM=y -# CONFIG_DCSSBLK is not set # CONFIG_DASD is not set CONFIG_ENCLOSURE_SERVICES=y CONFIG_SCSI=y diff --git a/arch/s390/crypto/phmac_s390.c b/arch/s390/crypto/phmac_s390.c index 7ecfdc4fba2d..89f3e6d8fd89 100644 --- a/arch/s390/crypto/phmac_s390.c +++ b/arch/s390/crypto/phmac_s390.c @@ -169,11 +169,18 @@ struct kmac_sha2_ctx { u64 buflen[2]; }; +enum async_op { + OP_NOP = 0, + OP_UPDATE, + OP_FINAL, + OP_FINUP, +}; + /* phmac request context */ struct phmac_req_ctx { struct hash_walk_helper hwh; struct kmac_sha2_ctx kmac_ctx; - bool final; + enum async_op async_op; }; /* @@ -610,6 +617,7 @@ static int phmac_update(struct ahash_request *req) * using engine to serialize requests. */ if (rc == 0 || rc == -EKEYEXPIRED) { + req_ctx->async_op = OP_UPDATE; atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); if (rc != -EINPROGRESS) @@ -647,8 +655,7 @@ static int phmac_final(struct ahash_request *req) * using engine to serialize requests. */ if (rc == 0 || rc == -EKEYEXPIRED) { - req->nbytes = 0; - req_ctx->final = true; + req_ctx->async_op = OP_FINAL; atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); if (rc != -EINPROGRESS) @@ -676,13 +683,16 @@ static int phmac_finup(struct ahash_request *req) if (rc) goto out; + req_ctx->async_op = OP_FINUP; + /* Try synchronous operations if no active engine usage */ if (!atomic_read(&tfm_ctx->via_engine_ctr)) { rc = phmac_kmac_update(req, false); if (rc == 0) - req->nbytes = 0; + req_ctx->async_op = OP_FINAL; } - if (!rc && !req->nbytes && !atomic_read(&tfm_ctx->via_engine_ctr)) { + if (!rc && req_ctx->async_op == OP_FINAL && + !atomic_read(&tfm_ctx->via_engine_ctr)) { rc = phmac_kmac_final(req, false); if (rc == 0) goto out; @@ -694,7 +704,7 @@ static int phmac_finup(struct ahash_request *req) * using engine to serialize requests. */ if (rc == 0 || rc == -EKEYEXPIRED) { - req_ctx->final = true; + /* req->async_op has been set to either OP_FINUP or OP_FINAL */ atomic_inc(&tfm_ctx->via_engine_ctr); rc = crypto_transfer_hash_request_to_engine(phmac_crypto_engine, req); if (rc != -EINPROGRESS) @@ -855,15 +865,16 @@ static int phmac_do_one_request(struct crypto_engine *engine, void *areq) /* * Three kinds of requests come in here: - * update when req->nbytes > 0 and req_ctx->final is false - * final when req->nbytes = 0 and req_ctx->final is true - * finup when req->nbytes > 0 and req_ctx->final is true - * For update and finup the hwh walk needs to be prepared and - * up to date but the actual nr of bytes in req->nbytes may be - * any non zero number. For final there is no hwh walk needed. + * 1. req->async_op == OP_UPDATE with req->nbytes > 0 + * 2. req->async_op == OP_FINUP with req->nbytes > 0 + * 3. req->async_op == OP_FINAL + * For update and finup the hwh walk has already been prepared + * by the caller. For final there is no hwh walk needed. */ - if (req->nbytes) { + switch (req_ctx->async_op) { + case OP_UPDATE: + case OP_FINUP: rc = phmac_kmac_update(req, true); if (rc == -EKEYEXPIRED) { /* @@ -880,10 +891,11 @@ static int phmac_do_one_request(struct crypto_engine *engine, void *areq) hwh_advance(hwh, rc); goto out; } - req->nbytes = 0; - } - - if (req_ctx->final) { + if (req_ctx->async_op == OP_UPDATE) + break; + req_ctx->async_op = OP_FINAL; + fallthrough; + case OP_FINAL: rc = phmac_kmac_final(req, true); if (rc == -EKEYEXPIRED) { /* @@ -897,10 +909,14 @@ static int phmac_do_one_request(struct crypto_engine *engine, void *areq) cond_resched(); return -ENOSPC; } + break; + default: + /* unknown/unsupported/unimplemented asynch op */ + return -EOPNOTSUPP; } out: - if (rc || req_ctx->final) + if (rc || req_ctx->async_op == OP_FINAL) memzero_explicit(kmac_ctx, sizeof(*kmac_ctx)); pr_debug("request complete with rc=%d\n", rc); local_bh_disable(); diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 6890925d5587..a32f465ecf73 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -145,7 +145,6 @@ struct zpci_dev { u8 has_resources : 1; u8 is_physfn : 1; u8 util_str_avail : 1; - u8 irqs_registered : 1; u8 tid_avail : 1; u8 rtr_avail : 1; /* Relaxed translation allowed */ unsigned int devfn; /* DEVFN part of the RID*/ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b7100c6a4054..6663f1619abb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1154,17 +1154,15 @@ static inline pte_t pte_mkhuge(pte_t pte) #define IPTE_NODAT 0x400 #define IPTE_GUEST_ASCE 0x800 -static __always_inline void __ptep_rdp(unsigned long addr, pte_t *ptep, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __ptep_rdp(unsigned long addr, pte_t *ptep, int local) { unsigned long pto; pto = __pa(ptep) & ~(PTRS_PER_PTE * sizeof(pte_t) - 1); - asm volatile(".insn rrf,0xb98b0000,%[r1],%[r2],%[asce],%[m4]" + asm volatile(".insn rrf,0xb98b0000,%[r1],%[r2],%%r0,%[m4]" : "+m" (*ptep) - : [r1] "a" (pto), [r2] "a" ((addr & PAGE_MASK) | opt), - [asce] "a" (asce), [m4] "i" (local)); + : [r1] "a" (pto), [r2] "a" (addr & PAGE_MASK), + [m4] "i" (local)); } static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, @@ -1348,7 +1346,7 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, * A local RDP can be used to do the flush. */ if (cpu_has_rdp() && !(pte_val(*ptep) & _PAGE_PROTECT)) - __ptep_rdp(address, ptep, 0, 0, 1); + __ptep_rdp(address, ptep, 1); } #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 9af2aae0a515..528d7c70979f 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -291,16 +291,14 @@ static int ptdump_cmp(const void *a, const void *b) static int add_marker(unsigned long start, unsigned long end, const char *name) { - size_t oldsize, newsize; + struct addr_marker *new; + size_t newsize; - oldsize = markers_cnt * sizeof(*markers); - newsize = oldsize + 2 * sizeof(*markers); - if (!oldsize) - markers = kvmalloc(newsize, GFP_KERNEL); - else - markers = kvrealloc(markers, newsize, GFP_KERNEL); - if (!markers) - goto error; + newsize = (markers_cnt + 2) * sizeof(*markers); + new = kvrealloc(markers, newsize, GFP_KERNEL); + if (!new) + return -ENOMEM; + markers = new; markers[markers_cnt].is_start = 1; markers[markers_cnt].start_address = start; markers[markers_cnt].size = end - start; @@ -312,9 +310,6 @@ static int add_marker(unsigned long start, unsigned long end, const char *name) markers[markers_cnt].name = name; markers_cnt++; return 0; -error: - markers_cnt = 0; - return -ENOMEM; } static int pt_dump_init(void) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 0fde20bbc50b..05974304d622 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -274,9 +274,9 @@ void ptep_reset_dat_prot(struct mm_struct *mm, unsigned long addr, pte_t *ptep, preempt_disable(); atomic_inc(&mm->context.flush_count); if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) - __ptep_rdp(addr, ptep, 0, 0, 1); + __ptep_rdp(addr, ptep, 1); else - __ptep_rdp(addr, ptep, 0, 0, 0); + __ptep_rdp(addr, ptep, 0); /* * PTE is not invalidated by RDP, only _PAGE_PROTECT is cleared. That * means it is still valid and active, and must not be changed according diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index b95376041501..27db1e72c623 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -188,7 +188,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) * is unbound or probed and that userspace can't access its * configuration space while we perform recovery. */ - pci_dev_lock(pdev); + device_lock(&pdev->dev); if (pdev->error_state == pci_channel_io_perm_failure) { ers_res = PCI_ERS_RESULT_DISCONNECT; goto out_unlock; @@ -257,7 +257,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) driver->err_handler->resume(pdev); pci_uevent_ers(pdev, PCI_ERS_RESULT_RECOVERED); out_unlock: - pci_dev_unlock(pdev); + device_unlock(&pdev->dev); zpci_report_status(zdev, "recovery", status_str); return ers_res; diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 84482a921332..e73be96ce5fe 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -107,9 +107,6 @@ static int zpci_set_irq(struct zpci_dev *zdev) else rc = zpci_set_airq(zdev); - if (!rc) - zdev->irqs_registered = 1; - return rc; } @@ -123,9 +120,6 @@ static int zpci_clear_irq(struct zpci_dev *zdev) else rc = zpci_clear_airq(zdev); - if (!rc) - zdev->irqs_registered = 0; - return rc; } @@ -427,8 +421,7 @@ bool arch_restore_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); - if (!zdev->irqs_registered) - zpci_set_irq(zdev); + zpci_set_irq(zdev); return true; } diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 4db7e4bf69f5..1a27efcf3c20 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -75,7 +75,7 @@ export BITS # # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # -KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx -mno-sse4a KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 @@ -98,7 +98,7 @@ ifeq ($(CONFIG_X86_KERNEL_IBT),y) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816 # KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables) -KBUILD_RUSTFLAGS += -Zcf-protection=branch -Zno-jump-tables +KBUILD_RUSTFLAGS += -Zcf-protection=branch $(if $(call rustc-min-version,109300),-Cjump-tables=n,-Zno-jump-tables) else KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 745caa6c15a3..fa6c47b50989 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2789,13 +2789,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; - - if (perf_hw_regs(regs)) + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; unwind_start(&state, current, regs, NULL); - else + } else { unwind_start(&state, current, NULL, (void *)regs->sp); + } for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 28f5468a6ea3..fe65be0b9d9c 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -7596,6 +7596,7 @@ __init int intel_pmu_init(void) break; case INTEL_PANTHERLAKE_L: + case INTEL_WILDCATLAKE_L: pr_cont("Pantherlake Hybrid events, "); name = "pantherlake_hybrid"; goto lnl_common; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index c0b7ac1c7594..01bc59e9286c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -317,7 +317,8 @@ static u64 __grt_latency_data(struct perf_event *event, u64 status, { u64 val; - WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big); + WARN_ON_ONCE(is_hybrid() && + hybrid_pmu(event->pmu)->pmu_type == hybrid_big); dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK; val = hybrid_var(event->pmu, pebs_data_source)[dse]; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index a762f7f5b161..d6c945cc5d07 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1895,6 +1895,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_ARROWLAKE_H, &mtl_uncore_init), X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_uncore_init), X86_MATCH_VFM(INTEL_PANTHERLAKE_L, &ptl_uncore_init), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, &ptl_uncore_init), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_uncore_init), diff --git a/arch/x86/include/asm/amd/node.h b/arch/x86/include/asm/amd/node.h index 23fe617898a8..a672b8765fa8 100644 --- a/arch/x86/include/asm/amd/node.h +++ b/arch/x86/include/asm/amd/node.h @@ -23,7 +23,6 @@ #define AMD_NODE0_PCI_SLOT 0x18 struct pci_dev *amd_node_get_func(u16 node, u8 func); -struct pci_dev *amd_node_get_root(u16 node); static inline u16 amd_num_nodes(void) { diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 93156ac4ffe0..b08c95872eed 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -56,6 +56,11 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &arch_ftrace_regs(fregs)->regs; } +#define arch_ftrace_partial_regs(regs) do { \ + regs->flags &= ~X86_EFLAGS_FIXED; \ + regs->cs = __KERNEL_CS; \ +} while (0) + #define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ (_regs)->ip = arch_ftrace_regs(fregs)->regs.ip; \ (_regs)->sp = arch_ftrace_regs(fregs)->regs.sp; \ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index f32a0eca2ae5..950bfd006905 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -150,12 +150,12 @@ #define INTEL_LUNARLAKE_M IFM(6, 0xBD) /* Lion Cove / Skymont */ -#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) /* Cougar Cove / Crestmont */ +#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) /* Cougar Cove / Darkmont */ #define INTEL_WILDCATLAKE_L IFM(6, 0xD5) -#define INTEL_NOVALAKE IFM(18, 0x01) -#define INTEL_NOVALAKE_L IFM(18, 0x03) +#define INTEL_NOVALAKE IFM(18, 0x01) /* Coyote Cove / Arctic Wolf */ +#define INTEL_NOVALAKE_L IFM(18, 0x03) /* Coyote Cove / Arctic Wolf */ /* "Small Core" Processors (Atom/E-Core) */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 015d23f3e01f..53f4089333f2 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -43,6 +43,9 @@ extern unsigned long __phys_addr_symbol(unsigned long); void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); +KCFI_REFERENCE(clear_page_orig); +KCFI_REFERENCE(clear_page_rep); +KCFI_REFERENCE(clear_page_erms); static inline void clear_page(void *page) { diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h index 8d983cfd06ea..e5a13dc8816e 100644 --- a/arch/x86/include/asm/runtime-const.h +++ b/arch/x86/include/asm/runtime-const.h @@ -2,6 +2,10 @@ #ifndef _ASM_RUNTIME_CONST_H #define _ASM_RUNTIME_CONST_H +#ifdef MODULE + #error "Cannot use runtime-const infrastructure from modules" +#endif + #ifdef __ASSEMBLY__ .macro RUNTIME_CONST_PTR sym reg diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index c8a5ae35c871..641f45c22f9d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -12,12 +12,12 @@ #include #include #include -#include -/* - * Virtual variable: there's no actual backing store for this, - * it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' - */ +#ifdef MODULE + #define runtime_const_ptr(sym) (sym) +#else + #include +#endif extern unsigned long USER_PTR_MAX; #ifdef CONFIG_ADDRESS_MASKING diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 9792e329343e..1baa86dfe029 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -93,6 +93,7 @@ #define EXIT_REASON_TPAUSE 68 #define EXIT_REASON_BUS_LOCK 74 #define EXIT_REASON_NOTIFY 75 +#define EXIT_REASON_SEAMCALL 76 #define EXIT_REASON_TDCALL 77 #define EXIT_REASON_MSR_READ_IMM 84 #define EXIT_REASON_MSR_WRITE_IMM 85 diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 7047124490f6..d7c8ef1e354d 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -196,7 +196,7 @@ int amd_detect_prefcore(bool *detected) break; } - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { u32 tmp; int ret; diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c index a40176b62eb5..3d0a4768d603 100644 --- a/arch/x86/kernel/amd_node.c +++ b/arch/x86/kernel/amd_node.c @@ -34,62 +34,6 @@ struct pci_dev *amd_node_get_func(u16 node, u8 func) return pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(AMD_NODE0_PCI_SLOT + node, func)); } -#define DF_BLK_INST_CNT 0x040 -#define DF_CFG_ADDR_CNTL_LEGACY 0x084 -#define DF_CFG_ADDR_CNTL_DF4 0xC04 - -#define DF_MAJOR_REVISION GENMASK(27, 24) - -static u16 get_cfg_addr_cntl_offset(struct pci_dev *df_f0) -{ - u32 reg; - - /* - * Revision fields added for DF4 and later. - * - * Major revision of '0' is found pre-DF4. Field is Read-as-Zero. - */ - if (pci_read_config_dword(df_f0, DF_BLK_INST_CNT, ®)) - return 0; - - if (reg & DF_MAJOR_REVISION) - return DF_CFG_ADDR_CNTL_DF4; - - return DF_CFG_ADDR_CNTL_LEGACY; -} - -struct pci_dev *amd_node_get_root(u16 node) -{ - struct pci_dev *root; - u16 cntl_off; - u8 bus; - - if (!cpu_feature_enabled(X86_FEATURE_ZEN)) - return NULL; - - /* - * D18F0xXXX [Config Address Control] (DF::CfgAddressCntl) - * Bits [7:0] (SecBusNum) holds the bus number of the root device for - * this Data Fabric instance. The segment, device, and function will be 0. - */ - struct pci_dev *df_f0 __free(pci_dev_put) = amd_node_get_func(node, 0); - if (!df_f0) - return NULL; - - cntl_off = get_cfg_addr_cntl_offset(df_f0); - if (!cntl_off) - return NULL; - - if (pci_read_config_byte(df_f0, cntl_off, &bus)) - return NULL; - - /* Grab the pointer for the actual root device instance. */ - root = pci_get_domain_bus_and_slot(0, bus, 0); - - pci_dbg(root, "is root for AMD node %u\n", node); - return root; -} - static struct pci_dev **amd_roots; /* Protect the PCI config register pairs used for SMN. */ @@ -274,51 +218,21 @@ DEFINE_SHOW_STORE_ATTRIBUTE(smn_node); DEFINE_SHOW_STORE_ATTRIBUTE(smn_address); DEFINE_SHOW_STORE_ATTRIBUTE(smn_value); -static int amd_cache_roots(void) +static struct pci_dev *get_next_root(struct pci_dev *root) { - u16 node, num_nodes = amd_num_nodes(); - - amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL); - if (!amd_roots) - return -ENOMEM; - - for (node = 0; node < num_nodes; node++) - amd_roots[node] = amd_node_get_root(node); - - return 0; -} - -static int reserve_root_config_spaces(void) -{ - struct pci_dev *root = NULL; - struct pci_bus *bus = NULL; - - while ((bus = pci_find_next_bus(bus))) { - /* Root device is Device 0 Function 0 on each Primary Bus. */ - root = pci_get_slot(bus, 0); - if (!root) + while ((root = pci_get_class(PCI_CLASS_BRIDGE_HOST << 8, root))) { + /* Root device is Device 0 Function 0. */ + if (root->devfn) continue; if (root->vendor != PCI_VENDOR_ID_AMD && root->vendor != PCI_VENDOR_ID_HYGON) continue; - pci_dbg(root, "Reserving PCI config space\n"); - - /* - * There are a few SMN index/data pairs and other registers - * that shouldn't be accessed by user space. - * So reserve the entire PCI config space for simplicity rather - * than covering specific registers piecemeal. - */ - if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) { - pci_err(root, "Failed to reserve config space\n"); - return -EEXIST; - } + break; } - smn_exclusive = true; - return 0; + return root; } static bool enable_dfs; @@ -332,7 +246,8 @@ __setup("amd_smn_debugfs_enable", amd_smn_enable_dfs); static int __init amd_smn_init(void) { - int err; + u16 count, num_roots, roots_per_node, node, num_nodes; + struct pci_dev *root; if (!cpu_feature_enabled(X86_FEATURE_ZEN)) return 0; @@ -342,13 +257,48 @@ static int __init amd_smn_init(void) if (amd_roots) return 0; - err = amd_cache_roots(); - if (err) - return err; + num_roots = 0; + root = NULL; + while ((root = get_next_root(root))) { + pci_dbg(root, "Reserving PCI config space\n"); - err = reserve_root_config_spaces(); - if (err) - return err; + /* + * There are a few SMN index/data pairs and other registers + * that shouldn't be accessed by user space. So reserve the + * entire PCI config space for simplicity rather than covering + * specific registers piecemeal. + */ + if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) { + pci_err(root, "Failed to reserve config space\n"); + return -EEXIST; + } + + num_roots++; + } + + pr_debug("Found %d AMD root devices\n", num_roots); + + if (!num_roots) + return -ENODEV; + + num_nodes = amd_num_nodes(); + amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL); + if (!amd_roots) + return -ENOMEM; + + roots_per_node = num_roots / num_nodes; + + count = 0; + node = 0; + root = NULL; + while (node < num_nodes && (root = get_next_root(root))) { + /* Use one root for each node and skip the rest. */ + if (count++ % roots_per_node) + continue; + + pci_dbg(root, "is root for AMD node %u\n", node); + amd_roots[node++] = root; + } if (enable_dfs) { debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir); @@ -358,6 +308,8 @@ static int __init amd_smn_init(void) debugfs_create_file("value", 0600, debugfs_dir, NULL, &smn_value_fops); } + smn_exclusive = true; + return 0; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ccaa51ce63f6..5d46709c58d0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -516,7 +516,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ZEN5); break; case 0x50 ... 0x5f: - case 0x90 ... 0xaf: + case 0x80 ... 0xaf: case 0xc0 ... 0xcf: setup_force_cpu_cap(X86_FEATURE_ZEN6); break; @@ -1035,8 +1035,26 @@ static void init_amd_zen4(struct cpuinfo_x86 *c) } } +static const struct x86_cpu_id zen5_rdseed_microcode[] = { + ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a), + ZEN_MODEL_STEP_UCODE(0x1a, 0x08, 0x1, 0x0b008121), + ZEN_MODEL_STEP_UCODE(0x1a, 0x11, 0x0, 0x0b101054), + ZEN_MODEL_STEP_UCODE(0x1a, 0x24, 0x0, 0x0b204037), + ZEN_MODEL_STEP_UCODE(0x1a, 0x44, 0x0, 0x0b404035), + ZEN_MODEL_STEP_UCODE(0x1a, 0x44, 0x1, 0x0b404108), + ZEN_MODEL_STEP_UCODE(0x1a, 0x60, 0x0, 0x0b600037), + ZEN_MODEL_STEP_UCODE(0x1a, 0x68, 0x0, 0x0b608038), + ZEN_MODEL_STEP_UCODE(0x1a, 0x70, 0x0, 0x0b700037), + {}, +}; + static void init_amd_zen5(struct cpuinfo_x86 *c) { + if (!x86_match_min_microcode_rev(zen5_rdseed_microcode)) { + clear_cpu_cap(c, X86_FEATURE_RDSEED); + msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18); + pr_emerg_once("RDSEED32 is broken. Disabling the corresponding CPUID bit.\n"); + } } static void init_amd(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 6a526ae1fe99..d7fa03bf51b4 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1463,7 +1463,9 @@ static void __init retbleed_update_mitigation(void) break; default: if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF) { - pr_err(RETBLEED_INTEL_MSG); + if (retbleed_mitigation != RETBLEED_MITIGATION_NONE) + pr_err(RETBLEED_INTEL_MSG); + retbleed_mitigation = RETBLEED_MITIGATION_NONE; } } @@ -1825,13 +1827,6 @@ void unpriv_ebpf_notify(int new_state) } #endif -static inline bool match_option(const char *arg, int arglen, const char *opt) -{ - int len = strlen(opt); - - return len == arglen && !strncmp(arg, opt, len); -} - /* The kernel command line selection for spectre v2 */ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_NONE, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c7d3512914ca..02d97834a1d4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -78,6 +78,10 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +/* Used for modules: built-in code uses runtime constants */ +unsigned long USER_PTR_MAX; +EXPORT_SYMBOL(USER_PTR_MAX); + u32 elf_hwcap2 __read_mostly; /* Number of siblings per CPU package */ @@ -2579,7 +2583,7 @@ void __init arch_cpu_finalize_init(void) alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { - unsigned long USER_PTR_MAX = TASK_SIZE_MAX; + USER_PTR_MAX = TASK_SIZE_MAX; /* * Enable this when LAM is gated on LASS support diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index cdce885e2fd5..a881bf4c2011 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -194,7 +194,7 @@ static bool need_sha_check(u32 cur_rev) } switch (cur_rev >> 8) { - case 0x80012: return cur_rev <= 0x800126f; break; + case 0x80012: return cur_rev <= 0x8001277; break; case 0x80082: return cur_rev <= 0x800820f; break; case 0x83010: return cur_rev <= 0x830107c; break; case 0x86001: return cur_rev <= 0x860010e; break; @@ -220,10 +220,13 @@ static bool need_sha_check(u32 cur_rev) case 0xaa001: return cur_rev <= 0xaa00116; break; case 0xaa002: return cur_rev <= 0xaa00218; break; case 0xb0021: return cur_rev <= 0xb002146; break; + case 0xb0081: return cur_rev <= 0xb008111; break; case 0xb1010: return cur_rev <= 0xb101046; break; case 0xb2040: return cur_rev <= 0xb204031; break; case 0xb4040: return cur_rev <= 0xb404031; break; + case 0xb4041: return cur_rev <= 0xb404101; break; case 0xb6000: return cur_rev <= 0xb600031; break; + case 0xb6080: return cur_rev <= 0xb608031; break; case 0xb7000: return cur_rev <= 0xb700031; break; default: break; } @@ -233,13 +236,31 @@ static bool need_sha_check(u32 cur_rev) return true; } +static bool cpu_has_entrysign(void) +{ + unsigned int fam = x86_family(bsp_cpuid_1_eax); + unsigned int model = x86_model(bsp_cpuid_1_eax); + + if (fam == 0x17 || fam == 0x19) + return true; + + if (fam == 0x1a) { + if (model <= 0x2f || + (0x40 <= model && model <= 0x4f) || + (0x60 <= model && model <= 0x6f)) + return true; + } + + return false; +} + static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len) { struct patch_digest *pd = NULL; u8 digest[SHA256_DIGEST_SIZE]; int i; - if (x86_family(bsp_cpuid_1_eax) < 0x17) + if (!cpu_has_entrysign()) return true; if (!need_sha_check(cur_rev)) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 2cd25a0d4637..fe1a2aa53c16 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -458,7 +458,16 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; } - if (rdt_cpu_has(X86_FEATURE_ABMC)) { + /* + * resctrl assumes a system that supports assignable counters can + * switch to "default" mode. Ensure that there is a "default" mode + * to switch to. This enforces a dependency between the independent + * X86_FEATURE_ABMC and X86_FEATURE_CQM_MBM_TOTAL/X86_FEATURE_CQM_MBM_LOCAL + * hardware features. + */ + if (rdt_cpu_has(X86_FEATURE_ABMC) && + (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL) || + rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))) { r->mon.mbm_cntr_assignable = true; cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx); r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 1f71cc135e9a..e88eacb1b5bb 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -825,6 +825,9 @@ void fpu__clear_user_states(struct fpu *fpu) !fpregs_state_valid(fpu, smp_processor_id())) os_xrstor_supervisor(fpu->fpstate); + /* Ensure XFD state is in sync before reloading XSTATE */ + xfd_update_state(fpu->fpstate); + /* Reset user states in registers. */ restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE); diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 367da3638167..823dbdd0eb41 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -354,12 +354,17 @@ SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR + /* Restore return_to_handler value that got eaten by previous ret instruction. */ + subq $8, %rsp + UNWIND_HINT_FUNC + /* Save ftrace_regs for function exit context */ subq $(FRAME_SIZE), %rsp movq %rax, RAX(%rsp) movq %rdx, RDX(%rsp) movq %rbp, RBP(%rsp) + movq %rsp, RSP(%rsp) movq %rsp, %rdi call ftrace_return_to_handler @@ -368,7 +373,8 @@ SYM_CODE_START(return_to_handler) movq RDX(%rsp), %rdx movq RAX(%rsp), %rax - addq $(FRAME_SIZE), %rsp + addq $(FRAME_SIZE) + 8, %rsp + /* * Jump back to the old return address. This cannot be JMP_NOSPEC rdi * since IBT would demand that contain ENDBR, which simply isn't so for diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index f286b5706d7c..fef00546c885 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -216,7 +216,7 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) * This function is called from IOMMU driver to notify * SVM to schedule in a particular vCPU of a particular VM. */ -int avic_ga_log_notifier(u32 ga_tag) +static int avic_ga_log_notifier(u32 ga_tag) { unsigned long flags; struct kvm_svm *kvm_svm; @@ -788,7 +788,7 @@ int avic_init_vcpu(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; INIT_LIST_HEAD(&svm->ir_list); - spin_lock_init(&svm->ir_list_lock); + raw_spin_lock_init(&svm->ir_list_lock); if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) return 0; @@ -816,9 +816,9 @@ static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd) if (!vcpu) return; - spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags); + raw_spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags); list_del(&irqfd->vcpu_list); - spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags); + raw_spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags); } int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, @@ -855,7 +855,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, * list of IRQs being posted to the vCPU, to ensure the IRTE * isn't programmed with stale pCPU/IsRunning information. */ - guard(spinlock_irqsave)(&svm->ir_list_lock); + guard(raw_spinlock_irqsave)(&svm->ir_list_lock); /* * Update the target pCPU for IOMMU doorbells if the vCPU is @@ -972,7 +972,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, * up-to-date entry information, or that this task will wait until * svm_ir_list_add() completes to set the new target pCPU. */ - spin_lock_irqsave(&svm->ir_list_lock, flags); + raw_spin_lock_irqsave(&svm->ir_list_lock, flags); entry = svm->avic_physical_id_entry; WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); @@ -997,7 +997,7 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action); - spin_unlock_irqrestore(&svm->ir_list_lock, flags); + raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags); } void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -1035,7 +1035,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action) * or that this task will wait until svm_ir_list_add() completes to * mark the vCPU as not running. */ - spin_lock_irqsave(&svm->ir_list_lock, flags); + raw_spin_lock_irqsave(&svm->ir_list_lock, flags); avic_update_iommu_vcpu_affinity(vcpu, -1, action); @@ -1059,7 +1059,7 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action) svm->avic_physical_id_entry = entry; - spin_unlock_irqrestore(&svm->ir_list_lock, flags); + raw_spin_unlock_irqrestore(&svm->ir_list_lock, flags); } void avic_vcpu_put(struct kvm_vcpu *vcpu) @@ -1243,3 +1243,9 @@ bool __init avic_hardware_setup(void) return true; } + +void avic_hardware_unsetup(void) +{ + if (avic) + amd_iommu_register_ga_log_notifier(NULL); +} diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index a6443feab252..da6e80b3ac35 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -677,11 +677,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 */ svm_copy_lbrs(vmcb02, vmcb12); vmcb02->save.dbgctl &= ~DEBUGCTL_RESERVED_BITS; - svm_update_lbrv(&svm->vcpu); - - } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { + } else { svm_copy_lbrs(vmcb02, vmcb01); } + svm_update_lbrv(&svm->vcpu); } static inline bool is_evtinj_soft(u32 evtinj) @@ -833,11 +832,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, svm->soft_int_next_rip = vmcb12_rip; } - vmcb02->control.virt_ext = vmcb01->control.virt_ext & - LBR_CTL_ENABLE_MASK; - if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV)) - vmcb02->control.virt_ext |= - (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); + /* LBR_CTL_ENABLE_MASK is controlled by svm_update_lbrv() */ if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; @@ -1189,13 +1184,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && - (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) svm_copy_lbrs(vmcb12, vmcb02); - svm_update_lbrv(vcpu); - } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { + else svm_copy_lbrs(vmcb01, vmcb02); - svm_update_lbrv(vcpu); - } + + svm_update_lbrv(vcpu); if (vnmi) { if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 153c12dbf3eb..10c21e4c5406 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -806,60 +806,43 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } +static void __svm_enable_lbrv(struct kvm_vcpu *vcpu) +{ + to_svm(vcpu)->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; +} + void svm_enable_lbrv(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; + __svm_enable_lbrv(vcpu); svm_recalc_lbr_msr_intercepts(vcpu); - - /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ - if (is_guest_mode(vcpu)) - svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); } -static void svm_disable_lbrv(struct kvm_vcpu *vcpu) +static void __svm_disable_lbrv(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); - svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; - svm_recalc_lbr_msr_intercepts(vcpu); - - /* - * Move the LBR msrs back to the vmcb01 to avoid copying them - * on nested guest entries. - */ - if (is_guest_mode(vcpu)) - svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb); -} - -static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm) -{ - /* - * If LBR virtualization is disabled, the LBR MSRs are always kept in - * vmcb01. If LBR virtualization is enabled and L1 is running VMs of - * its own, the MSRs are moved between vmcb01 and vmcb02 as needed. - */ - return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb : - svm->vmcb01.ptr; + to_svm(vcpu)->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; } void svm_update_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK; - bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) || + bool enable_lbrv = (svm->vmcb->save.dbgctl & DEBUGCTLMSR_LBR) || (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)); - if (enable_lbrv == current_enable_lbrv) - return; + if (enable_lbrv && !current_enable_lbrv) + __svm_enable_lbrv(vcpu); + else if (!enable_lbrv && current_enable_lbrv) + __svm_disable_lbrv(vcpu); - if (enable_lbrv) - svm_enable_lbrv(vcpu); - else - svm_disable_lbrv(vcpu); + /* + * During nested transitions, it is possible that the current VMCB has + * LBR_CTL set, but the previous LBR_CTL had it cleared (or vice versa). + * In this case, even though LBR_CTL does not need an update, intercepts + * do, so always recalculate the intercepts here. + */ + svm_recalc_lbr_msr_intercepts(vcpu); } void disable_nmi_singlestep(struct vcpu_svm *svm) @@ -921,6 +904,8 @@ static void svm_hardware_unsetup(void) { int cpu; + avic_hardware_unsetup(); + sev_hardware_unsetup(); for_each_possible_cpu(cpu) @@ -2722,19 +2707,19 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = svm->tsc_aux; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl; + msr_info->data = svm->vmcb->save.dbgctl; break; case MSR_IA32_LASTBRANCHFROMIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from; + msr_info->data = svm->vmcb->save.br_from; break; case MSR_IA32_LASTBRANCHTOIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to; + msr_info->data = svm->vmcb->save.br_to; break; case MSR_IA32_LASTINTFROMIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from; + msr_info->data = svm->vmcb->save.last_excp_from; break; case MSR_IA32_LASTINTTOIP: - msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to; + msr_info->data = svm->vmcb->save.last_excp_to; break; case MSR_VM_HSAVE_PA: msr_info->data = svm->nested.hsave_msr; @@ -3002,7 +2987,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & DEBUGCTL_RESERVED_BITS) return 1; - svm_get_lbr_vmcb(svm)->save.dbgctl = data; + if (svm->vmcb->save.dbgctl == data) + break; + + svm->vmcb->save.dbgctl = data; + vmcb_mark_dirty(svm->vmcb, VMCB_LBR); svm_update_lbrv(vcpu); break; case MSR_VM_HSAVE_PA: @@ -5386,12 +5375,6 @@ static __init int svm_hardware_setup(void) svm_hv_hardware_setup(); - for_each_possible_cpu(cpu) { - r = svm_cpu_init(cpu); - if (r) - goto err; - } - enable_apicv = avic_hardware_setup(); if (!enable_apicv) { enable_ipiv = false; @@ -5435,6 +5418,13 @@ static __init int svm_hardware_setup(void) svm_set_cpu_caps(); kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED; + + for_each_possible_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err; + } + return 0; err: diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index e4b04f435b3d..c856d8e0f95e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -329,7 +329,7 @@ struct vcpu_svm { * back into remapped mode). */ struct list_head ir_list; - spinlock_t ir_list_lock; + raw_spinlock_t ir_list_lock; struct vcpu_sev_es_state sev_es; @@ -805,7 +805,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; ) bool __init avic_hardware_setup(void); -int avic_ga_log_notifier(u32 ga_tag); +void avic_hardware_unsetup(void); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb); diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index bc5ece76533a..412d0829d7a2 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -98,7 +98,7 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa, error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK) ? PFERR_PRESENT_MASK : 0; - if (error_code & EPT_VIOLATION_GVA_IS_VALID) + if (exit_qualification & EPT_VIOLATION_GVA_IS_VALID) error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 76271962cb70..bcea087b642f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6728,6 +6728,14 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_NOTIFY: /* Notify VM exit is not exposed to L1 */ return false; + case EXIT_REASON_SEAMCALL: + case EXIT_REASON_TDCALL: + /* + * SEAMCALL and TDCALL unconditionally VM-Exit, but aren't + * virtualized by KVM for L1 hypervisors, i.e. L1 should + * never want or expect such an exit. + */ + return false; default: return true; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f87c216d976d..91b6f2f3edc2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6032,6 +6032,12 @@ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) return 1; } +static int handle_tdx_instruction(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + #ifndef CONFIG_X86_SGX_KVM static int handle_encls(struct kvm_vcpu *vcpu) { @@ -6157,6 +6163,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, [EXIT_REASON_NOTIFY] = handle_notify, + [EXIT_REASON_SEAMCALL] = handle_tdx_instruction, + [EXIT_REASON_TDCALL] = handle_tdx_instruction, [EXIT_REASON_MSR_READ_IMM] = handle_rdmsr_imm, [EXIT_REASON_MSR_WRITE_IMM] = handle_wrmsr_imm, }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b4b5d2d09634..c9c2aa6f4705 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3874,15 +3874,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu) /* * Returns true if the MSR in question is managed via XSTATE, i.e. is context - * switched with the rest of guest FPU state. Note! S_CET is _not_ context - * switched via XSTATE even though it _is_ saved/restored via XSAVES/XRSTORS. - * Because S_CET is loaded on VM-Enter and VM-Exit via dedicated VMCS fields, - * the value saved/restored via XSTATE is always the host's value. That detail - * is _extremely_ important, as the guest's S_CET must _never_ be resident in - * hardware while executing in the host. Loading guest values for U_CET and - * PL[0-3]_SSP while executing in the kernel is safe, as U_CET is specific to - * userspace, and PL[0-3]_SSP are only consumed when transitioning to lower - * privilege levels, i.e. are effectively only consumed by userspace as well. + * switched with the rest of guest FPU state. + * + * Note, S_CET is _not_ saved/restored via XSAVES/XRSTORS. */ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) { @@ -3905,6 +3899,11 @@ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) * MSR that is managed via XSTATE. Note, the caller is responsible for doing * the initial FPU load, this helper only ensures that guest state is resident * in hardware (the kernel can load its FPU state in IRQ context). + * + * Note, loading guest values for U_CET and PL[0-3]_SSP while executing in the + * kernel is safe, as U_CET is specific to userspace, and PL[0-3]_SSP are only + * consumed when transitioning to lower privilege levels, i.e. are effectively + * only consumed by userspace as well. */ static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info, @@ -11807,6 +11806,9 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) + return; + /* Exclude PKRU, it's restored separately immediately after VM-Exit. */ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); @@ -11815,6 +11817,9 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) + return; + fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); @@ -12137,9 +12142,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, int r; vcpu_load(vcpu); - if (kvm_mpx_supported()) - kvm_load_guest_fpu(vcpu); - kvm_vcpu_srcu_read_lock(vcpu); r = kvm_apic_accept_events(vcpu); @@ -12156,9 +12158,6 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, out: kvm_vcpu_srcu_read_unlock(vcpu); - - if (kvm_mpx_supported()) - kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return r; } @@ -12788,6 +12787,7 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) { struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; u64 xfeatures_mask; + bool fpu_in_use; int i; /* @@ -12811,13 +12811,23 @@ static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX); /* - * All paths that lead to INIT are required to load the guest's FPU - * state (because most paths are buried in KVM_RUN). + * Unload guest FPU state (if necessary) before zeroing XSTATE fields + * as the kernel can only modify the state when its resident in memory, + * i.e. when it's not loaded into hardware. + * + * WARN if the vCPU's desire to run, i.e. whether or not its in KVM_RUN, + * doesn't match the loaded/in-use state of the FPU, as KVM_RUN is the + * only path that can trigger INIT emulation _and_ loads FPU state, and + * KVM_RUN should _always_ load FPU state. */ - kvm_put_guest_fpu(vcpu); + WARN_ON_ONCE(vcpu->wants_to_run != fpstate->in_use); + fpu_in_use = fpstate->in_use; + if (fpu_in_use) + kvm_put_guest_fpu(vcpu); for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX) fpstate_clear_xstate_component(fpstate, i); - kvm_load_guest_fpu(vcpu); + if (fpu_in_use) + kvm_load_guest_fpu(vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index d4c93d9e73e4..de5083cb1d37 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2701,7 +2701,7 @@ st: if (is_imm8(insn->off)) /* Update cleanup_addr */ ctx->cleanup_addr = proglen; if (bpf_prog_was_classic(bpf_prog) && - !capable(CAP_SYS_ADMIN)) { + !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) { u8 *ip = image + addrs[i - 1]; if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog)) diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 4b1ad84d1b5a..3e7bf1974cbd 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -292,7 +292,7 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr) } if (!bio_crypt_check_alignment(bio)) { - bio->bi_status = BLK_STS_IOERR; + bio->bi_status = BLK_STS_INVAL; goto fail; } diff --git a/block/blk-settings.c b/block/blk-settings.c index 54cffaae4df4..d74b13ec8e54 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -184,6 +184,16 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) if (!bi->interval_exp) bi->interval_exp = ilog2(lim->logical_block_size); + /* + * The PI generation / validation helpers do not expect intervals to + * straddle multiple bio_vecs. Enforce alignment so that those are + * never generated, and that each buffer is aligned as expected. + */ + if (bi->csum_type) { + lim->dma_alignment = max(lim->dma_alignment, + (1U << bi->interval_exp) - 1); + } + return 0; } diff --git a/drivers/acpi/acpi_mrrm.c b/drivers/acpi/acpi_mrrm.c index 47ea3ccc2142..6d69554c940e 100644 --- a/drivers/acpi/acpi_mrrm.c +++ b/drivers/acpi/acpi_mrrm.c @@ -63,6 +63,9 @@ static __init int acpi_parse_mrrm(struct acpi_table_header *table) if (!mrrm) return -ENODEV; + if (mrrm->header.revision != 1) + return -EINVAL; + if (mrrm->flags & ACPI_MRRM_FLAGS_REGION_ASSIGNMENT_OS) return -EOPNOTSUPP; @@ -149,26 +152,49 @@ ATTRIBUTE_GROUPS(memory_range); static __init int add_boot_memory_ranges(void) { - struct kobject *pkobj, *kobj; + struct kobject *pkobj, *kobj, **kobjs; int ret = -EINVAL; - char *name; + char name[16]; + int i; pkobj = kobject_create_and_add("memory_ranges", acpi_kobj); + if (!pkobj) + return -ENOMEM; - for (int i = 0; i < mrrm_mem_entry_num; i++) { - name = kasprintf(GFP_KERNEL, "range%d", i); - if (!name) { - ret = -ENOMEM; - break; - } - - kobj = kobject_create_and_add(name, pkobj); - - ret = sysfs_create_groups(kobj, memory_range_groups); - if (ret) - return ret; + kobjs = kcalloc(mrrm_mem_entry_num, sizeof(*kobjs), GFP_KERNEL); + if (!kobjs) { + kobject_put(pkobj); + return -ENOMEM; } + for (i = 0; i < mrrm_mem_entry_num; i++) { + scnprintf(name, sizeof(name), "range%d", i); + kobj = kobject_create_and_add(name, pkobj); + if (!kobj) { + ret = -ENOMEM; + goto cleanup; + } + + ret = sysfs_create_groups(kobj, memory_range_groups); + if (ret) { + kobject_put(kobj); + goto cleanup; + } + kobjs[i] = kobj; + } + + kfree(kobjs); + return 0; + +cleanup: + for (int j = 0; j < i; j++) { + if (kobjs[j]) { + sysfs_remove_groups(kobjs[j], memory_range_groups); + kobject_put(kobjs[j]); + } + } + kfree(kobjs); + kobject_put(pkobj); return ret; } diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 103f29661576..be8e7e18abca 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -1959,8 +1959,10 @@ static void acpi_video_bus_remove_notify_handler(struct acpi_video_bus *video) struct acpi_video_device *dev; mutex_lock(&video->device_list_lock); - list_for_each_entry(dev, &video->video_device_list, entry) + list_for_each_entry(dev, &video->video_device_list, entry) { acpi_video_dev_remove_notify_handler(dev); + cancel_delayed_work_sync(&dev->switch_brightness_work); + } mutex_unlock(&video->device_list_lock); acpi_video_bus_stop_devices(video); diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index 049f6c2f1e32..e5631027f7f1 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -95,6 +95,11 @@ acpi_tb_print_table_header(acpi_physical_address address, { struct acpi_table_header local_header; +#pragma GCC diagnostic push +#if defined(__GNUC__) && __GNUC__ >= 11 +#pragma GCC diagnostic ignored "-Wstringop-overread" +#endif + if (ACPI_COMPARE_NAMESEG(header->signature, ACPI_SIG_FACS)) { /* FACS only has signature and length fields */ @@ -143,4 +148,5 @@ acpi_tb_print_table_header(acpi_physical_address address, local_header.asl_compiler_id, local_header.asl_compiler_revision)); } +#pragma GCC diagnostic pop } diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0a7026040188..3c6dd9b4ba0a 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -619,8 +619,10 @@ static int acpi_button_add(struct acpi_device *device) input_set_drvdata(input, device); error = input_register_device(input); - if (error) + if (error) { + input_free_device(input); goto err_remove_fs; + } switch (device->device_type) { case ACPI_BUS_TYPE_POWER_BUTTON: diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index ab4651205e8a..3bdeeee3414e 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -460,7 +460,7 @@ bool acpi_cpc_valid(void) if (acpi_disabled) return false; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); if (!cpc_ptr) return false; @@ -476,7 +476,7 @@ bool cppc_allow_fast_switch(void) struct cpc_desc *cpc_ptr; int cpu; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF]; if (!CPC_IN_SYSTEM_MEMORY(desired_reg) && @@ -750,7 +750,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) } /* - * Disregard _CPC if the number of entries in the return pachage is not + * Disregard _CPC if the number of entries in the return package is not * as expected, but support future revisions being proper supersets of * the v3 and only causing more entries to be returned by _CPC. */ @@ -1435,7 +1435,7 @@ bool cppc_perf_ctrs_in_pcc(void) { int cpu; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct cpc_register_resource *ref_perf_reg; struct cpc_desc *cpc_desc; diff --git a/drivers/acpi/fan.h b/drivers/acpi/fan.h index 8a28a72a7c6a..bedbab0e8e4e 100644 --- a/drivers/acpi/fan.h +++ b/drivers/acpi/fan.h @@ -49,6 +49,7 @@ struct acpi_fan_fst { }; struct acpi_fan { + acpi_handle handle; bool acpi4; bool has_fst; struct acpi_fan_fif fif; @@ -59,14 +60,14 @@ struct acpi_fan { struct device_attribute fine_grain_control; }; -int acpi_fan_get_fst(struct acpi_device *device, struct acpi_fan_fst *fst); +int acpi_fan_get_fst(acpi_handle handle, struct acpi_fan_fst *fst); int acpi_fan_create_attributes(struct acpi_device *device); void acpi_fan_delete_attributes(struct acpi_device *device); #if IS_REACHABLE(CONFIG_HWMON) -int devm_acpi_fan_create_hwmon(struct acpi_device *device); +int devm_acpi_fan_create_hwmon(struct device *dev); #else -static inline int devm_acpi_fan_create_hwmon(struct acpi_device *device) { return 0; }; +static inline int devm_acpi_fan_create_hwmon(struct device *dev) { return 0; }; #endif #endif diff --git a/drivers/acpi/fan_attr.c b/drivers/acpi/fan_attr.c index c1afb7b5ed3d..9b7fa52f3c2a 100644 --- a/drivers/acpi/fan_attr.c +++ b/drivers/acpi/fan_attr.c @@ -55,7 +55,7 @@ static ssize_t show_fan_speed(struct device *dev, struct device_attribute *attr, struct acpi_fan_fst fst; int status; - status = acpi_fan_get_fst(acpi_dev, &fst); + status = acpi_fan_get_fst(acpi_dev->handle, &fst); if (status) return status; diff --git a/drivers/acpi/fan_core.c b/drivers/acpi/fan_core.c index 04ff608f2ff0..46e7fe7a506d 100644 --- a/drivers/acpi/fan_core.c +++ b/drivers/acpi/fan_core.c @@ -44,25 +44,30 @@ static int fan_get_max_state(struct thermal_cooling_device *cdev, unsigned long return 0; } -int acpi_fan_get_fst(struct acpi_device *device, struct acpi_fan_fst *fst) +int acpi_fan_get_fst(acpi_handle handle, struct acpi_fan_fst *fst) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; acpi_status status; int ret = 0; - status = acpi_evaluate_object(device->handle, "_FST", NULL, &buffer); - if (ACPI_FAILURE(status)) { - dev_err(&device->dev, "Get fan state failed\n"); - return -ENODEV; - } + status = acpi_evaluate_object(handle, "_FST", NULL, &buffer); + if (ACPI_FAILURE(status)) + return -EIO; obj = buffer.pointer; - if (!obj || obj->type != ACPI_TYPE_PACKAGE || - obj->package.count != 3 || - obj->package.elements[1].type != ACPI_TYPE_INTEGER) { - dev_err(&device->dev, "Invalid _FST data\n"); - ret = -EINVAL; + if (!obj) + return -ENODATA; + + if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count != 3) { + ret = -EPROTO; + goto err; + } + + if (obj->package.elements[0].type != ACPI_TYPE_INTEGER || + obj->package.elements[1].type != ACPI_TYPE_INTEGER || + obj->package.elements[2].type != ACPI_TYPE_INTEGER) { + ret = -EPROTO; goto err; } @@ -81,7 +86,7 @@ static int fan_get_state_acpi4(struct acpi_device *device, unsigned long *state) struct acpi_fan_fst fst; int status, i; - status = acpi_fan_get_fst(device, &fst); + status = acpi_fan_get_fst(device->handle, &fst); if (status) return status; @@ -311,11 +316,16 @@ static int acpi_fan_probe(struct platform_device *pdev) struct acpi_device *device = ACPI_COMPANION(&pdev->dev); char *name; + if (!device) + return -ENODEV; + fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL); if (!fan) { dev_err(&device->dev, "No memory for fan\n"); return -ENOMEM; } + + fan->handle = device->handle; device->driver_data = fan; platform_set_drvdata(pdev, fan); @@ -337,7 +347,7 @@ static int acpi_fan_probe(struct platform_device *pdev) } if (fan->has_fst) { - result = devm_acpi_fan_create_hwmon(device); + result = devm_acpi_fan_create_hwmon(&pdev->dev); if (result) return result; diff --git a/drivers/acpi/fan_hwmon.c b/drivers/acpi/fan_hwmon.c index e8d90605106e..4b2c2007f2d7 100644 --- a/drivers/acpi/fan_hwmon.c +++ b/drivers/acpi/fan_hwmon.c @@ -93,13 +93,12 @@ static umode_t acpi_fan_hwmon_is_visible(const void *drvdata, enum hwmon_sensor_ static int acpi_fan_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { - struct acpi_device *adev = to_acpi_device(dev->parent); struct acpi_fan *fan = dev_get_drvdata(dev); struct acpi_fan_fps *fps; struct acpi_fan_fst fst; int ret; - ret = acpi_fan_get_fst(adev, &fst); + ret = acpi_fan_get_fst(fan->handle, &fst); if (ret < 0) return ret; @@ -167,12 +166,12 @@ static const struct hwmon_chip_info acpi_fan_hwmon_chip_info = { .info = acpi_fan_hwmon_info, }; -int devm_acpi_fan_create_hwmon(struct acpi_device *device) +int devm_acpi_fan_create_hwmon(struct device *dev) { - struct acpi_fan *fan = acpi_driver_data(device); + struct acpi_fan *fan = dev_get_drvdata(dev); struct device *hdev; - hdev = devm_hwmon_device_register_with_info(&device->dev, "acpi_fan", fan, - &acpi_fan_hwmon_chip_info, NULL); + hdev = devm_hwmon_device_register_with_info(dev, "acpi_fan", fan, &acpi_fan_hwmon_chip_info, + NULL); return PTR_ERR_OR_ZERO(hdev); } diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 5a36d57289b4..11e4483685c9 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -874,10 +874,32 @@ static void hmat_register_target_devices(struct memory_target *target) } } -static void hmat_register_target(struct memory_target *target) +static void hmat_hotplug_target(struct memory_target *target) { int nid = pxm_to_node(target->memory_pxm); + /* + * Skip offline nodes. This can happen when memory marked EFI_MEMORY_SP, + * "specific purpose", is applied to all the memory in a proximity + * domain leading to * the node being marked offline / unplugged, or if + * memory-only "hotplug" node is offline. + */ + if (nid == NUMA_NO_NODE || !node_online(nid)) + return; + + guard(mutex)(&target_lock); + if (target->registered) + return; + + hmat_register_target_initiators(target); + hmat_register_target_cache(target); + hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); + hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); + target->registered = true; +} + +static void hmat_register_target(struct memory_target *target) +{ /* * Devices may belong to either an offline or online * node, so unconditionally add them. @@ -895,25 +917,7 @@ static void hmat_register_target(struct memory_target *target) } mutex_unlock(&target_lock); - /* - * Skip offline nodes. This can happen when memory - * marked EFI_MEMORY_SP, "specific purpose", is applied - * to all the memory in a proximity domain leading to - * the node being marked offline / unplugged, or if - * memory-only "hotplug" node is offline. - */ - if (nid == NUMA_NO_NODE || !node_online(nid)) - return; - - mutex_lock(&target_lock); - if (!target->registered) { - hmat_register_target_initiators(target); - hmat_register_target_cache(target); - hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); - hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); - target->registered = true; - } - mutex_unlock(&target_lock); + hmat_hotplug_target(target); } static void hmat_register_targets(void) @@ -939,7 +943,7 @@ static int hmat_callback(struct notifier_block *self, if (!target) return NOTIFY_OK; - hmat_register_target(target); + hmat_hotplug_target(target); return NOTIFY_OK; } diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 53816dfab645..aa87ee1583a4 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -237,7 +237,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) struct acpi_srat_generic_affinity *p = (struct acpi_srat_generic_affinity *)header; - if (p->device_handle_type == 0) { + if (p->device_handle_type == 1) { /* * For pci devices this may be the only place they * are assigned a proximity domain diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 1b997a5497e7..43d5e457814e 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1107,7 +1107,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, size_t num_args, struct fwnode_reference_args *args) { - return acpi_fwnode_get_reference_args(fwnode, propname, NULL, index, num_args, args); + return acpi_fwnode_get_reference_args(fwnode, propname, NULL, num_args, index, args); } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); diff --git a/drivers/acpi/riscv/rimt.c b/drivers/acpi/riscv/rimt.c index 683fcfe35c31..7f423405e5ef 100644 --- a/drivers/acpi/riscv/rimt.c +++ b/drivers/acpi/riscv/rimt.c @@ -61,30 +61,6 @@ static int rimt_set_fwnode(struct acpi_rimt_node *rimt_node, return 0; } -/** - * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node - * - * @node: RIMT table node to be looked-up - * - * Returns: fwnode_handle pointer on success, NULL on failure - */ -static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node) -{ - struct fwnode_handle *fwnode = NULL; - struct rimt_fwnode *curr; - - spin_lock(&rimt_fwnode_lock); - list_for_each_entry(curr, &rimt_fwnode_list, list) { - if (curr->rimt_node == node) { - fwnode = curr->fwnode; - break; - } - } - spin_unlock(&rimt_fwnode_lock); - - return fwnode; -} - static acpi_status rimt_match_node_callback(struct acpi_rimt_node *node, void *context) { @@ -202,6 +178,67 @@ static struct acpi_rimt_node *rimt_scan_node(enum acpi_rimt_node_type type, return NULL; } +/* + * RISC-V supports IOMMU as a PCI device or a platform device. + * When it is a platform device, there should be a namespace device as + * well along with RIMT. To create the link between RIMT information and + * the platform device, the IOMMU driver should register itself with the + * RIMT module. This is true for PCI based IOMMU as well. + */ +int rimt_iommu_register(struct device *dev) +{ + struct fwnode_handle *rimt_fwnode; + struct acpi_rimt_node *node; + + node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev); + if (!node) { + pr_err("Could not find IOMMU node in RIMT\n"); + return -ENODEV; + } + + if (dev_is_pci(dev)) { + rimt_fwnode = acpi_alloc_fwnode_static(); + if (!rimt_fwnode) + return -ENOMEM; + + rimt_fwnode->dev = dev; + if (!dev->fwnode) + dev->fwnode = rimt_fwnode; + + rimt_set_fwnode(node, rimt_fwnode); + } else { + rimt_set_fwnode(node, dev->fwnode); + } + + return 0; +} + +#ifdef CONFIG_IOMMU_API + +/** + * rimt_get_fwnode() - Retrieve fwnode associated with an RIMT node + * + * @node: RIMT table node to be looked-up + * + * Returns: fwnode_handle pointer on success, NULL on failure + */ +static struct fwnode_handle *rimt_get_fwnode(struct acpi_rimt_node *node) +{ + struct fwnode_handle *fwnode = NULL; + struct rimt_fwnode *curr; + + spin_lock(&rimt_fwnode_lock); + list_for_each_entry(curr, &rimt_fwnode_list, list) { + if (curr->rimt_node == node) { + fwnode = curr->fwnode; + break; + } + } + spin_unlock(&rimt_fwnode_lock); + + return fwnode; +} + static bool rimt_pcie_rc_supports_ats(struct acpi_rimt_node *node) { struct acpi_rimt_pcie_rc *pci_rc; @@ -290,43 +327,6 @@ static struct acpi_rimt_node *rimt_node_get_id(struct acpi_rimt_node *node, return NULL; } -/* - * RISC-V supports IOMMU as a PCI device or a platform device. - * When it is a platform device, there should be a namespace device as - * well along with RIMT. To create the link between RIMT information and - * the platform device, the IOMMU driver should register itself with the - * RIMT module. This is true for PCI based IOMMU as well. - */ -int rimt_iommu_register(struct device *dev) -{ - struct fwnode_handle *rimt_fwnode; - struct acpi_rimt_node *node; - - node = rimt_scan_node(ACPI_RIMT_NODE_TYPE_IOMMU, dev); - if (!node) { - pr_err("Could not find IOMMU node in RIMT\n"); - return -ENODEV; - } - - if (dev_is_pci(dev)) { - rimt_fwnode = acpi_alloc_fwnode_static(); - if (!rimt_fwnode) - return -ENOMEM; - - rimt_fwnode->dev = dev; - if (!dev->fwnode) - dev->fwnode = rimt_fwnode; - - rimt_set_fwnode(node, rimt_fwnode); - } else { - rimt_set_fwnode(node, dev->fwnode); - } - - return 0; -} - -#ifdef CONFIG_IOMMU_API - static struct acpi_rimt_node *rimt_node_map_id(struct acpi_rimt_node *node, u32 id_in, u32 *id_out, u8 type_mask) diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index a3f95a3fffde..d3edc3bcbf01 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -487,7 +487,7 @@ static int acpi_battery_read(struct acpi_battery *battery) if (result) return result; - battery->present = state & (1 << battery->id); + battery->present = !!(state & (1 << battery->id)); if (!battery->present) return 0; diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index d4d52d5e9016..73cb933fdc89 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -155,7 +155,7 @@ int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console) * Baud Rate field. If this field is zero or not present, Configured * Baud Rate is used. */ - if (table->precise_baudrate) + if (table->header.revision >= 4 && table->precise_baudrate) baud_rate = table->precise_baudrate; else switch (table->baud_rate) { case 0: diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8c99ceaa303b..a3a1b5c33ba3 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -851,17 +851,8 @@ static int binder_inc_node_nilocked(struct binder_node *node, int strong, } else { if (!internal) node->local_weak_refs++; - if (!node->has_weak_ref && list_empty(&node->work.entry)) { - if (target_list == NULL) { - pr_err("invalid inc weak node for %d\n", - node->debug_id); - return -EINVAL; - } - /* - * See comment above - */ + if (!node->has_weak_ref && target_list && list_empty(&node->work.entry)) binder_enqueue_work_ilocked(&node->work, target_list); - } } return 0; } @@ -2418,10 +2409,10 @@ static int binder_translate_fd(u32 fd, binder_size_t fd_offset, /** * struct binder_ptr_fixup - data to be fixed-up in target buffer - * @offset offset in target buffer to fixup - * @skip_size bytes to skip in copy (fixup will be written later) - * @fixup_data data to write at fixup offset - * @node list node + * @offset: offset in target buffer to fixup + * @skip_size: bytes to skip in copy (fixup will be written later) + * @fixup_data: data to write at fixup offset + * @node: list node * * This is used for the pointer fixup list (pf) which is created and consumed * during binder_transaction() and is only accessed locally. No @@ -2438,10 +2429,10 @@ struct binder_ptr_fixup { /** * struct binder_sg_copy - scatter-gather data to be copied - * @offset offset in target buffer - * @sender_uaddr user address in source buffer - * @length bytes to copy - * @node list node + * @offset: offset in target buffer + * @sender_uaddr: user address in source buffer + * @length: bytes to copy + * @node: list node * * This is used for the sg copy list (sgc) which is created and consumed * during binder_transaction() and is only accessed locally. No @@ -4063,14 +4054,15 @@ binder_freeze_notification_done(struct binder_proc *proc, /** * binder_free_buf() - free the specified buffer - * @proc: binder proc that owns buffer - * @buffer: buffer to be freed - * @is_failure: failed to send transaction + * @proc: binder proc that owns buffer + * @thread: binder thread performing the buffer release + * @buffer: buffer to be freed + * @is_failure: failed to send transaction * - * If buffer for an async transaction, enqueue the next async + * If the buffer is for an async transaction, enqueue the next async * transaction from the node. * - * Cleanup buffer and free it. + * Cleanup the buffer and free it. */ static void binder_free_buf(struct binder_proc *proc, diff --git a/drivers/android/binder/freeze.rs b/drivers/android/binder/freeze.rs index e68c3c8bc55a..220de35ae85a 100644 --- a/drivers/android/binder/freeze.rs +++ b/drivers/android/binder/freeze.rs @@ -106,13 +106,22 @@ fn do_work( return Ok(true); } if freeze.is_clearing { - _removed_listener = freeze_entry.remove_node(); + kernel::warn_on!(freeze.num_cleared_duplicates != 0); + if freeze.num_pending_duplicates > 0 { + // The primary freeze listener was deleted, so convert a pending duplicate back + // into the primary one. + freeze.num_pending_duplicates -= 1; + freeze.is_pending = true; + freeze.is_clearing = true; + } else { + _removed_listener = freeze_entry.remove_node(); + } drop(node_refs); writer.write_code(BR_CLEAR_FREEZE_NOTIFICATION_DONE)?; writer.write_payload(&self.cookie.0)?; Ok(true) } else { - let is_frozen = freeze.node.owner.inner.lock().is_frozen; + let is_frozen = freeze.node.owner.inner.lock().is_frozen.is_fully_frozen(); if freeze.last_is_frozen == Some(is_frozen) { return Ok(true); } @@ -245,8 +254,9 @@ pub(crate) fn freeze_notif_done(self: &Arc, reader: &mut UserSliceReader) ); return Err(EINVAL); } - if freeze.is_clearing { - // Immediately send another FreezeMessage for BR_CLEAR_FREEZE_NOTIFICATION_DONE. + let is_frozen = freeze.node.owner.inner.lock().is_frozen.is_fully_frozen(); + if freeze.is_clearing || freeze.last_is_frozen != Some(is_frozen) { + // Immediately send another FreezeMessage. clear_msg = Some(FreezeMessage::init(alloc, cookie)); } freeze.is_pending = false; diff --git a/drivers/android/binder/node.rs b/drivers/android/binder/node.rs index ade895ef791e..08d362deaf61 100644 --- a/drivers/android/binder/node.rs +++ b/drivers/android/binder/node.rs @@ -687,7 +687,7 @@ pub(crate) fn remove_freeze_listener(&self, p: &Arc) { ); } if inner.freeze_list.is_empty() { - _unused_capacity = mem::replace(&mut inner.freeze_list, KVVec::new()); + _unused_capacity = mem::take(&mut inner.freeze_list); } } diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs index f13a747e784c..7607353a5e92 100644 --- a/drivers/android/binder/process.rs +++ b/drivers/android/binder/process.rs @@ -72,6 +72,33 @@ fn new(address: usize, size: usize) -> Self { const PROC_DEFER_FLUSH: u8 = 1; const PROC_DEFER_RELEASE: u8 = 2; +#[derive(Copy, Clone)] +pub(crate) enum IsFrozen { + Yes, + No, + InProgress, +} + +impl IsFrozen { + /// Whether incoming transactions should be rejected due to freeze. + pub(crate) fn is_frozen(self) -> bool { + match self { + IsFrozen::Yes => true, + IsFrozen::No => false, + IsFrozen::InProgress => true, + } + } + + /// Whether freeze notifications consider this process frozen. + pub(crate) fn is_fully_frozen(self) -> bool { + match self { + IsFrozen::Yes => true, + IsFrozen::No => false, + IsFrozen::InProgress => false, + } + } +} + /// The fields of `Process` protected by the spinlock. pub(crate) struct ProcessInner { is_manager: bool, @@ -98,7 +125,7 @@ pub(crate) struct ProcessInner { /// are woken up. outstanding_txns: u32, /// Process is frozen and unable to service binder transactions. - pub(crate) is_frozen: bool, + pub(crate) is_frozen: IsFrozen, /// Process received sync transactions since last frozen. pub(crate) sync_recv: bool, /// Process received async transactions since last frozen. @@ -124,7 +151,7 @@ fn new() -> Self { started_thread_count: 0, defer_work: 0, outstanding_txns: 0, - is_frozen: false, + is_frozen: IsFrozen::No, sync_recv: false, async_recv: false, binderfs_file: None, @@ -1260,7 +1287,7 @@ fn deferred_release(self: Arc) { let is_manager = { let mut inner = self.inner.lock(); inner.is_dead = true; - inner.is_frozen = false; + inner.is_frozen = IsFrozen::No; inner.sync_recv = false; inner.async_recv = false; inner.is_manager @@ -1346,10 +1373,6 @@ fn deferred_release(self: Arc) { .alloc .take_for_each(|offset, size, debug_id, odata| { let ptr = offset + address; - pr_warn!( - "{}: removing orphan mapping {offset}:{size}\n", - self.pid_in_current_ns() - ); let mut alloc = Allocation::new(self.clone(), debug_id, offset, size, ptr, false); if let Some(data) = odata { @@ -1371,7 +1394,7 @@ pub(crate) fn drop_outstanding_txn(&self) { return; } inner.outstanding_txns -= 1; - inner.is_frozen && inner.outstanding_txns == 0 + inner.is_frozen.is_frozen() && inner.outstanding_txns == 0 }; if wake { @@ -1385,7 +1408,7 @@ pub(crate) fn ioctl_freeze(&self, info: &BinderFreezeInfo) -> Result { let mut inner = self.inner.lock(); inner.sync_recv = false; inner.async_recv = false; - inner.is_frozen = false; + inner.is_frozen = IsFrozen::No; drop(inner); msgs.send_messages(); return Ok(()); @@ -1394,7 +1417,7 @@ pub(crate) fn ioctl_freeze(&self, info: &BinderFreezeInfo) -> Result { let mut inner = self.inner.lock(); inner.sync_recv = false; inner.async_recv = false; - inner.is_frozen = true; + inner.is_frozen = IsFrozen::InProgress; if info.timeout_ms > 0 { let mut jiffies = kernel::time::msecs_to_jiffies(info.timeout_ms); @@ -1408,7 +1431,7 @@ pub(crate) fn ioctl_freeze(&self, info: &BinderFreezeInfo) -> Result { .wait_interruptible_timeout(&mut inner, jiffies) { CondVarTimeoutResult::Signal { .. } => { - inner.is_frozen = false; + inner.is_frozen = IsFrozen::No; return Err(ERESTARTSYS); } CondVarTimeoutResult::Woken { jiffies: remaining } => { @@ -1422,17 +1445,18 @@ pub(crate) fn ioctl_freeze(&self, info: &BinderFreezeInfo) -> Result { } if inner.txns_pending_locked() { - inner.is_frozen = false; + inner.is_frozen = IsFrozen::No; Err(EAGAIN) } else { drop(inner); match self.prepare_freeze_messages() { Ok(batch) => { + self.inner.lock().is_frozen = IsFrozen::Yes; batch.send_messages(); Ok(()) } Err(kernel::alloc::AllocError) => { - self.inner.lock().is_frozen = false; + self.inner.lock().is_frozen = IsFrozen::No; Err(ENOMEM) } } diff --git a/drivers/android/binder/transaction.rs b/drivers/android/binder/transaction.rs index 02512175d622..4bd3c0e417eb 100644 --- a/drivers/android/binder/transaction.rs +++ b/drivers/android/binder/transaction.rs @@ -249,7 +249,7 @@ pub(crate) fn submit(self: DLArc) -> BinderResult { if oneway { if let Some(target_node) = self.target_node.clone() { - if process_inner.is_frozen { + if process_inner.is_frozen.is_frozen() { process_inner.async_recv = true; if self.flags & TF_UPDATE_TXN != 0 { if let Some(t_outdated) = @@ -270,7 +270,7 @@ pub(crate) fn submit(self: DLArc) -> BinderResult { } } - if process_inner.is_frozen { + if process_inner.is_frozen.is_frozen() { return Err(BinderError::new_frozen_oneway()); } else { return Ok(()); @@ -280,7 +280,7 @@ pub(crate) fn submit(self: DLArc) -> BinderResult { } } - if process_inner.is_frozen { + if process_inner.is_frozen.is_frozen() { process_inner.sync_recv = true; return Err(BinderError::new_frozen()); } diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1037169abb45..e1eff05bea4a 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -292,7 +292,7 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) * frequency (by keeping the initial capacity_freq_ref value). */ cpu_clk = of_clk_get(cpu_node, 0); - if (!PTR_ERR_OR_ZERO(cpu_clk)) { + if (!IS_ERR_OR_NULL(cpu_clk)) { per_cpu(capacity_freq_ref, cpu) = clk_get_rate(cpu_clk) / HZ_PER_KHZ; clk_put(cpu_clk); diff --git a/drivers/base/core.c b/drivers/base/core.c index 3c533dab8fa5..f69dc9c85954 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1784,7 +1784,7 @@ static int fw_devlink_dev_sync_state(struct device *dev, void *data) return 0; if (fw_devlink_sync_state == FW_DEVLINK_SYNC_STATE_STRICT) { - dev_warn(sup, "sync_state() pending due to %s\n", + dev_info(sup, "sync_state() pending due to %s\n", dev_name(link->consumer)); return 0; } diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 37faf6156d7c..55bdc7f5e59d 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -23,50 +23,46 @@ struct devcd_entry { void *data; size_t datalen; /* - * Here, mutex is required to serialize the calls to del_wk work between - * user/kernel space which happens when devcd is added with device_add() - * and that sends uevent to user space. User space reads the uevents, - * and calls to devcd_data_write() which try to modify the work which is - * not even initialized/queued from devcoredump. + * There are 2 races for which mutex is required. * + * The first race is between device creation and userspace writing to + * schedule immediately destruction. * + * This race is handled by arming the timer before device creation, but + * when device creation fails the timer still exists. * - * cpu0(X) cpu1(Y) + * To solve this, hold the mutex during device_add(), and set + * init_completed on success before releasing the mutex. * - * dev_coredump() uevent sent to user space - * device_add() ======================> user space process Y reads the - * uevents writes to devcd fd - * which results into writes to + * That way the timer will never fire until device_add() is called, + * it will do nothing if init_completed is not set. The timer is also + * cancelled in that case. * - * devcd_data_write() - * mod_delayed_work() - * try_to_grab_pending() - * timer_delete() - * debug_assert_init() - * INIT_DELAYED_WORK() - * schedule_delayed_work() - * - * - * Also, mutex alone would not be enough to avoid scheduling of - * del_wk work after it get flush from a call to devcd_free() - * mentioned as below. - * - * disabled_store() - * devcd_free() - * mutex_lock() devcd_data_write() - * flush_delayed_work() - * mutex_unlock() - * mutex_lock() - * mod_delayed_work() - * mutex_unlock() - * So, delete_work flag is required. + * The second race involves multiple parallel invocations of devcd_free(), + * add a deleted flag so only 1 can call the destructor. */ struct mutex mutex; - bool delete_work; + bool init_completed, deleted; struct module *owner; ssize_t (*read)(char *buffer, loff_t offset, size_t count, void *data, size_t datalen); void (*free)(void *data); + /* + * If nothing interferes and device_add() was returns success, + * del_wk will destroy the device after the timer fires. + * + * Multiple userspace processes can interfere in the working of the timer: + * - Writing to the coredump will reschedule the timer to run immediately, + * if still armed. + * + * This is handled by using "if (cancel_delayed_work()) { + * schedule_delayed_work() }", to prevent re-arming after having + * been previously fired. + * - Writing to /sys/class/devcoredump/disabled will destroy the + * coredump synchronously. + * This is handled by using disable_delayed_work_sync(), and then + * checking if deleted flag is set with &devcd->mutex held. + */ struct delayed_work del_wk; struct device *failing_dev; }; @@ -95,14 +91,27 @@ static void devcd_dev_release(struct device *dev) kfree(devcd); } +static void __devcd_del(struct devcd_entry *devcd) +{ + devcd->deleted = true; + device_del(&devcd->devcd_dev); + put_device(&devcd->devcd_dev); +} + static void devcd_del(struct work_struct *wk) { struct devcd_entry *devcd; + bool init_completed; devcd = container_of(wk, struct devcd_entry, del_wk.work); - device_del(&devcd->devcd_dev); - put_device(&devcd->devcd_dev); + /* devcd->mutex serializes against dev_coredumpm_timeout */ + mutex_lock(&devcd->mutex); + init_completed = devcd->init_completed; + mutex_unlock(&devcd->mutex); + + if (init_completed) + __devcd_del(devcd); } static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj, @@ -122,12 +131,12 @@ static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct devcd_entry *devcd = dev_to_devcd(dev); - mutex_lock(&devcd->mutex); - if (!devcd->delete_work) { - devcd->delete_work = true; - mod_delayed_work(system_wq, &devcd->del_wk, 0); - } - mutex_unlock(&devcd->mutex); + /* + * Although it's tempting to use mod_delayed work here, + * that will cause a reschedule if the timer already fired. + */ + if (cancel_delayed_work(&devcd->del_wk)) + schedule_delayed_work(&devcd->del_wk, 0); return count; } @@ -151,11 +160,21 @@ static int devcd_free(struct device *dev, void *data) { struct devcd_entry *devcd = dev_to_devcd(dev); + /* + * To prevent a race with devcd_data_write(), disable work and + * complete manually instead. + * + * We cannot rely on the return value of + * disable_delayed_work_sync() here, because it might be in the + * middle of a cancel_delayed_work + schedule_delayed_work pair. + * + * devcd->mutex here guards against multiple parallel invocations + * of devcd_free(). + */ + disable_delayed_work_sync(&devcd->del_wk); mutex_lock(&devcd->mutex); - if (!devcd->delete_work) - devcd->delete_work = true; - - flush_delayed_work(&devcd->del_wk); + if (!devcd->deleted) + __devcd_del(devcd); mutex_unlock(&devcd->mutex); return 0; } @@ -179,12 +198,10 @@ static ssize_t disabled_show(const struct class *class, const struct class_attri * put_device() <- last reference * error = fn(dev, data) devcd_dev_release() * devcd_free(dev, data) kfree(devcd) - * mutex_lock(&devcd->mutex); * * * In the above diagram, it looks like disabled_store() would be racing with parallelly - * running devcd_del() and result in memory abort while acquiring devcd->mutex which - * is called after kfree of devcd memory after dropping its last reference with + * running devcd_del() and result in memory abort after dropping its last reference with * put_device(). However, this will not happens as fn(dev, data) runs * with its own reference to device via klist_node so it is not its last reference. * so, above situation would not occur. @@ -374,7 +391,7 @@ void dev_coredumpm_timeout(struct device *dev, struct module *owner, devcd->read = read; devcd->free = free; devcd->failing_dev = get_device(dev); - devcd->delete_work = false; + devcd->deleted = false; mutex_init(&devcd->mutex); device_initialize(&devcd->devcd_dev); @@ -383,8 +400,14 @@ void dev_coredumpm_timeout(struct device *dev, struct module *owner, atomic_inc_return(&devcd_count)); devcd->devcd_dev.class = &devcd_class; - mutex_lock(&devcd->mutex); dev_set_uevent_suppress(&devcd->devcd_dev, true); + + /* devcd->mutex prevents devcd_del() completing until init finishes */ + mutex_lock(&devcd->mutex); + devcd->init_completed = false; + INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); + schedule_delayed_work(&devcd->del_wk, timeout); + if (device_add(&devcd->devcd_dev)) goto put_device; @@ -401,13 +424,20 @@ void dev_coredumpm_timeout(struct device *dev, struct module *owner, dev_set_uevent_suppress(&devcd->devcd_dev, false); kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); - INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); - schedule_delayed_work(&devcd->del_wk, timeout); + + /* + * Safe to run devcd_del() now that we are done with devcd_dev. + * Alternatively we could have taken a ref on devcd_dev before + * dropping the lock. + */ + devcd->init_completed = true; mutex_unlock(&devcd->mutex); return; put_device: - put_device(&devcd->devcd_dev); mutex_unlock(&devcd->mutex); + cancel_delayed_work_sync(&devcd->del_wk); + put_device(&devcd->devcd_dev); + put_module: module_put(owner); free: diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c index 54eb7d227cf4..e523fae73004 100644 --- a/drivers/base/regmap/regmap-slimbus.c +++ b/drivers/base/regmap/regmap-slimbus.c @@ -48,8 +48,7 @@ struct regmap *__regmap_init_slimbus(struct slim_device *slimbus, if (IS_ERR(bus)) return ERR_CAST(bus); - return __regmap_init(&slimbus->dev, bus, &slimbus->dev, config, - lock_key, lock_name); + return __regmap_init(&slimbus->dev, bus, slimbus, config, lock_key, lock_name); } EXPORT_SYMBOL_GPL(__regmap_init_slimbus); @@ -63,8 +62,7 @@ struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus, if (IS_ERR(bus)) return ERR_CAST(bus); - return __devm_regmap_init(&slimbus->dev, bus, &slimbus, config, - lock_key, lock_name); + return __devm_regmap_init(&slimbus->dev, bus, slimbus, config, lock_key, lock_name); } EXPORT_SYMBOL_GPL(__devm_regmap_init_slimbus); diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 6ecfc821cf83..72f045e6ed51 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -294,6 +294,8 @@ static int bcma_register_devices(struct bcma_bus *bus) int err; list_for_each_entry(core, &bus->cores, list) { + struct device_node *np; + /* We support that core ourselves */ switch (core->id.id) { case BCMA_CORE_4706_CHIPCOMMON: @@ -311,6 +313,10 @@ static int bcma_register_devices(struct bcma_bus *bus) if (bcma_is_core_needed_early(core->id.id)) continue; + np = core->dev.of_node; + if (np && !of_device_is_available(np)) + continue; + /* Only first GMAC core on BCM4706 is connected and working */ if (core->id.id == BCMA_CORE_4706_MAC_GBIT && core->core_unit > 0) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 1188f32a5e5e..a853c65ac65d 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -52,6 +52,7 @@ static DEFINE_IDR(nbd_index_idr); static DEFINE_MUTEX(nbd_index_mutex); static struct workqueue_struct *nbd_del_wq; +static struct cred *nbd_cred; static int nbd_total_devices = 0; struct nbd_sock { @@ -554,6 +555,7 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, int result; struct msghdr msg = {} ; unsigned int noreclaim_flag; + const struct cred *old_cred; if (unlikely(!sock)) { dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -562,6 +564,8 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, return -EINVAL; } + old_cred = override_creds(nbd_cred); + msg.msg_iter = *iter; noreclaim_flag = memalloc_noreclaim_save(); @@ -586,6 +590,8 @@ static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, memalloc_noreclaim_restore(noreclaim_flag); + revert_creds(old_cred); + return result; } @@ -2677,7 +2683,15 @@ static int __init nbd_init(void) return -ENOMEM; } + nbd_cred = prepare_kernel_cred(&init_task); + if (!nbd_cred) { + destroy_workqueue(nbd_del_wq); + unregister_blkdev(NBD_MAJOR, "nbd"); + return -ENOMEM; + } + if (genl_register_family(&nbd_genl_family)) { + put_cred(nbd_cred); destroy_workqueue(nbd_del_wq); unregister_blkdev(NBD_MAJOR, "nbd"); return -EINVAL; @@ -2732,6 +2746,7 @@ static void __exit nbd_cleanup(void) /* Also wait for nbd_dev_remove_work() completes */ destroy_workqueue(nbd_del_wq); + put_cred(nbd_cred); idr_destroy(&nbd_index_idr); unregister_blkdev(NBD_MAJOR, "nbd"); } diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index f982027e8c85..0ee55f889cfd 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1949,6 +1949,7 @@ static int null_add_dev(struct nullb_device *dev) .logical_block_size = dev->blocksize, .physical_block_size = dev->blocksize, .max_hw_sectors = dev->max_sectors, + .dma_alignment = dev->blocksize - 1, }; struct nullb *nullb; diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c index b7ba667a3d09..e305d04aac9d 100644 --- a/drivers/bluetooth/bpa10x.c +++ b/drivers/bluetooth/bpa10x.c @@ -41,6 +41,7 @@ struct bpa10x_data { struct usb_anchor rx_anchor; struct sk_buff *rx_skb[2]; + struct hci_uart hu; }; static void bpa10x_tx_complete(struct urb *urb) @@ -96,7 +97,7 @@ static void bpa10x_rx_complete(struct urb *urb) if (urb->status == 0) { bool idx = usb_pipebulk(urb->pipe); - data->rx_skb[idx] = h4_recv_buf(hdev, data->rx_skb[idx], + data->rx_skb[idx] = h4_recv_buf(&data->hu, data->rx_skb[idx], urb->transfer_buffer, urb->actual_length, bpa10x_recv_pkts, @@ -388,6 +389,7 @@ static int bpa10x_probe(struct usb_interface *intf, hci_set_drvdata(hdev, data); data->hdev = hdev; + data->hu.hdev = hdev; SET_HCIDEV_DEV(hdev, &intf->dev); diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 6d3963bd56a9..a075d8ec4677 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1467,11 +1467,6 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id) if (intr_hw & BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP1) btintel_pcie_msix_gp1_handler(data); - /* This interrupt is triggered by the firmware after updating - * boot_stage register and image_response register - */ - if (intr_hw & BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0) - btintel_pcie_msix_gp0_handler(data); /* For TX */ if (intr_fh & BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0) { @@ -1487,6 +1482,12 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id) btintel_pcie_msix_tx_handle(data); } + /* This interrupt is triggered by the firmware after updating + * boot_stage register and image_response register + */ + if (intr_hw & BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0) + btintel_pcie_msix_gp0_handler(data); + /* * Before sending the interrupt the HW disables it to prevent a nested * interrupt. This is done by writing 1 to the corresponding bit in diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 50abefba6d04..62db31bd6592 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1270,6 +1270,12 @@ static void btmtksdio_reset(struct hci_dev *hdev) sdio_claim_host(bdev->func); + /* set drv_pmctrl if BT is closed before doing reset */ + if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state)) { + sdio_enable_func(bdev->func); + btmtksdio_drv_pmctrl(bdev); + } + sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, NULL); skb_queue_purge(&bdev->txq); cancel_work_sync(&bdev->txrx_work); @@ -1285,6 +1291,12 @@ static void btmtksdio_reset(struct hci_dev *hdev) goto err; } + /* set fw_pmctrl back if BT is closed after doing reset */ + if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state)) { + btmtksdio_fw_pmctrl(bdev); + sdio_disable_func(bdev->func); + } + clear_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state); err: sdio_release_host(bdev->func); diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index d9b90ea2ad38..27aa48ff3ac2 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -79,6 +79,7 @@ struct btmtkuart_dev { u16 stp_dlen; const struct btmtkuart_data *data; + struct hci_uart hu; }; #define btmtkuart_is_standalone(bdev) \ @@ -368,7 +369,7 @@ static void btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count) sz_left -= adv; p_left += adv; - bdev->rx_skb = h4_recv_buf(bdev->hdev, bdev->rx_skb, p_h4, + bdev->rx_skb = h4_recv_buf(&bdev->hu, bdev->rx_skb, p_h4, sz_h4, mtk_recv_pkts, ARRAY_SIZE(mtk_recv_pkts)); if (IS_ERR(bdev->rx_skb)) { @@ -858,6 +859,7 @@ static int btmtkuart_probe(struct serdev_device *serdev) } bdev->hdev = hdev; + bdev->hu.hdev = hdev; hdev->bus = HCI_UART; hci_set_drvdata(hdev, bdev); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index d5153fed0518..3b1e9224e965 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -212,6 +212,7 @@ struct btnxpuart_dev { struct ps_data psdata; struct btnxpuart_data *nxp_data; struct reset_control *pdn; + struct hci_uart hu; }; #define NXP_V1_FW_REQ_PKT 0xa5 @@ -1756,7 +1757,7 @@ static size_t btnxpuart_receive_buf(struct serdev_device *serdev, ps_start_timer(nxpdev); - nxpdev->rx_skb = h4_recv_buf(nxpdev->hdev, nxpdev->rx_skb, data, count, + nxpdev->rx_skb = h4_recv_buf(&nxpdev->hu, nxpdev->rx_skb, data, count, nxp_recv_pkts, ARRAY_SIZE(nxp_recv_pkts)); if (IS_ERR(nxpdev->rx_skb)) { int err = PTR_ERR(nxpdev->rx_skb); @@ -1875,6 +1876,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev) reset_control_deassert(nxpdev->pdn); nxpdev->hdev = hdev; + nxpdev->hu.hdev = hdev; hdev->bus = HCI_UART; hci_set_drvdata(hdev, nxpdev); diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 6abd962502e3..52794db2739b 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -50,7 +50,7 @@ #define RTL_CHIP_SUBVER (&(struct rtl_vendor_cmd) {{0x10, 0x38, 0x04, 0x28, 0x80}}) #define RTL_CHIP_REV (&(struct rtl_vendor_cmd) {{0x10, 0x3A, 0x04, 0x28, 0x80}}) -#define RTL_SEC_PROJ (&(struct rtl_vendor_cmd) {{0x10, 0xA4, 0x0D, 0x00, 0xb0}}) +#define RTL_SEC_PROJ (&(struct rtl_vendor_cmd) {{0x10, 0xA4, 0xAD, 0x00, 0xb0}}) #define RTL_PATCH_SNIPPETS 0x01 #define RTL_PATCH_DUMMY_HEADER 0x02 @@ -534,7 +534,6 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, { struct rtl_epatch_header_v2 *hdr; int rc; - u8 reg_val[2]; u8 key_id; u32 num_sections; struct rtl_section *section; @@ -549,14 +548,7 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, .len = btrtl_dev->fw_len - 7, /* Cut the tail */ }; - rc = btrtl_vendor_read_reg16(hdev, RTL_SEC_PROJ, reg_val); - if (rc < 0) - return -EIO; - key_id = reg_val[0]; - - rtl_dev_dbg(hdev, "%s: key id %u", __func__, key_id); - - btrtl_dev->key_id = key_id; + key_id = btrtl_dev->key_id; hdr = rtl_iov_pull_data(&iov, sizeof(*hdr)); if (!hdr) @@ -625,8 +617,10 @@ static int rtlbt_parse_firmware_v2(struct hci_dev *hdev, len += entry->len; } - if (!len) + if (!len) { + kvfree(ptr); return -EPERM; + } *_buf = ptr; return len; @@ -1068,6 +1062,8 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, u16 hci_rev, lmp_subver; u8 hci_ver, lmp_ver, chip_type = 0; int ret; + int rc; + u8 key_id; u8 reg_val[2]; btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL); @@ -1178,6 +1174,14 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, goto err_free; } + rc = btrtl_vendor_read_reg16(hdev, RTL_SEC_PROJ, reg_val); + if (rc < 0) + goto err_free; + + key_id = reg_val[0]; + btrtl_dev->key_id = key_id; + rtl_dev_info(hdev, "%s: key id %u", __func__, key_id); + btrtl_dev->fw_len = -EIO; if (lmp_subver == RTL_ROM_LMP_8852A && hci_rev == 0x000c) { snprintf(fw_name, sizeof(fw_name), "%s_v2.bin", @@ -1200,7 +1204,7 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, goto err_free; } - if (btrtl_dev->ic_info->cfg_name) { + if (btrtl_dev->ic_info->cfg_name && !btrtl_dev->key_id) { if (postfix) { snprintf(cfg_name, sizeof(cfg_name), "%s-%s.bin", btrtl_dev->ic_info->cfg_name, postfix); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5e9ebf0c5312..a722446ec73d 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4361,6 +4361,11 @@ static void btusb_disconnect(struct usb_interface *intf) hci_unregister_dev(hdev); + if (data->oob_wake_irq) + device_init_wakeup(&data->udev->dev, false); + if (data->reset_gpio) + gpiod_put(data->reset_gpio); + if (intf == data->intf) { if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); @@ -4371,17 +4376,11 @@ static void btusb_disconnect(struct usb_interface *intf) usb_driver_release_interface(&btusb_driver, data->diag); usb_driver_release_interface(&btusb_driver, data->intf); } else if (intf == data->diag) { - usb_driver_release_interface(&btusb_driver, data->intf); if (data->isoc) usb_driver_release_interface(&btusb_driver, data->isoc); + usb_driver_release_interface(&btusb_driver, data->intf); } - if (data->oob_wake_irq) - device_init_wakeup(&data->udev->dev, false); - - if (data->reset_gpio) - gpiod_put(data->reset_gpio); - hci_free_dev(hdev); } diff --git a/drivers/bluetooth/hci_ag6xx.c b/drivers/bluetooth/hci_ag6xx.c index 2d40302409ff..94588676510f 100644 --- a/drivers/bluetooth/hci_ag6xx.c +++ b/drivers/bluetooth/hci_ag6xx.c @@ -105,7 +105,7 @@ static int ag6xx_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - ag6xx->rx_skb = h4_recv_buf(hu->hdev, ag6xx->rx_skb, data, count, + ag6xx->rx_skb = h4_recv_buf(hu, ag6xx->rx_skb, data, count, ag6xx_recv_pkts, ARRAY_SIZE(ag6xx_recv_pkts)); if (IS_ERR(ag6xx->rx_skb)) { diff --git a/drivers/bluetooth/hci_aml.c b/drivers/bluetooth/hci_aml.c index 707e90f80130..b1f32c5a8a3f 100644 --- a/drivers/bluetooth/hci_aml.c +++ b/drivers/bluetooth/hci_aml.c @@ -650,7 +650,7 @@ static int aml_recv(struct hci_uart *hu, const void *data, int count) struct aml_data *aml_data = hu->priv; int err; - aml_data->rx_skb = h4_recv_buf(hu->hdev, aml_data->rx_skb, data, count, + aml_data->rx_skb = h4_recv_buf(hu, aml_data->rx_skb, data, count, aml_recv_pkts, ARRAY_SIZE(aml_recv_pkts)); if (IS_ERR(aml_data->rx_skb)) { diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index dbfe34664633..8d2b5e7f0d6a 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -191,7 +191,7 @@ static int ath_recv(struct hci_uart *hu, const void *data, int count) { struct ath_struct *ath = hu->priv; - ath->rx_skb = h4_recv_buf(hu->hdev, ath->rx_skb, data, count, + ath->rx_skb = h4_recv_buf(hu, ath->rx_skb, data, count, ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts)); if (IS_ERR(ath->rx_skb)) { int err = PTR_ERR(ath->rx_skb); diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index f96617b85d87..fff845ed44e3 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -698,7 +698,7 @@ static int bcm_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - bcm->rx_skb = h4_recv_buf(hu->hdev, bcm->rx_skb, data, count, + bcm->rx_skb = h4_recv_buf(hu, bcm->rx_skb, data, count, bcm_recv_pkts, ARRAY_SIZE(bcm_recv_pkts)); if (IS_ERR(bcm->rx_skb)) { int err = PTR_ERR(bcm->rx_skb); diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c index 9070e31a68bf..ec017df8572c 100644 --- a/drivers/bluetooth/hci_h4.c +++ b/drivers/bluetooth/hci_h4.c @@ -112,7 +112,7 @@ static int h4_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - h4->rx_skb = h4_recv_buf(hu->hdev, h4->rx_skb, data, count, + h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count, h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts)); if (IS_ERR(h4->rx_skb)) { int err = PTR_ERR(h4->rx_skb); @@ -151,12 +151,12 @@ int __exit h4_deinit(void) return hci_uart_unregister_proto(&h4p); } -struct sk_buff *h4_recv_buf(struct hci_dev *hdev, struct sk_buff *skb, +struct sk_buff *h4_recv_buf(struct hci_uart *hu, struct sk_buff *skb, const unsigned char *buffer, int count, const struct h4_recv_pkt *pkts, int pkts_count) { - struct hci_uart *hu = hci_get_drvdata(hdev); u8 alignment = hu->alignment ? hu->alignment : 1; + struct hci_dev *hdev = hu->hdev; /* Check for error from previous call */ if (IS_ERR(skb)) diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 9b353c3d6442..1d6e09508f1f 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -972,7 +972,7 @@ static int intel_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - intel->rx_skb = h4_recv_buf(hu->hdev, intel->rx_skb, data, count, + intel->rx_skb = h4_recv_buf(hu, intel->rx_skb, data, count, intel_recv_pkts, ARRAY_SIZE(intel_recv_pkts)); if (IS_ERR(intel->rx_skb)) { diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 7044c86325ce..6f4e25917b86 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -429,7 +429,7 @@ static int ll_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - ll->rx_skb = h4_recv_buf(hu->hdev, ll->rx_skb, data, count, + ll->rx_skb = h4_recv_buf(hu, ll->rx_skb, data, count, ll_recv_pkts, ARRAY_SIZE(ll_recv_pkts)); if (IS_ERR(ll->rx_skb)) { int err = PTR_ERR(ll->rx_skb); diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index e08222395772..8767522ec4c6 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -264,9 +264,9 @@ static int mrvl_recv(struct hci_uart *hu, const void *data, int count) !test_bit(STATE_FW_LOADED, &mrvl->flags)) return count; - mrvl->rx_skb = h4_recv_buf(hu->hdev, mrvl->rx_skb, data, count, - mrvl_recv_pkts, - ARRAY_SIZE(mrvl_recv_pkts)); + mrvl->rx_skb = h4_recv_buf(hu, mrvl->rx_skb, data, count, + mrvl_recv_pkts, + ARRAY_SIZE(mrvl_recv_pkts)); if (IS_ERR(mrvl->rx_skb)) { int err = PTR_ERR(mrvl->rx_skb); bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err); diff --git a/drivers/bluetooth/hci_nokia.c b/drivers/bluetooth/hci_nokia.c index cd7575c20f65..1e65b541f8ad 100644 --- a/drivers/bluetooth/hci_nokia.c +++ b/drivers/bluetooth/hci_nokia.c @@ -624,8 +624,8 @@ static int nokia_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - btdev->rx_skb = h4_recv_buf(hu->hdev, btdev->rx_skb, data, count, - nokia_recv_pkts, ARRAY_SIZE(nokia_recv_pkts)); + btdev->rx_skb = h4_recv_buf(hu, btdev->rx_skb, data, count, + nokia_recv_pkts, ARRAY_SIZE(nokia_recv_pkts)); if (IS_ERR(btdev->rx_skb)) { err = PTR_ERR(btdev->rx_skb); dev_err(dev, "Frame reassembly failed (%d)", err); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 4cff4d9be313..888176b0faa9 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1277,7 +1277,7 @@ static int qca_recv(struct hci_uart *hu, const void *data, int count) if (!test_bit(HCI_UART_REGISTERED, &hu->flags)) return -EUNATCH; - qca->rx_skb = h4_recv_buf(hu->hdev, qca->rx_skb, data, count, + qca->rx_skb = h4_recv_buf(hu, qca->rx_skb, data, count, qca_recv_pkts, ARRAY_SIZE(qca_recv_pkts)); if (IS_ERR(qca->rx_skb)) { int err = PTR_ERR(qca->rx_skb); diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index cbbe79b241ce..48ac7ca9334e 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -162,7 +162,7 @@ struct h4_recv_pkt { int h4_init(void); int h4_deinit(void); -struct sk_buff *h4_recv_buf(struct hci_dev *hdev, struct sk_buff *skb, +struct sk_buff *h4_recv_buf(struct hci_uart *hu, struct sk_buff *skb, const unsigned char *buffer, int count, const struct h4_recv_pkt *pkts, int pkts_count); #endif diff --git a/drivers/comedi/comedi_buf.c b/drivers/comedi/comedi_buf.c index 002c0e76baff..c7c262a2d8ca 100644 --- a/drivers/comedi/comedi_buf.c +++ b/drivers/comedi/comedi_buf.c @@ -317,7 +317,7 @@ static unsigned int comedi_buf_munge(struct comedi_subdevice *s, unsigned int count = 0; const unsigned int num_sample_bytes = comedi_bytes_per_sample(s); - if (!s->munge || (async->cmd.flags & CMDF_RAWDATA)) { + if (!s->munge || (async->cmd.flags & CMDF_RAWDATA) || async->cmd.chanlist_len == 0) { async->munge_count += num_bytes; return num_bytes; } diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 298e92d8cc03..b44f0f7a5ba1 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1614,7 +1614,11 @@ static int amd_pstate_cpu_offline(struct cpufreq_policy *policy) * min_perf value across kexec reboots. If this CPU is just onlined normally after this, the * limits, epp and desired perf will get reset to the cached values in cpudata struct */ - return amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false); + return amd_pstate_update_perf(policy, perf.bios_min_perf, + FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached), + false); } static int amd_pstate_suspend(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 38897bb14a2c..492a10f1bdbf 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -603,9 +603,6 @@ static bool turbo_is_disabled(void) { u64 misc_en; - if (!cpu_feature_enabled(X86_FEATURE_IDA)) - return true; - rdmsrq(MSR_IA32_MISC_ENABLE, misc_en); return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); @@ -2106,7 +2103,8 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -2271,7 +2269,8 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) val |= (u64)1 << 32; return val; diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index a360bc4d20b7..19be6475d356 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -303,8 +304,8 @@ static int sbi_cpuidle_init_cpu(struct device *dev, int cpu) drv->states[0].exit_latency = 1; drv->states[0].target_residency = 1; drv->states[0].power_usage = UINT_MAX; - strcpy(drv->states[0].name, "WFI"); - strcpy(drv->states[0].desc, "RISC-V WFI"); + strscpy(drv->states[0].name, "WFI"); + strscpy(drv->states[0].desc, "RISC-V WFI"); /* * If no DT idle states are detected (ret == 0) let the driver diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 4d9aa5ce31f0..23239b0c04f9 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -188,20 +188,17 @@ static unsigned int get_typical_interval(struct menu_device *data) * * This can deal with workloads that have long pauses interspersed * with sporadic activity with a bunch of short pauses. + * + * However, if the number of remaining samples is too small to exclude + * any more outliers, allow the deepest available idle state to be + * selected because there are systems where the time spent by CPUs in + * deep idle states is correlated to the maximum frequency the CPUs + * can get to. On those systems, shallow idle states should be avoided + * unless there is a clear indication that the given CPU is most likley + * going to be woken up shortly. */ - if (divisor * 4 <= INTERVALS * 3) { - /* - * If there are sufficiently many data points still under - * consideration after the outliers have been eliminated, - * returning without a prediction would be a mistake because it - * is likely that the next interval will not exceed the current - * maximum, so return the latter in that case. - */ - if (divisor >= INTERVALS / 2) - return max; - + if (divisor * 4 <= INTERVALS * 3) return UINT_MAX; - } /* Update the thresholds for the next round. */ if (avg - min > max - avg) @@ -321,10 +318,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, /* * Use a physical idle state, not busy polling, unless a timer - * is going to trigger soon enough. + * is going to trigger soon enough or the exit latency of the + * idle state in question is greater than the predicted idle + * duration. */ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && - s->target_residency_ns <= data->next_timer_ns) { + s->target_residency_ns <= data->next_timer_ns && + s->exit_latency_ns <= predicted_ns) { predicted_ns = s->target_residency_ns; idx = i; break; diff --git a/drivers/crypto/aspeed/aspeed-acry.c b/drivers/crypto/aspeed/aspeed-acry.c index 8d1c79aaca07..5993bcba9716 100644 --- a/drivers/crypto/aspeed/aspeed-acry.c +++ b/drivers/crypto/aspeed/aspeed-acry.c @@ -787,7 +787,6 @@ static int aspeed_acry_probe(struct platform_device *pdev) err_engine_rsa_start: crypto_engine_exit(acry_dev->crypt_engine_rsa); clk_exit: - clk_disable_unprepare(acry_dev->clk); return rc; } @@ -799,7 +798,6 @@ static void aspeed_acry_remove(struct platform_device *pdev) aspeed_acry_unregister(acry_dev); crypto_engine_exit(acry_dev->crypt_engine_rsa); tasklet_kill(&acry_dev->done_task); - clk_disable_unprepare(acry_dev->clk); } MODULE_DEVICE_TABLE(of, aspeed_acry_of_matches); diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index a5b96adf2d1e..3b391a146635 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3871,10 +3871,12 @@ static ssize_t qm_get_qos_value(struct hisi_qm *qm, const char *buf, pdev = container_of(dev, struct pci_dev, dev); if (pci_physfn(pdev) != qm->pdev) { pci_err(qm->pdev, "the pdev input does not match the pf!\n"); + put_device(dev); return -EINVAL; } *fun_index = pdev->devfn; + put_device(dev); return 0; } diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index b06fee1978ba..41b64d871c5a 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -3702,6 +3702,7 @@ static int cxl_region_debugfs_poison_inject(void *data, u64 offset) if (validate_region_offset(cxlr, offset)) return -EINVAL; + offset -= cxlr->params.cache_size; rc = region_offset_to_dpa_result(cxlr, offset, &result); if (rc || !result.cxlmd || result.dpa == ULLONG_MAX) { dev_dbg(&cxlr->dev, @@ -3734,6 +3735,7 @@ static int cxl_region_debugfs_poison_clear(void *data, u64 offset) if (validate_region_offset(cxlr, offset)) return -EINVAL; + offset -= cxlr->params.cache_size; rc = region_offset_to_dpa_result(cxlr, offset, &result); if (rc || !result.cxlmd || result.dpa == ULLONG_MAX) { dev_dbg(&cxlr->dev, diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 35e241041c10..b4f5c8635276 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -997,19 +997,21 @@ EXPORT_SYMBOL(dma_fence_set_deadline); */ void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq) { - const char __rcu *timeline; - const char __rcu *driver; + const char __rcu *timeline = ""; + const char __rcu *driver = ""; + const char *signaled = ""; rcu_read_lock(); - timeline = dma_fence_timeline_name(fence); - driver = dma_fence_driver_name(fence); + if (!dma_fence_is_signaled(fence)) { + timeline = dma_fence_timeline_name(fence); + driver = dma_fence_driver_name(fence); + signaled = "un"; + } - seq_printf(seq, "%s %s seq %llu %ssignalled\n", - rcu_dereference(driver), - rcu_dereference(timeline), - fence->seqno, - dma_fence_is_signaled(fence) ? "" : "un"); + seq_printf(seq, "%llu:%llu %s %s %ssignalled\n", + fence->context, fence->seqno, timeline, driver, + signaled); rcu_read_unlock(); } @@ -1139,7 +1141,7 @@ const char __rcu *dma_fence_timeline_name(struct dma_fence *fence) "RCU protection is required for safe access to returned string"); if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - return fence->ops->get_driver_name(fence); + return fence->ops->get_timeline_name(fence); else return "signaled-timeline"; } diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index bbe7881f1360..4c782fe33fd4 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -186,20 +186,35 @@ static int system_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) struct system_heap_buffer *buffer = dmabuf->priv; struct sg_table *table = &buffer->sg_table; unsigned long addr = vma->vm_start; - struct sg_page_iter piter; - int ret; + unsigned long pgoff = vma->vm_pgoff; + struct scatterlist *sg; + int i, ret; - for_each_sgtable_page(table, &piter, vma->vm_pgoff) { - struct page *page = sg_page_iter_page(&piter); + for_each_sgtable_sg(table, sg, i) { + unsigned long n = sg->length >> PAGE_SHIFT; - ret = remap_pfn_range(vma, addr, page_to_pfn(page), PAGE_SIZE, - vma->vm_page_prot); + if (pgoff < n) + break; + pgoff -= n; + } + + for (; sg && addr < vma->vm_end; sg = sg_next(sg)) { + unsigned long n = (sg->length >> PAGE_SHIFT) - pgoff; + struct page *page = sg_page(sg) + pgoff; + unsigned long size = n << PAGE_SHIFT; + + if (addr + size > vma->vm_end) + size = vma->vm_end - addr; + + ret = remap_pfn_range(vma, addr, page_to_pfn(page), + size, vma->vm_page_prot); if (ret) return ret; - addr += PAGE_SIZE; - if (addr >= vma->vm_end) - return 0; + + addr += size; + pgoff = 0; } + return 0; } diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 3c20f1d31cf5..6f09d13be6b6 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -349,6 +350,9 @@ static long sw_sync_ioctl_create_fence(struct sync_timeline *obj, struct sync_file *sync_file; struct sw_sync_create_fence_data data; + /* SW sync fence are inherently unsafe and can deadlock the kernel */ + add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); + if (fd < 0) return fd; diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 74c1f0ca95f2..a4153bcb6dcf 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -1559,16 +1559,18 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info) return -EMSGSIZE; } pin = dpll_pin_find_from_nlattr(info); - if (!IS_ERR(pin)) { - if (!dpll_pin_available(pin)) { - nlmsg_free(msg); - return -ENODEV; - } - ret = dpll_msg_add_pin_handle(msg, pin); - if (ret) { - nlmsg_free(msg); - return ret; - } + if (IS_ERR(pin)) { + nlmsg_free(msg); + return PTR_ERR(pin); + } + if (!dpll_pin_available(pin)) { + nlmsg_free(msg); + return -ENODEV; + } + ret = dpll_msg_add_pin_handle(msg, pin); + if (ret) { + nlmsg_free(msg); + return ret; } genlmsg_end(msg, hdr); @@ -1735,12 +1737,14 @@ int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info) } dpll = dpll_device_find_from_nlattr(info); - if (!IS_ERR(dpll)) { - ret = dpll_msg_add_dev_handle(msg, dpll); - if (ret) { - nlmsg_free(msg); - return ret; - } + if (IS_ERR(dpll)) { + nlmsg_free(msg); + return PTR_ERR(dpll); + } + ret = dpll_msg_add_dev_handle(msg, dpll); + if (ret) { + nlmsg_free(msg); + return ret; } genlmsg_end(msg, hdr); diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c index 93dc93eec79e..f93f9a458324 100644 --- a/drivers/dpll/zl3073x/dpll.c +++ b/drivers/dpll/zl3073x/dpll.c @@ -1904,7 +1904,7 @@ zl3073x_dpll_pin_is_registrable(struct zl3073x_dpll *zldpll, } is_diff = zl3073x_out_is_diff(zldev, out); - is_enabled = zl3073x_out_is_enabled(zldev, out); + is_enabled = zl3073x_output_pin_is_enabled(zldev, index); } /* Skip N-pin if the corresponding input/output is differential */ diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 103b2c2eba2a..0c5b94e64ea1 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1184,10 +1184,22 @@ altr_check_ocram_deps_init(struct altr_edac_device_dev *device) if (ret) return ret; - /* Verify OCRAM has been initialized */ + /* + * Verify that OCRAM has been initialized. + * During a warm reset, OCRAM contents are retained, but the control + * and status registers are reset to their default values. Therefore, + * ECC must be explicitly re-enabled in the control register. + * Error condition: if INITCOMPLETEA is clear and ECC_EN is already set. + */ if (!ecc_test_bits(ALTR_A10_ECC_INITCOMPLETEA, - (base + ALTR_A10_ECC_INITSTAT_OFST))) - return -ENODEV; + (base + ALTR_A10_ECC_INITSTAT_OFST))) { + if (!ecc_test_bits(ALTR_A10_ECC_EN, + (base + ALTR_A10_ECC_CTRL_OFST))) + ecc_set_bits(ALTR_A10_ECC_EN, + (base + ALTR_A10_ECC_CTRL_OFST)); + else + return -ENODEV; + } /* Enable IRQ on Single Bit Error */ writel(ALTR_A10_ECC_SERRINTEN, (base + ALTR_A10_ECC_ERRINTENS_OFST)); @@ -1357,7 +1369,7 @@ static const struct edac_device_prv_data a10_enetecc_data = { .ue_set_mask = ALTR_A10_ECC_TDERRA, .set_err_ofst = ALTR_A10_ECC_INTTEST_OFST, .ecc_irq_handler = altr_edac_a10_ecc_irq, - .inject_fops = &altr_edac_a10_device_inject2_fops, + .inject_fops = &altr_edac_a10_device_inject_fops, }; #endif /* CONFIG_EDAC_ALTERA_ETHERNET */ @@ -1447,7 +1459,7 @@ static const struct edac_device_prv_data a10_usbecc_data = { .ue_set_mask = ALTR_A10_ECC_TDERRA, .set_err_ofst = ALTR_A10_ECC_INTTEST_OFST, .ecc_irq_handler = altr_edac_a10_ecc_irq, - .inject_fops = &altr_edac_a10_device_inject2_fops, + .inject_fops = &altr_edac_a10_device_inject_fops, }; #endif /* CONFIG_EDAC_ALTERA_USB */ diff --git a/drivers/edac/versalnet_edac.c b/drivers/edac/versalnet_edac.c index 7c5db8bf0595..1a1092793092 100644 --- a/drivers/edac/versalnet_edac.c +++ b/drivers/edac/versalnet_edac.c @@ -433,7 +433,7 @@ static void handle_error(struct mc_priv *priv, struct ecc_status *stat, phys_addr_t pfn; int err; - if (WARN_ON_ONCE(ctl_num > NUM_CONTROLLERS)) + if (WARN_ON_ONCE(ctl_num >= NUM_CONTROLLERS)) return; mci = priv->mci[ctl_num]; @@ -605,21 +605,23 @@ static int rpmsg_cb(struct rpmsg_device *rpdev, void *data, length = result[MSG_ERR_LENGTH]; offset = result[MSG_ERR_OFFSET]; + /* + * The data can come in two stretches. Construct the regs from two + * messages. The offset indicates the offset from which the data is to + * be taken. + */ + for (i = 0 ; i < length; i++) { + k = offset + i; + j = ERROR_DATA + i; + mc_priv->regs[k] = result[j]; + } + if (result[TOTAL_ERR_LENGTH] > length) { if (!mc_priv->part_len) mc_priv->part_len = length; else mc_priv->part_len += length; - /* - * The data can come in 2 stretches. Construct the regs from 2 - * messages the offset indicates the offset from which the data is to - * be taken - */ - for (i = 0 ; i < length; i++) { - k = offset + i; - j = ERROR_DATA + i; - mc_priv->regs[k] = result[j]; - } + if (mc_priv->part_len < result[TOTAL_ERR_LENGTH]) return 0; mc_priv->part_len = 0; @@ -705,7 +707,7 @@ static int rpmsg_cb(struct rpmsg_device *rpdev, void *data, /* Convert to bytes */ length = result[TOTAL_ERR_LENGTH] * 4; log_non_standard_event(sec_type, &amd_versalnet_guid, mc_priv->message, - sec_sev, (void *)&result[ERROR_DATA], length); + sec_sev, (void *)&mc_priv->regs, length); return 0; } diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index e5e0174a0335..66e1106db5e7 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -577,6 +577,8 @@ void fw_card_initialize(struct fw_card *card, INIT_LIST_HEAD(&card->transactions.list); spin_lock_init(&card->transactions.lock); + spin_lock_init(&card->topology_map.lock); + card->split_timeout.hi = DEFAULT_SPLIT_TIMEOUT / 8000; card->split_timeout.lo = (DEFAULT_SPLIT_TIMEOUT % 8000) << 19; card->split_timeout.cycles = DEFAULT_SPLIT_TIMEOUT; diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 2f73bcd5696f..ed3ae8cdb0cd 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -441,12 +441,13 @@ static void update_topology_map(__be32 *buffer, size_t buffer_size, int root_nod const u32 *self_ids, int self_id_count) { __be32 *map = buffer; + u32 next_generation = be32_to_cpu(buffer[1]) + 1; int node_count = (root_node_id & 0x3f) + 1; memset(map, 0, buffer_size); *map++ = cpu_to_be32((self_id_count + 2) << 16); - *map++ = cpu_to_be32(be32_to_cpu(buffer[1]) + 1); + *map++ = cpu_to_be32(next_generation); *map++ = cpu_to_be32((node_count << 16) | self_id_count); while (self_id_count--) diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index dd3656a0c1ff..c65f491c54d0 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -269,7 +269,7 @@ static void fw_fill_request(struct fw_packet *packet, int tcode, int tlabel, } static int allocate_tlabel(struct fw_card *card) -__must_hold(&card->transactions_lock) +__must_hold(&card->transactions.lock) { int tlabel; diff --git a/drivers/firewire/init_ohci1394_dma.c b/drivers/firewire/init_ohci1394_dma.c index 48b879e9e831..121f0c2f6401 100644 --- a/drivers/firewire/init_ohci1394_dma.c +++ b/drivers/firewire/init_ohci1394_dma.c @@ -167,6 +167,7 @@ static inline void __init init_ohci1394_initialize(struct ohci *ohci) /** * init_ohci1394_wait_for_busresets - wait until bus resets are completed + * @ohci: Pointer to the OHCI-1394 controller structure * * OHCI1394 initialization itself and any device going on- or offline * and any cable issue cause a IEEE1394 bus reset. The OHCI1394 spec @@ -189,6 +190,8 @@ static inline void __init init_ohci1394_wait_for_busresets(struct ohci *ohci) /** * init_ohci1394_enable_physical_dma - Enable physical DMA for remote debugging + * @ohci: Pointer to the OHCI-1394 controller structure + * * This enables remote DMA access over IEEE1394 from every host for the low * 4GB of address space. DMA accesses above 4GB are not available currently. */ @@ -201,6 +204,8 @@ static inline void __init init_ohci1394_enable_physical_dma(struct ohci *ohci) /** * init_ohci1394_reset_and_init_dma - init controller and enable DMA + * @ohci: Pointer to the OHCI-1394 controller structure + * * This initializes the given controller and enables physical DMA engine in it. */ static inline void __init init_ohci1394_reset_and_init_dma(struct ohci *ohci) @@ -230,6 +235,10 @@ static inline void __init init_ohci1394_reset_and_init_dma(struct ohci *ohci) /** * init_ohci1394_controller - Map the registers of the controller and init DMA + * @num: PCI bus number + * @slot: PCI device number + * @func: PCI function number + * * This maps the registers of the specified controller and initializes it */ static inline void __init init_ohci1394_controller(int num, int slot, int func) @@ -284,6 +293,7 @@ void __init init_ohci1394_dma_on_all_controllers(void) /** * setup_ohci1394_dma - enables early OHCI1394 DMA initialization + * @opt: Kernel command line parameter string */ static int __init setup_ohci1394_dma(char *opt) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 65bf1685350a..c72ee4756585 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -649,6 +649,26 @@ static u16 ffa_memory_attributes_get(u32 func_id) return FFA_MEM_NORMAL | FFA_MEM_WRITE_BACK | FFA_MEM_INNER_SHAREABLE; } +static void ffa_emad_impdef_value_init(u32 version, void *dst, void *src) +{ + struct ffa_mem_region_attributes *ep_mem_access; + + if (FFA_EMAD_HAS_IMPDEF_FIELD(version)) + memcpy(dst, src, sizeof(ep_mem_access->impdef_val)); +} + +static void +ffa_mem_region_additional_setup(u32 version, struct ffa_mem_region *mem_region) +{ + if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version)) { + mem_region->ep_mem_size = 0; + } else { + mem_region->ep_mem_size = ffa_emad_size_get(version); + mem_region->ep_mem_offset = sizeof(*mem_region); + memset(mem_region->reserved, 0, 12); + } +} + static int ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, struct ffa_mem_ops_args *args) @@ -667,27 +687,24 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, mem_region->flags = args->flags; mem_region->sender_id = drv_info->vm_id; mem_region->attributes = ffa_memory_attributes_get(func_id); - ep_mem_access = buffer + - ffa_mem_desc_offset(buffer, 0, drv_info->version); composite_offset = ffa_mem_desc_offset(buffer, args->nattrs, drv_info->version); - for (idx = 0; idx < args->nattrs; idx++, ep_mem_access++) { + for (idx = 0; idx < args->nattrs; idx++) { + ep_mem_access = buffer + + ffa_mem_desc_offset(buffer, idx, drv_info->version); ep_mem_access->receiver = args->attrs[idx].receiver; ep_mem_access->attrs = args->attrs[idx].attrs; ep_mem_access->composite_off = composite_offset; ep_mem_access->flag = 0; ep_mem_access->reserved = 0; + ffa_emad_impdef_value_init(drv_info->version, + ep_mem_access->impdef_val, + args->attrs[idx].impdef_val); } mem_region->handle = 0; mem_region->ep_count = args->nattrs; - if (drv_info->version <= FFA_VERSION_1_0) { - mem_region->ep_mem_size = 0; - } else { - mem_region->ep_mem_size = sizeof(*ep_mem_access); - mem_region->ep_mem_offset = sizeof(*mem_region); - memset(mem_region->reserved, 0, 12); - } + ffa_mem_region_additional_setup(drv_info->version, mem_region); composite = buffer + composite_offset; composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg); diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 07b9e629276d..7c35c95fddba 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -309,16 +309,36 @@ enum debug_counters { SCMI_DEBUG_COUNTERS_LAST }; -static inline void scmi_inc_count(atomic_t *arr, int stat) +/** + * struct scmi_debug_info - Debug common info + * @top_dentry: A reference to the top debugfs dentry + * @name: Name of this SCMI instance + * @type: Type of this SCMI instance + * @is_atomic: Flag to state if the transport of this instance is atomic + * @counters: An array of atomic_c's used for tracking statistics (if enabled) + */ +struct scmi_debug_info { + struct dentry *top_dentry; + const char *name; + const char *type; + bool is_atomic; + atomic_t counters[SCMI_DEBUG_COUNTERS_LAST]; +}; + +static inline void scmi_inc_count(struct scmi_debug_info *dbg, int stat) { - if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) - atomic_inc(&arr[stat]); + if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) { + if (dbg) + atomic_inc(&dbg->counters[stat]); + } } -static inline void scmi_dec_count(atomic_t *arr, int stat) +static inline void scmi_dec_count(struct scmi_debug_info *dbg, int stat) { - if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) - atomic_dec(&arr[stat]); + if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) { + if (dbg) + atomic_dec(&dbg->counters[stat]); + } } enum scmi_bad_msg { diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index bd56a877fdfc..5caa9191a8d1 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -115,22 +115,6 @@ struct scmi_protocol_instance { #define ph_to_pi(h) container_of(h, struct scmi_protocol_instance, ph) -/** - * struct scmi_debug_info - Debug common info - * @top_dentry: A reference to the top debugfs dentry - * @name: Name of this SCMI instance - * @type: Type of this SCMI instance - * @is_atomic: Flag to state if the transport of this instance is atomic - * @counters: An array of atomic_c's used for tracking statistics (if enabled) - */ -struct scmi_debug_info { - struct dentry *top_dentry; - const char *name; - const char *type; - bool is_atomic; - atomic_t counters[SCMI_DEBUG_COUNTERS_LAST]; -}; - /** * struct scmi_info - Structure representing a SCMI instance * @@ -610,7 +594,7 @@ scmi_xfer_inflight_register_unlocked(struct scmi_xfer *xfer, /* Set in-flight */ set_bit(xfer->hdr.seq, minfo->xfer_alloc_table); hash_add(minfo->pending_xfers, &xfer->node, xfer->hdr.seq); - scmi_inc_count(info->dbg->counters, XFERS_INFLIGHT); + scmi_inc_count(info->dbg, XFERS_INFLIGHT); xfer->pending = true; } @@ -819,8 +803,9 @@ __scmi_xfer_put(struct scmi_xfers_info *minfo, struct scmi_xfer *xfer) hash_del(&xfer->node); xfer->pending = false; - scmi_dec_count(info->dbg->counters, XFERS_INFLIGHT); + scmi_dec_count(info->dbg, XFERS_INFLIGHT); } + xfer->flags = 0; hlist_add_head(&xfer->node, &minfo->free_xfers); } spin_unlock_irqrestore(&minfo->xfer_lock, flags); @@ -839,8 +824,6 @@ void scmi_xfer_raw_put(const struct scmi_handle *handle, struct scmi_xfer *xfer) { struct scmi_info *info = handle_to_scmi_info(handle); - xfer->flags &= ~SCMI_XFER_FLAG_IS_RAW; - xfer->flags &= ~SCMI_XFER_FLAG_CHAN_SET; return __scmi_xfer_put(&info->tx_minfo, xfer); } @@ -1034,7 +1017,7 @@ scmi_xfer_command_acquire(struct scmi_chan_info *cinfo, u32 msg_hdr) spin_unlock_irqrestore(&minfo->xfer_lock, flags); scmi_bad_message_trace(cinfo, msg_hdr, MSG_UNEXPECTED); - scmi_inc_count(info->dbg->counters, ERR_MSG_UNEXPECTED); + scmi_inc_count(info->dbg, ERR_MSG_UNEXPECTED); return xfer; } @@ -1062,7 +1045,7 @@ scmi_xfer_command_acquire(struct scmi_chan_info *cinfo, u32 msg_hdr) msg_type, xfer_id, msg_hdr, xfer->state); scmi_bad_message_trace(cinfo, msg_hdr, MSG_INVALID); - scmi_inc_count(info->dbg->counters, ERR_MSG_INVALID); + scmi_inc_count(info->dbg, ERR_MSG_INVALID); /* On error the refcount incremented above has to be dropped */ __scmi_xfer_put(minfo, xfer); @@ -1107,7 +1090,7 @@ static void scmi_handle_notification(struct scmi_chan_info *cinfo, PTR_ERR(xfer)); scmi_bad_message_trace(cinfo, msg_hdr, MSG_NOMEM); - scmi_inc_count(info->dbg->counters, ERR_MSG_NOMEM); + scmi_inc_count(info->dbg, ERR_MSG_NOMEM); scmi_clear_channel(info, cinfo); return; @@ -1123,7 +1106,7 @@ static void scmi_handle_notification(struct scmi_chan_info *cinfo, trace_scmi_msg_dump(info->id, cinfo->id, xfer->hdr.protocol_id, xfer->hdr.id, "NOTI", xfer->hdr.seq, xfer->hdr.status, xfer->rx.buf, xfer->rx.len); - scmi_inc_count(info->dbg->counters, NOTIFICATION_OK); + scmi_inc_count(info->dbg, NOTIFICATION_OK); scmi_notify(cinfo->handle, xfer->hdr.protocol_id, xfer->hdr.id, xfer->rx.buf, xfer->rx.len, ts); @@ -1183,10 +1166,10 @@ static void scmi_handle_response(struct scmi_chan_info *cinfo, if (xfer->hdr.type == MSG_TYPE_DELAYED_RESP) { scmi_clear_channel(info, cinfo); complete(xfer->async_done); - scmi_inc_count(info->dbg->counters, DELAYED_RESPONSE_OK); + scmi_inc_count(info->dbg, DELAYED_RESPONSE_OK); } else { complete(&xfer->done); - scmi_inc_count(info->dbg->counters, RESPONSE_OK); + scmi_inc_count(info->dbg, RESPONSE_OK); } if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { @@ -1296,7 +1279,7 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, "timed out in resp(caller: %pS) - polling\n", (void *)_RET_IP_); ret = -ETIMEDOUT; - scmi_inc_count(info->dbg->counters, XFERS_RESPONSE_POLLED_TIMEOUT); + scmi_inc_count(info->dbg, XFERS_RESPONSE_POLLED_TIMEOUT); } } @@ -1321,7 +1304,7 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, "RESP" : "resp", xfer->hdr.seq, xfer->hdr.status, xfer->rx.buf, xfer->rx.len); - scmi_inc_count(info->dbg->counters, RESPONSE_POLLED_OK); + scmi_inc_count(info->dbg, RESPONSE_POLLED_OK); if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { scmi_raw_message_report(info->raw, xfer, @@ -1336,7 +1319,7 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, dev_err(dev, "timed out in resp(caller: %pS)\n", (void *)_RET_IP_); ret = -ETIMEDOUT; - scmi_inc_count(info->dbg->counters, XFERS_RESPONSE_TIMEOUT); + scmi_inc_count(info->dbg, XFERS_RESPONSE_TIMEOUT); } } @@ -1420,13 +1403,13 @@ static int do_xfer(const struct scmi_protocol_handle *ph, !is_transport_polling_capable(info->desc)) { dev_warn_once(dev, "Polling mode is not supported by transport.\n"); - scmi_inc_count(info->dbg->counters, SENT_FAIL_POLLING_UNSUPPORTED); + scmi_inc_count(info->dbg, SENT_FAIL_POLLING_UNSUPPORTED); return -EINVAL; } cinfo = idr_find(&info->tx_idr, pi->proto->id); if (unlikely(!cinfo)) { - scmi_inc_count(info->dbg->counters, SENT_FAIL_CHANNEL_NOT_FOUND); + scmi_inc_count(info->dbg, SENT_FAIL_CHANNEL_NOT_FOUND); return -EINVAL; } /* True ONLY if also supported by transport. */ @@ -1461,19 +1444,19 @@ static int do_xfer(const struct scmi_protocol_handle *ph, ret = info->desc->ops->send_message(cinfo, xfer); if (ret < 0) { dev_dbg(dev, "Failed to send message %d\n", ret); - scmi_inc_count(info->dbg->counters, SENT_FAIL); + scmi_inc_count(info->dbg, SENT_FAIL); return ret; } trace_scmi_msg_dump(info->id, cinfo->id, xfer->hdr.protocol_id, xfer->hdr.id, "CMND", xfer->hdr.seq, xfer->hdr.status, xfer->tx.buf, xfer->tx.len); - scmi_inc_count(info->dbg->counters, SENT_OK); + scmi_inc_count(info->dbg, SENT_OK); ret = scmi_wait_for_message_response(cinfo, xfer); if (!ret && xfer->hdr.status) { ret = scmi_to_linux_errno(xfer->hdr.status); - scmi_inc_count(info->dbg->counters, ERR_PROTOCOL); + scmi_inc_count(info->dbg, ERR_PROTOCOL); } if (info->desc->ops->mark_txdone) @@ -3044,9 +3027,6 @@ static int scmi_debugfs_raw_mode_setup(struct scmi_info *info) u8 channels[SCMI_MAX_CHANNELS] = {}; DECLARE_BITMAP(protos, SCMI_MAX_CHANNELS) = {}; - if (!info->dbg) - return -EINVAL; - /* Enumerate all channels to collect their ids */ idr_for_each_entry(&info->tx_idr, cinfo, id) { /* @@ -3218,7 +3198,7 @@ static int scmi_probe(struct platform_device *pdev) if (!info->dbg) dev_warn(dev, "Failed to setup SCMI debugfs.\n"); - if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { + if (info->dbg && IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) { ret = scmi_debugfs_raw_mode_setup(info); if (!coex) { if (ret) @@ -3423,6 +3403,9 @@ int scmi_inflight_count(const struct scmi_handle *handle) if (IS_ENABLED(CONFIG_ARM_SCMI_DEBUG_COUNTERS)) { struct scmi_info *info = handle_to_scmi_info(handle); + if (!info->dbg) + return 0; + return atomic_read(&info->dbg->counters[XFERS_INFLIGHT]); } else { return 0; diff --git a/drivers/gpio/gpio-104-idio-16.c b/drivers/gpio/gpio-104-idio-16.c index ffe7e1cb6b23..fe5c10cd5c32 100644 --- a/drivers/gpio/gpio-104-idio-16.c +++ b/drivers/gpio/gpio-104-idio-16.c @@ -59,6 +59,7 @@ static const struct regmap_config idio_16_regmap_config = { .reg_stride = 1, .val_bits = 8, .io_port = true, + .max_register = 0x5, .wr_table = &idio_16_wr_table, .rd_table = &idio_16_rd_table, .volatile_table = &idio_16_rd_table, diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 37600faf4a4b..416f265d09d0 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -723,6 +723,7 @@ struct gpiochip_fwd *devm_gpiochip_fwd_alloc(struct device *dev, chip->get_multiple = gpio_fwd_get_multiple_locked; chip->set = gpio_fwd_set; chip->set_multiple = gpio_fwd_set_multiple_locked; + chip->set_config = gpio_fwd_set_config; chip->to_irq = gpio_fwd_to_irq; chip->base = -1; chip->ngpio = ngpios; diff --git a/drivers/gpio/gpio-idio-16.c b/drivers/gpio/gpio-idio-16.c index 0103be977c66..4fbae6f6a497 100644 --- a/drivers/gpio/gpio-idio-16.c +++ b/drivers/gpio/gpio-idio-16.c @@ -6,6 +6,7 @@ #define DEFAULT_SYMBOL_NAMESPACE "GPIO_IDIO_16" +#include #include #include #include @@ -107,6 +108,7 @@ int devm_idio_16_regmap_register(struct device *const dev, struct idio_16_data *data; struct regmap_irq_chip *chip; struct regmap_irq_chip_data *chip_data; + DECLARE_BITMAP(fixed_direction_output, IDIO_16_NGPIO); if (!config->parent) return -EINVAL; @@ -164,6 +166,9 @@ int devm_idio_16_regmap_register(struct device *const dev, gpio_config.irq_domain = regmap_irq_get_domain(chip_data); gpio_config.reg_mask_xlate = idio_16_reg_mask_xlate; + bitmap_from_u64(fixed_direction_output, GENMASK_U64(15, 0)); + gpio_config.fixed_direction_output = fixed_direction_output; + return PTR_ERR_OR_ZERO(devm_gpio_regmap_register(dev, &gpio_config)); } EXPORT_SYMBOL_GPL(devm_idio_16_regmap_register); diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c index 3b4f8830c741..f32d1d237795 100644 --- a/drivers/gpio/gpio-ljca.c +++ b/drivers/gpio/gpio-ljca.c @@ -286,22 +286,14 @@ static void ljca_gpio_event_cb(void *context, u8 cmd, const void *evt_data, { const struct ljca_gpio_packet *packet = evt_data; struct ljca_gpio_dev *ljca_gpio = context; - int i, irq; + int i; if (cmd != LJCA_GPIO_INT_EVENT) return; for (i = 0; i < packet->num; i++) { - irq = irq_find_mapping(ljca_gpio->gc.irq.domain, - packet->item[i].index); - if (!irq) { - dev_err(ljca_gpio->gc.parent, - "gpio_id %u does not mapped to IRQ yet\n", - packet->item[i].index); - return; - } - - generic_handle_domain_irq(ljca_gpio->gc.irq.domain, irq); + generic_handle_domain_irq(ljca_gpio->gc.irq.domain, + packet->item[i].index); set_bit(packet->item[i].index, ljca_gpio->reenable_irqs); } diff --git a/drivers/gpio/gpio-pci-idio-16.c b/drivers/gpio/gpio-pci-idio-16.c index 476cea1b5ed7..9d28ca8e1d6f 100644 --- a/drivers/gpio/gpio-pci-idio-16.c +++ b/drivers/gpio/gpio-pci-idio-16.c @@ -41,6 +41,7 @@ static const struct regmap_config idio_16_regmap_config = { .reg_stride = 1, .val_bits = 8, .io_port = true, + .max_register = 0x7, .wr_table = &idio_16_wr_table, .rd_table = &idio_16_rd_table, .volatile_table = &idio_16_rd_table, diff --git a/drivers/gpio/gpio-regmap.c b/drivers/gpio/gpio-regmap.c index ab9e4077fa60..f4267af00027 100644 --- a/drivers/gpio/gpio-regmap.c +++ b/drivers/gpio/gpio-regmap.c @@ -31,6 +31,7 @@ struct gpio_regmap { unsigned int reg_clr_base; unsigned int reg_dir_in_base; unsigned int reg_dir_out_base; + unsigned long *fixed_direction_output; #ifdef CONFIG_REGMAP_IRQ int regmap_irq_line; @@ -134,6 +135,13 @@ static int gpio_regmap_get_direction(struct gpio_chip *chip, unsigned int base, val, reg, mask; int invert, ret; + if (gpio->fixed_direction_output) { + if (test_bit(offset, gpio->fixed_direction_output)) + return GPIO_LINE_DIRECTION_OUT; + else + return GPIO_LINE_DIRECTION_IN; + } + if (gpio->reg_dat_base && !gpio->reg_set_base) return GPIO_LINE_DIRECTION_IN; if (gpio->reg_set_base && !gpio->reg_dat_base) @@ -284,6 +292,17 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config goto err_free_gpio; } + if (config->fixed_direction_output) { + gpio->fixed_direction_output = bitmap_alloc(chip->ngpio, + GFP_KERNEL); + if (!gpio->fixed_direction_output) { + ret = -ENOMEM; + goto err_free_gpio; + } + bitmap_copy(gpio->fixed_direction_output, + config->fixed_direction_output, chip->ngpio); + } + /* if not set, assume there is only one register */ gpio->ngpio_per_reg = config->ngpio_per_reg; if (!gpio->ngpio_per_reg) @@ -300,7 +319,7 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config ret = gpiochip_add_data(chip, gpio); if (ret < 0) - goto err_free_gpio; + goto err_free_bitmap; #ifdef CONFIG_REGMAP_IRQ if (config->regmap_irq_chip) { @@ -309,7 +328,7 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config config->regmap_irq_line, config->regmap_irq_flags, 0, config->regmap_irq_chip, &gpio->irq_chip_data); if (ret) - goto err_free_gpio; + goto err_free_bitmap; irq_domain = regmap_irq_get_domain(gpio->irq_chip_data); } else @@ -326,6 +345,8 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config err_remove_gpiochip: gpiochip_remove(chip); +err_free_bitmap: + bitmap_free(gpio->fixed_direction_output); err_free_gpio: kfree(gpio); return ERR_PTR(ret); @@ -344,6 +365,7 @@ void gpio_regmap_unregister(struct gpio_regmap *gpio) #endif gpiochip_remove(&gpio->gpio_chip); + bitmap_free(gpio->fixed_direction_output); kfree(gpio); } EXPORT_SYMBOL_GPL(gpio_regmap_unregister); diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c index 09a448ce3eec..3c8fd322a713 100644 --- a/drivers/gpio/gpio-tb10x.c +++ b/drivers/gpio/gpio-tb10x.c @@ -50,25 +50,6 @@ static inline u32 tb10x_reg_read(struct tb10x_gpio *gpio, unsigned int offs) return ioread32(gpio->base + offs); } -static inline void tb10x_reg_write(struct tb10x_gpio *gpio, unsigned int offs, - u32 val) -{ - iowrite32(val, gpio->base + offs); -} - -static inline void tb10x_set_bits(struct tb10x_gpio *gpio, unsigned int offs, - u32 mask, u32 val) -{ - u32 r; - - guard(gpio_generic_lock_irqsave)(&gpio->chip); - - r = tb10x_reg_read(gpio, offs); - r = (r & ~mask) | (val & mask); - - tb10x_reg_write(gpio, offs, r); -} - static int tb10x_gpio_to_irq(struct gpio_chip *chip, unsigned offset) { struct tb10x_gpio *tb10x_gpio = gpiochip_get_data(chip); diff --git a/drivers/gpio/gpiolib-acpi-core.c b/drivers/gpio/gpiolib-acpi-core.c index 284e762d92c4..d441c1236d8c 100644 --- a/drivers/gpio/gpiolib-acpi-core.c +++ b/drivers/gpio/gpiolib-acpi-core.c @@ -291,6 +291,19 @@ acpi_gpio_to_gpiod_flags(const struct acpi_resource_gpio *agpio, int polarity) return GPIOD_ASIS; } +static void acpi_gpio_set_debounce_timeout(struct gpio_desc *desc, + unsigned int acpi_debounce) +{ + int ret; + + /* ACPI uses hundredths of milliseconds units */ + acpi_debounce *= 10; + ret = gpio_set_debounce_timeout(desc, acpi_debounce); + if (ret) + gpiod_warn(desc, "Failed to set debounce-timeout %u: %d\n", + acpi_debounce, ret); +} + static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, struct acpi_resource_gpio *agpio, unsigned int index, @@ -300,18 +313,12 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, enum gpiod_flags flags = acpi_gpio_to_gpiod_flags(agpio, polarity); unsigned int pin = agpio->pin_table[index]; struct gpio_desc *desc; - int ret; desc = gpiochip_request_own_desc(chip, pin, label, polarity, flags); if (IS_ERR(desc)) return desc; - /* ACPI uses hundredths of milliseconds units */ - ret = gpio_set_debounce_timeout(desc, agpio->debounce_timeout * 10); - if (ret) - dev_warn(chip->parent, - "Failed to set debounce-timeout for pin 0x%04X, err %d\n", - pin, ret); + acpi_gpio_set_debounce_timeout(desc, agpio->debounce_timeout); return desc; } @@ -375,8 +382,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, desc = acpi_request_own_gpiod(chip, agpio, 0, "ACPI:Event"); if (IS_ERR(desc)) { dev_err(chip->parent, - "Failed to request GPIO for pin 0x%04X, err %ld\n", - pin, PTR_ERR(desc)); + "Failed to request GPIO for pin 0x%04X, err %pe\n", + pin, desc); return AE_OK; } @@ -944,7 +951,6 @@ struct gpio_desc *acpi_find_gpio(struct fwnode_handle *fwnode, bool can_fallback = acpi_can_fallback_to_crs(adev, con_id); struct acpi_gpio_info info = {}; struct gpio_desc *desc; - int ret; desc = __acpi_find_gpio(fwnode, con_id, idx, can_fallback, &info); if (IS_ERR(desc)) @@ -959,10 +965,7 @@ struct gpio_desc *acpi_find_gpio(struct fwnode_handle *fwnode, acpi_gpio_update_gpiod_flags(dflags, &info); acpi_gpio_update_gpiod_lookup_flags(lookupflags, &info); - /* ACPI uses hundredths of milliseconds units */ - ret = gpio_set_debounce_timeout(desc, info.debounce * 10); - if (ret) - return ERR_PTR(ret); + acpi_gpio_set_debounce_timeout(desc, info.debounce); return desc; } diff --git a/drivers/gpio/gpiolib-swnode.c b/drivers/gpio/gpiolib-swnode.c index f21dbc28cf2c..e3806db1c0e0 100644 --- a/drivers/gpio/gpiolib-swnode.c +++ b/drivers/gpio/gpiolib-swnode.c @@ -41,7 +41,7 @@ static struct gpio_device *swnode_get_gpio_device(struct fwnode_handle *fwnode) !strcmp(gdev_node->name, GPIOLIB_SWNODE_UNDEFINED_NAME)) return ERR_PTR(-ENOENT); - gdev = gpio_device_find_by_label(gdev_node->name); + gdev = gpio_device_find_by_fwnode(fwnode); return gdev ?: ERR_PTR(-EPROBE_DEFER); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 9952e412da50..cd8800ba5825 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -5296,6 +5296,8 @@ static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos) struct gpio_device *gdev; loff_t index = *pos; + s->private = NULL; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return NULL; @@ -5329,7 +5331,11 @@ static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos) static void gpiolib_seq_stop(struct seq_file *s, void *v) { - struct gpiolib_seq_priv *priv = s->private; + struct gpiolib_seq_priv *priv; + + priv = s->private; + if (!priv) + return; srcu_read_unlock(&gpio_devices_srcu, priv->idx); kfree(priv); diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index c2672f369aed..4b3f3ad5058a 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -41,6 +41,7 @@ drm-y := \ drm_bridge.o \ drm_cache.o \ drm_color_mgmt.o \ + drm_colorop.o \ drm_connector.o \ drm_crtc.o \ drm_displayid.o \ @@ -76,7 +77,8 @@ drm-y := \ drm-$(CONFIG_DRM_CLIENT) += \ drm_client.o \ drm_client_event.o \ - drm_client_modeset.o + drm_client_modeset.o \ + drm_client_sysrq.o drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o drm-$(CONFIG_COMPAT) += drm_ioc32.o drm-$(CONFIG_DRM_PANEL) += drm_panel.o @@ -246,7 +248,7 @@ always-$(CONFIG_DRM_HEADER_TEST) += \ quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \ - PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ + PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ touch $@ $(obj)/%.hdrtest: $(src)/%.h FORCE diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index 4926996f94da..381ef205b0df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -302,17 +302,19 @@ static int acp_hw_init(struct amdgpu_ip_block *ip_block) adev->acp.acp_res[2].end = adev->acp.acp_res[2].start; adev->acp.acp_cell[0].name = "acp_audio_dma"; + adev->acp.acp_cell[0].id = 0; adev->acp.acp_cell[0].num_resources = 3; adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0]; adev->acp.acp_cell[0].platform_data = &adev->asic_type; adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type); adev->acp.acp_cell[1].name = "designware-i2s"; + adev->acp.acp_cell[1].id = 1; adev->acp.acp_cell[1].num_resources = 1; adev->acp.acp_cell[1].resources = &adev->acp.acp_res[1]; adev->acp.acp_cell[1].platform_data = &i2s_pdata[0]; adev->acp.acp_cell[1].pdata_size = sizeof(struct i2s_platform_data); - r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell, 2); + r = mfd_add_devices(adev->acp.parent, 0, adev->acp.acp_cell, 2, NULL, 0, NULL); if (r) goto failure; r = device_for_each_child(adev->acp.parent, &adev->acp.acp_genpd->gpd, @@ -410,30 +412,34 @@ static int acp_hw_init(struct amdgpu_ip_block *ip_block) adev->acp.acp_res[4].end = adev->acp.acp_res[4].start; adev->acp.acp_cell[0].name = "acp_audio_dma"; + adev->acp.acp_cell[0].id = 0; adev->acp.acp_cell[0].num_resources = 5; adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0]; adev->acp.acp_cell[0].platform_data = &adev->asic_type; adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type); adev->acp.acp_cell[1].name = "designware-i2s"; + adev->acp.acp_cell[1].id = 1; adev->acp.acp_cell[1].num_resources = 1; adev->acp.acp_cell[1].resources = &adev->acp.acp_res[1]; adev->acp.acp_cell[1].platform_data = &i2s_pdata[0]; adev->acp.acp_cell[1].pdata_size = sizeof(struct i2s_platform_data); adev->acp.acp_cell[2].name = "designware-i2s"; + adev->acp.acp_cell[2].id = 2; adev->acp.acp_cell[2].num_resources = 1; adev->acp.acp_cell[2].resources = &adev->acp.acp_res[2]; adev->acp.acp_cell[2].platform_data = &i2s_pdata[1]; adev->acp.acp_cell[2].pdata_size = sizeof(struct i2s_platform_data); adev->acp.acp_cell[3].name = "designware-i2s"; + adev->acp.acp_cell[3].id = 3; adev->acp.acp_cell[3].num_resources = 1; adev->acp.acp_cell[3].resources = &adev->acp.acp_res[3]; adev->acp.acp_cell[3].platform_data = &i2s_pdata[2]; adev->acp.acp_cell[3].pdata_size = sizeof(struct i2s_platform_data); - r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell, ACP_DEVS); + r = mfd_add_devices(adev->acp.parent, 0, adev->acp.acp_cell, ACP_DEVS, NULL, 0, NULL); if (r) goto failure; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index bfbf874a1000..903c4706040d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2665,6 +2665,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) chip_name = "navi12"; break; case CHIP_CYAN_SKILLFISH: + if (adev->discovery.bin) + return 0; chip_name = "cyan_skillfish"; break; } @@ -3680,6 +3682,20 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev) "failed to release exclusive mode on fini\n"); } + /* + * Driver reload on the APU can fail due to firmware validation because + * the PSP is always running, as it is shared across the whole SoC. + * This same issue does not occur on dGPU because it has a mechanism + * that checks whether the PSP is running. A solution for those issues + * in the APU is to trigger a GPU reset, but this should be done during + * the unload phase to avoid adding boot latency and screen flicker. + */ + if ((adev->flags & AMD_IS_APU) && !adev->gmc.is_app_apu) { + r = amdgpu_asic_reset(adev); + if (r) + dev_err(adev->dev, "asic reset on %s failed\n", __func__); + } + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index c1461317eb29..e22cfa7c6d32 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -83,6 +83,18 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r; + /* + * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+. + * Such buffers cannot be safely accessed over P2P due to device-local + * compression metadata. Fallback to system-memory path instead. + * Device supports GFX12 (GC 12.x or newer) + * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag + * + */ + if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) && + bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) + attach->peer2peer = false; + /* * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+. * Such buffers cannot be safely accessed over P2P due to device-local diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 9dcf51991b5b..869bceb0fe2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -597,6 +597,9 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev) /* reserve engine 5 for firmware */ if (adev->enable_mes) vm_inv_engs[i] &= ~(1 << 5); + /* reserve engine 6 for uni mes */ + if (adev->enable_uni_mes) + vm_inv_engs[i] &= ~(1 << 6); /* reserve mmhub engine 3 for firmware */ if (adev->enable_umsch_mm) vm_inv_engs[i] &= ~(1 << 3); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index 55097ca10738..727342689d4b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -86,6 +86,11 @@ enum amdgpu_memory_partition { #define AMDGPU_MAX_MEM_RANGES 8 +#define AMDGPU_GMC9_FAULT_SOURCE_DATA_RETRY 0x80 +#define AMDGPU_GMC9_FAULT_SOURCE_DATA_READ 0x40 +#define AMDGPU_GMC9_FAULT_SOURCE_DATA_WRITE 0x20 +#define AMDGPU_GMC9_FAULT_SOURCE_DATA_EXE 0x10 + /* * GMC page fault information */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 7d8ef7ae10c2..0a0dcbf0798d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -224,6 +224,7 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, kfree((*job)->hw_fence); err_job: kfree(*job); + *job = NULL; return r; } @@ -245,7 +246,10 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, if (r) { if (entity) drm_sched_job_cleanup(&(*job)->base); + kfree((*job)->hw_vm_fence); + kfree((*job)->hw_fence); kfree(*job); + *job = NULL; } return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 9e2e098af86c..2a6cf7963dde 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -150,6 +150,8 @@ static void amdgpu_ras_critical_region_fini(struct amdgpu_device *adev); #ifdef CONFIG_X86_MCE_AMD static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev); +static void +amdgpu_unregister_bad_pages_mca_notifier(struct amdgpu_device *adev); struct mce_notifier_adev_list { struct amdgpu_device *devs[MAX_GPU_INSTANCE]; int num_gpu; @@ -3954,7 +3956,9 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev) mutex_unlock(&con->recovery_lock); amdgpu_ras_critical_region_init(adev); - +#ifdef CONFIG_X86_MCE_AMD + amdgpu_unregister_bad_pages_mca_notifier(adev); +#endif return 0; } /* recovery end */ @@ -4988,6 +4992,28 @@ static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev) notifier_registered = true; } } +static void amdgpu_unregister_bad_pages_mca_notifier(struct amdgpu_device *adev) +{ + int i, j; + + if (!notifier_registered && !mce_adev_list.num_gpu) + return; + for (i = 0, j = 0; i < mce_adev_list.num_gpu; i++) { + if (mce_adev_list.devs[i] == adev) + mce_adev_list.devs[i] = NULL; + if (!mce_adev_list.devs[i]) + ++j; + } + + if (j == mce_adev_list.num_gpu) { + mce_adev_list.num_gpu = 0; + /* Unregister x86 notifier with MCE subsystem. */ + if (notifier_registered) { + mce_unregister_decode_chain(&amdgpu_bad_page_nb); + notifier_registered = false; + } + } +} #endif struct amdgpu_ras *amdgpu_ras_get_context(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index cd8873c6931a..c596b6df2e2d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -520,9 +520,14 @@ static ssize_t amdgpu_ras_cper_debugfs_read(struct file *f, char __user *buf, return -ENOMEM; if (!(*offset)) { + /* Need at least 12 bytes for the header on the first read */ + if (size < ring_header_size) + return -EINVAL; + if (copy_to_user(buf, ring_header, ring_header_size)) return -EFAULT; buf += ring_header_size; + size -= ring_header_size; } r = amdgpu_ras_mgr_handle_ras_cmd(ring->adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 838a51b6098b..2b931e855abd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1329,7 +1329,7 @@ uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem) mem->mem_type == AMDGPU_PL_MMIO_REMAP)) { flags |= AMDGPU_PTE_SYSTEM; - if (ttm->caching == ttm_cached) + if (ttm && ttm->caching == ttm_cached) flags |= AMDGPU_PTE_SNOOPED; } @@ -1486,6 +1486,7 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, if (r) goto out; + mutex_lock(&adev->mman.gtt_window_lock); amdgpu_res_first(abo->tbo.resource, offset, len, &src_mm); src_addr = amdgpu_ttm_domain_start(adev, bo->resource->mem_type) + src_mm.start; @@ -1500,6 +1501,7 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo, WARN_ON(job->ibs[0].length_dw > num_dw); fence = amdgpu_job_submit(job); + mutex_unlock(&adev->mman.gtt_window_lock); if (!dma_fence_wait_timeout(fence, false, adev->sdma_timeout)) r = -ETIMEDOUT; @@ -2185,8 +2187,10 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable) } else { drm_sched_entity_destroy(&adev->mman.high_pr); drm_sched_entity_destroy(&adev->mman.low_pr); - dma_fence_put(man->move); - man->move = NULL; + /* Drop all the old fences since re-creating the scheduler entities + * will allocate new contexts. + */ + ttm_resource_manager_cleanup(man); } /* this just adjusts TTM size idea, which sets lpfn to the correct value */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 7fc081e88b6a..a67285118c37 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1069,7 +1069,7 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params, } /* Prepare a TLB flush fence to be attached to PTs */ - if (!params->unlocked && vm->is_compute_context) { + if (!params->unlocked) { amdgpu_vm_tlb_fence_create(params->adev, vm, fence); /* Makes sure no PD/PT is freed before the flush */ @@ -2093,7 +2093,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo *bo = before->bo_va->base.bo; amdgpu_vm_it_insert(before, &vm->va); - if (before->flags & AMDGPU_PTE_PRT_FLAG(adev)) + if (before->flags & AMDGPU_VM_PAGE_PRT) amdgpu_vm_prt_get(adev); if (amdgpu_vm_is_bo_always_valid(vm, bo) && @@ -2108,7 +2108,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo *bo = after->bo_va->base.bo; amdgpu_vm_it_insert(after, &vm->va); - if (after->flags & AMDGPU_PTE_PRT_FLAG(adev)) + if (after->flags & AMDGPU_VM_PAGE_PRT) amdgpu_vm_prt_get(adev); if (amdgpu_vm_is_bo_always_valid(vm, bo) && @@ -2916,8 +2916,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) switch (args->in.op) { case AMDGPU_VM_OP_RESERVE_VMID: /* We only have requirement to reserve vmid from gfxhub */ - amdgpu_vmid_alloc_reserved(adev, vm, AMDGPU_GFXHUB(0)); - break; + return amdgpu_vmid_alloc_reserved(adev, vm, AMDGPU_GFXHUB(0)); case AMDGPU_VM_OP_UNRESERVE_VMID: amdgpu_vmid_free_reserved(adev, vm, AMDGPU_GFXHUB(0)); break; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index 41f4705bdbbd..876a3256dba4 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -156,6 +156,9 @@ static int cik_ih_irq_init(struct amdgpu_device *adev) /* enable irqs */ cik_ih_enable_interrupts(adev); + if (adev->irq.ih_soft.ring_size) + adev->irq.ih_soft.enabled = true; + return 0; } @@ -192,6 +195,9 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev, wptr = le32_to_cpu(*ih->wptr_cpu); + if (ih == &adev->irq.ih_soft) + goto out; + if (wptr & IH_RB_WPTR__RB_OVERFLOW_MASK) { wptr &= ~IH_RB_WPTR__RB_OVERFLOW_MASK; /* When a ring buffer overflow happen start parsing interrupt @@ -211,6 +217,8 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev, tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(mmIH_RB_CNTL, tmp); } + +out: return (wptr & ih->ptr_mask); } @@ -306,6 +314,10 @@ static int cik_ih_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + r = amdgpu_ih_ring_init(adev, &adev->irq.ih_soft, IH_SW_RING_SIZE, true); + if (r) + return r; + r = amdgpu_irq_init(adev); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index 2f891fb846d5..bc7a2e06ab5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -157,6 +157,9 @@ static int cz_ih_irq_init(struct amdgpu_device *adev) /* enable interrupts */ cz_ih_enable_interrupts(adev); + if (adev->irq.ih_soft.ring_size) + adev->irq.ih_soft.enabled = true; + return 0; } @@ -194,6 +197,9 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev, wptr = le32_to_cpu(*ih->wptr_cpu); + if (ih == &adev->irq.ih_soft) + goto out; + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) goto out; @@ -297,6 +303,10 @@ static int cz_ih_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + r = amdgpu_ih_ring_init(adev, &adev->irq.ih_soft, IH_SW_RING_SIZE, true); + if (r) + return r; + r = amdgpu_irq_init(adev); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 02d7cfae22bd..8a2ee2de390f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -5874,9 +5874,9 @@ static void gfx_v11_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, if (flags & AMDGPU_IB_PREEMPTED) control |= INDIRECT_BUFFER_PRE_RESUME(1); - if (vmid) + if (vmid && !ring->adev->gfx.rs64_enable) gfx_v11_0_ring_emit_de_meta(ring, - (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? true : false); + !amdgpu_sriov_vf(ring->adev) && (flags & AMDGPU_IB_PREEMPTED)); } amdgpu_ring_write(ring, header); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index d7499be8c4bf..ce6e04242c52 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -103,8 +103,10 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev, uint32_t vmhub_index = entry->client_id == SOC15_IH_CLIENTID_VMC ? AMDGPU_MMHUB0(0) : AMDGPU_GFXHUB(0); struct amdgpu_vmhub *hub = &adev->vmhub[vmhub_index]; - bool retry_fault = !!(entry->src_data[1] & 0x80); - bool write_fault = !!(entry->src_data[1] & 0x20); + bool retry_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_RETRY); + bool write_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_WRITE); struct amdgpu_task_info *task_info; uint32_t status = 0; u64 addr; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 7bc389d9f5c4..ba59ee8e398a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -103,12 +103,41 @@ static int gmc_v11_0_process_interrupt(struct amdgpu_device *adev, uint32_t vmhub_index = entry->client_id == SOC21_IH_CLIENTID_VMC ? AMDGPU_MMHUB0(0) : AMDGPU_GFXHUB(0); struct amdgpu_vmhub *hub = &adev->vmhub[vmhub_index]; + bool retry_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_RETRY); + bool write_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_WRITE); uint32_t status = 0; u64 addr; addr = (u64)entry->src_data[0] << 12; addr |= ((u64)entry->src_data[1] & 0xf) << 44; + if (retry_fault) { + /* Returning 1 here also prevents sending the IV to the KFD */ + + /* Process it only if it's the first fault for this address */ + if (entry->ih != &adev->irq.ih_soft && + amdgpu_gmc_filter_faults(adev, entry->ih, addr, entry->pasid, + entry->timestamp)) + return 1; + + /* Delegate it to a different ring if the hardware hasn't + * already done it. + */ + if (entry->ih == &adev->irq.ih) { + amdgpu_irq_delegate(adev, entry, 8); + return 1; + } + + /* Try to handle the recoverable page faults by filling page + * tables + */ + if (amdgpu_vm_handle_fault(adev, entry->pasid, 0, 0, addr, + entry->timestamp, write_fault)) + return 1; + } + if (!amdgpu_sriov_vf(adev)) { /* * Issue a dummy read to wait for the status register to diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index cad2d19105c4..7a9d6894e321 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -91,6 +91,10 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry) { struct amdgpu_vmhub *hub; + bool retry_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_RETRY); + bool write_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_WRITE); uint32_t status = 0; u64 addr; @@ -102,6 +106,31 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev, else hub = &adev->vmhub[AMDGPU_GFXHUB(0)]; + if (retry_fault) { + /* Returning 1 here also prevents sending the IV to the KFD */ + + /* Process it only if it's the first fault for this address */ + if (entry->ih != &adev->irq.ih_soft && + amdgpu_gmc_filter_faults(adev, entry->ih, addr, entry->pasid, + entry->timestamp)) + return 1; + + /* Delegate it to a different ring if the hardware hasn't + * already done it. + */ + if (entry->ih == &adev->irq.ih) { + amdgpu_irq_delegate(adev, entry, 8); + return 1; + } + + /* Try to handle the recoverable page faults by filling page + * tables + */ + if (amdgpu_vm_handle_fault(adev, entry->pasid, 0, 0, addr, + entry->timestamp, write_fault)) + return 1; + } + if (!amdgpu_sriov_vf(adev)) { /* * Issue a dummy read to wait for the status register to diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 499dfd78092d..a8ec95f42926 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -610,23 +610,21 @@ static void gmc_v6_0_gart_disable(struct amdgpu_device *adev) } static void gmc_v6_0_vm_decode_fault(struct amdgpu_device *adev, - u32 status, u32 addr, u32 mc_client) + u32 status, u32 addr) { u32 mc_id; u32 vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID); u32 protections = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, PROTECTIONS); - char block[5] = { mc_client >> 24, (mc_client >> 16) & 0xff, - (mc_client >> 8) & 0xff, mc_client & 0xff, 0 }; mc_id = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, MEMORY_CLIENT_ID); - dev_err(adev->dev, "VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n", + dev_err(adev->dev, "VM fault (0x%02x, vmid %d) at page %u, %s from %d\n", protections, vmid, addr, REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, MEMORY_CLIENT_RW) ? - "write" : "read", block, mc_client, mc_id); + "write" : "read", mc_id); } static const u32 mc_cg_registers[] = { @@ -1072,6 +1070,12 @@ static int gmc_v6_0_process_interrupt(struct amdgpu_device *adev, { u32 addr, status; + /* Delegate to the soft IRQ handler ring */ + if (adev->irq.ih_soft.enabled && entry->ih != &adev->irq.ih_soft) { + amdgpu_irq_delegate(adev, entry, 4); + return 1; + } + addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1); @@ -1079,6 +1083,10 @@ static int gmc_v6_0_process_interrupt(struct amdgpu_device *adev, if (!addr && !status) return 0; + amdgpu_vm_update_fault_cache(adev, entry->pasid, + ((u64)addr) << AMDGPU_GPU_PAGE_SHIFT, + status, AMDGPU_GFXHUB(0)); + if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST) gmc_v6_0_set_fault_enable_default(adev, false); @@ -1089,7 +1097,7 @@ static int gmc_v6_0_process_interrupt(struct amdgpu_device *adev, addr); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); - gmc_v6_0_vm_decode_fault(adev, status, addr, 0); + gmc_v6_0_vm_decode_fault(adev, status, addr); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 0e5e54d0a9a5..fbd0bf147f50 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -1261,6 +1261,12 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, { u32 addr, status, mc_client, vmid; + /* Delegate to the soft IRQ handler ring */ + if (adev->irq.ih_soft.enabled && entry->ih != &adev->irq.ih_soft) { + amdgpu_irq_delegate(adev, entry, 4); + return 1; + } + addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index e1509480dfc2..6551b60f2584 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1439,6 +1439,12 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, return 0; } + /* Delegate to the soft IRQ handler ring */ + if (adev->irq.ih_soft.enabled && entry->ih != &adev->irq.ih_soft) { + amdgpu_irq_delegate(adev, entry, 4); + return 1; + } + addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index e716097dfde4..8ad7519f7b58 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -544,8 +544,10 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - bool retry_fault = !!(entry->src_data[1] & 0x80); - bool write_fault = !!(entry->src_data[1] & 0x20); + bool retry_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_RETRY); + bool write_fault = !!(entry->src_data[1] & + AMDGPU_GMC9_FAULT_SOURCE_DATA_WRITE); uint32_t status = 0, cid = 0, rw = 0, fed = 0; struct amdgpu_task_info *task_info; struct amdgpu_vmhub *hub; diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index 1317ede131b6..01cadf898c00 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -157,6 +157,9 @@ static int iceland_ih_irq_init(struct amdgpu_device *adev) /* enable interrupts */ iceland_ih_enable_interrupts(adev); + if (adev->irq.ih_soft.ring_size) + adev->irq.ih_soft.enabled = true; + return 0; } @@ -194,6 +197,9 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev, wptr = le32_to_cpu(*ih->wptr_cpu); + if (ih == &adev->irq.ih_soft) + goto out; + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) goto out; @@ -296,6 +302,10 @@ static int iceland_ih_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + r = amdgpu_ih_ring_init(adev, &adev->irq.ih_soft, IH_SW_RING_SIZE, true); + if (r) + return r; + r = amdgpu_irq_init(adev); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 0ceeb19df2e5..217040044987 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1390,7 +1390,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 3): - if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq) + if (adev->sdma.instance[0].fw_version >= 29 && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 1, 0): diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index 1df00f8a2406..66f650f87243 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -96,6 +96,9 @@ static int si_ih_irq_init(struct amdgpu_device *adev) pci_set_master(adev->pdev); si_ih_enable_interrupts(adev); + if (adev->irq.ih_soft.ring_size) + adev->irq.ih_soft.enabled = true; + return 0; } @@ -112,6 +115,9 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev, wptr = le32_to_cpu(*ih->wptr_cpu); + if (ih == &adev->irq.ih_soft) + goto out; + if (wptr & IH_RB_WPTR__RB_OVERFLOW_MASK) { wptr &= ~IH_RB_WPTR__RB_OVERFLOW_MASK; dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n", @@ -127,6 +133,8 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev, tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK; WREG32(IH_RB_CNTL, tmp); } + +out: return (wptr & ih->ptr_mask); } @@ -175,6 +183,10 @@ static int si_ih_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + r = amdgpu_ih_ring_init(adev, &adev->irq.ih_soft, IH_SW_RING_SIZE, true); + if (r) + return r; + return amdgpu_irq_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 9785fada4fa7..42f5d9c0e3af 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -853,10 +853,6 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev) { u32 sol_reg; - /* CP hangs in IGT reloading test on RN, reset to WA */ - if (adev->asic_type == CHIP_RENOIR) - return true; - if (amdgpu_gmc_need_reset_on_init(adev)) return true; if (amdgpu_psp_tos_reload_needed(adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index 7d17ae56f901..ee8038df17e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -159,6 +159,9 @@ static int tonga_ih_irq_init(struct amdgpu_device *adev) /* enable interrupts */ tonga_ih_enable_interrupts(adev); + if (adev->irq.ih_soft.ring_size) + adev->irq.ih_soft.enabled = true; + return 0; } @@ -196,6 +199,9 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev, wptr = le32_to_cpu(*ih->wptr_cpu); + if (ih == &adev->irq.ih_soft) + goto out; + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) goto out; @@ -306,6 +312,10 @@ static int tonga_ih_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + r = amdgpu_ih_ring_init(adev, &adev->irq.ih_soft, IH_SW_RING_SIZE, true); + if (r) + return r; + adev->irq.ih.use_doorbell = true; adev->irq.ih.doorbell_index = adev->doorbell_index.ih; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index eacf4e93ba2f..cb7123ec1a5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -141,7 +141,7 @@ static int vcn_v4_0_3_late_init(struct amdgpu_ip_block *ip_block) adev->vcn.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]); - if (amdgpu_dpm_reset_vcn_is_supported(adev)) + if (amdgpu_dpm_reset_vcn_is_supported(adev) && !amdgpu_sriov_vf(adev)) adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index 714350cabf2f..8bd457dea4cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -122,7 +122,9 @@ static int vcn_v5_0_1_late_init(struct amdgpu_ip_block *ip_block) switch (amdgpu_ip_version(adev, MP0_HWIP, 0)) { case IP_VERSION(13, 0, 12): - if ((adev->psp.sos.fw_version >= 0x00450025) && amdgpu_dpm_reset_vcn_is_supported(adev)) + if ((adev->psp.sos.fw_version >= 0x00450025) && + amdgpu_dpm_reset_vcn_is_supported(adev) && + !amdgpu_sriov_vf(adev)) adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; break; default: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 5c98746eb72d..811636af14ea 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -530,7 +530,9 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version", dev->gpu->kfd->sdma_fw_version); sysfs_show_64bit_prop(buffer, offs, "unique_id", - dev->gpu->xcp ? + dev->gpu->xcp && + (dev->gpu->xcp->xcp_mgr->mode != + AMDGPU_SPX_PARTITION_MODE) ? dev->gpu->xcp->unique_id : dev->gpu->adev->unique_id); sysfs_show_32bit_prop(buffer, offs, "num_xcc", diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile index 7329b8cc2576..8e949fe77312 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile @@ -39,7 +39,8 @@ AMDGPUDM = \ amdgpu_dm_psr.o \ amdgpu_dm_replay.o \ amdgpu_dm_quirks.o \ - amdgpu_dm_wb.o + amdgpu_dm_wb.o \ + amdgpu_dm_colorop.o ifdef CONFIG_DRM_AMD_DC_FP AMDGPUDM += dc_fpu.o 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 e6728fd12eeb..740711ac1037 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3932,6 +3932,97 @@ void amdgpu_dm_update_connector_after_detect( mutex_unlock(&dev->mode_config.mutex); } +static bool are_sinks_equal(const struct dc_sink *sink1, const struct dc_sink *sink2) +{ + if (!sink1 || !sink2) + return false; + if (sink1->sink_signal != sink2->sink_signal) + return false; + + if (sink1->dc_edid.length != sink2->dc_edid.length) + return false; + + if (memcmp(sink1->dc_edid.raw_edid, sink2->dc_edid.raw_edid, + sink1->dc_edid.length) != 0) + return false; + return true; +} + + +/** + * DOC: hdmi_hpd_debounce_work + * + * HDMI HPD debounce delay in milliseconds. When an HDMI display toggles HPD + * (such as during power save transitions), this delay determines how long to + * wait before processing the HPD event. This allows distinguishing between a + * physical unplug (>hdmi_hpd_debounce_delay) + * and a spontaneous RX HPD toggle (base; + struct drm_device *dev = connector->dev; + struct amdgpu_device *adev = drm_to_adev(dev); + struct dc *dc = aconnector->dc_link->ctx->dc; + bool fake_reconnect = false; + bool reallow_idle = false; + bool ret = false; + guard(mutex)(&aconnector->hpd_lock); + + /* Re-detect the display */ + scoped_guard(mutex, &adev->dm.dc_lock) { + if (dc->caps.ips_support && dc->ctx->dmub_srv->idle_allowed) { + dc_allow_idle_optimizations(dc, false); + reallow_idle = true; + } + ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + } + + if (ret) { + /* Apply workaround delay for certain panels */ + apply_delay_after_dpcd_poweroff(adev, aconnector->dc_sink); + /* Compare sinks to determine if this was a spontaneous HPD toggle */ + if (are_sinks_equal(aconnector->dc_link->local_sink, aconnector->hdmi_prev_sink)) { + /* + * Sinks match - this was a spontaneous HDMI HPD toggle. + */ + drm_dbg_kms(dev, "HDMI HPD: Sink unchanged after debounce, internal re-enable\n"); + fake_reconnect = true; + } + + /* Update connector state */ + amdgpu_dm_update_connector_after_detect(aconnector); + + drm_modeset_lock_all(dev); + dm_restore_drm_connector_state(dev, connector); + drm_modeset_unlock_all(dev); + + /* Only notify OS if sink actually changed */ + if (!fake_reconnect && aconnector->base.force == DRM_FORCE_UNSPECIFIED) + drm_kms_helper_hotplug_event(dev); + } + + /* Release the cached sink reference */ + if (aconnector->hdmi_prev_sink) { + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = NULL; + } + + scoped_guard(mutex, &adev->dm.dc_lock) { + if (reallow_idle && dc->caps.ips_support) + dc_allow_idle_optimizations(dc, true); + } +} + static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) { struct drm_connector *connector = &aconnector->base; @@ -3941,6 +4032,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) struct dm_connector_state *dm_con_state = to_dm_connector_state(connector->state); struct dc *dc = aconnector->dc_link->ctx->dc; bool ret = false; + bool debounce_required = false; if (adev->dm.disable_hpd_irq) return; @@ -3963,6 +4055,14 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) if (!dc_link_detect_connection_type(aconnector->dc_link, &new_connection_type)) drm_err(adev_to_drm(adev), "KMS: Failed to detect connector\n"); + /* + * Check for HDMI disconnect with debounce enabled. + */ + debounce_required = (aconnector->hdmi_hpd_debounce_delay_ms > 0 && + dc_is_hdmi_signal(aconnector->dc_link->connector_signal) && + new_connection_type == dc_connection_none && + aconnector->dc_link->local_sink != NULL); + if (aconnector->base.force && new_connection_type == dc_connection_none) { emulated_link_detect(aconnector->dc_link); @@ -3972,7 +4072,34 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) if (aconnector->base.force == DRM_FORCE_UNSPECIFIED) drm_kms_helper_connector_hotplug_event(connector); + } else if (debounce_required) { + /* + * HDMI disconnect detected - schedule delayed work instead of + * processing immediately. This allows us to coalesce spurious + * HDMI signals from physical unplugs. + */ + drm_dbg_kms(dev, "HDMI HPD: Disconnect detected, scheduling debounce work (%u ms)\n", + aconnector->hdmi_hpd_debounce_delay_ms); + + /* Cache the current sink for later comparison */ + if (aconnector->hdmi_prev_sink) + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = aconnector->dc_link->local_sink; + if (aconnector->hdmi_prev_sink) + dc_sink_retain(aconnector->hdmi_prev_sink); + + /* Schedule delayed detection. */ + if (mod_delayed_work(system_wq, + &aconnector->hdmi_hpd_debounce_work, + msecs_to_jiffies(aconnector->hdmi_hpd_debounce_delay_ms))) + drm_dbg_kms(dev, "HDMI HPD: Re-scheduled debounce work\n"); + } else { + + /* If the aconnector->hdmi_hpd_debounce_work is scheduled, exit early */ + if (delayed_work_pending(&aconnector->hdmi_hpd_debounce_work)) + return; + scoped_guard(mutex, &adev->dm.dc_lock) { dc_exit_ips_for_hw_access(dc); ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); @@ -4998,6 +5125,21 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, struct dc_link *link; u32 brightness; bool rc, reallow_idle = false; + struct drm_connector *connector; + + list_for_each_entry(connector, &dm->ddev->mode_config.connector_list, head) { + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + if (aconnector->bl_idx != bl_idx) + continue; + + /* if connector is off, save the brightness for next time it's on */ + if (!aconnector->base.encoder) { + dm->brightness[bl_idx] = user_brightness; + dm->actual_brightness[bl_idx] = 0; + return; + } + } amdgpu_dm_update_backlight_caps(dm, bl_idx); caps = &dm->backlight_caps[bl_idx]; @@ -5888,6 +6030,10 @@ fill_plane_color_attributes(const struct drm_plane_state *plane_state, *color_space = COLOR_SPACE_SRGB; + /* Ignore properties when DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE is set */ + if (plane_state->state && plane_state->state->plane_color_pipeline) + return 0; + /* DRM color properties only affect non-RGB formats. */ if (format < SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) return 0; @@ -7590,6 +7736,13 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) if (aconnector->mst_mgr.dev) drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); + /* Cancel and flush any pending HDMI HPD debounce work */ + cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work); + if (aconnector->hdmi_prev_sink) { + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = NULL; + } + if (aconnector->bl_idx != -1) { backlight_device_unregister(dm->backlight_dev[aconnector->bl_idx]); dm->backlight_dev[aconnector->bl_idx] = NULL; @@ -8686,8 +8839,14 @@ static void amdgpu_dm_connector_add_freesync_modes(struct drm_connector *connect if (!(amdgpu_freesync_vid_mode && drm_edid)) return; - if (!amdgpu_dm_connector->dc_sink || amdgpu_dm_connector->dc_sink->edid_caps.analog || - !dc_supports_vrr(amdgpu_dm_connector->dc_sink->ctx->dce_version)) + if (!amdgpu_dm_connector->dc_sink || !amdgpu_dm_connector->dc_link) + return; + + if (!dc_supports_vrr(amdgpu_dm_connector->dc_sink->ctx->dce_version)) + return; + + if (dc_connector_supports_analog(amdgpu_dm_connector->dc_link->link_id.id) && + amdgpu_dm_connector->dc_sink->edid_caps.analog) return; if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) @@ -8699,11 +8858,11 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); + struct dc_link *dc_link = amdgpu_dm_connector->dc_link; struct drm_encoder *encoder; const struct drm_edid *drm_edid = amdgpu_dm_connector->drm_edid; - struct dc_link_settings *verified_link_cap = - &amdgpu_dm_connector->dc_link->verified_link_cap; - const struct dc *dc = amdgpu_dm_connector->dc_link->dc; + struct dc_link_settings *verified_link_cap = &dc_link->verified_link_cap; + const struct dc *dc = dc_link->dc; encoder = amdgpu_dm_connector_to_encoder(connector); @@ -8714,7 +8873,9 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) amdgpu_dm_connector->num_modes += drm_add_modes_noedid(connector, 1920, 1080); - if (amdgpu_dm_connector->dc_sink && amdgpu_dm_connector->dc_sink->edid_caps.analog) { + if (amdgpu_dm_connector->dc_sink && + amdgpu_dm_connector->dc_sink->edid_caps.analog && + dc_connector_supports_analog(dc_link->link_id.id)) { /* Analog monitor connected by DAC load detection. * Add common modes. It will be up to the user to select one that works. */ @@ -8769,6 +8930,10 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, mutex_init(&aconnector->hpd_lock); mutex_init(&aconnector->handle_mst_msg_ready); + aconnector->hdmi_hpd_debounce_delay_ms = AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS; + INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); + aconnector->hdmi_prev_sink = NULL; + /* * configure support HPD hot plug connector_>polled default value is 0 * which means HPD hot plug not supported diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 5a7aa903bd3c..ef97cede9926 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -59,6 +59,7 @@ #define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL) +#define AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS 1500 /* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" @@ -819,6 +820,11 @@ struct amdgpu_dm_connector { bool pack_sdp_v1_3; enum adaptive_sync_type as_type; struct amdgpu_hdmi_vsdb_info vsdb_info; + + /* HDMI HPD debounce support */ + unsigned int hdmi_hpd_debounce_delay_ms; + struct delayed_work hdmi_hpd_debounce_work; + struct dc_sink *hdmi_prev_sink; }; static inline void amdgpu_dm_set_mst_status(uint8_t *status, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index a4ac6d442278..1dcc79b35225 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -26,12 +26,39 @@ #include "amdgpu.h" #include "amdgpu_mode.h" #include "amdgpu_dm.h" +#include "amdgpu_dm_colorop.h" #include "dc.h" #include "modules/color/color_gamma.h" /** * DOC: overview * + * We have three types of color management in the AMD display driver. + * 1. the legacy &drm_crtc DEGAMMA, CTM, and GAMMA properties + * 2. AMD driver private color management on &drm_plane and &drm_crtc + * 3. AMD plane color pipeline + * + * The CRTC properties are the original color management. When they were + * implemented per-plane color management was not a thing yet. Because + * of that we could get away with plumbing the DEGAMMA and CTM + * properties to pre-blending HW functions. This is incompatible with + * per-plane color management, such as via the AMD private properties or + * the new drm_plane color pipeline. The only compatible CRTC property + * with per-plane color management is the GAMMA property as it is + * applied post-blending. + * + * The AMD driver private color management properties are only exposed + * when the kernel is built explicitly with -DAMD_PRIVATE_COLOR. They + * are temporary building blocks on the path to full-fledged &drm_plane + * and &drm_crtc color pipelines and lay the driver's groundwork for the + * color pipelines. + * + * The AMD plane color pipeline describes AMD's &drm_colorops via the + * &drm_plane's COLOR_PIPELINE property. + * + * drm_crtc Properties + * ------------------- + * * The DC interface to HW gives us the following color management blocks * per pipe (surface): * @@ -42,36 +69,93 @@ * - Surface regamma LUT (normalized) * - Output CSC (normalized) * - * But these aren't a direct mapping to DRM color properties. The current DRM - * interface exposes CRTC degamma, CRTC CTM and CRTC regamma while our hardware - * is essentially giving: + * But these aren't a direct mapping to DRM color properties. The + * current DRM interface exposes CRTC degamma, CRTC CTM and CRTC regamma + * while our hardware is essentially giving: * * Plane CTM -> Plane degamma -> Plane CTM -> Plane regamma -> Plane CTM * - * The input gamma LUT block isn't really applicable here since it operates - * on the actual input data itself rather than the HW fp representation. The - * input and output CSC blocks are technically available to use as part of - * the DC interface but are typically used internally by DC for conversions - * between color spaces. These could be blended together with user - * adjustments in the future but for now these should remain untouched. + * The input gamma LUT block isn't really applicable here since it + * operates on the actual input data itself rather than the HW fp + * representation. The input and output CSC blocks are technically + * available to use as part of the DC interface but are typically used + * internally by DC for conversions between color spaces. These could be + * blended together with user adjustments in the future but for now + * these should remain untouched. * - * The pipe blending also happens after these blocks so we don't actually - * support any CRTC props with correct blending with multiple planes - but we - * can still support CRTC color management properties in DM in most single - * plane cases correctly with clever management of the DC interface in DM. + * The pipe blending also happens after these blocks so we don't + * actually support any CRTC props with correct blending with multiple + * planes - but we can still support CRTC color management properties in + * DM in most single plane cases correctly with clever management of the + * DC interface in DM. * - * As per DRM documentation, blocks should be in hardware bypass when their - * respective property is set to NULL. A linear DGM/RGM LUT should also - * considered as putting the respective block into bypass mode. + * As per DRM documentation, blocks should be in hardware bypass when + * their respective property is set to NULL. A linear DGM/RGM LUT should + * also considered as putting the respective block into bypass mode. * - * This means that the following - * configuration is assumed to be the default: + * This means that the following configuration is assumed to be the + * default: + * + * Plane DGM Bypass -> Plane CTM Bypass -> Plane RGM Bypass -> ... CRTC + * DGM Bypass -> CRTC CTM Bypass -> CRTC RGM Bypass + * + * AMD Private Color Management on drm_plane + * ----------------------------------------- + * + * The AMD private color management properties on a &drm_plane are: + * + * - AMD_PLANE_DEGAMMA_LUT + * - AMD_PLANE_DEGAMMA_LUT_SIZE + * - AMD_PLANE_DEGAMMA_TF + * - AMD_PLANE_HDR_MULT + * - AMD_PLANE_CTM + * - AMD_PLANE_SHAPER_LUT + * - AMD_PLANE_SHAPER_LUT_SIZE + * - AMD_PLANE_SHAPER_TF + * - AMD_PLANE_LUT3D + * - AMD_PLANE_LUT3D_SIZE + * - AMD_PLANE_BLEND_LUT + * - AMD_PLANE_BLEND_LUT_SIZE + * - AMD_PLANE_BLEND_TF + * + * The AMD private color management property on a &drm_crtc is: + * + * - AMD_CRTC_REGAMMA_TF + * + * Use of these properties is discouraged. + * + * AMD plane color pipeline + * ------------------------ + * + * The AMD &drm_plane color pipeline is advertised for DCN generations + * 3.0 and newer. It exposes these elements in this order: + * + * 1. 1D curve colorop + * 2. Multiplier + * 3. 3x4 CTM + * 4. 1D curve colorop + * 5. 1D LUT + * 6. 3D LUT + * 7. 1D curve colorop + * 8. 1D LUT + * + * The multiplier (#2) is a simple multiplier that is applied to all + * channels. + * + * The 3x4 CTM (#3) is a simple 3x4 matrix. + * + * #1, and #7 are non-linear to linear curves. #4 is a linear to + * non-linear curve. They support sRGB, PQ, and BT.709/BT.2020 EOTFs or + * their inverse. + * + * The 1D LUTs (#5 and #8) are plain 4096 entry LUTs. + * + * The 3DLUT (#6) is a tetrahedrally interpolated 17 cube LUT. * - * Plane DGM Bypass -> Plane CTM Bypass -> Plane RGM Bypass -> ... - * CRTC DGM Bypass -> CRTC CTM Bypass -> CRTC RGM Bypass */ #define MAX_DRM_LUT_VALUE 0xFFFF +#define MAX_DRM_LUT32_VALUE 0xFFFFFFFF #define SDR_WHITE_LEVEL_INIT_VALUE 80 /** @@ -341,6 +425,21 @@ __extract_blob_lut(const struct drm_property_blob *blob, uint32_t *size) return blob ? (struct drm_color_lut *)blob->data : NULL; } +/** + * __extract_blob_lut32 - Extracts the DRM lut and lut size from a blob. + * @blob: DRM color mgmt property blob + * @size: lut size + * + * Returns: + * DRM LUT or NULL + */ +static const struct drm_color_lut32 * +__extract_blob_lut32(const struct drm_property_blob *blob, uint32_t *size) +{ + *size = blob ? drm_color_lut32_size(blob) : 0; + return blob ? (struct drm_color_lut32 *)blob->data : NULL; +} + /** * __is_lut_linear - check if the given lut is a linear mapping of values * @lut: given lut to check values @@ -414,6 +513,24 @@ static void __drm_lut_to_dc_gamma(const struct drm_color_lut *lut, } } +/** + * __drm_lut32_to_dc_gamma - convert the drm_color_lut to dc_gamma. + * @lut: DRM lookup table for color conversion + * @gamma: DC gamma to set entries + * + * The conversion depends on the size of the lut - whether or not it's legacy. + */ +static void __drm_lut32_to_dc_gamma(const struct drm_color_lut32 *lut, struct dc_gamma *gamma) +{ + int i; + + for (i = 0; i < MAX_COLOR_LUT_ENTRIES; i++) { + gamma->entries.red[i] = dc_fixpt_from_fraction(lut[i].red, MAX_DRM_LUT32_VALUE); + gamma->entries.green[i] = dc_fixpt_from_fraction(lut[i].green, MAX_DRM_LUT32_VALUE); + gamma->entries.blue[i] = dc_fixpt_from_fraction(lut[i].blue, MAX_DRM_LUT32_VALUE); + } +} + /** * __drm_ctm_to_dc_matrix - converts a DRM CTM to a DC CSC float matrix * @ctm: DRM color transformation matrix @@ -566,6 +683,63 @@ static int __set_output_tf(struct dc_transfer_func *func, return res ? 0 : -ENOMEM; } +/** + * __set_output_tf_32 - calculates the output transfer function based on expected input space. + * @func: transfer function + * @lut: lookup table that defines the color space + * @lut_size: size of respective lut + * @has_rom: if ROM can be used for hardcoded curve + * + * Returns: + * 0 in case of success. -ENOMEM if fails. + */ +static int __set_output_tf_32(struct dc_transfer_func *func, + const struct drm_color_lut32 *lut, uint32_t lut_size, + bool has_rom) +{ + struct dc_gamma *gamma = NULL; + struct calculate_buffer cal_buffer = {0}; + bool res; + + cal_buffer.buffer_index = -1; + + if (lut_size) { + gamma = dc_create_gamma(); + if (!gamma) + return -ENOMEM; + + gamma->num_entries = lut_size; + __drm_lut32_to_dc_gamma(lut, gamma); + } + + if (func->tf == TRANSFER_FUNCTION_LINEAR) { + /* + * Color module doesn't like calculating regamma params + * on top of a linear input. But degamma params can be used + * instead to simulate this. + */ + if (gamma) + gamma->type = GAMMA_CUSTOM; + res = mod_color_calculate_degamma_params(NULL, func, + gamma, gamma != NULL); + } else { + /* + * Assume sRGB. The actual mapping will depend on whether the + * input was legacy or not. + */ + if (gamma) + gamma->type = GAMMA_CS_TFM_1D; + res = mod_color_calculate_regamma_params(func, gamma, gamma != NULL, + has_rom, NULL, &cal_buffer); + } + + if (gamma) + dc_gamma_release(&gamma); + + return res ? 0 : -ENOMEM; +} + + static int amdgpu_dm_set_atomic_regamma(struct dc_transfer_func *out_tf, const struct drm_color_lut *regamma_lut, uint32_t regamma_size, bool has_rom, @@ -638,6 +812,42 @@ static int __set_input_tf(struct dc_color_caps *caps, struct dc_transfer_func *f return res ? 0 : -ENOMEM; } +/** + * __set_input_tf_32 - calculates the input transfer function based on expected + * input space. + * @caps: dc color capabilities + * @func: transfer function + * @lut: lookup table that defines the color space + * @lut_size: size of respective lut. + * + * Returns: + * 0 in case of success. -ENOMEM if fails. + */ +static int __set_input_tf_32(struct dc_color_caps *caps, struct dc_transfer_func *func, + const struct drm_color_lut32 *lut, uint32_t lut_size) +{ + struct dc_gamma *gamma = NULL; + bool res; + + if (lut_size) { + gamma = dc_create_gamma(); + if (!gamma) + return -ENOMEM; + + gamma->type = GAMMA_CUSTOM; + gamma->num_entries = lut_size; + + __drm_lut32_to_dc_gamma(lut, gamma); + } + + res = mod_color_calculate_degamma_params(caps, func, gamma, gamma != NULL); + + if (gamma) + dc_gamma_release(&gamma); + + return res ? 0 : -ENOMEM; +} + static enum dc_transfer_func_predefined amdgpu_tf_to_dc_tf(enum amdgpu_transfer_function tf) { @@ -667,6 +877,27 @@ amdgpu_tf_to_dc_tf(enum amdgpu_transfer_function tf) } } +static enum dc_transfer_func_predefined +amdgpu_colorop_tf_to_dc_tf(enum drm_colorop_curve_1d_type tf) +{ + switch (tf) { + case DRM_COLOROP_1D_CURVE_SRGB_EOTF: + case DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF: + return TRANSFER_FUNCTION_SRGB; + case DRM_COLOROP_1D_CURVE_PQ_125_EOTF: + case DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF: + return TRANSFER_FUNCTION_PQ; + case DRM_COLOROP_1D_CURVE_BT2020_INV_OETF: + case DRM_COLOROP_1D_CURVE_BT2020_OETF: + return TRANSFER_FUNCTION_BT709; + case DRM_COLOROP_1D_CURVE_GAMMA22: + case DRM_COLOROP_1D_CURVE_GAMMA22_INV: + return TRANSFER_FUNCTION_GAMMA22; + default: + return TRANSFER_FUNCTION_LINEAR; + } +} + static void __to_dc_lut3d_color(struct dc_rgb *rgb, const struct drm_color_lut lut, int bit_precision) @@ -720,6 +951,59 @@ static void __drm_3dlut_to_dc_3dlut(const struct drm_color_lut *lut, __to_dc_lut3d_color(&lut0[lut_i], lut[i], bit_depth); } +static void __to_dc_lut3d_32_color(struct dc_rgb *rgb, + const struct drm_color_lut32 lut, + int bit_precision) +{ + rgb->red = drm_color_lut32_extract(lut.red, bit_precision); + rgb->green = drm_color_lut32_extract(lut.green, bit_precision); + rgb->blue = drm_color_lut32_extract(lut.blue, bit_precision); +} + +static void __drm_3dlut32_to_dc_3dlut(const struct drm_color_lut32 *lut, + uint32_t lut3d_size, + struct tetrahedral_params *params, + bool use_tetrahedral_9, + int bit_depth) +{ + struct dc_rgb *lut0; + struct dc_rgb *lut1; + struct dc_rgb *lut2; + struct dc_rgb *lut3; + int lut_i, i; + + + if (use_tetrahedral_9) { + lut0 = params->tetrahedral_9.lut0; + lut1 = params->tetrahedral_9.lut1; + lut2 = params->tetrahedral_9.lut2; + lut3 = params->tetrahedral_9.lut3; + } else { + lut0 = params->tetrahedral_17.lut0; + lut1 = params->tetrahedral_17.lut1; + lut2 = params->tetrahedral_17.lut2; + lut3 = params->tetrahedral_17.lut3; + } + + for (lut_i = 0, i = 0; i < lut3d_size - 4; lut_i++, i += 4) { + /* + * We should consider the 3D LUT RGB values are distributed + * along four arrays lut0-3 where the first sizes 1229 and the + * other 1228. The bit depth supported for 3dlut channel is + * 12-bit, but DC also supports 10-bit. + * + * TODO: improve color pipeline API to enable the userspace set + * bit depth and 3D LUT size/stride, as specified by VA-API. + */ + __to_dc_lut3d_32_color(&lut0[lut_i], lut[i], bit_depth); + __to_dc_lut3d_32_color(&lut1[lut_i], lut[i + 1], bit_depth); + __to_dc_lut3d_32_color(&lut2[lut_i], lut[i + 2], bit_depth); + __to_dc_lut3d_32_color(&lut3[lut_i], lut[i + 3], bit_depth); + } + /* lut0 has 1229 points (lut_size/4 + 1) */ + __to_dc_lut3d_32_color(&lut0[lut_i], lut[i], bit_depth); +} + /* amdgpu_dm_atomic_lut3d - set DRM 3D LUT to DC stream * @drm_lut3d: user 3D LUT * @drm_lut3d_size: size of 3D LUT @@ -1177,6 +1461,360 @@ __set_dm_plane_degamma(struct drm_plane_state *plane_state, return 0; } +static int +__set_colorop_in_tf_1d_curve(struct dc_plane_state *dc_plane_state, + struct drm_colorop_state *colorop_state) +{ + struct dc_transfer_func *tf = &dc_plane_state->in_transfer_func; + struct drm_colorop *colorop = colorop_state->colorop; + struct drm_device *drm = colorop->dev; + + if (colorop->type != DRM_COLOROP_1D_CURVE) + return -EINVAL; + + if (!(BIT(colorop_state->curve_1d_type) & amdgpu_dm_supported_degam_tfs)) + return -EINVAL; + + if (colorop_state->bypass) { + tf->type = TF_TYPE_BYPASS; + tf->tf = TRANSFER_FUNCTION_LINEAR; + return 0; + } + + drm_dbg(drm, "Degamma colorop with ID: %d\n", colorop->base.id); + + tf->type = TF_TYPE_PREDEFINED; + tf->tf = amdgpu_colorop_tf_to_dc_tf(colorop_state->curve_1d_type); + + return 0; +} + +static int +__set_dm_plane_colorop_degamma(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state, + struct drm_colorop *colorop) +{ + struct drm_colorop *old_colorop; + struct drm_colorop_state *colorop_state = NULL, *new_colorop_state; + struct drm_atomic_state *state = plane_state->state; + int i = 0; + + old_colorop = colorop; + + /* 1st op: 1d curve - degamma */ + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + (BIT(new_colorop_state->curve_1d_type) & amdgpu_dm_supported_degam_tfs)) { + colorop_state = new_colorop_state; + break; + } + } + + if (!colorop_state) + return -EINVAL; + + return __set_colorop_in_tf_1d_curve(dc_plane_state, colorop_state); +} + +static int +__set_dm_plane_colorop_3x4_matrix(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state, + struct drm_colorop *colorop) +{ + struct drm_colorop *old_colorop; + struct drm_colorop_state *colorop_state = NULL, *new_colorop_state; + struct drm_atomic_state *state = plane_state->state; + const struct drm_device *dev = colorop->dev; + const struct drm_property_blob *blob; + struct drm_color_ctm_3x4 *ctm = NULL; + int i = 0; + + /* 3x4 matrix */ + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + new_colorop_state->colorop->type == DRM_COLOROP_CTM_3X4) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_CTM_3X4) { + drm_dbg(dev, "3x4 matrix colorop with ID: %d\n", colorop->base.id); + blob = colorop_state->data; + if (blob->length == sizeof(struct drm_color_ctm_3x4)) { + ctm = (struct drm_color_ctm_3x4 *) blob->data; + __drm_ctm_3x4_to_dc_matrix(ctm, dc_plane_state->gamut_remap_matrix.matrix); + dc_plane_state->gamut_remap_matrix.enable_remap = true; + dc_plane_state->input_csc_color_matrix.enable_adjustment = false; + } else { + drm_warn(dev, "blob->length (%zu) isn't equal to drm_color_ctm_3x4 (%zu)\n", + blob->length, sizeof(struct drm_color_ctm_3x4)); + return -EINVAL; + } + } + + return 0; +} + +static int +__set_dm_plane_colorop_multiplier(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state, + struct drm_colorop *colorop) +{ + struct drm_colorop *old_colorop; + struct drm_colorop_state *colorop_state = NULL, *new_colorop_state; + struct drm_atomic_state *state = plane_state->state; + const struct drm_device *dev = colorop->dev; + int i = 0; + + /* Multiplier */ + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + new_colorop_state->colorop->type == DRM_COLOROP_MULTIPLIER) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_MULTIPLIER) { + drm_dbg(dev, "Multiplier colorop with ID: %d\n", colorop->base.id); + dc_plane_state->hdr_mult = amdgpu_dm_fixpt_from_s3132(colorop_state->multiplier); + } + + return 0; +} + +static int +__set_dm_plane_colorop_shaper(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state, + struct drm_colorop *colorop) +{ + struct drm_colorop *old_colorop; + struct drm_colorop_state *colorop_state = NULL, *new_colorop_state; + struct drm_atomic_state *state = plane_state->state; + enum dc_transfer_func_predefined default_tf = TRANSFER_FUNCTION_LINEAR; + struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func; + const struct drm_color_lut32 *shaper_lut; + struct drm_device *dev = colorop->dev; + bool enabled = false; + u32 shaper_size; + int i = 0, ret = 0; + + /* 1D Curve - SHAPER TF */ + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + (BIT(new_colorop_state->curve_1d_type) & amdgpu_dm_supported_shaper_tfs)) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_CURVE) { + drm_dbg(dev, "Shaper TF colorop with ID: %d\n", colorop->base.id); + tf->type = TF_TYPE_DISTRIBUTED_POINTS; + tf->tf = default_tf = amdgpu_colorop_tf_to_dc_tf(colorop_state->curve_1d_type); + tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE; + ret = __set_output_tf(tf, 0, 0, false); + if (ret) + return ret; + enabled = true; + } + + /* 1D LUT - SHAPER LUT */ + colorop = old_colorop->next; + if (!colorop) { + drm_dbg(dev, "no Shaper LUT colorop found\n"); + return -EINVAL; + } + + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + new_colorop_state->colorop->type == DRM_COLOROP_1D_LUT) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_LUT) { + drm_dbg(dev, "Shaper LUT colorop with ID: %d\n", colorop->base.id); + tf->type = TF_TYPE_DISTRIBUTED_POINTS; + tf->tf = default_tf; + tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE; + shaper_lut = __extract_blob_lut32(colorop_state->data, &shaper_size); + shaper_size = shaper_lut != NULL ? shaper_size : 0; + + /* Custom LUT size must be the same as supported size */ + if (shaper_size == colorop->size) { + ret = __set_output_tf_32(tf, shaper_lut, shaper_size, false); + if (ret) + return ret; + enabled = true; + } + } + + if (!enabled) + tf->type = TF_TYPE_BYPASS; + + return 0; +} + +/* __set_colorop_3dlut - set DRM 3D LUT to DC stream + * @drm_lut3d: user 3D LUT + * @drm_lut3d_size: size of 3D LUT + * @lut3d: DC 3D LUT + * + * Map user 3D LUT data to DC 3D LUT and all necessary bits to program it + * on DCN accordingly. + * + * Returns: + * 0 on success. -EINVAL if drm_lut3d_size is zero. + */ +static int __set_colorop_3dlut(const struct drm_color_lut32 *drm_lut3d, + uint32_t drm_lut3d_size, + struct dc_3dlut *lut) +{ + if (!drm_lut3d_size) { + lut->state.bits.initialized = 0; + return -EINVAL; + } + + /* Only supports 17x17x17 3D LUT (12-bit) now */ + lut->lut_3d.use_12bits = true; + lut->lut_3d.use_tetrahedral_9 = false; + + lut->state.bits.initialized = 1; + __drm_3dlut32_to_dc_3dlut(drm_lut3d, drm_lut3d_size, &lut->lut_3d, + lut->lut_3d.use_tetrahedral_9, 12); + + return 0; +} + +static int +__set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state, + struct drm_colorop *colorop) +{ + struct drm_colorop *old_colorop; + struct drm_colorop_state *colorop_state = NULL, *new_colorop_state; + struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func; + struct drm_atomic_state *state = plane_state->state; + const struct amdgpu_device *adev = drm_to_adev(colorop->dev); + const struct drm_device *dev = colorop->dev; + const struct drm_color_lut32 *lut3d; + uint32_t lut3d_size; + int i = 0, ret = 0; + + /* 3D LUT */ + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + new_colorop_state->colorop->type == DRM_COLOROP_3D_LUT) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_3D_LUT) { + if (!adev->dm.dc->caps.color.dpp.hw_3d_lut) { + drm_dbg(dev, "3D LUT is not supported by hardware\n"); + return -EINVAL; + } + + drm_dbg(dev, "3D LUT colorop with ID: %d\n", colorop->base.id); + lut3d = __extract_blob_lut32(colorop_state->data, &lut3d_size); + lut3d_size = lut3d != NULL ? lut3d_size : 0; + ret = __set_colorop_3dlut(lut3d, lut3d_size, &dc_plane_state->lut3d_func); + if (ret) { + drm_dbg(dev, "3D LUT colorop with ID: %d has LUT size = %d\n", + colorop->base.id, lut3d_size); + return ret; + } + + /* 3D LUT requires shaper. If shaper colorop is bypassed, enable shaper curve + * with TRANSFER_FUNCTION_LINEAR + */ + if (tf->type == TF_TYPE_BYPASS) { + tf->type = TF_TYPE_DISTRIBUTED_POINTS; + tf->tf = TRANSFER_FUNCTION_LINEAR; + tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE; + ret = __set_output_tf_32(tf, NULL, 0, false); + } + } + + return ret; +} + +static int +__set_dm_plane_colorop_blend(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state, + struct drm_colorop *colorop) +{ + struct drm_colorop *old_colorop; + struct drm_colorop_state *colorop_state = NULL, *new_colorop_state; + struct drm_atomic_state *state = plane_state->state; + enum dc_transfer_func_predefined default_tf = TRANSFER_FUNCTION_LINEAR; + struct dc_transfer_func *tf = &dc_plane_state->blend_tf; + const struct drm_color_lut32 *blend_lut = NULL; + struct drm_device *dev = colorop->dev; + uint32_t blend_size = 0; + int i = 0; + + /* 1D Curve - BLND TF */ + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + (BIT(new_colorop_state->curve_1d_type) & amdgpu_dm_supported_blnd_tfs)) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_CURVE && + (BIT(colorop_state->curve_1d_type) & amdgpu_dm_supported_blnd_tfs)) { + drm_dbg(dev, "Blend TF colorop with ID: %d\n", colorop->base.id); + tf->type = TF_TYPE_DISTRIBUTED_POINTS; + tf->tf = default_tf = amdgpu_colorop_tf_to_dc_tf(colorop_state->curve_1d_type); + tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE; + __set_input_tf_32(NULL, tf, blend_lut, blend_size); + } + + /* 1D Curve - BLND LUT */ + colorop = old_colorop->next; + if (!colorop) { + drm_dbg(dev, "no Blend LUT colorop found\n"); + return -EINVAL; + } + + old_colorop = colorop; + for_each_new_colorop_in_state(state, colorop, new_colorop_state, i) { + if (new_colorop_state->colorop == old_colorop && + new_colorop_state->colorop->type == DRM_COLOROP_1D_LUT) { + colorop_state = new_colorop_state; + break; + } + } + + if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_1D_LUT && + (BIT(colorop_state->curve_1d_type) & amdgpu_dm_supported_blnd_tfs)) { + drm_dbg(dev, "Blend LUT colorop with ID: %d\n", colorop->base.id); + tf->type = TF_TYPE_DISTRIBUTED_POINTS; + tf->tf = default_tf; + tf->sdr_ref_white_level = SDR_WHITE_LEVEL_INIT_VALUE; + blend_lut = __extract_blob_lut32(colorop_state->data, &blend_size); + blend_size = blend_lut != NULL ? blend_size : 0; + + /* Custom LUT size must be the same as supported size */ + if (blend_size == colorop->size) + __set_input_tf_32(NULL, tf, blend_lut, blend_size); + } + + return 0; +} + static int amdgpu_dm_plane_set_color_properties(struct drm_plane_state *plane_state, struct dc_plane_state *dc_plane_state) @@ -1227,6 +1865,93 @@ amdgpu_dm_plane_set_color_properties(struct drm_plane_state *plane_state, return 0; } +static int +amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state, + struct dc_plane_state *dc_plane_state) +{ + struct drm_colorop *colorop = plane_state->color_pipeline; + struct drm_device *dev = plane_state->plane->dev; + struct amdgpu_device *adev = drm_to_adev(dev); + int ret; + + /* 1D Curve - DEGAM TF */ + if (!colorop) + return -EINVAL; + + ret = __set_dm_plane_colorop_degamma(plane_state, dc_plane_state, colorop); + if (ret) + return ret; + + /* Multiplier */ + colorop = colorop->next; + if (!colorop) { + drm_dbg(dev, "no multiplier colorop found\n"); + return -EINVAL; + } + + ret = __set_dm_plane_colorop_multiplier(plane_state, dc_plane_state, colorop); + if (ret) + return ret; + + /* 3x4 matrix */ + colorop = colorop->next; + if (!colorop) { + drm_dbg(dev, "no 3x4 matrix colorop found\n"); + return -EINVAL; + } + + ret = __set_dm_plane_colorop_3x4_matrix(plane_state, dc_plane_state, colorop); + if (ret) + return ret; + + if (adev->dm.dc->caps.color.dpp.hw_3d_lut) { + /* 1D Curve & LUT - SHAPER TF & LUT */ + colorop = colorop->next; + if (!colorop) { + drm_dbg(dev, "no Shaper TF colorop found\n"); + return -EINVAL; + } + + ret = __set_dm_plane_colorop_shaper(plane_state, dc_plane_state, colorop); + if (ret) + return ret; + + /* Shaper LUT colorop is already handled, just skip here */ + colorop = colorop->next; + if (!colorop) + return -EINVAL; + + /* 3D LUT */ + colorop = colorop->next; + if (!colorop) { + drm_dbg(dev, "no 3D LUT colorop found\n"); + return -EINVAL; + } + + ret = __set_dm_plane_colorop_3dlut(plane_state, dc_plane_state, colorop); + if (ret) + return ret; + } + + /* 1D Curve & LUT - BLND TF & LUT */ + colorop = colorop->next; + if (!colorop) { + drm_dbg(dev, "no Blend TF colorop found\n"); + return -EINVAL; + } + + ret = __set_dm_plane_colorop_blend(plane_state, dc_plane_state, colorop); + if (ret) + return ret; + + /* BLND LUT colorop is already handled, just skip here */ + colorop = colorop->next; + if (!colorop) + return -EINVAL; + + return 0; +} + /** * amdgpu_dm_update_plane_color_mgmt: Maps DRM color management to DC plane. * @crtc: amdgpu_dm crtc state @@ -1323,5 +2048,8 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc, dc_plane_state->input_csc_color_matrix.enable_adjustment = false; } + if (!amdgpu_dm_plane_set_colorop_properties(plane_state, dc_plane_state)) + return 0; + return amdgpu_dm_plane_set_color_properties(plane_state, dc_plane_state); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c new file mode 100644 index 000000000000..d585618b8064 --- /dev/null +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright 2023 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 +#include +#include +#include + +#include "amdgpu.h" +#include "amdgpu_dm_colorop.h" +#include "dc.h" + +const u64 amdgpu_dm_supported_degam_tfs = + BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) | + BIT(DRM_COLOROP_1D_CURVE_PQ_125_EOTF) | + BIT(DRM_COLOROP_1D_CURVE_BT2020_INV_OETF) | + BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV); + +const u64 amdgpu_dm_supported_shaper_tfs = + BIT(DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF) | + BIT(DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF) | + BIT(DRM_COLOROP_1D_CURVE_BT2020_OETF) | + BIT(DRM_COLOROP_1D_CURVE_GAMMA22); + +const u64 amdgpu_dm_supported_blnd_tfs = + BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) | + BIT(DRM_COLOROP_1D_CURVE_PQ_125_EOTF) | + BIT(DRM_COLOROP_1D_CURVE_BT2020_INV_OETF) | + BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV); + +#define MAX_COLOR_PIPELINE_OPS 10 + +#define LUT3D_SIZE 17 + +int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_prop_enum_list *list) +{ + struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS]; + struct drm_device *dev = plane->dev; + struct amdgpu_device *adev = drm_to_adev(dev); + int ret; + int i = 0; + + memset(ops, 0, sizeof(ops)); + + /* 1D curve - DEGAM TF */ + ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane, + amdgpu_dm_supported_degam_tfs, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + list->type = ops[i]->base.id; + list->name = kasprintf(GFP_KERNEL, "Color Pipeline %d", ops[i]->base.id); + + i++; + + /* Multiplier */ + ops[i] = kzalloc(sizeof(struct drm_colorop), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_mult_init(dev, ops[i], plane, DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i-1], ops[i]); + + i++; + + /* 3x4 matrix */ + ops[i] = kzalloc(sizeof(struct drm_colorop), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_ctm_3x4_init(dev, ops[i], plane, DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i-1], ops[i]); + + i++; + + if (adev->dm.dc->caps.color.dpp.hw_3d_lut) { + /* 1D curve - SHAPER TF */ + ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane, + amdgpu_dm_supported_shaper_tfs, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i-1], ops[i]); + + i++; + + /* 1D LUT - SHAPER LUT */ + ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_curve_1d_lut_init(dev, ops[i], plane, MAX_COLOR_LUT_ENTRIES, + DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i-1], ops[i]); + + i++; + + /* 3D LUT */ + ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_3dlut_init(dev, ops[i], plane, LUT3D_SIZE, + DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i-1], ops[i]); + + i++; + } + + /* 1D curve - BLND TF */ + ops[i] = kzalloc(sizeof(*ops[0]), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_curve_1d_init(dev, ops[i], plane, + amdgpu_dm_supported_blnd_tfs, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i - 1], ops[i]); + + i++; + + /* 1D LUT - BLND LUT */ + ops[i] = kzalloc(sizeof(struct drm_colorop), GFP_KERNEL); + if (!ops[i]) { + ret = -ENOMEM; + goto cleanup; + } + + ret = drm_plane_colorop_curve_1d_lut_init(dev, ops[i], plane, MAX_COLOR_LUT_ENTRIES, + DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR, + DRM_COLOROP_FLAG_ALLOW_BYPASS); + if (ret) + goto cleanup; + + drm_colorop_set_next_property(ops[i-1], ops[i]); + return 0; + +cleanup: + if (ret == -ENOMEM) + drm_err(plane->dev, "KMS: Failed to allocate colorop\n"); + + drm_colorop_pipeline_destroy(dev); + + return ret; +} diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.h new file mode 100644 index 000000000000..2e1617ffc8ee --- /dev/null +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright 2023 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 __AMDGPU_DM_COLOROP_H__ +#define __AMDGPU_DM_COLOROP_H__ + +extern const u64 amdgpu_dm_supported_degam_tfs; +extern const u64 amdgpu_dm_supported_shaper_tfs; +extern const u64 amdgpu_dm_supported_blnd_tfs; + +int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_prop_enum_list *list); + +#endif /* __AMDGPU_DM_COLOROP_H__*/ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 38f9ea313dcb..697e232acebf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -736,7 +736,7 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, { struct amdgpu_crtc *acrtc = NULL; struct drm_plane *cursor_plane; - bool is_dcn; + bool has_degamma; int res = -ENOMEM; cursor_plane = kzalloc(sizeof(*cursor_plane), GFP_KERNEL); @@ -775,20 +775,18 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, dm->adev->mode_info.crtcs[crtc_index] = acrtc; - /* Don't enable DRM CRTC degamma property for DCE since it doesn't - * support programmable degamma anywhere. + /* Don't enable DRM CRTC degamma property for + * 1. Degamma is replaced by color pipeline. + * 2. DCE since it doesn't support programmable degamma anywhere. + * 3. DCN401 since pre-blending degamma LUT doesn't apply to cursor. */ - is_dcn = dm->adev->dm.dc->caps.color.dpp.dcn_arch; - /* Dont't enable DRM CRTC degamma property for DCN401 since the - * pre-blending degamma LUT doesn't apply to cursor, and therefore - * can't work similar to a post-blending degamma LUT as in other hw - * versions. - * TODO: revisit it once KMS plane color API is merged. - */ - drm_crtc_enable_color_mgmt(&acrtc->base, - (is_dcn && - dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01) ? - MAX_COLOR_LUT_ENTRIES : 0, + if (plane->color_pipeline_property) + has_degamma = false; + else + has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch && + dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01; + + drm_crtc_enable_color_mgmt(&acrtc->base, has_degamma ? MAX_COLOR_LUT_ENTRIES : 0, true, MAX_COLOR_LUT_ENTRIES); drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES); 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 eb2c587b0b9b..ac98c746c3de 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 @@ -998,8 +998,8 @@ enum dc_edid_status dm_helpers_read_local_edid( struct amdgpu_dm_connector *aconnector = link->priv; struct drm_connector *connector = &aconnector->base; struct i2c_adapter *ddc; - int retry = 3; - enum dc_edid_status edid_status; + int retry = 25; + enum dc_edid_status edid_status = EDID_NO_RESPONSE; const struct drm_edid *drm_edid; const struct edid *edid; @@ -1029,7 +1029,7 @@ enum dc_edid_status dm_helpers_read_local_edid( } if (!drm_edid) - return EDID_NO_RESPONSE; + continue; edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw() if (!edid || @@ -1047,7 +1047,7 @@ enum dc_edid_status dm_helpers_read_local_edid( &sink->dc_edid, &sink->edid_caps); - } while (edid_status == EDID_BAD_CHECKSUM && --retry > 0); + } while ((edid_status == EDID_BAD_CHECKSUM || edid_status == EDID_NO_RESPONSE) && --retry > 0); if (edid_status != EDID_OK) DRM_ERROR("EDID err: %d, on connector: %s", 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 5e92eaa67aa3..dbd1da4d85d3 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 @@ -884,26 +884,28 @@ struct dsc_mst_fairness_params { }; #if defined(CONFIG_DRM_AMD_DC_FP) -static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link) +static uint64_t kbps_to_pbn(int kbps, bool is_peak_pbn) { - u8 link_coding_cap; - uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B; + uint64_t effective_kbps = (uint64_t)kbps; - link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link); - if (link_coding_cap == DP_128b_132b_ENCODING) - fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B; + if (is_peak_pbn) { // add 0.6% (1006/1000) overhead into effective kbps + effective_kbps *= 1006; + effective_kbps = div_u64(effective_kbps, 1000); + } - return fec_overhead_multiplier_x1000; + return (uint64_t) DIV64_U64_ROUND_UP(effective_kbps * 64, (54 * 8 * 1000)); } -static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000) +static uint32_t pbn_to_kbps(unsigned int pbn, bool with_margin) { - u64 peak_kbps = kbps; + uint64_t pbn_effective = (uint64_t)pbn; - peak_kbps *= 1006; - peak_kbps *= fec_overhead_multiplier_x1000; - peak_kbps = div_u64(peak_kbps, 1000 * 1000); - return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000)); + if (with_margin) // deduct 0.6% (994/1000) overhead from effective pbn + pbn_effective *= (1000000 / PEAK_FACTOR_X1000); + else + pbn_effective *= 1000; + + return DIV_U64_ROUND_UP(pbn_effective * 8 * 54, 64); } static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params, @@ -974,7 +976,7 @@ static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn) dc_dsc_get_default_config_option(param.sink->ctx->dc, &dsc_options); dsc_options.max_target_bpp_limit_override_x16 = drm_connector->display_info.max_dsc_bpp * 16; - kbps = div_u64((u64)pbn * 994 * 8 * 54, 64); + kbps = pbn_to_kbps(pbn, false); dc_dsc_compute_config( param.sink->ctx->dc->res_pool->dscs[0], ¶m.sink->dsc_caps.dsc_dec_caps, @@ -1003,12 +1005,11 @@ static int increase_dsc_bpp(struct drm_atomic_state *state, int link_timeslots_used; int fair_pbn_alloc; int ret = 0; - uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { initial_slack[i] = - kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn; + kbps_to_pbn(params[i].bw_range.max_kbps, false) - vars[i + k].pbn; bpp_increased[i] = false; remaining_to_increase += 1; } else { @@ -1104,7 +1105,6 @@ static int try_disable_dsc(struct drm_atomic_state *state, int next_index; int remaining_to_try = 0; int ret; - uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); int var_pbn; for (i = 0; i < count; i++) { @@ -1137,7 +1137,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC index #%d, try no compression\n", next_index); var_pbn = vars[next_index].pbn; - vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); + vars[next_index].pbn = kbps_to_pbn(params[next_index].bw_range.stream_kbps, true); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -1197,7 +1197,6 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, int count = 0; int i, k, ret; bool debugfs_overwrite = false; - uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); struct drm_connector_state *new_conn_state; memset(params, 0, sizeof(params)); @@ -1278,7 +1277,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC Try no compression\n"); for (i = 0; i < count; i++) { vars[i + k].aconnector = params[i].aconnector; - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); + vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.stream_kbps, false); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, @@ -1300,7 +1299,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC Try max compression\n"); for (i = 0; i < count; i++) { if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000); + vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.min_kbps, false); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1308,7 +1307,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (ret < 0) return ret; } else { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); + vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.stream_kbps, false); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1763,18 +1762,6 @@ int pre_validate_dsc(struct drm_atomic_state *state, return ret; } -static uint32_t kbps_from_pbn(unsigned int pbn) -{ - uint64_t kbps = (uint64_t)pbn; - - kbps *= (1000000 / PEAK_FACTOR_X1000); - kbps *= 8; - kbps *= 54; - kbps /= 64; - - return (uint32_t)kbps; -} - static bool is_dsc_common_config_possible(struct dc_stream_state *stream, struct dc_dsc_bw_range *bw_range) { @@ -1873,7 +1860,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( dc_link_get_highest_encoding_format(stream->link)); cur_link_settings = stream->link->verified_link_cap; root_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings); - virtual_channel_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn); + virtual_channel_bw_in_kbps = pbn_to_kbps(aconnector->mst_output_port->full_pbn, true); /* pick the end to end bw bottleneck */ end_to_end_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); @@ -1926,7 +1913,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( immediate_upstream_port = aconnector->mst_output_port->parent->port_parent; if (immediate_upstream_port) { - virtual_channel_bw_in_kbps = kbps_from_pbn(immediate_upstream_port->full_pbn); + virtual_channel_bw_in_kbps = pbn_to_kbps(immediate_upstream_port->full_pbn, true); virtual_channel_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); } else { /* For topology LCT 1 case - only one mstb*/ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index e027798ece03..2e3ee78999d9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -37,6 +37,7 @@ #include "amdgpu_display.h" #include "amdgpu_dm_trace.h" #include "amdgpu_dm_plane.h" +#include "amdgpu_dm_colorop.h" #include "gc/gc_11_0_0_offset.h" #include "gc/gc_11_0_0_sh_mask.h" @@ -1782,6 +1783,39 @@ dm_atomic_plane_get_property(struct drm_plane *plane, return 0; } +#else + +#define MAX_COLOR_PIPELINES 5 + +static int +dm_plane_init_colorops(struct drm_plane *plane) +{ + struct drm_prop_enum_list pipelines[MAX_COLOR_PIPELINES]; + struct drm_device *dev = plane->dev; + struct amdgpu_device *adev = drm_to_adev(dev); + struct dc *dc = adev->dm.dc; + int len = 0; + int ret; + + if (plane->type == DRM_PLANE_TYPE_CURSOR) + return 0; + + /* initialize pipeline */ + if (dc->ctx->dce_version >= DCN_VERSION_3_0) { + ret = amdgpu_dm_initialize_default_pipeline(plane, &pipelines[len]); + if (ret) { + drm_err(plane->dev, "Failed to create color pipeline for plane %d: %d\n", + plane->base.id, ret); + return ret; + } + len++; + + /* Create COLOR_PIPELINE property and attach */ + drm_plane_create_color_pipeline_property(plane, pipelines, len); + } + + return 0; +} #endif static const struct drm_plane_funcs dm_plane_funcs = { @@ -1890,7 +1924,12 @@ int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, #ifdef AMD_PRIVATE_COLOR dm_atomic_plane_attach_color_mgmt_properties(dm, plane); +#else + res = dm_plane_init_colorops(plane); + if (res) + return res; #endif + /* Create (reset) the plane state */ if (plane->funcs->reset) plane->funcs->reset(plane); diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c index 4120d6c4c5e4..d1471f34e419 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c @@ -805,7 +805,7 @@ static enum bp_result bios_parser_dac_load_detection( if (bp_params.device_id == ATOM_DEVICE_CRT1_SUPPORT) device_id_mask = ATOM_S0_CRT1_MASK; - else if (bp_params.device_id == ATOM_DEVICE_CRT1_SUPPORT) + else if (bp_params.device_id == ATOM_DEVICE_CRT2_SUPPORT) device_id_mask = ATOM_S0_CRT2_MASK; else return BP_RESULT_UNSUPPORTED; 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 04eb647acc4e..550a9f1d03f8 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1480,10 +1480,10 @@ static enum bp_result get_embedded_panel_info_v2_1( /* not provided by VBIOS */ info->lcd_timing.misc_info.HORIZONTAL_CUT_OFF = 0; - info->lcd_timing.misc_info.H_SYNC_POLARITY = ~(uint32_t) (lvds->lcd_timing.miscinfo - & ATOM_HSYNC_POLARITY); - info->lcd_timing.misc_info.V_SYNC_POLARITY = ~(uint32_t) (lvds->lcd_timing.miscinfo - & ATOM_VSYNC_POLARITY); + info->lcd_timing.misc_info.H_SYNC_POLARITY = !(lvds->lcd_timing.miscinfo & + ATOM_HSYNC_POLARITY); + info->lcd_timing.misc_info.V_SYNC_POLARITY = !(lvds->lcd_timing.miscinfo & + ATOM_VSYNC_POLARITY); /* not provided by VBIOS */ info->lcd_timing.misc_info.VERTICAL_CUT_OFF = 0; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 5764f15c16b7..8be9cbd43e18 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -303,6 +303,7 @@ static bool create_links( link->link_id.id = CONNECTOR_ID_VIRTUAL; link->link_id.enum_id = ENUM_ID_1; link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; + link->replay_settings.config.replay_version = DC_REPLAY_VERSION_UNSUPPORTED; link->link_enc = kzalloc(sizeof(*link->link_enc), GFP_KERNEL); if (!link->link_enc) { @@ -2146,6 +2147,14 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c if (!dcb->funcs->is_accelerated_mode(dcb)) { disable_vbios_mode_if_required(dc, context); dc->hwss.enable_accelerated_mode(dc, context); + } else if (get_seamless_boot_stream_count(dc->current_state) > 0) { + /* If the previous Stream still retains the apply seamless boot flag, + * it means the OS has not actually performed a flip yet. + * At this point, if we receive dc_commit_streams again, we should + * once more check whether the actual HW timing matches what the OS + * has provided + */ + disable_vbios_mode_if_required(dc, context); } if (dc->hwseq->funcs.wait_for_pipe_update_if_needed) { @@ -6003,6 +6012,12 @@ bool dc_smart_power_oled_enable(const struct dc_link *link, bool enable, uint16_ if (pipe_ctx) otg_inst = pipe_ctx->stream_res.tg->inst; + // before enable smart power OLED, we need to call set pipe for DMUB to set ABM config + if (enable) { + if (dc->hwss.set_pipe && pipe_ctx) + dc->hwss.set_pipe(pipe_ctx); + } + // fill in cmd memset(&cmd, 0, sizeof(cmd)); @@ -6511,6 +6526,567 @@ void dc_get_power_feature_status(struct dc *dc, int primary_otg_inst, out_data->fams = dc->current_state->bw_ctx.bw.dcn.clk.fw_based_mclk_switching; } +bool dc_capture_register_software_state(struct dc *dc, struct dc_register_software_state *state) +{ + struct dc_state *context; + struct resource_context *res_ctx; + int i; + + if (!dc || !dc->current_state || !state) { + if (state) + state->state_valid = false; + return false; + } + + /* Initialize the state structure */ + memset(state, 0, sizeof(struct dc_register_software_state)); + + context = dc->current_state; + res_ctx = &context->res_ctx; + + /* Count active pipes and streams */ + state->active_pipe_count = 0; + state->active_stream_count = context->stream_count; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (res_ctx->pipe_ctx[i].stream) + state->active_pipe_count++; + } + + /* Capture HUBP programming state for each pipe */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + + state->hubp[i].valid_stream = false; + if (!pipe_ctx->stream) + continue; + + state->hubp[i].valid_stream = true; + + /* HUBP register programming variables */ + if (pipe_ctx->stream_res.tg) + state->hubp[i].vtg_sel = pipe_ctx->stream_res.tg->inst; + + state->hubp[i].hubp_clock_enable = (pipe_ctx->plane_res.hubp != NULL) ? 1 : 0; + + state->hubp[i].valid_plane_state = false; + if (pipe_ctx->plane_state) { + state->hubp[i].valid_plane_state = true; + state->hubp[i].surface_pixel_format = pipe_ctx->plane_state->format; + state->hubp[i].rotation_angle = pipe_ctx->plane_state->rotation; + state->hubp[i].h_mirror_en = pipe_ctx->plane_state->horizontal_mirror ? 1 : 0; + + /* Surface size */ + if (pipe_ctx->plane_state->plane_size.surface_size.width > 0) { + state->hubp[i].surface_size_width = pipe_ctx->plane_state->plane_size.surface_size.width; + state->hubp[i].surface_size_height = pipe_ctx->plane_state->plane_size.surface_size.height; + } + + /* Viewport dimensions from scaler data */ + if (pipe_ctx->plane_state->src_rect.width > 0) { + state->hubp[i].pri_viewport_width = pipe_ctx->plane_state->src_rect.width; + state->hubp[i].pri_viewport_height = pipe_ctx->plane_state->src_rect.height; + state->hubp[i].pri_viewport_x_start = pipe_ctx->plane_state->src_rect.x; + state->hubp[i].pri_viewport_y_start = pipe_ctx->plane_state->src_rect.y; + } + + /* DCC settings */ + state->hubp[i].surface_dcc_en = (pipe_ctx->plane_state->dcc.enable) ? 1 : 0; + state->hubp[i].surface_dcc_ind_64b_blk = pipe_ctx->plane_state->dcc.independent_64b_blks; + state->hubp[i].surface_dcc_ind_128b_blk = pipe_ctx->plane_state->dcc.dcc_ind_blk; + + /* Surface pitch */ + state->hubp[i].surface_pitch = pipe_ctx->plane_state->plane_size.surface_pitch; + state->hubp[i].meta_pitch = pipe_ctx->plane_state->dcc.meta_pitch; + state->hubp[i].chroma_pitch = pipe_ctx->plane_state->plane_size.chroma_pitch; + state->hubp[i].meta_pitch_c = pipe_ctx->plane_state->dcc.meta_pitch_c; + + /* Surface addresses - primary */ + state->hubp[i].primary_surface_address_low = pipe_ctx->plane_state->address.grph.addr.low_part; + state->hubp[i].primary_surface_address_high = pipe_ctx->plane_state->address.grph.addr.high_part; + state->hubp[i].primary_meta_surface_address_low = pipe_ctx->plane_state->address.grph.meta_addr.low_part; + state->hubp[i].primary_meta_surface_address_high = pipe_ctx->plane_state->address.grph.meta_addr.high_part; + + /* TMZ settings */ + state->hubp[i].primary_surface_tmz = pipe_ctx->plane_state->address.tmz_surface; + state->hubp[i].primary_meta_surface_tmz = pipe_ctx->plane_state->address.tmz_surface; + + /* Tiling configuration */ + state->hubp[i].min_dc_gfx_version9 = false; + if (pipe_ctx->plane_state->tiling_info.gfxversion >= DcGfxVersion9) { + state->hubp[i].min_dc_gfx_version9 = true; + state->hubp[i].sw_mode = pipe_ctx->plane_state->tiling_info.gfx9.swizzle; + state->hubp[i].num_pipes = pipe_ctx->plane_state->tiling_info.gfx9.num_pipes; + state->hubp[i].num_banks = pipe_ctx->plane_state->tiling_info.gfx9.num_banks; + state->hubp[i].pipe_interleave = pipe_ctx->plane_state->tiling_info.gfx9.pipe_interleave; + state->hubp[i].num_shader_engines = pipe_ctx->plane_state->tiling_info.gfx9.num_shader_engines; + state->hubp[i].num_rb_per_se = pipe_ctx->plane_state->tiling_info.gfx9.num_rb_per_se; + state->hubp[i].num_pkrs = pipe_ctx->plane_state->tiling_info.gfx9.num_pkrs; + } + } + + /* DML Request Size Configuration */ + if (pipe_ctx->rq_regs.rq_regs_l.chunk_size > 0) { + state->hubp[i].rq_chunk_size = pipe_ctx->rq_regs.rq_regs_l.chunk_size; + state->hubp[i].rq_min_chunk_size = pipe_ctx->rq_regs.rq_regs_l.min_chunk_size; + state->hubp[i].rq_meta_chunk_size = pipe_ctx->rq_regs.rq_regs_l.meta_chunk_size; + state->hubp[i].rq_min_meta_chunk_size = pipe_ctx->rq_regs.rq_regs_l.min_meta_chunk_size; + state->hubp[i].rq_dpte_group_size = pipe_ctx->rq_regs.rq_regs_l.dpte_group_size; + state->hubp[i].rq_mpte_group_size = pipe_ctx->rq_regs.rq_regs_l.mpte_group_size; + state->hubp[i].rq_swath_height_l = pipe_ctx->rq_regs.rq_regs_l.swath_height; + state->hubp[i].rq_pte_row_height_l = pipe_ctx->rq_regs.rq_regs_l.pte_row_height_linear; + } + + /* Chroma request size configuration */ + if (pipe_ctx->rq_regs.rq_regs_c.chunk_size > 0) { + state->hubp[i].rq_chunk_size_c = pipe_ctx->rq_regs.rq_regs_c.chunk_size; + state->hubp[i].rq_min_chunk_size_c = pipe_ctx->rq_regs.rq_regs_c.min_chunk_size; + state->hubp[i].rq_meta_chunk_size_c = pipe_ctx->rq_regs.rq_regs_c.meta_chunk_size; + state->hubp[i].rq_min_meta_chunk_size_c = pipe_ctx->rq_regs.rq_regs_c.min_meta_chunk_size; + state->hubp[i].rq_dpte_group_size_c = pipe_ctx->rq_regs.rq_regs_c.dpte_group_size; + state->hubp[i].rq_mpte_group_size_c = pipe_ctx->rq_regs.rq_regs_c.mpte_group_size; + state->hubp[i].rq_swath_height_c = pipe_ctx->rq_regs.rq_regs_c.swath_height; + state->hubp[i].rq_pte_row_height_c = pipe_ctx->rq_regs.rq_regs_c.pte_row_height_linear; + } + + /* DML expansion modes */ + state->hubp[i].drq_expansion_mode = pipe_ctx->rq_regs.drq_expansion_mode; + state->hubp[i].prq_expansion_mode = pipe_ctx->rq_regs.prq_expansion_mode; + state->hubp[i].mrq_expansion_mode = pipe_ctx->rq_regs.mrq_expansion_mode; + state->hubp[i].crq_expansion_mode = pipe_ctx->rq_regs.crq_expansion_mode; + + /* DML DLG parameters - nominal */ + state->hubp[i].dst_y_per_vm_vblank = pipe_ctx->dlg_regs.dst_y_per_vm_vblank; + state->hubp[i].dst_y_per_row_vblank = pipe_ctx->dlg_regs.dst_y_per_row_vblank; + state->hubp[i].dst_y_per_vm_flip = pipe_ctx->dlg_regs.dst_y_per_vm_flip; + state->hubp[i].dst_y_per_row_flip = pipe_ctx->dlg_regs.dst_y_per_row_flip; + + /* DML prefetch settings */ + state->hubp[i].dst_y_prefetch = pipe_ctx->dlg_regs.dst_y_prefetch; + state->hubp[i].vratio_prefetch = pipe_ctx->dlg_regs.vratio_prefetch; + state->hubp[i].vratio_prefetch_c = pipe_ctx->dlg_regs.vratio_prefetch_c; + + /* TTU parameters */ + state->hubp[i].qos_level_low_wm = pipe_ctx->ttu_regs.qos_level_low_wm; + state->hubp[i].qos_level_high_wm = pipe_ctx->ttu_regs.qos_level_high_wm; + state->hubp[i].qos_level_flip = pipe_ctx->ttu_regs.qos_level_flip; + state->hubp[i].min_ttu_vblank = pipe_ctx->ttu_regs.min_ttu_vblank; + } + + /* Capture HUBBUB programming state */ + if (dc->res_pool->hubbub) { + /* Individual DET buffer sizes - software state variables that program DET registers */ + for (i = 0; i < 4 && i < dc->res_pool->pipe_count; i++) { + uint32_t det_size = res_ctx->pipe_ctx[i].det_buffer_size_kb; + switch (i) { + case 0: + state->hubbub.det0_size = det_size; + break; + case 1: + state->hubbub.det1_size = det_size; + break; + case 2: + state->hubbub.det2_size = det_size; + break; + case 3: + state->hubbub.det3_size = det_size; + break; + } + } + + /* Compression buffer configuration - software state that programs COMPBUF_SIZE register */ + // TODO: Handle logic for legacy DCN pre-DCN401 + state->hubbub.compbuf_size = context->bw_ctx.bw.dcn.arb_regs.compbuf_size; + } + + /* Capture DPP programming state for each pipe */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + + if (!pipe_ctx->stream) + continue; + + state->dpp[i].dpp_clock_enable = (pipe_ctx->plane_res.dpp != NULL) ? 1 : 0; + + if (pipe_ctx->plane_state && pipe_ctx->plane_res.scl_data.recout.width > 0) { + /* Access dscl_prog_data directly - this contains the actual software state used for register programming */ + struct dscl_prog_data *dscl_data = &pipe_ctx->plane_res.scl_data.dscl_prog_data; + + /* Recout (Rectangle of Interest) configuration - software state that programs RECOUT registers */ + state->dpp[i].recout_start_x = dscl_data->recout.x; + state->dpp[i].recout_start_y = dscl_data->recout.y; + state->dpp[i].recout_width = dscl_data->recout.width; + state->dpp[i].recout_height = dscl_data->recout.height; + + /* MPC (Multiple Pipe/Plane Combiner) size - software state that programs MPC_SIZE registers */ + state->dpp[i].mpc_width = dscl_data->mpc_size.width; + state->dpp[i].mpc_height = dscl_data->mpc_size.height; + + /* DSCL mode - software state that programs SCL_MODE registers */ + state->dpp[i].dscl_mode = dscl_data->dscl_mode; + + /* Scaler ratios - software state that programs scale ratio registers (use actual programmed ratios) */ + state->dpp[i].horz_ratio_int = dscl_data->ratios.h_scale_ratio >> 19; // Extract integer part from programmed ratio + state->dpp[i].vert_ratio_int = dscl_data->ratios.v_scale_ratio >> 19; // Extract integer part from programmed ratio + + /* Basic scaler taps - software state that programs tap control registers (use actual programmed taps) */ + state->dpp[i].h_taps = dscl_data->taps.h_taps + 1; // dscl_prog_data.taps stores (taps - 1), so add 1 back + state->dpp[i].v_taps = dscl_data->taps.v_taps + 1; // dscl_prog_data.taps stores (taps - 1), so add 1 back + } + } + + /* Capture essential clock state for underflow analysis */ + if (dc->clk_mgr && dc->clk_mgr->clks.dispclk_khz > 0) { + /* Core display clocks affecting bandwidth and timing */ + state->dccg.dispclk_khz = dc->clk_mgr->clks.dispclk_khz; + + /* Per-pipe clock configuration - only capture what's essential */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + if (pipe_ctx->stream) { + /* Essential clocks that directly affect underflow risk */ + state->dccg.dppclk_khz[i] = dc->clk_mgr->clks.dppclk_khz; + state->dccg.pixclk_khz[i] = pipe_ctx->stream->timing.pix_clk_100hz / 10; + state->dccg.dppclk_enable[i] = 1; + + /* DP stream clock only for DP signals */ + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT || + pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + state->dccg.dpstreamclk_enable[i] = 1; + } else { + state->dccg.dpstreamclk_enable[i] = 0; + } + } else { + /* Inactive pipe - no clocks */ + state->dccg.dppclk_khz[i] = 0; + state->dccg.pixclk_khz[i] = 0; + state->dccg.dppclk_enable[i] = 0; + if (i < 4) { + state->dccg.dpstreamclk_enable[i] = 0; + } + } + } + + /* DSC clock state - only when actually using DSC */ + for (i = 0; i < MAX_PIPES; i++) { + struct pipe_ctx *pipe_ctx = (i < dc->res_pool->pipe_count) ? &res_ctx->pipe_ctx[i] : NULL; + if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->timing.dsc_cfg.num_slices_h > 0) { + state->dccg.dscclk_khz[i] = 400000; /* Typical DSC clock frequency */ + } else { + state->dccg.dscclk_khz[i] = 0; + } + } + + /* SYMCLK32 LE Control - only the essential HPO state for underflow analysis */ + for (i = 0; i < 2; i++) { + state->dccg.symclk32_le_enable[i] = 0; /* Default: disabled */ + } + + } + + /* Capture essential DSC configuration for underflow analysis */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->stream->timing.dsc_cfg.num_slices_h > 0) { + /* DSC is enabled - capture essential configuration */ + state->dsc[i].dsc_clock_enable = 1; + + /* DSC configuration affecting bandwidth and timing */ + struct dc_dsc_config *dsc_cfg = &pipe_ctx->stream->timing.dsc_cfg; + state->dsc[i].dsc_num_slices_h = dsc_cfg->num_slices_h; + state->dsc[i].dsc_num_slices_v = dsc_cfg->num_slices_v; + state->dsc[i].dsc_bits_per_pixel = dsc_cfg->bits_per_pixel; + + /* OPP pipe source for DSC forwarding */ + if (pipe_ctx->stream_res.opp) { + state->dsc[i].dscrm_dsc_forward_enable = 1; + state->dsc[i].dscrm_dsc_opp_pipe_source = pipe_ctx->stream_res.opp->inst; + } else { + state->dsc[i].dscrm_dsc_forward_enable = 0; + state->dsc[i].dscrm_dsc_opp_pipe_source = 0; + } + } else { + /* DSC not enabled - clear all fields */ + memset(&state->dsc[i], 0, sizeof(state->dsc[i])); + } + } + + /* Capture MPC programming state - comprehensive register field coverage */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + + if (pipe_ctx->plane_state && pipe_ctx->stream) { + struct dc_plane_state *plane_state = pipe_ctx->plane_state; + + /* MPCC blending tree and mode control - capture actual blend configuration */ + state->mpc.mpcc_mode[i] = (plane_state->blend_tf.type != TF_TYPE_BYPASS) ? 1 : 0; + state->mpc.mpcc_alpha_blend_mode[i] = plane_state->per_pixel_alpha ? 1 : 0; + state->mpc.mpcc_alpha_multiplied_mode[i] = plane_state->pre_multiplied_alpha ? 1 : 0; + state->mpc.mpcc_blnd_active_overlap_only[i] = 0; /* Default - no overlap restriction */ + state->mpc.mpcc_global_alpha[i] = plane_state->global_alpha_value; + state->mpc.mpcc_global_gain[i] = plane_state->global_alpha ? 255 : 0; + state->mpc.mpcc_bg_bpc[i] = 8; /* Standard 8-bit background */ + state->mpc.mpcc_bot_gain_mode[i] = 0; /* Standard gain mode */ + + /* MPCC blending tree connections - capture tree topology */ + if (pipe_ctx->bottom_pipe) { + state->mpc.mpcc_bot_sel[i] = pipe_ctx->bottom_pipe->pipe_idx; + } else { + state->mpc.mpcc_bot_sel[i] = 0xF; /* No bottom connection */ + } + state->mpc.mpcc_top_sel[i] = pipe_ctx->pipe_idx; /* This pipe's DPP ID */ + + /* MPCC output gamma control - capture gamma programming */ + if (plane_state->gamma_correction.type != GAMMA_CS_TFM_1D && plane_state->gamma_correction.num_entries > 0) { + state->mpc.mpcc_ogam_mode[i] = 1; /* Gamma enabled */ + state->mpc.mpcc_ogam_select[i] = 0; /* Bank A selection */ + state->mpc.mpcc_ogam_pwl_disable[i] = 0; /* PWL enabled */ + } else { + state->mpc.mpcc_ogam_mode[i] = 0; /* Bypass mode */ + state->mpc.mpcc_ogam_select[i] = 0; + state->mpc.mpcc_ogam_pwl_disable[i] = 1; /* PWL disabled */ + } + + /* MPCC pipe assignment and operational status */ + if (pipe_ctx->stream_res.opp) { + state->mpc.mpcc_opp_id[i] = pipe_ctx->stream_res.opp->inst; + } else { + state->mpc.mpcc_opp_id[i] = 0xF; /* No OPP assignment */ + } + + /* MPCC status indicators - active pipe state */ + state->mpc.mpcc_idle[i] = 0; /* Active pipe - not idle */ + state->mpc.mpcc_busy[i] = 1; /* Active pipe - busy processing */ + + } else { + /* Pipe not active - set disabled/idle state for all fields */ + state->mpc.mpcc_mode[i] = 0; + state->mpc.mpcc_alpha_blend_mode[i] = 0; + state->mpc.mpcc_alpha_multiplied_mode[i] = 0; + state->mpc.mpcc_blnd_active_overlap_only[i] = 0; + state->mpc.mpcc_global_alpha[i] = 0; + state->mpc.mpcc_global_gain[i] = 0; + state->mpc.mpcc_bg_bpc[i] = 0; + state->mpc.mpcc_bot_gain_mode[i] = 0; + state->mpc.mpcc_bot_sel[i] = 0xF; /* No bottom connection */ + state->mpc.mpcc_top_sel[i] = 0xF; /* No top connection */ + state->mpc.mpcc_ogam_mode[i] = 0; /* Bypass */ + state->mpc.mpcc_ogam_select[i] = 0; + state->mpc.mpcc_ogam_pwl_disable[i] = 1; /* PWL disabled */ + state->mpc.mpcc_opp_id[i] = 0xF; /* No OPP assignment */ + state->mpc.mpcc_idle[i] = 1; /* Idle */ + state->mpc.mpcc_busy[i] = 0; /* Not busy */ + } + } + + /* Capture OPP programming state for each pipe - comprehensive register field coverage */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + + if (!pipe_ctx->stream) + continue; + + if (pipe_ctx->stream_res.opp) { + struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + + /* OPP Pipe Control */ + state->opp[i].opp_pipe_clock_enable = 1; /* Active pipe has clock enabled */ + + /* Display Pattern Generator (DPG) Control - 19 fields */ + if (pipe_ctx->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE) { + state->opp[i].dpg_enable = 1; + } else { + /* Video mode - DPG disabled */ + state->opp[i].dpg_enable = 0; + } + + /* Format Control (FMT) - 18 fields */ + state->opp[i].fmt_pixel_encoding = timing->pixel_encoding; + + /* Chroma subsampling mode based on pixel encoding */ + if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) { + state->opp[i].fmt_subsampling_mode = 1; /* 4:2:0 subsampling */ + } else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) { + state->opp[i].fmt_subsampling_mode = 2; /* 4:2:2 subsampling */ + } else { + state->opp[i].fmt_subsampling_mode = 0; /* No subsampling (4:4:4) */ + } + + state->opp[i].fmt_cbcr_bit_reduction_bypass = (timing->pixel_encoding == PIXEL_ENCODING_RGB) ? 1 : 0; + state->opp[i].fmt_stereosync_override = (timing->timing_3d_format != TIMING_3D_FORMAT_NONE) ? 1 : 0; + + /* Dithering control based on bit depth */ + if (timing->display_color_depth < COLOR_DEPTH_121212) { + state->opp[i].fmt_spatial_dither_frame_counter_max = 15; /* Typical frame counter max */ + state->opp[i].fmt_spatial_dither_frame_counter_bit_swap = 0; /* No bit swapping */ + state->opp[i].fmt_spatial_dither_enable = 1; + state->opp[i].fmt_spatial_dither_mode = 0; /* Spatial dithering mode */ + state->opp[i].fmt_spatial_dither_depth = timing->display_color_depth; + state->opp[i].fmt_temporal_dither_enable = 0; /* Spatial dithering preferred */ + } else { + state->opp[i].fmt_spatial_dither_frame_counter_max = 0; + state->opp[i].fmt_spatial_dither_frame_counter_bit_swap = 0; + state->opp[i].fmt_spatial_dither_enable = 0; + state->opp[i].fmt_spatial_dither_mode = 0; + state->opp[i].fmt_spatial_dither_depth = 0; + state->opp[i].fmt_temporal_dither_enable = 0; + } + + /* Truncation control for bit depth reduction */ + if (timing->display_color_depth < COLOR_DEPTH_121212) { + state->opp[i].fmt_truncate_enable = 1; + state->opp[i].fmt_truncate_depth = timing->display_color_depth; + state->opp[i].fmt_truncate_mode = 0; /* Round mode */ + } else { + state->opp[i].fmt_truncate_enable = 0; + state->opp[i].fmt_truncate_depth = 0; + state->opp[i].fmt_truncate_mode = 0; + } + + /* Data clamping control */ + state->opp[i].fmt_clamp_data_enable = 1; /* Clamping typically enabled */ + state->opp[i].fmt_clamp_color_format = timing->pixel_encoding; + + /* Dynamic expansion for limited range content */ + if (timing->pixel_encoding != PIXEL_ENCODING_RGB) { + state->opp[i].fmt_dynamic_exp_enable = 1; /* YCbCr typically needs expansion */ + state->opp[i].fmt_dynamic_exp_mode = 0; /* Standard expansion */ + } else { + state->opp[i].fmt_dynamic_exp_enable = 0; /* RGB typically full range */ + state->opp[i].fmt_dynamic_exp_mode = 0; + } + + /* Legacy field for compatibility */ + state->opp[i].fmt_bit_depth_control = timing->display_color_depth; + + /* Output Buffer (OPPBUF) Control - 6 fields */ + state->opp[i].oppbuf_active_width = timing->h_addressable; + state->opp[i].oppbuf_pixel_repetition = 0; /* No pixel repetition by default */ + + /* Multi-Stream Output (MSO) / ODM segmentation */ + if (pipe_ctx->next_odm_pipe) { + state->opp[i].oppbuf_display_segmentation = 1; /* Segmented display */ + state->opp[i].oppbuf_overlap_pixel_num = 0; /* ODM overlap pixels */ + } else { + state->opp[i].oppbuf_display_segmentation = 0; /* Single segment */ + state->opp[i].oppbuf_overlap_pixel_num = 0; + } + + /* 3D/Stereo control */ + if (timing->timing_3d_format != TIMING_3D_FORMAT_NONE) { + state->opp[i].oppbuf_3d_vact_space1_size = 30; /* Typical stereo blanking */ + state->opp[i].oppbuf_3d_vact_space2_size = 30; + } else { + state->opp[i].oppbuf_3d_vact_space1_size = 0; + state->opp[i].oppbuf_3d_vact_space2_size = 0; + } + + /* DSC Forward Config - 3 fields */ + if (timing->dsc_cfg.num_slices_h > 0) { + state->opp[i].dscrm_dsc_forward_enable = 1; + state->opp[i].dscrm_dsc_opp_pipe_source = pipe_ctx->stream_res.opp->inst; + state->opp[i].dscrm_dsc_forward_enable_status = 1; /* Status follows enable */ + } else { + state->opp[i].dscrm_dsc_forward_enable = 0; + state->opp[i].dscrm_dsc_opp_pipe_source = 0; + state->opp[i].dscrm_dsc_forward_enable_status = 0; + } + } else { + /* No OPP resource - set all fields to disabled state */ + memset(&state->opp[i], 0, sizeof(state->opp[i])); + } + } + + /* Capture OPTC programming state for each pipe - comprehensive register field coverage */ + for (i = 0; i < MAX_PIPES && i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; + + if (!pipe_ctx->stream) + continue; + + if (pipe_ctx->stream_res.tg) { + struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + + state->optc[i].otg_master_inst = pipe_ctx->stream_res.tg->inst; + + /* OTG_CONTROL register - 5 fields */ + state->optc[i].otg_master_enable = 1; /* Active stream */ + state->optc[i].otg_disable_point_cntl = 0; /* Normal operation */ + state->optc[i].otg_start_point_cntl = 0; /* Normal start */ + state->optc[i].otg_field_number_cntl = (timing->flags.INTERLACE) ? 1 : 0; + state->optc[i].otg_out_mux = 0; /* Direct output */ + + /* OTG Horizontal Timing - 7 fields */ + state->optc[i].otg_h_total = timing->h_total; + state->optc[i].otg_h_blank_start = timing->h_addressable; + state->optc[i].otg_h_blank_end = timing->h_total - timing->h_front_porch; + state->optc[i].otg_h_sync_start = timing->h_addressable + timing->h_front_porch; + state->optc[i].otg_h_sync_end = timing->h_addressable + timing->h_front_porch + timing->h_sync_width; + state->optc[i].otg_h_sync_polarity = timing->flags.HSYNC_POSITIVE_POLARITY ? 0 : 1; + state->optc[i].otg_h_timing_div_mode = (pipe_ctx->next_odm_pipe) ? 1 : 0; /* ODM divide mode */ + + /* OTG Vertical Timing - 7 fields */ + state->optc[i].otg_v_total = timing->v_total; + state->optc[i].otg_v_blank_start = timing->v_addressable; + state->optc[i].otg_v_blank_end = timing->v_total - timing->v_front_porch; + state->optc[i].otg_v_sync_start = timing->v_addressable + timing->v_front_porch; + state->optc[i].otg_v_sync_end = timing->v_addressable + timing->v_front_porch + timing->v_sync_width; + state->optc[i].otg_v_sync_polarity = timing->flags.VSYNC_POSITIVE_POLARITY ? 0 : 1; + state->optc[i].otg_v_sync_mode = 0; /* Normal sync mode */ + + /* Initialize remaining core fields with appropriate defaults */ + // TODO: Update logic for accurate vtotal min/max + state->optc[i].otg_v_total_max = timing->v_total + 100; /* Typical DRR range */ + state->optc[i].otg_v_total_min = timing->v_total - 50; + state->optc[i].otg_v_total_mid = timing->v_total; + + /* ODM configuration */ + // TODO: Update logic to have complete ODM mappings (e.g. 3:1 and 4:1) stored in single pipe + if (pipe_ctx->next_odm_pipe) { + state->optc[i].optc_seg0_src_sel = pipe_ctx->stream_res.opp ? pipe_ctx->stream_res.opp->inst : 0; + state->optc[i].optc_seg1_src_sel = pipe_ctx->next_odm_pipe->stream_res.opp ? pipe_ctx->next_odm_pipe->stream_res.opp->inst : 0; + state->optc[i].optc_num_of_input_segment = 1; /* 2 segments - 1 */ + } else { + state->optc[i].optc_seg0_src_sel = pipe_ctx->stream_res.opp ? pipe_ctx->stream_res.opp->inst : 0; + state->optc[i].optc_seg1_src_sel = 0; + state->optc[i].optc_num_of_input_segment = 0; /* Single segment */ + } + + /* DSC configuration */ + if (timing->dsc_cfg.num_slices_h > 0) { + state->optc[i].optc_dsc_mode = 1; /* DSC enabled */ + state->optc[i].optc_dsc_bytes_per_pixel = timing->dsc_cfg.bits_per_pixel / 16; /* Convert to bytes */ + state->optc[i].optc_dsc_slice_width = timing->h_addressable / timing->dsc_cfg.num_slices_h; + } else { + state->optc[i].optc_dsc_mode = 0; + state->optc[i].optc_dsc_bytes_per_pixel = 0; + state->optc[i].optc_dsc_slice_width = 0; + } + + /* Essential control fields */ + state->optc[i].otg_stereo_enable = (timing->timing_3d_format != TIMING_3D_FORMAT_NONE) ? 1 : 0; + state->optc[i].otg_interlace_enable = timing->flags.INTERLACE ? 1 : 0; + state->optc[i].otg_clock_enable = 1; /* OTG clock enabled */ + state->optc[i].vtg0_enable = 1; /* VTG enabled for timing generation */ + + /* Initialize other key fields to defaults */ + state->optc[i].optc_input_pix_clk_en = 1; + state->optc[i].optc_segment_width = (pipe_ctx->next_odm_pipe) ? (timing->h_addressable / 2) : timing->h_addressable; + state->optc[i].otg_vready_offset = 1; + state->optc[i].otg_vstartup_start = timing->v_addressable + 10; + state->optc[i].otg_vupdate_offset = 0; + state->optc[i].otg_vupdate_width = 5; + } else { + /* No timing generator resource - initialize all fields to 0 */ + memset(&state->optc[i], 0, sizeof(state->optc[i])); + } + } + + state->state_valid = true; + return true; +} + void dc_log_preos_dmcub_info(const struct dc *dc) { dc_dmub_srv_log_preos_dmcub_info(dc->ctx->dmub_srv); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index a7ec633b26c0..e2763b60482a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -265,7 +265,7 @@ void color_space_to_black_color( black_color_format[BLACK_COLOR_FORMAT_RGB_LIMITED]; break; - /** + /* * Remove default and add case for all color space * so when we forget to add new color space * compiler will give a warning @@ -1293,6 +1293,9 @@ void hwss_execute_sequence(struct dc *dc, case HUBP_MEM_PROGRAM_VIEWPORT: hwss_hubp_mem_program_viewport(params); break; + case ABORT_CURSOR_OFFLOAD_UPDATE: + hwss_abort_cursor_offload_update(params); + break; case SET_CURSOR_ATTRIBUTE: hwss_set_cursor_attribute(params); break; @@ -1318,7 +1321,7 @@ void hwss_execute_sequence(struct dc *dc, } } -/** +/* * Helper function to add OPTC pipe control lock to block sequence */ void hwss_add_optc_pipe_control_lock(struct block_sequence_state *seq_state, @@ -1335,7 +1338,7 @@ void hwss_add_optc_pipe_control_lock(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP set flip control GSL to block sequence */ void hwss_add_hubp_set_flip_control_gsl(struct block_sequence_state *seq_state, @@ -1350,7 +1353,7 @@ void hwss_add_hubp_set_flip_control_gsl(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP program triplebuffer to block sequence */ void hwss_add_hubp_program_triplebuffer(struct block_sequence_state *seq_state, @@ -1367,7 +1370,7 @@ void hwss_add_hubp_program_triplebuffer(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP update plane address to block sequence */ void hwss_add_hubp_update_plane_addr(struct block_sequence_state *seq_state, @@ -1382,7 +1385,7 @@ void hwss_add_hubp_update_plane_addr(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add DPP set input transfer function to block sequence */ void hwss_add_dpp_set_input_transfer_func(struct block_sequence_state *seq_state, @@ -1399,7 +1402,7 @@ void hwss_add_dpp_set_input_transfer_func(struct block_sequence_state *seq_state } } -/** +/* * Helper function to add DPP program gamut remap to block sequence */ void hwss_add_dpp_program_gamut_remap(struct block_sequence_state *seq_state, @@ -1412,7 +1415,7 @@ void hwss_add_dpp_program_gamut_remap(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add DPP program bias and scale to block sequence */ void hwss_add_dpp_program_bias_and_scale(struct block_sequence_state *seq_state, struct pipe_ctx *pipe_ctx) @@ -1424,7 +1427,7 @@ void hwss_add_dpp_program_bias_and_scale(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add OPTC program manual trigger to block sequence */ void hwss_add_optc_program_manual_trigger(struct block_sequence_state *seq_state, @@ -1437,7 +1440,7 @@ void hwss_add_optc_program_manual_trigger(struct block_sequence_state *seq_state } } -/** +/* * Helper function to add DPP set output transfer function to block sequence */ void hwss_add_dpp_set_output_transfer_func(struct block_sequence_state *seq_state, @@ -1454,7 +1457,7 @@ void hwss_add_dpp_set_output_transfer_func(struct block_sequence_state *seq_stat } } -/** +/* * Helper function to add MPC update visual confirm to block sequence */ void hwss_add_mpc_update_visual_confirm(struct block_sequence_state *seq_state, @@ -1471,7 +1474,7 @@ void hwss_add_mpc_update_visual_confirm(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add MPC power on MPC mem PWR to block sequence */ void hwss_add_mpc_power_on_mpc_mem_pwr(struct block_sequence_state *seq_state, @@ -1488,7 +1491,7 @@ void hwss_add_mpc_power_on_mpc_mem_pwr(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add MPC set output CSC to block sequence */ void hwss_add_mpc_set_output_csc(struct block_sequence_state *seq_state, @@ -1507,7 +1510,7 @@ void hwss_add_mpc_set_output_csc(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add MPC set OCSC default to block sequence */ void hwss_add_mpc_set_ocsc_default(struct block_sequence_state *seq_state, @@ -1526,7 +1529,7 @@ void hwss_add_mpc_set_ocsc_default(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add DMUB send DMCUB command to block sequence */ void hwss_add_dmub_send_dmcub_cmd(struct block_sequence_state *seq_state, @@ -1543,7 +1546,7 @@ void hwss_add_dmub_send_dmcub_cmd(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add DMUB SubVP save surface address to block sequence */ void hwss_add_dmub_subvp_save_surf_addr(struct block_sequence_state *seq_state, @@ -1560,7 +1563,7 @@ void hwss_add_dmub_subvp_save_surf_addr(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP wait for DCC meta propagation to block sequence */ void hwss_add_hubp_wait_for_dcc_meta_prop(struct block_sequence_state *seq_state, @@ -1575,7 +1578,7 @@ void hwss_add_hubp_wait_for_dcc_meta_prop(struct block_sequence_state *seq_state } } -/** +/* * Helper function to add HUBP wait pipe read start to block sequence */ void hwss_add_hubp_wait_pipe_read_start(struct block_sequence_state *seq_state, @@ -1588,7 +1591,7 @@ void hwss_add_hubp_wait_pipe_read_start(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HWS apply update flags for phantom to block sequence */ void hwss_add_hws_apply_update_flags_for_phantom(struct block_sequence_state *seq_state, @@ -1601,7 +1604,7 @@ void hwss_add_hws_apply_update_flags_for_phantom(struct block_sequence_state *se } } -/** +/* * Helper function to add HWS update phantom VP position to block sequence */ void hwss_add_hws_update_phantom_vp_position(struct block_sequence_state *seq_state, @@ -1618,7 +1621,7 @@ void hwss_add_hws_update_phantom_vp_position(struct block_sequence_state *seq_st } } -/** +/* * Helper function to add OPTC set ODM combine to block sequence */ void hwss_add_optc_set_odm_combine(struct block_sequence_state *seq_state, @@ -1636,7 +1639,7 @@ void hwss_add_optc_set_odm_combine(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add OPTC set ODM bypass to block sequence */ void hwss_add_optc_set_odm_bypass(struct block_sequence_state *seq_state, @@ -1659,7 +1662,7 @@ void hwss_send_dmcub_cmd(union block_sequence_params *params) dc_wake_and_execute_dmub_cmd(ctx, cmd, wait_type); } -/** +/* * Helper function to add TG program global sync to block sequence */ void hwss_add_tg_program_global_sync(struct block_sequence_state *seq_state, @@ -1682,7 +1685,7 @@ void hwss_add_tg_program_global_sync(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add TG wait for state to block sequence */ void hwss_add_tg_wait_for_state(struct block_sequence_state *seq_state, @@ -1697,7 +1700,7 @@ void hwss_add_tg_wait_for_state(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add TG set VTG params to block sequence */ void hwss_add_tg_set_vtg_params(struct block_sequence_state *seq_state, @@ -1714,7 +1717,7 @@ void hwss_add_tg_set_vtg_params(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add TG setup vertical interrupt2 to block sequence */ void hwss_add_tg_setup_vertical_interrupt2(struct block_sequence_state *seq_state, @@ -1728,7 +1731,7 @@ void hwss_add_tg_setup_vertical_interrupt2(struct block_sequence_state *seq_stat } } -/** +/* * Helper function to add DPP set HDR multiplier to block sequence */ void hwss_add_dpp_set_hdr_multiplier(struct block_sequence_state *seq_state, @@ -1742,7 +1745,7 @@ void hwss_add_dpp_set_hdr_multiplier(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP program DET size to block sequence */ void hwss_add_hubp_program_det_size(struct block_sequence_state *seq_state, @@ -1785,7 +1788,7 @@ void hwss_add_hubbub_force_pstate_change_control(struct block_sequence_state *se } } -/** +/* * Helper function to add HUBP program DET segments to block sequence */ void hwss_add_hubp_program_det_segments(struct block_sequence_state *seq_state, @@ -1802,7 +1805,7 @@ void hwss_add_hubp_program_det_segments(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add OPP set dynamic expansion to block sequence */ void hwss_add_opp_set_dyn_expansion(struct block_sequence_state *seq_state, @@ -1821,7 +1824,7 @@ void hwss_add_opp_set_dyn_expansion(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add OPP program FMT to block sequence */ void hwss_add_opp_program_fmt(struct block_sequence_state *seq_state, @@ -1852,7 +1855,7 @@ void hwss_add_opp_program_left_edge_extra_pixel(struct block_sequence_state *seq } } -/** +/* * Helper function to add ABM set pipe to block sequence */ void hwss_add_abm_set_pipe(struct block_sequence_state *seq_state, @@ -1867,7 +1870,7 @@ void hwss_add_abm_set_pipe(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add ABM set level to block sequence */ void hwss_add_abm_set_level(struct block_sequence_state *seq_state, @@ -1882,7 +1885,7 @@ void hwss_add_abm_set_level(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add TG enable CRTC to block sequence */ void hwss_add_tg_enable_crtc(struct block_sequence_state *seq_state, @@ -1895,7 +1898,7 @@ void hwss_add_tg_enable_crtc(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP wait flip pending to block sequence */ void hwss_add_hubp_wait_flip_pending(struct block_sequence_state *seq_state, @@ -1912,7 +1915,7 @@ void hwss_add_hubp_wait_flip_pending(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add TG wait double buffer pending to block sequence */ void hwss_add_tg_wait_double_buffer_pending(struct block_sequence_state *seq_state, @@ -3076,6 +3079,15 @@ void hwss_hubp_mem_program_viewport(union block_sequence_params *params) hubp->funcs->mem_program_viewport(hubp, viewport, viewport_c); } +void hwss_abort_cursor_offload_update(union block_sequence_params *params) +{ + struct dc *dc = params->abort_cursor_offload_update_params.dc; + struct pipe_ctx *pipe_ctx = params->abort_cursor_offload_update_params.pipe_ctx; + + if (dc && dc->hwss.abort_cursor_offload_update) + dc->hwss.abort_cursor_offload_update(dc, pipe_ctx); +} + void hwss_set_cursor_attribute(union block_sequence_params *params) { struct dc *dc = params->set_cursor_attribute_params.dc; @@ -3270,7 +3282,7 @@ void hwss_add_opp_set_disp_pattern_generator(struct block_sequence_state *seq_st } } -/** +/* * Helper function to add MPC update blending to block sequence */ void hwss_add_mpc_update_blending(struct block_sequence_state *seq_state, @@ -3287,7 +3299,7 @@ void hwss_add_mpc_update_blending(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add MPC insert plane to block sequence */ void hwss_add_mpc_insert_plane(struct block_sequence_state *seq_state, @@ -3312,7 +3324,7 @@ void hwss_add_mpc_insert_plane(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add MPC assert idle MPCC to block sequence */ void hwss_add_mpc_assert_idle_mpcc(struct block_sequence_state *seq_state, @@ -3327,7 +3339,7 @@ void hwss_add_mpc_assert_idle_mpcc(struct block_sequence_state *seq_state, } } -/** +/* * Helper function to add HUBP set blank to block sequence */ void hwss_add_hubp_set_blank(struct block_sequence_state *seq_state, @@ -3934,6 +3946,18 @@ void hwss_add_hubp_mem_program_viewport(struct block_sequence_state *seq_state, } } +void hwss_add_abort_cursor_offload_update(struct block_sequence_state *seq_state, + struct dc *dc, + struct pipe_ctx *pipe_ctx) +{ + if (*seq_state->num_steps < MAX_HWSS_BLOCK_SEQUENCE_SIZE) { + seq_state->steps[*seq_state->num_steps].func = ABORT_CURSOR_OFFLOAD_UPDATE; + seq_state->steps[*seq_state->num_steps].params.abort_cursor_offload_update_params.dc = dc; + seq_state->steps[*seq_state->num_steps].params.abort_cursor_offload_update_params.pipe_ctx = pipe_ctx; + (*seq_state->num_steps)++; + } +} + void hwss_add_set_cursor_attribute(struct block_sequence_state *seq_state, struct dc *dc, struct pipe_ctx *pipe_ctx) 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 dc0c4065a92c..848c267ef11e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -99,6 +99,40 @@ #define UNABLE_TO_SPLIT -1 +static void capture_pipe_topology_data(struct dc *dc, int plane_idx, int slice_idx, int stream_idx, + int dpp_inst, int opp_inst, int tg_inst, bool is_phantom_pipe) +{ + struct pipe_topology_snapshot *current_snapshot = &dc->debug_data.topology_history.snapshots[dc->debug_data.topology_history.current_snapshot_index]; + + if (current_snapshot->line_count >= MAX_PIPES) + return; + + current_snapshot->pipe_log_lines[current_snapshot->line_count].is_phantom_pipe = is_phantom_pipe; + current_snapshot->pipe_log_lines[current_snapshot->line_count].plane_idx = plane_idx; + current_snapshot->pipe_log_lines[current_snapshot->line_count].slice_idx = slice_idx; + current_snapshot->pipe_log_lines[current_snapshot->line_count].stream_idx = stream_idx; + current_snapshot->pipe_log_lines[current_snapshot->line_count].dpp_inst = dpp_inst; + current_snapshot->pipe_log_lines[current_snapshot->line_count].opp_inst = opp_inst; + current_snapshot->pipe_log_lines[current_snapshot->line_count].tg_inst = tg_inst; + + current_snapshot->line_count++; +} + +static void start_new_topology_snapshot(struct dc *dc, struct dc_state *state) +{ + // Move to next snapshot slot (circular buffer) + dc->debug_data.topology_history.current_snapshot_index = (dc->debug_data.topology_history.current_snapshot_index + 1) % MAX_TOPOLOGY_SNAPSHOTS; + + // Clear the new snapshot + struct pipe_topology_snapshot *current_snapshot = &dc->debug_data.topology_history.snapshots[dc->debug_data.topology_history.current_snapshot_index]; + memset(current_snapshot, 0, sizeof(*current_snapshot)); + + // Set metadata + current_snapshot->timestamp_us = dm_get_timestamp(dc->ctx); + current_snapshot->stream_count = state->stream_count; + current_snapshot->phantom_stream_count = state->phantom_stream_count; +} + enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id) { enum dce_version dc_version = DCE_VERSION_UNKNOWN; @@ -2311,10 +2345,11 @@ bool resource_is_odm_topology_changed(const struct pipe_ctx *otg_master_a, static void resource_log_pipe(struct dc *dc, struct pipe_ctx *pipe, int stream_idx, int slice_idx, int plane_idx, int slice_count, - bool is_primary) + bool is_primary, bool is_phantom_pipe) { DC_LOGGER_INIT(dc->ctx->logger); + // new format for logging: bit storing code if (slice_idx == 0 && plane_idx == 0 && is_primary) { /* case 0 (OTG master pipe with plane) */ DC_LOG_DC(" | plane%d slice%d stream%d|", @@ -2323,6 +2358,10 @@ static void resource_log_pipe(struct dc *dc, struct pipe_ctx *pipe, pipe->plane_res.dpp->inst, pipe->stream_res.opp->inst, pipe->stream_res.tg->inst); + capture_pipe_topology_data(dc, plane_idx, slice_idx, stream_idx, + pipe->plane_res.dpp->inst, + pipe->stream_res.opp->inst, + pipe->stream_res.tg->inst, is_phantom_pipe); } else if (slice_idx == 0 && plane_idx == -1) { /* case 1 (OTG master pipe without plane) */ DC_LOG_DC(" | slice%d stream%d|", @@ -2331,6 +2370,10 @@ static void resource_log_pipe(struct dc *dc, struct pipe_ctx *pipe, pipe->stream_res.opp->inst, pipe->stream_res.opp->inst, pipe->stream_res.tg->inst); + capture_pipe_topology_data(dc, 0xF, slice_idx, stream_idx, + pipe->plane_res.dpp->inst, + pipe->stream_res.opp->inst, + pipe->stream_res.tg->inst, is_phantom_pipe); } else if (slice_idx != 0 && plane_idx == 0 && is_primary) { /* case 2 (OPP head pipe with plane) */ DC_LOG_DC(" | plane%d slice%d | |", @@ -2338,27 +2381,43 @@ static void resource_log_pipe(struct dc *dc, struct pipe_ctx *pipe, DC_LOG_DC(" |DPP%d----OPP%d----| |", pipe->plane_res.dpp->inst, pipe->stream_res.opp->inst); + capture_pipe_topology_data(dc, plane_idx, slice_idx, stream_idx, + pipe->plane_res.dpp->inst, + pipe->stream_res.opp->inst, + pipe->stream_res.tg->inst, is_phantom_pipe); } else if (slice_idx != 0 && plane_idx == -1) { /* case 3 (OPP head pipe without plane) */ DC_LOG_DC(" | slice%d | |", slice_idx); DC_LOG_DC(" |DPG%d----OPP%d----| |", pipe->plane_res.dpp->inst, pipe->stream_res.opp->inst); + capture_pipe_topology_data(dc, 0xF, slice_idx, stream_idx, + pipe->plane_res.dpp->inst, + pipe->stream_res.opp->inst, + pipe->stream_res.tg->inst, is_phantom_pipe); } else if (slice_idx == slice_count - 1) { /* case 4 (DPP pipe in last slice) */ DC_LOG_DC(" | plane%d | |", plane_idx); DC_LOG_DC(" |DPP%d----| |", pipe->plane_res.dpp->inst); + capture_pipe_topology_data(dc, plane_idx, slice_idx, stream_idx, + pipe->plane_res.dpp->inst, + pipe->stream_res.opp->inst, + pipe->stream_res.tg->inst, is_phantom_pipe); } else { /* case 5 (DPP pipe not in last slice) */ DC_LOG_DC(" | plane%d | | |", plane_idx); DC_LOG_DC(" |DPP%d----| | |", pipe->plane_res.dpp->inst); + capture_pipe_topology_data(dc, plane_idx, slice_idx, stream_idx, + pipe->plane_res.dpp->inst, + pipe->stream_res.opp->inst, + pipe->stream_res.tg->inst, is_phantom_pipe); } } static void resource_log_pipe_for_stream(struct dc *dc, struct dc_state *state, - struct pipe_ctx *otg_master, int stream_idx) + struct pipe_ctx *otg_master, int stream_idx, bool is_phantom_pipe) { struct pipe_ctx *opp_heads[MAX_PIPES]; struct pipe_ctx *dpp_pipes[MAX_PIPES]; @@ -2384,12 +2443,12 @@ static void resource_log_pipe_for_stream(struct dc *dc, struct dc_state *state, resource_log_pipe(dc, dpp_pipes[dpp_idx], stream_idx, slice_idx, plane_idx, slice_count, - is_primary); + is_primary, is_phantom_pipe); } } else { resource_log_pipe(dc, opp_heads[slice_idx], stream_idx, slice_idx, plane_idx, - slice_count, true); + slice_count, true, is_phantom_pipe); } } @@ -2420,6 +2479,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state) struct pipe_ctx *otg_master; int stream_idx, phantom_stream_idx; DC_LOGGER_INIT(dc->ctx->logger); + bool is_phantom_pipe = false; + + // Start a new snapshot for this topology update + start_new_topology_snapshot(dc, state); DC_LOG_DC(" pipe topology update"); DC_LOG_DC(" ________________________"); @@ -2433,9 +2496,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state) if (!otg_master) continue; - resource_log_pipe_for_stream(dc, state, otg_master, stream_idx); + resource_log_pipe_for_stream(dc, state, otg_master, stream_idx, is_phantom_pipe); } if (state->phantom_stream_count > 0) { + is_phantom_pipe = true; DC_LOG_DC(" | (phantom pipes) |"); for (stream_idx = 0; stream_idx < state->stream_count; stream_idx++) { if (state->stream_status[stream_idx].mall_stream_config.type != SUBVP_MAIN) @@ -2448,7 +2512,7 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state) if (!otg_master) continue; - resource_log_pipe_for_stream(dc, state, otg_master, stream_idx); + resource_log_pipe_for_stream(dc, state, otg_master, stream_idx, is_phantom_pipe); } } DC_LOG_DC(" |________________________|\n"); 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 6d309c320253..129cd5f84983 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -737,9 +737,14 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream, { uint8_t i; bool ret = false; - struct dc *dc = stream->ctx->dc; - struct resource_context *res_ctx = - &dc->current_state->res_ctx; + struct dc *dc; + struct resource_context *res_ctx; + + if (!stream->ctx) + return false; + + dc = stream->ctx->dc; + res_ctx = &dc->current_state->res_ctx; dc_exit_ips_for_hw_access(dc); diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 1db7eb8f9a5b..29edfa51ea2c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -63,7 +63,7 @@ struct dcn_dsc_reg_state; struct dcn_optc_reg_state; struct dcn_dccg_reg_state; -#define DC_VER "3.2.358" +#define DC_VER "3.2.359" /** * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC @@ -899,6 +899,7 @@ struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; uint32_t auxErrorCount; + struct pipe_topology_history topology_history; }; struct dc_phy_addr_space_config { @@ -2792,4 +2793,491 @@ void dc_get_underflow_debug_data_for_otg(struct dc *dc, int primary_otg_inst, st void dc_get_power_feature_status(struct dc *dc, int primary_otg_inst, struct power_features *out_data); +/** + * Software state variables used to program register fields across the display pipeline + */ +struct dc_register_software_state { + /* HUBP register programming variables for each pipe */ + struct { + bool valid_plane_state; + bool valid_stream; + bool min_dc_gfx_version9; + uint32_t vtg_sel; /* DCHUBP_CNTL->HUBP_VTG_SEL from pipe_ctx->stream_res.tg->inst */ + uint32_t hubp_clock_enable; /* HUBP_CLK_CNTL->HUBP_CLOCK_ENABLE from power management */ + uint32_t surface_pixel_format; /* DCSURF_SURFACE_CONFIG->SURFACE_PIXEL_FORMAT from plane_state->format */ + uint32_t rotation_angle; /* DCSURF_SURFACE_CONFIG->ROTATION_ANGLE from plane_state->rotation */ + uint32_t h_mirror_en; /* DCSURF_SURFACE_CONFIG->H_MIRROR_EN from plane_state->horizontal_mirror */ + uint32_t surface_dcc_en; /* DCSURF_SURFACE_CONTROL->PRIMARY_SURFACE_DCC_EN from dcc->enable */ + uint32_t surface_size_width; /* HUBP_SIZE->SURFACE_SIZE_WIDTH from plane_size.surface_size.width */ + uint32_t surface_size_height; /* HUBP_SIZE->SURFACE_SIZE_HEIGHT from plane_size.surface_size.height */ + uint32_t pri_viewport_width; /* DCSURF_PRI_VIEWPORT_DIMENSION->PRI_VIEWPORT_WIDTH from scaler_data.viewport.width */ + uint32_t pri_viewport_height; /* DCSURF_PRI_VIEWPORT_DIMENSION->PRI_VIEWPORT_HEIGHT from scaler_data.viewport.height */ + uint32_t pri_viewport_x_start; /* DCSURF_PRI_VIEWPORT_START->PRI_VIEWPORT_X_START from scaler_data.viewport.x */ + uint32_t pri_viewport_y_start; /* DCSURF_PRI_VIEWPORT_START->PRI_VIEWPORT_Y_START from scaler_data.viewport.y */ + uint32_t cursor_enable; /* CURSOR_CONTROL->CURSOR_ENABLE from cursor_attributes.enable */ + uint32_t cursor_width; /* CURSOR_SETTINGS->CURSOR_WIDTH from cursor_position.width */ + uint32_t cursor_height; /* CURSOR_SETTINGS->CURSOR_HEIGHT from cursor_position.height */ + + /* Additional DCC configuration */ + uint32_t surface_dcc_ind_64b_blk; /* DCSURF_SURFACE_CONTROL->PRIMARY_SURFACE_DCC_IND_64B_BLK from dcc.independent_64b_blks */ + uint32_t surface_dcc_ind_128b_blk; /* DCSURF_SURFACE_CONTROL->PRIMARY_SURFACE_DCC_IND_128B_BLK from dcc.independent_128b_blks */ + + /* Surface pitch configuration */ + uint32_t surface_pitch; /* DCSURF_SURFACE_PITCH->PITCH from plane_size.surface_pitch */ + uint32_t meta_pitch; /* DCSURF_SURFACE_PITCH->META_PITCH from dcc.meta_pitch */ + uint32_t chroma_pitch; /* DCSURF_SURFACE_PITCH_C->PITCH_C from plane_size.chroma_pitch */ + uint32_t meta_pitch_c; /* DCSURF_SURFACE_PITCH_C->META_PITCH_C from dcc.meta_pitch_c */ + + /* Surface addresses */ + uint32_t primary_surface_address_low; /* DCSURF_PRIMARY_SURFACE_ADDRESS->PRIMARY_SURFACE_ADDRESS from address.grph.addr.low_part */ + uint32_t primary_surface_address_high; /* DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH->PRIMARY_SURFACE_ADDRESS_HIGH from address.grph.addr.high_part */ + uint32_t primary_meta_surface_address_low; /* DCSURF_PRIMARY_META_SURFACE_ADDRESS->PRIMARY_META_SURFACE_ADDRESS from address.grph.meta_addr.low_part */ + uint32_t primary_meta_surface_address_high; /* DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH->PRIMARY_META_SURFACE_ADDRESS_HIGH from address.grph.meta_addr.high_part */ + + /* TMZ configuration */ + uint32_t primary_surface_tmz; /* DCSURF_SURFACE_CONTROL->PRIMARY_SURFACE_TMZ from address.tmz_surface */ + uint32_t primary_meta_surface_tmz; /* DCSURF_SURFACE_CONTROL->PRIMARY_META_SURFACE_TMZ from address.tmz_surface */ + + /* Tiling configuration */ + uint32_t sw_mode; /* DCSURF_TILING_CONFIG->SW_MODE from tiling_info.gfx9.swizzle */ + uint32_t num_pipes; /* DCSURF_ADDR_CONFIG->NUM_PIPES from tiling_info.gfx9.num_pipes */ + uint32_t num_banks; /* DCSURF_ADDR_CONFIG->NUM_BANKS from tiling_info.gfx9.num_banks */ + uint32_t pipe_interleave; /* DCSURF_ADDR_CONFIG->PIPE_INTERLEAVE from tiling_info.gfx9.pipe_interleave */ + uint32_t num_shader_engines; /* DCSURF_ADDR_CONFIG->NUM_SE from tiling_info.gfx9.num_shader_engines */ + uint32_t num_rb_per_se; /* DCSURF_ADDR_CONFIG->NUM_RB_PER_SE from tiling_info.gfx9.num_rb_per_se */ + uint32_t num_pkrs; /* DCSURF_ADDR_CONFIG->NUM_PKRS from tiling_info.gfx9.num_pkrs */ + + /* DML Request Size Configuration - Luma */ + uint32_t rq_chunk_size; /* DCHUBP_REQ_SIZE_CONFIG->CHUNK_SIZE from rq_regs.rq_regs_l.chunk_size */ + uint32_t rq_min_chunk_size; /* DCHUBP_REQ_SIZE_CONFIG->MIN_CHUNK_SIZE from rq_regs.rq_regs_l.min_chunk_size */ + uint32_t rq_meta_chunk_size; /* DCHUBP_REQ_SIZE_CONFIG->META_CHUNK_SIZE from rq_regs.rq_regs_l.meta_chunk_size */ + uint32_t rq_min_meta_chunk_size; /* DCHUBP_REQ_SIZE_CONFIG->MIN_META_CHUNK_SIZE from rq_regs.rq_regs_l.min_meta_chunk_size */ + uint32_t rq_dpte_group_size; /* DCHUBP_REQ_SIZE_CONFIG->DPTE_GROUP_SIZE from rq_regs.rq_regs_l.dpte_group_size */ + uint32_t rq_mpte_group_size; /* DCHUBP_REQ_SIZE_CONFIG->MPTE_GROUP_SIZE from rq_regs.rq_regs_l.mpte_group_size */ + uint32_t rq_swath_height_l; /* DCHUBP_REQ_SIZE_CONFIG->SWATH_HEIGHT_L from rq_regs.rq_regs_l.swath_height */ + uint32_t rq_pte_row_height_l; /* DCHUBP_REQ_SIZE_CONFIG->PTE_ROW_HEIGHT_L from rq_regs.rq_regs_l.pte_row_height */ + + /* DML Request Size Configuration - Chroma */ + uint32_t rq_chunk_size_c; /* DCHUBP_REQ_SIZE_CONFIG_C->CHUNK_SIZE_C from rq_regs.rq_regs_c.chunk_size */ + uint32_t rq_min_chunk_size_c; /* DCHUBP_REQ_SIZE_CONFIG_C->MIN_CHUNK_SIZE_C from rq_regs.rq_regs_c.min_chunk_size */ + uint32_t rq_meta_chunk_size_c; /* DCHUBP_REQ_SIZE_CONFIG_C->META_CHUNK_SIZE_C from rq_regs.rq_regs_c.meta_chunk_size */ + uint32_t rq_min_meta_chunk_size_c; /* DCHUBP_REQ_SIZE_CONFIG_C->MIN_META_CHUNK_SIZE_C from rq_regs.rq_regs_c.min_meta_chunk_size */ + uint32_t rq_dpte_group_size_c; /* DCHUBP_REQ_SIZE_CONFIG_C->DPTE_GROUP_SIZE_C from rq_regs.rq_regs_c.dpte_group_size */ + uint32_t rq_mpte_group_size_c; /* DCHUBP_REQ_SIZE_CONFIG_C->MPTE_GROUP_SIZE_C from rq_regs.rq_regs_c.mpte_group_size */ + uint32_t rq_swath_height_c; /* DCHUBP_REQ_SIZE_CONFIG_C->SWATH_HEIGHT_C from rq_regs.rq_regs_c.swath_height */ + uint32_t rq_pte_row_height_c; /* DCHUBP_REQ_SIZE_CONFIG_C->PTE_ROW_HEIGHT_C from rq_regs.rq_regs_c.pte_row_height */ + + /* DML Expansion Modes */ + uint32_t drq_expansion_mode; /* DCN_EXPANSION_MODE->DRQ_EXPANSION_MODE from rq_regs.drq_expansion_mode */ + uint32_t prq_expansion_mode; /* DCN_EXPANSION_MODE->PRQ_EXPANSION_MODE from rq_regs.prq_expansion_mode */ + uint32_t mrq_expansion_mode; /* DCN_EXPANSION_MODE->MRQ_EXPANSION_MODE from rq_regs.mrq_expansion_mode */ + uint32_t crq_expansion_mode; /* DCN_EXPANSION_MODE->CRQ_EXPANSION_MODE from rq_regs.crq_expansion_mode */ + + /* DML DLG parameters - nominal */ + uint32_t dst_y_per_vm_vblank; /* NOM_PARAMETERS_0->DST_Y_PER_VM_VBLANK from dlg_regs.dst_y_per_vm_vblank */ + uint32_t dst_y_per_row_vblank; /* NOM_PARAMETERS_0->DST_Y_PER_ROW_VBLANK from dlg_regs.dst_y_per_row_vblank */ + uint32_t dst_y_per_vm_flip; /* NOM_PARAMETERS_1->DST_Y_PER_VM_FLIP from dlg_regs.dst_y_per_vm_flip */ + uint32_t dst_y_per_row_flip; /* NOM_PARAMETERS_1->DST_Y_PER_ROW_FLIP from dlg_regs.dst_y_per_row_flip */ + + /* DML prefetch settings */ + uint32_t dst_y_prefetch; /* PREFETCH_SETTINS->DST_Y_PREFETCH from dlg_regs.dst_y_prefetch */ + uint32_t vratio_prefetch; /* PREFETCH_SETTINS->VRATIO_PREFETCH from dlg_regs.vratio_prefetch */ + uint32_t vratio_prefetch_c; /* PREFETCH_SETTINS_C->VRATIO_PREFETCH_C from dlg_regs.vratio_prefetch_c */ + + /* TTU parameters */ + uint32_t qos_level_low_wm; /* TTU_CNTL1->QoSLevelLowWaterMark from ttu_regs.qos_level_low_wm */ + uint32_t qos_level_high_wm; /* TTU_CNTL1->QoSLevelHighWaterMark from ttu_regs.qos_level_high_wm */ + uint32_t qos_level_flip; /* TTU_CNTL2->QoS_LEVEL_FLIP_L from ttu_regs.qos_level_flip */ + uint32_t min_ttu_vblank; /* DCN_GLOBAL_TTU_CNTL->MIN_TTU_VBLANK from ttu_regs.min_ttu_vblank */ + } hubp[MAX_PIPES]; + + /* HUBBUB register programming variables */ + struct { + /* Individual DET buffer control per pipe - software state that programs DET registers */ + uint32_t det0_size; /* DCHUBBUB_DET0_CTRL->DET0_SIZE from hubbub->funcs->program_det_size(hubbub, 0, det_buffer_size_kb) */ + uint32_t det1_size; /* DCHUBBUB_DET1_CTRL->DET1_SIZE from hubbub->funcs->program_det_size(hubbub, 1, det_buffer_size_kb) */ + uint32_t det2_size; /* DCHUBBUB_DET2_CTRL->DET2_SIZE from hubbub->funcs->program_det_size(hubbub, 2, det_buffer_size_kb) */ + uint32_t det3_size; /* DCHUBBUB_DET3_CTRL->DET3_SIZE from hubbub->funcs->program_det_size(hubbub, 3, det_buffer_size_kb) */ + + /* Compression buffer control - software state that programs COMPBUF registers */ + uint32_t compbuf_size; /* DCHUBBUB_COMPBUF_CTRL->COMPBUF_SIZE from hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, safe_to_increase) */ + uint32_t compbuf_reserved_space_64b; /* COMPBUF_RESERVED_SPACE->COMPBUF_RESERVED_SPACE_64B from hubbub2->pixel_chunk_size / 32 */ + uint32_t compbuf_reserved_space_zs; /* COMPBUF_RESERVED_SPACE->COMPBUF_RESERVED_SPACE_ZS from hubbub2->pixel_chunk_size / 128 */ + } hubbub; + + /* DPP register programming variables for each pipe (simplified for available fields) */ + struct { + uint32_t dpp_clock_enable; /* DPP_CONTROL->DPP_CLOCK_ENABLE from dppclk_enable */ + + /* Recout (Rectangle of Interest) configuration */ + uint32_t recout_start_x; /* RECOUT_START->RECOUT_START_X from pipe_ctx->plane_res.scl_data.recout.x */ + uint32_t recout_start_y; /* RECOUT_START->RECOUT_START_Y from pipe_ctx->plane_res.scl_data.recout.y */ + uint32_t recout_width; /* RECOUT_SIZE->RECOUT_WIDTH from pipe_ctx->plane_res.scl_data.recout.width */ + uint32_t recout_height; /* RECOUT_SIZE->RECOUT_HEIGHT from pipe_ctx->plane_res.scl_data.recout.height */ + + /* MPC (Multiple Pipe/Plane Combiner) size configuration */ + uint32_t mpc_width; /* MPC_SIZE->MPC_WIDTH from pipe_ctx->plane_res.scl_data.h_active */ + uint32_t mpc_height; /* MPC_SIZE->MPC_HEIGHT from pipe_ctx->plane_res.scl_data.v_active */ + + /* DSCL mode configuration */ + uint32_t dscl_mode; /* SCL_MODE->DSCL_MODE from pipe_ctx->plane_res.scl_data.dscl_prog_data.dscl_mode */ + + /* Scaler ratios (simplified to integer parts) */ + uint32_t horz_ratio_int; /* SCL_HORZ_FILTER_SCALE_RATIO->SCL_H_SCALE_RATIO integer part from ratios.horz */ + uint32_t vert_ratio_int; /* SCL_VERT_FILTER_SCALE_RATIO->SCL_V_SCALE_RATIO integer part from ratios.vert */ + + /* Basic scaler taps */ + uint32_t h_taps; /* SCL_TAP_CONTROL->SCL_H_NUM_TAPS from taps.h_taps */ + uint32_t v_taps; /* SCL_TAP_CONTROL->SCL_V_NUM_TAPS from taps.v_taps */ + } dpp[MAX_PIPES]; + + /* DCCG register programming variables */ + struct { + /* Core Display Clock Control */ + uint32_t dispclk_khz; /* DENTIST_DISPCLK_CNTL->DENTIST_DISPCLK_WDIVIDER from clk_mgr.dispclk_khz */ + uint32_t dc_mem_global_pwr_req_dis; /* DC_MEM_GLOBAL_PWR_REQ_CNTL->DC_MEM_GLOBAL_PWR_REQ_DIS from memory power management settings */ + + /* DPP Clock Control - 4 fields per pipe */ + uint32_t dppclk_khz[MAX_PIPES]; /* DPPCLK_CTRL->DPPCLK_R_GATE_DISABLE from dpp_clocks[pipe] */ + uint32_t dppclk_enable[MAX_PIPES]; /* DPPCLK_CTRL->DPPCLK0_EN,DPPCLK1_EN,DPPCLK2_EN,DPPCLK3_EN from dccg31_update_dpp_dto() */ + uint32_t dppclk_dto_enable[MAX_PIPES]; /* DPPCLK_DTO_CTRL->DPPCLK_DTO_ENABLE from dccg->dpp_clock_gated[dpp_inst] state */ + uint32_t dppclk_dto_phase[MAX_PIPES]; /* DPPCLK0_DTO_PARAM->DPPCLK0_DTO_PHASE from phase calculation req_dppclk/ref_dppclk */ + uint32_t dppclk_dto_modulo[MAX_PIPES]; /* DPPCLK0_DTO_PARAM->DPPCLK0_DTO_MODULO from modulo = 0xff */ + + /* DSC Clock Control - 4 fields per DSC resource */ + uint32_t dscclk_khz[MAX_PIPES]; /* DSCCLK_DTO_CTRL->DSCCLK_DTO_ENABLE from dsc_clocks */ + uint32_t dscclk_dto_enable[MAX_PIPES]; /* DSCCLK_DTO_CTRL->DSCCLK0_DTO_ENABLE,DSCCLK1_DTO_ENABLE,DSCCLK2_DTO_ENABLE,DSCCLK3_DTO_ENABLE */ + uint32_t dscclk_dto_phase[MAX_PIPES]; /* DSCCLK0_DTO_PARAM->DSCCLK0_DTO_PHASE from dccg31_enable_dscclk() */ + uint32_t dscclk_dto_modulo[MAX_PIPES]; /* DSCCLK0_DTO_PARAM->DSCCLK0_DTO_MODULO from dccg31_enable_dscclk() */ + + /* Pixel Clock Control - per pipe */ + uint32_t pixclk_khz[MAX_PIPES]; /* PIXCLK_RESYNC_CNTL->PIXCLK_RESYNC_ENABLE from stream.timing.pix_clk_100hz */ + uint32_t otg_pixel_rate_div[MAX_PIPES]; /* OTG_PIXEL_RATE_DIV->OTG_PIXEL_RATE_DIV from OTG pixel rate divider control */ + uint32_t dtbclk_dto_enable[MAX_PIPES]; /* OTG0_PIXEL_RATE_CNTL->DTBCLK_DTO_ENABLE from dccg31_set_dtbclk_dto() */ + uint32_t pipe_dto_src_sel[MAX_PIPES]; /* OTG0_PIXEL_RATE_CNTL->PIPE_DTO_SRC_SEL from dccg31_set_dtbclk_dto() source selection */ + uint32_t dtbclk_dto_div[MAX_PIPES]; /* OTG0_PIXEL_RATE_CNTL->DTBCLK_DTO_DIV from dtbdto_div calculation */ + uint32_t otg_add_pixel[MAX_PIPES]; /* OTG0_PIXEL_RATE_CNTL->OTG_ADD_PIXEL from dccg31_otg_add_pixel() */ + uint32_t otg_drop_pixel[MAX_PIPES]; /* OTG0_PIXEL_RATE_CNTL->OTG_DROP_PIXEL from dccg31_otg_drop_pixel() */ + + /* DTBCLK DTO Control - 4 DTOs */ + uint32_t dtbclk_dto_modulo[4]; /* DTBCLK_DTO0_MODULO->DTBCLK_DTO0_MODULO from dccg31_set_dtbclk_dto() modulo calculation */ + uint32_t dtbclk_dto_phase[4]; /* DTBCLK_DTO0_PHASE->DTBCLK_DTO0_PHASE from phase calculation pixclk_khz/ref_dtbclk_khz */ + uint32_t dtbclk_dto_dbuf_en; /* DTBCLK_DTO_DBUF_EN->DTBCLK DTO data buffer enable */ + + /* DP Stream Clock Control - 4 pipes */ + uint32_t dpstreamclk_enable[MAX_PIPES]; /* DPSTREAMCLK_CNTL->DPSTREAMCLK_PIPE0_EN,DPSTREAMCLK_PIPE1_EN,DPSTREAMCLK_PIPE2_EN,DPSTREAMCLK_PIPE3_EN */ + uint32_t dp_dto_modulo[4]; /* DP_DTO0_MODULO->DP_DTO0_MODULO from DP stream DTO programming */ + uint32_t dp_dto_phase[4]; /* DP_DTO0_PHASE->DP_DTO0_PHASE from DP stream DTO programming */ + uint32_t dp_dto_dbuf_en; /* DP_DTO_DBUF_EN->DP DTO data buffer enable */ + + /* PHY Symbol Clock Control - 5 PHYs (A,B,C,D,E) */ + uint32_t phy_symclk_force_en[5]; /* PHYASYMCLK_CLOCK_CNTL->PHYASYMCLK_FORCE_EN from dccg31_set_physymclk() force_enable */ + uint32_t phy_symclk_force_src_sel[5]; /* PHYASYMCLK_CLOCK_CNTL->PHYASYMCLK_FORCE_SRC_SEL from dccg31_set_physymclk() clk_src */ + uint32_t phy_symclk_gate_disable[5]; /* DCCG_GATE_DISABLE_CNTL2->PHYASYMCLK_GATE_DISABLE from debug.root_clock_optimization.bits.physymclk */ + + /* SYMCLK32 SE Control - 4 instances */ + uint32_t symclk32_se_src_sel[4]; /* SYMCLK32_SE_CNTL->SYMCLK32_SE0_SRC_SEL from dccg31_enable_symclk32_se() with get_phy_mux_symclk() mapping */ + uint32_t symclk32_se_enable[4]; /* SYMCLK32_SE_CNTL->SYMCLK32_SE0_EN from dccg31_enable_symclk32_se() enable */ + uint32_t symclk32_se_gate_disable[4]; /* DCCG_GATE_DISABLE_CNTL3->SYMCLK32_SE0_GATE_DISABLE from debug.root_clock_optimization.bits.symclk32_se */ + + /* SYMCLK32 LE Control - 2 instances */ + uint32_t symclk32_le_src_sel[2]; /* SYMCLK32_LE_CNTL->SYMCLK32_LE0_SRC_SEL from dccg31_enable_symclk32_le() phyd32clk source */ + uint32_t symclk32_le_enable[2]; /* SYMCLK32_LE_CNTL->SYMCLK32_LE0_EN from dccg31_enable_symclk32_le() enable */ + uint32_t symclk32_le_gate_disable[2]; /* DCCG_GATE_DISABLE_CNTL3->SYMCLK32_LE0_GATE_DISABLE from debug.root_clock_optimization.bits.symclk32_le */ + + /* DPIA Clock Control */ + uint32_t dpiaclk_540m_dto_modulo; /* DPIACLK_540M_DTO_MODULO->DPIA 540MHz DTO modulo */ + uint32_t dpiaclk_540m_dto_phase; /* DPIACLK_540M_DTO_PHASE->DPIA 540MHz DTO phase */ + uint32_t dpiaclk_810m_dto_modulo; /* DPIACLK_810M_DTO_MODULO->DPIA 810MHz DTO modulo */ + uint32_t dpiaclk_810m_dto_phase; /* DPIACLK_810M_DTO_PHASE->DPIA 810MHz DTO phase */ + uint32_t dpiaclk_dto_cntl; /* DPIACLK_DTO_CNTL->DPIA clock DTO control */ + uint32_t dpiasymclk_cntl; /* DPIASYMCLK_CNTL->DPIA symbol clock control */ + + /* Clock Gating Control */ + uint32_t dccg_gate_disable_cntl; /* DCCG_GATE_DISABLE_CNTL->Clock gate disable control from dccg31_init() */ + uint32_t dpstreamclk_gate_disable; /* DCCG_GATE_DISABLE_CNTL3->DPSTREAMCLK_GATE_DISABLE from debug.root_clock_optimization.bits.dpstream */ + uint32_t dpstreamclk_root_gate_disable; /* DCCG_GATE_DISABLE_CNTL3->DPSTREAMCLK_ROOT_GATE_DISABLE from debug.root_clock_optimization.bits.dpstream */ + + /* VSync Control */ + uint32_t vsync_cnt_ctrl; /* DCCG_VSYNC_CNT_CTRL->VSync counter control */ + uint32_t vsync_cnt_int_ctrl; /* DCCG_VSYNC_CNT_INT_CTRL->VSync counter interrupt control */ + uint32_t vsync_otg_latch_value[6]; /* DCCG_VSYNC_OTG0_LATCH_VALUE->OTG0 VSync latch value (for OTG0-5) */ + + /* Time Base Control */ + uint32_t microsecond_time_base_div; /* MICROSECOND_TIME_BASE_DIV->Microsecond time base divider */ + uint32_t millisecond_time_base_div; /* MILLISECOND_TIME_BASE_DIV->Millisecond time base divider */ + } dccg; + + /* DSC essential configuration for underflow analysis */ + struct { + /* DSC active state - critical for bandwidth analysis */ + uint32_t dsc_clock_enable; /* DSC enabled - affects bandwidth requirements */ + + /* DSC configuration affecting bandwidth and timing */ + uint32_t dsc_num_slices_h; /* Horizontal slice count - affects throughput */ + uint32_t dsc_num_slices_v; /* Vertical slice count - affects throughput */ + uint32_t dsc_bits_per_pixel; /* Compression ratio - affects bandwidth */ + + /* OPP integration - affects pipeline flow */ + uint32_t dscrm_dsc_forward_enable; /* DSC forwarding to OPP enabled */ + uint32_t dscrm_dsc_opp_pipe_source; /* Which OPP receives DSC output */ + } dsc[MAX_PIPES]; + + /* MPC register programming variables */ + struct { + /* MPCC blending tree and mode control */ + uint32_t mpcc_mode[MAX_PIPES]; /* MPCC_CONTROL->MPCC_MODE from blend_cfg.blend_mode */ + uint32_t mpcc_alpha_blend_mode[MAX_PIPES]; /* MPCC_CONTROL->MPCC_ALPHA_BLND_MODE from blend_cfg.alpha_mode */ + uint32_t mpcc_alpha_multiplied_mode[MAX_PIPES]; /* MPCC_CONTROL->MPCC_ALPHA_MULTIPLIED_MODE from blend_cfg.pre_multiplied_alpha */ + uint32_t mpcc_blnd_active_overlap_only[MAX_PIPES]; /* MPCC_CONTROL->MPCC_BLND_ACTIVE_OVERLAP_ONLY from blend_cfg.overlap_only */ + uint32_t mpcc_global_alpha[MAX_PIPES]; /* MPCC_CONTROL->MPCC_GLOBAL_ALPHA from blend_cfg.global_alpha */ + uint32_t mpcc_global_gain[MAX_PIPES]; /* MPCC_CONTROL->MPCC_GLOBAL_GAIN from blend_cfg.global_gain */ + uint32_t mpcc_bg_bpc[MAX_PIPES]; /* MPCC_CONTROL->MPCC_BG_BPC from background color depth */ + uint32_t mpcc_bot_gain_mode[MAX_PIPES]; /* MPCC_CONTROL->MPCC_BOT_GAIN_MODE from bottom layer gain control */ + + /* MPCC blending tree connections */ + uint32_t mpcc_bot_sel[MAX_PIPES]; /* MPCC_BOT_SEL->MPCC_BOT_SEL from mpcc_state->bot_sel */ + uint32_t mpcc_top_sel[MAX_PIPES]; /* MPCC_TOP_SEL->MPCC_TOP_SEL from mpcc_state->dpp_id */ + + /* MPCC output gamma control */ + uint32_t mpcc_ogam_mode[MAX_PIPES]; /* MPCC_OGAM_CONTROL->MPCC_OGAM_MODE from output gamma mode */ + uint32_t mpcc_ogam_select[MAX_PIPES]; /* MPCC_OGAM_CONTROL->MPCC_OGAM_SELECT from gamma LUT bank selection */ + uint32_t mpcc_ogam_pwl_disable[MAX_PIPES]; /* MPCC_OGAM_CONTROL->MPCC_OGAM_PWL_DISABLE from PWL control */ + + /* MPCC pipe assignment and status */ + uint32_t mpcc_opp_id[MAX_PIPES]; /* MPCC_OPP_ID->MPCC_OPP_ID from mpcc_state->opp_id */ + uint32_t mpcc_idle[MAX_PIPES]; /* MPCC_STATUS->MPCC_IDLE from mpcc idle status */ + uint32_t mpcc_busy[MAX_PIPES]; /* MPCC_STATUS->MPCC_BUSY from mpcc busy status */ + + /* MPC output processing */ + uint32_t mpc_out_csc_mode; /* MPC_OUT_CSC_COEF->MPC_OUT_CSC_MODE from output_csc */ + uint32_t mpc_out_gamma_mode; /* MPC_OUT_GAMMA_LUT->MPC_OUT_GAMMA_MODE from output_gamma */ + } mpc; + + /* OPP register programming variables for each pipe */ + struct { + /* Display Pattern Generator (DPG) Control - 19 fields from DPG_CONTROL register */ + uint32_t dpg_enable; /* DPG_CONTROL->DPG_EN from test_pattern parameter (enable/disable) */ + + /* Format Control (FMT) - 18 fields from FMT_CONTROL register */ + uint32_t fmt_pixel_encoding; /* FMT_CONTROL->FMT_PIXEL_ENCODING from clamping->pixel_encoding */ + uint32_t fmt_subsampling_mode; /* FMT_CONTROL->FMT_SUBSAMPLING_MODE from force_chroma_subsampling_1tap */ + uint32_t fmt_cbcr_bit_reduction_bypass; /* FMT_CONTROL->FMT_CBCR_BIT_REDUCTION_BYPASS from pixel_encoding bypass control */ + uint32_t fmt_stereosync_override; /* FMT_CONTROL->FMT_STEREOSYNC_OVERRIDE from stereo timing override */ + uint32_t fmt_spatial_dither_frame_counter_max; /* FMT_CONTROL->FMT_SPATIAL_DITHER_FRAME_COUNTER_MAX from fmt_bit_depth->flags */ + uint32_t fmt_spatial_dither_frame_counter_bit_swap; /* FMT_CONTROL->FMT_SPATIAL_DITHER_FRAME_COUNTER_BIT_SWAP from dither control */ + uint32_t fmt_truncate_enable; /* FMT_CONTROL->FMT_TRUNCATE_EN from fmt_bit_depth->flags.TRUNCATE_ENABLED */ + uint32_t fmt_truncate_depth; /* FMT_CONTROL->FMT_TRUNCATE_DEPTH from fmt_bit_depth->flags.TRUNCATE_DEPTH */ + uint32_t fmt_truncate_mode; /* FMT_CONTROL->FMT_TRUNCATE_MODE from fmt_bit_depth->flags.TRUNCATE_MODE */ + uint32_t fmt_spatial_dither_enable; /* FMT_CONTROL->FMT_SPATIAL_DITHER_EN from fmt_bit_depth->flags.SPATIAL_DITHER_ENABLED */ + uint32_t fmt_spatial_dither_mode; /* FMT_CONTROL->FMT_SPATIAL_DITHER_MODE from fmt_bit_depth->flags.SPATIAL_DITHER_MODE */ + uint32_t fmt_spatial_dither_depth; /* FMT_CONTROL->FMT_SPATIAL_DITHER_DEPTH from fmt_bit_depth->flags.SPATIAL_DITHER_DEPTH */ + uint32_t fmt_temporal_dither_enable; /* FMT_CONTROL->FMT_TEMPORAL_DITHER_EN from fmt_bit_depth->flags.TEMPORAL_DITHER_ENABLED */ + uint32_t fmt_clamp_data_enable; /* FMT_CONTROL->FMT_CLAMP_DATA_EN from clamping->clamping_range enable */ + uint32_t fmt_clamp_color_format; /* FMT_CONTROL->FMT_CLAMP_COLOR_FORMAT from clamping->color_format */ + uint32_t fmt_dynamic_exp_enable; /* FMT_CONTROL->FMT_DYNAMIC_EXP_EN from color_sp/color_dpth/signal */ + uint32_t fmt_dynamic_exp_mode; /* FMT_CONTROL->FMT_DYNAMIC_EXP_MODE from color space mode mapping */ + uint32_t fmt_bit_depth_control; /* Legacy field - kept for compatibility */ + + /* OPP Pipe Control - 1 field from OPP_PIPE_CONTROL register */ + uint32_t opp_pipe_clock_enable; /* OPP_PIPE_CONTROL->OPP_PIPE_CLOCK_EN from enable parameter (bool) */ + + /* OPP CRC Control - 3 fields from OPP_PIPE_CRC_CONTROL register */ + uint32_t opp_crc_enable; /* OPP_PIPE_CRC_CONTROL->CRC_EN from CRC enable control */ + uint32_t opp_crc_select_source; /* OPP_PIPE_CRC_CONTROL->CRC_SELECT_SOURCE from CRC source selection */ + uint32_t opp_crc_stereo_cont; /* OPP_PIPE_CRC_CONTROL->CRC_STEREO_CONT from stereo continuous CRC */ + + /* Output Buffer (OPPBUF) Control - 6 fields from OPPBUF_CONTROL register */ + uint32_t oppbuf_active_width; /* OPPBUF_CONTROL->OPPBUF_ACTIVE_WIDTH from oppbuf_params->active_width */ + uint32_t oppbuf_pixel_repetition; /* OPPBUF_CONTROL->OPPBUF_PIXEL_REPETITION from oppbuf_params->pixel_repetition */ + uint32_t oppbuf_display_segmentation; /* OPPBUF_CONTROL->OPPBUF_DISPLAY_SEGMENTATION from oppbuf_params->mso_segmentation */ + uint32_t oppbuf_overlap_pixel_num; /* OPPBUF_CONTROL->OPPBUF_OVERLAP_PIXEL_NUM from oppbuf_params->mso_overlap_pixel_num */ + uint32_t oppbuf_3d_vact_space1_size; /* OPPBUF_CONTROL->OPPBUF_3D_VACT_SPACE1_SIZE from 3D timing space1_size */ + uint32_t oppbuf_3d_vact_space2_size; /* OPPBUF_CONTROL->OPPBUF_3D_VACT_SPACE2_SIZE from 3D timing space2_size */ + + /* DSC Forward Config - 3 fields from DSCRM_DSC_FORWARD_CONFIG register */ + uint32_t dscrm_dsc_forward_enable; /* DSCRM_DSC_FORWARD_CONFIG->DSCRM_DSC_FORWARD_EN from DSC forward enable control */ + uint32_t dscrm_dsc_opp_pipe_source; /* DSCRM_DSC_FORWARD_CONFIG->DSCRM_DSC_OPP_PIPE_SOURCE from opp_pipe parameter */ + uint32_t dscrm_dsc_forward_enable_status; /* DSCRM_DSC_FORWARD_CONFIG->DSCRM_DSC_FORWARD_EN_STATUS from DSC forward status (read-only) */ + } opp[MAX_PIPES]; + + /* OPTC register programming variables for each pipe */ + struct { + uint32_t otg_master_inst; + + /* OTG_CONTROL register - 5 fields for OTG control */ + uint32_t otg_master_enable; /* OTG_CONTROL->OTG_MASTER_EN from timing enable/disable control */ + uint32_t otg_disable_point_cntl; /* OTG_CONTROL->OTG_DISABLE_POINT_CNTL from disable timing control */ + uint32_t otg_start_point_cntl; /* OTG_CONTROL->OTG_START_POINT_CNTL from start timing control */ + uint32_t otg_field_number_cntl; /* OTG_CONTROL->OTG_FIELD_NUMBER_CNTL from interlace field control */ + uint32_t otg_out_mux; /* OTG_CONTROL->OTG_OUT_MUX from output mux selection */ + + /* OTG Horizontal Timing - 7 fields */ + uint32_t otg_h_total; /* OTG_H_TOTAL->OTG_H_TOTAL from dc_crtc_timing->h_total */ + uint32_t otg_h_blank_start; /* OTG_H_BLANK_START_END->OTG_H_BLANK_START from dc_crtc_timing->h_front_porch */ + uint32_t otg_h_blank_end; /* OTG_H_BLANK_START_END->OTG_H_BLANK_END from dc_crtc_timing->h_addressable_video_pixel_width */ + uint32_t otg_h_sync_start; /* OTG_H_SYNC_A->OTG_H_SYNC_A_START from dc_crtc_timing->h_sync_width */ + uint32_t otg_h_sync_end; /* OTG_H_SYNC_A->OTG_H_SYNC_A_END from calculated sync end position */ + uint32_t otg_h_sync_polarity; /* OTG_H_SYNC_A_CNTL->OTG_H_SYNC_A_POL from dc_crtc_timing->flags.HSYNC_POSITIVE_POLARITY */ + uint32_t otg_h_timing_div_mode; /* OTG_H_TIMING_CNTL->OTG_H_TIMING_DIV_MODE from horizontal timing division mode */ + + /* OTG Vertical Timing - 7 fields */ + uint32_t otg_v_total; /* OTG_V_TOTAL->OTG_V_TOTAL from dc_crtc_timing->v_total */ + uint32_t otg_v_blank_start; /* OTG_V_BLANK_START_END->OTG_V_BLANK_START from dc_crtc_timing->v_front_porch */ + uint32_t otg_v_blank_end; /* OTG_V_BLANK_START_END->OTG_V_BLANK_END from dc_crtc_timing->v_addressable_video_line_width */ + uint32_t otg_v_sync_start; /* OTG_V_SYNC_A->OTG_V_SYNC_A_START from dc_crtc_timing->v_sync_width */ + uint32_t otg_v_sync_end; /* OTG_V_SYNC_A->OTG_V_SYNC_A_END from calculated sync end position */ + uint32_t otg_v_sync_polarity; /* OTG_V_SYNC_A_CNTL->OTG_V_SYNC_A_POL from dc_crtc_timing->flags.VSYNC_POSITIVE_POLARITY */ + uint32_t otg_v_sync_mode; /* OTG_V_SYNC_A_CNTL->OTG_V_SYNC_MODE from sync mode selection */ + + /* OTG DRR (Dynamic Refresh Rate) Control - 8 fields */ + uint32_t otg_v_total_max; /* OTG_V_TOTAL_MAX->OTG_V_TOTAL_MAX from drr_params->vertical_total_max */ + uint32_t otg_v_total_min; /* OTG_V_TOTAL_MIN->OTG_V_TOTAL_MIN from drr_params->vertical_total_min */ + uint32_t otg_v_total_mid; /* OTG_V_TOTAL_MID->OTG_V_TOTAL_MID from drr_params->vertical_total_mid */ + uint32_t otg_v_total_max_sel; /* OTG_V_TOTAL_CONTROL->OTG_V_TOTAL_MAX_SEL from DRR max selection enable */ + uint32_t otg_v_total_min_sel; /* OTG_V_TOTAL_CONTROL->OTG_V_TOTAL_MIN_SEL from DRR min selection enable */ + uint32_t otg_vtotal_mid_replacing_max_en; /* OTG_V_TOTAL_CONTROL->OTG_VTOTAL_MID_REPLACING_MAX_EN from DRR mid-frame enable */ + uint32_t otg_vtotal_mid_frame_num; /* OTG_V_TOTAL_CONTROL->OTG_VTOTAL_MID_FRAME_NUM from drr_params->vertical_total_mid_frame_num */ + uint32_t otg_set_v_total_min_mask; /* OTG_V_TOTAL_CONTROL->OTG_SET_V_TOTAL_MIN_MASK from DRR trigger mask */ + uint32_t otg_force_lock_on_event; /* OTG_V_TOTAL_CONTROL->OTG_FORCE_LOCK_ON_EVENT from DRR force lock control */ + + /* OPTC Data Source and ODM - 6 fields */ + uint32_t optc_seg0_src_sel; /* OPTC_DATA_SOURCE_SELECT->OPTC_SEG0_SRC_SEL from opp_id[0] ODM segment 0 source */ + uint32_t optc_seg1_src_sel; /* OPTC_DATA_SOURCE_SELECT->OPTC_SEG1_SRC_SEL from opp_id[1] ODM segment 1 source */ + uint32_t optc_seg2_src_sel; /* OPTC_DATA_SOURCE_SELECT->OPTC_SEG2_SRC_SEL from opp_id[2] ODM segment 2 source */ + uint32_t optc_seg3_src_sel; /* OPTC_DATA_SOURCE_SELECT->OPTC_SEG3_SRC_SEL from opp_id[3] ODM segment 3 source */ + uint32_t optc_num_of_input_segment; /* OPTC_DATA_SOURCE_SELECT->OPTC_NUM_OF_INPUT_SEGMENT from opp_cnt-1 number of input segments */ + uint32_t optc_mem_sel; /* OPTC_MEMORY_CONFIG->OPTC_MEM_SEL from memory_mask ODM memory selection */ + + /* OPTC Data Format and DSC - 4 fields */ + uint32_t optc_data_format; /* OPTC_DATA_FORMAT_CONTROL->OPTC_DATA_FORMAT from data format selection */ + uint32_t optc_dsc_mode; /* OPTC_DATA_FORMAT_CONTROL->OPTC_DSC_MODE from dsc_mode parameter */ + uint32_t optc_dsc_bytes_per_pixel; /* OPTC_BYTES_PER_PIXEL->OPTC_DSC_BYTES_PER_PIXEL from dsc_bytes_per_pixel parameter */ + uint32_t optc_segment_width; /* OPTC_WIDTH_CONTROL->OPTC_SEGMENT_WIDTH from segment_width parameter */ + uint32_t optc_dsc_slice_width; /* OPTC_WIDTH_CONTROL->OPTC_DSC_SLICE_WIDTH from dsc_slice_width parameter */ + + /* OPTC Clock and Underflow Control - 4 fields */ + uint32_t optc_input_pix_clk_en; /* OPTC_INPUT_CLOCK_CONTROL->OPTC_INPUT_PIX_CLK_EN from pixel clock enable */ + uint32_t optc_underflow_occurred_status; /* OPTC_INPUT_GLOBAL_CONTROL->OPTC_UNDERFLOW_OCCURRED_STATUS from underflow status (read-only) */ + uint32_t optc_underflow_clear; /* OPTC_INPUT_GLOBAL_CONTROL->OPTC_UNDERFLOW_CLEAR from underflow clear control */ + uint32_t otg_clock_enable; /* OTG_CLOCK_CONTROL->OTG_CLOCK_EN from OTG clock enable */ + uint32_t otg_clock_gate_dis; /* OTG_CLOCK_CONTROL->OTG_CLOCK_GATE_DIS from clock gate disable */ + + /* OTG Stereo and 3D Control - 6 fields */ + uint32_t otg_stereo_enable; /* OTG_STEREO_CONTROL->OTG_STEREO_EN from stereo enable control */ + uint32_t otg_stereo_sync_output_line_num; /* OTG_STEREO_CONTROL->OTG_STEREO_SYNC_OUTPUT_LINE_NUM from timing->stereo_3d_format line num */ + uint32_t otg_stereo_sync_output_polarity; /* OTG_STEREO_CONTROL->OTG_STEREO_SYNC_OUTPUT_POLARITY from stereo polarity control */ + uint32_t otg_3d_structure_en; /* OTG_3D_STRUCTURE_CONTROL->OTG_3D_STRUCTURE_EN from 3D structure enable */ + uint32_t otg_3d_structure_v_update_mode; /* OTG_3D_STRUCTURE_CONTROL->OTG_3D_STRUCTURE_V_UPDATE_MODE from 3D vertical update mode */ + uint32_t otg_3d_structure_stereo_sel_ovr; /* OTG_3D_STRUCTURE_CONTROL->OTG_3D_STRUCTURE_STEREO_SEL_OVR from 3D stereo selection override */ + uint32_t otg_interlace_enable; /* OTG_INTERLACE_CONTROL->OTG_INTERLACE_ENABLE from dc_crtc_timing->flags.INTERLACE */ + + /* OTG GSL (Global Sync Lock) Control - 5 fields */ + uint32_t otg_gsl0_en; /* OTG_GSL_CONTROL->OTG_GSL0_EN from GSL group 0 enable */ + uint32_t otg_gsl1_en; /* OTG_GSL_CONTROL->OTG_GSL1_EN from GSL group 1 enable */ + uint32_t otg_gsl2_en; /* OTG_GSL_CONTROL->OTG_GSL2_EN from GSL group 2 enable */ + uint32_t otg_gsl_master_en; /* OTG_GSL_CONTROL->OTG_GSL_MASTER_EN from GSL master enable */ + uint32_t otg_gsl_master_mode; /* OTG_GSL_CONTROL->OTG_GSL_MASTER_MODE from gsl_params->gsl_master mode */ + + /* OTG DRR Advanced Control - 4 fields */ + uint32_t otg_v_total_last_used_by_drr; /* OTG_DRR_CONTROL->OTG_V_TOTAL_LAST_USED_BY_DRR from last used DRR V_TOTAL (read-only) */ + uint32_t otg_drr_trigger_window_start_x; /* OTG_DRR_TRIGGER_WINDOW->OTG_DRR_TRIGGER_WINDOW_START_X from window_start parameter */ + uint32_t otg_drr_trigger_window_end_x; /* OTG_DRR_TRIGGER_WINDOW->OTG_DRR_TRIGGER_WINDOW_END_X from window_end parameter */ + uint32_t otg_drr_v_total_change_limit; /* OTG_DRR_V_TOTAL_CHANGE->OTG_DRR_V_TOTAL_CHANGE_LIMIT from limit parameter */ + + /* OTG DSC Position Control - 2 fields */ + uint32_t otg_dsc_start_position_x; /* OTG_DSC_START_POSITION->OTG_DSC_START_POSITION_X from DSC start X position */ + uint32_t otg_dsc_start_position_line_num; /* OTG_DSC_START_POSITION->OTG_DSC_START_POSITION_LINE_NUM from DSC start line number */ + + /* OTG Double Buffer Control - 2 fields */ + uint32_t otg_drr_timing_dbuf_update_mode; /* OTG_DOUBLE_BUFFER_CONTROL->OTG_DRR_TIMING_DBUF_UPDATE_MODE from DRR double buffer mode */ + uint32_t otg_blank_data_double_buffer_en; /* OTG_DOUBLE_BUFFER_CONTROL->OTG_BLANK_DATA_DOUBLE_BUFFER_EN from blank data double buffer enable */ + + /* OTG Vertical Interrupts - 6 fields */ + uint32_t otg_vertical_interrupt0_int_enable; /* OTG_VERTICAL_INTERRUPT0_CONTROL->OTG_VERTICAL_INTERRUPT0_INT_ENABLE from interrupt 0 enable */ + uint32_t otg_vertical_interrupt0_line_start; /* OTG_VERTICAL_INTERRUPT0_POSITION->OTG_VERTICAL_INTERRUPT0_LINE_START from start_line parameter */ + uint32_t otg_vertical_interrupt1_int_enable; /* OTG_VERTICAL_INTERRUPT1_CONTROL->OTG_VERTICAL_INTERRUPT1_INT_ENABLE from interrupt 1 enable */ + uint32_t otg_vertical_interrupt1_line_start; /* OTG_VERTICAL_INTERRUPT1_POSITION->OTG_VERTICAL_INTERRUPT1_LINE_START from start_line parameter */ + uint32_t otg_vertical_interrupt2_int_enable; /* OTG_VERTICAL_INTERRUPT2_CONTROL->OTG_VERTICAL_INTERRUPT2_INT_ENABLE from interrupt 2 enable */ + uint32_t otg_vertical_interrupt2_line_start; /* OTG_VERTICAL_INTERRUPT2_POSITION->OTG_VERTICAL_INTERRUPT2_LINE_START from start_line parameter */ + + /* OTG Global Sync Parameters - 6 fields */ + uint32_t otg_vready_offset; /* OTG_VREADY_PARAM->OTG_VREADY_OFFSET from vready_offset parameter */ + uint32_t otg_vstartup_start; /* OTG_VSTARTUP_PARAM->OTG_VSTARTUP_START from vstartup_start parameter */ + uint32_t otg_vupdate_offset; /* OTG_VUPDATE_PARAM->OTG_VUPDATE_OFFSET from vupdate_offset parameter */ + uint32_t otg_vupdate_width; /* OTG_VUPDATE_PARAM->OTG_VUPDATE_WIDTH from vupdate_width parameter */ + uint32_t master_update_lock_vupdate_keepout_start_offset; /* OTG_VUPDATE_KEEPOUT->MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET from pstate_keepout start */ + uint32_t master_update_lock_vupdate_keepout_end_offset; /* OTG_VUPDATE_KEEPOUT->MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET from pstate_keepout end */ + + /* OTG Manual Trigger Control - 11 fields */ + uint32_t otg_triga_source_select; /* OTG_TRIGA_CNTL->OTG_TRIGA_SOURCE_SELECT from trigger A source selection */ + uint32_t otg_triga_source_pipe_select; /* OTG_TRIGA_CNTL->OTG_TRIGA_SOURCE_PIPE_SELECT from trigger A pipe selection */ + uint32_t otg_triga_rising_edge_detect_cntl; /* OTG_TRIGA_CNTL->OTG_TRIGA_RISING_EDGE_DETECT_CNTL from trigger A rising edge detect */ + uint32_t otg_triga_falling_edge_detect_cntl; /* OTG_TRIGA_CNTL->OTG_TRIGA_FALLING_EDGE_DETECT_CNTL from trigger A falling edge detect */ + uint32_t otg_triga_polarity_select; /* OTG_TRIGA_CNTL->OTG_TRIGA_POLARITY_SELECT from trigger A polarity selection */ + uint32_t otg_triga_frequency_select; /* OTG_TRIGA_CNTL->OTG_TRIGA_FREQUENCY_SELECT from trigger A frequency selection */ + uint32_t otg_triga_delay; /* OTG_TRIGA_CNTL->OTG_TRIGA_DELAY from trigger A delay */ + uint32_t otg_triga_clear; /* OTG_TRIGA_CNTL->OTG_TRIGA_CLEAR from trigger A clear */ + uint32_t otg_triga_manual_trig; /* OTG_TRIGA_MANUAL_TRIG->OTG_TRIGA_MANUAL_TRIG from manual trigger A */ + uint32_t otg_trigb_source_select; /* OTG_TRIGB_CNTL->OTG_TRIGB_SOURCE_SELECT from trigger B source selection */ + uint32_t otg_trigb_polarity_select; /* OTG_TRIGB_CNTL->OTG_TRIGB_POLARITY_SELECT from trigger B polarity selection */ + uint32_t otg_trigb_manual_trig; /* OTG_TRIGB_MANUAL_TRIG->OTG_TRIGB_MANUAL_TRIG from manual trigger B */ + + /* OTG Static Screen and Update Control - 6 fields */ + uint32_t otg_static_screen_event_mask; /* OTG_STATIC_SCREEN_CONTROL->OTG_STATIC_SCREEN_EVENT_MASK from event_triggers parameter */ + uint32_t otg_static_screen_frame_count; /* OTG_STATIC_SCREEN_CONTROL->OTG_STATIC_SCREEN_FRAME_COUNT from num_frames parameter */ + uint32_t master_update_lock; /* OTG_MASTER_UPDATE_LOCK->MASTER_UPDATE_LOCK from update lock control */ + uint32_t master_update_mode; /* OTG_MASTER_UPDATE_MODE->MASTER_UPDATE_MODE from update mode selection */ + uint32_t otg_force_count_now_mode; /* OTG_FORCE_COUNT_NOW_CNTL->OTG_FORCE_COUNT_NOW_MODE from force count mode */ + uint32_t otg_force_count_now_clear; /* OTG_FORCE_COUNT_NOW_CNTL->OTG_FORCE_COUNT_NOW_CLEAR from force count clear */ + + /* VTG Control - 3 fields */ + uint32_t vtg0_enable; /* CONTROL->VTG0_ENABLE from VTG enable control */ + uint32_t vtg0_fp2; /* CONTROL->VTG0_FP2 from VTG front porch 2 */ + uint32_t vtg0_vcount_init; /* CONTROL->VTG0_VCOUNT_INIT from VTG vertical count init */ + + /* OTG Status (Read-Only) - 12 fields */ + uint32_t otg_v_blank; /* OTG_STATUS->OTG_V_BLANK from vertical blank status (read-only) */ + uint32_t otg_v_active_disp; /* OTG_STATUS->OTG_V_ACTIVE_DISP from vertical active display (read-only) */ + uint32_t otg_frame_count; /* OTG_STATUS_FRAME_COUNT->OTG_FRAME_COUNT from frame count (read-only) */ + uint32_t otg_horz_count; /* OTG_STATUS_POSITION->OTG_HORZ_COUNT from horizontal position (read-only) */ + uint32_t otg_vert_count; /* OTG_STATUS_POSITION->OTG_VERT_COUNT from vertical position (read-only) */ + uint32_t otg_horz_count_hv; /* OTG_STATUS_HV_COUNT->OTG_HORZ_COUNT from horizontal count (read-only) */ + uint32_t otg_vert_count_nom; /* OTG_STATUS_HV_COUNT->OTG_VERT_COUNT_NOM from vertical count nominal (read-only) */ + uint32_t otg_flip_pending; /* OTG_PIPE_UPDATE_STATUS->OTG_FLIP_PENDING from flip pending status (read-only) */ + uint32_t otg_dc_reg_update_pending; /* OTG_PIPE_UPDATE_STATUS->OTG_DC_REG_UPDATE_PENDING from DC register update pending (read-only) */ + uint32_t otg_cursor_update_pending; /* OTG_PIPE_UPDATE_STATUS->OTG_CURSOR_UPDATE_PENDING from cursor update pending (read-only) */ + uint32_t otg_vupdate_keepout_status; /* OTG_PIPE_UPDATE_STATUS->OTG_VUPDATE_KEEPOUT_STATUS from VUPDATE keepout status (read-only) */ + } optc[MAX_PIPES]; + + /* Metadata */ + uint32_t active_pipe_count; + uint32_t active_stream_count; + bool state_valid; +}; + +/** + * dc_capture_register_software_state() - Capture software state for register programming + * @dc: DC context containing current display configuration + * @state: Pointer to dc_register_software_state structure to populate + * + * Extracts all software state variables that are used to program hardware register + * fields across the display driver pipeline. This provides a complete snapshot + * of the software configuration that drives hardware register programming. + * + * The function traverses the DC context and extracts values from: + * - Stream configurations (timing, format, DSC settings) + * - Plane states (surface format, rotation, scaling, cursor) + * - Pipe contexts (resource allocation, blending, viewport) + * - Clock manager (display clocks, DPP clocks, pixel clocks) + * - Resource context (DET buffer allocation, ODM configuration) + * + * This is essential for underflow debugging as it captures the exact software + * state that determines how registers are programmed, allowing analysis of + * whether underflow is caused by incorrect register programming or timing issues. + * + * Return: true if state was successfully captured, false on error + */ +bool dc_capture_register_software_state(struct dc *dc, struct dc_register_software_state *state); + #endif /* DC_INTERFACE_H_ */ 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 db669ccb1d58..79e1696def63 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -1157,6 +1157,16 @@ struct dprx_states { bool cable_id_written; }; +union dpcd_panel_replay_capability_supported { + struct { + unsigned char PANEL_REPLAY_SUPPORT :1; + unsigned char SELECTIVE_UPDATE_SUPPORT :1; + unsigned char EARLY_TRANSPORT_SUPPORT :1; + unsigned char RESERVED :5; + } bits; + unsigned char raw; +}; + enum dpcd_downstream_port_max_bpc { DOWN_STREAM_MAX_8BPC = 0, DOWN_STREAM_MAX_10BPC, @@ -1280,6 +1290,7 @@ struct dpcd_caps { struct edp_psr_info psr_info; struct replay_info pr_info; + union dpcd_panel_replay_capability_supported pr_caps_supported; uint16_t edp_oled_emission_rate; union dp_receive_port0_cap receive_port0_cap; /* Indicates the number of SST links supported by MSO (Multi-Stream Output) */ @@ -1346,6 +1357,31 @@ union dpcd_replay_configuration { unsigned char raw; }; +union panel_replay_enable_and_configuration_1 { + struct { + unsigned char PANEL_REPLAY_ENABLE :1; + unsigned char PANEL_REPLAY_CRC_ENABLE :1; + unsigned char IRQ_HPD_ASSDP_MISSING :1; + unsigned char IRQ_HPD_VSCSDP_UNCORRECTABLE_ERROR :1; + unsigned char IRQ_HPD_RFB_ERROR :1; + unsigned char IRQ_HPD_ACTIVE_FRAME_CRC_ERROR :1; + unsigned char PANEL_REPLAY_SELECTIVE_UPDATE_ENABLE :1; + unsigned char PANEL_REPLAY_EARLY_TRANSPORT_ENABLE :1; + } bits; + unsigned char raw; +}; + +union panel_replay_enable_and_configuration_2 { + struct { + unsigned char SINK_REFRESH_RATE_UNLOCK_GRANTED :1; + unsigned char RESERVED :1; + unsigned char SU_Y_GRANULARITY_EXT_VALUE_ENABLED :1; + unsigned char SU_Y_GRANULARITY_EXT_VALUE :4; + unsigned char SU_REGION_SCAN_LINE_CAPTURE_INDICATION :1; + } bits; + unsigned char raw; +}; + union dpcd_alpm_configuration { struct { unsigned char ENABLE : 1; diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 0495e6cfcca0..f46039f64203 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -941,6 +941,12 @@ enum dc_psr_version { DC_PSR_VERSION_UNSUPPORTED = 0xFFFFFFFF, }; +enum dc_replay_version { + DC_FREESYNC_REPLAY = 0, + DC_VESA_PANEL_REPLAY = 1, + DC_REPLAY_VERSION_UNSUPPORTED = 0XFF, +}; + /* Possible values of display_endpoint_id.endpoint */ enum display_endpoint_type { DISPLAY_ENDPOINT_PHY = 0, /* Physical connector. */ @@ -1093,6 +1099,7 @@ enum replay_FW_Message_type { Replay_Set_Residency_Frameupdate_Timer, Replay_Set_Pseudo_VTotal, Replay_Disabled_Adaptive_Sync_SDP, + Replay_Set_Version, Replay_Set_General_Cmd, }; @@ -1128,6 +1135,8 @@ union replay_low_refresh_rate_enable_options { }; struct replay_config { + /* Replay version */ + enum dc_replay_version replay_version; /* Replay feature is supported */ bool replay_supported; /* Replay caps support DPCD & EDID caps*/ 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 eeed840073fe..fcad61c618a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_audio.c @@ -1143,7 +1143,8 @@ void dce_aud_wall_dto_setup( REG_UPDATE(DCCG_AUDIO_DTO1_PHASE, DCCG_AUDIO_DTO1_PHASE, clock_info.audio_dto_phase); - REG_UPDATE(DCCG_AUDIO_DTO_SOURCE, + if (aud->masks->DCCG_AUDIO_DTO2_USE_512FBR_DTO) + REG_UPDATE(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO2_USE_512FBR_DTO, 1); } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c index f8996ee2856b..574618d5d4a4 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c @@ -1568,7 +1568,7 @@ void dce110_stream_encoder_construct( enc110->se_mask = se_mask; } -static const struct stream_encoder_funcs dce110_an_str_enc_funcs = {0}; +static const struct stream_encoder_funcs dce110_an_str_enc_funcs = {}; void dce110_analog_stream_encoder_construct( struct dce110_stream_encoder *enc110, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c index fd8244c94687..cf1372aaff6c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c @@ -387,6 +387,19 @@ static void dmub_replay_send_cmd(struct dmub_replay *dmub, cmd.replay_disabled_adaptive_sync_sdp.data.force_disabled = cmd_element->disabled_adaptive_sync_sdp_data.force_disabled; break; + case Replay_Set_Version: + //Header + cmd.replay_set_version.header.sub_type = + DMUB_CMD__REPLAY_SET_VERSION; + cmd.replay_set_version.header.payload_bytes = + sizeof(struct dmub_rb_cmd_replay_set_version) - + sizeof(struct dmub_cmd_header); + //Cmd Body + cmd.replay_set_version.replay_set_version_data.panel_inst = + cmd_element->version_data.panel_inst; + cmd.replay_set_version.replay_set_version_data.version = + cmd_element->version_data.version; + break; case Replay_Set_General_Cmd: //Header cmd.replay_set_general_cmd.header.sub_type = diff --git a/drivers/gpu/drm/amd/display/dc/dml2_0/display_mode_core_structs.h b/drivers/gpu/drm/amd/display/dc/dml2_0/display_mode_core_structs.h index 3b1d92e7697f..5b40dcdc4406 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2_0/display_mode_core_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml2_0/display_mode_core_structs.h @@ -1893,7 +1893,7 @@ struct display_mode_lib_scratch_st { struct CalculatePrefetchSchedule_params_st CalculatePrefetchSchedule_params; }; -/// @brief Represent the overall soc/ip enviroment. It contains data structure represent the soc/ip characteristic and also structures that hold calculation output +/// @brief Represent the overall soc/ip environment. It contains data structure represent the soc/ip characteristic and also structures that hold calculation output struct display_mode_lib_st { dml_uint_t project; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 3005115c8505..8fe399939220 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -685,7 +685,6 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) uint32_t early_control = 0; struct timing_generator *tg = pipe_ctx->stream_res.tg; - link_hwss->setup_stream_attribute(pipe_ctx); link_hwss->setup_stream_encoder(pipe_ctx); dc->hwss.update_info_frame(pipe_ctx); @@ -1103,6 +1102,9 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) if (!pipe_ctx->stream) return; + if (dc_is_rgb_signal(pipe_ctx->stream->signal)) + return; + dc = pipe_ctx->stream->ctx->dc; clk_mgr = dc->clk_mgr; link_hwss = get_link_hwss(pipe_ctx->stream->link, &pipe_ctx->link_res); @@ -1139,6 +1141,9 @@ void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx) if (!pipe_ctx || !pipe_ctx->stream) return; + if (dc_is_rgb_signal(pipe_ctx->stream->signal)) + return; + dc = pipe_ctx->stream->ctx->dc; clk_mgr = dc->clk_mgr; link_hwss = get_link_hwss(pipe_ctx->stream->link, &pipe_ctx->link_res); @@ -1193,8 +1198,7 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets( pipe_ctx->stream_res.stream_enc); - if (!dc_is_rgb_signal(pipe_ctx->stream->signal)) - dc->hwss.disable_audio_stream(pipe_ctx); + dc->hwss.disable_audio_stream(pipe_ctx); link_hwss->reset_stream_encoder(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 6bd905905984..c8ff8ae85a03 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -614,6 +614,14 @@ void dcn20_dpp_pg_control( * DOMAIN11_PGFSM_PWR_STATUS, pwr_status, * 1, 1000); */ + + /* Force disable cursor on plane powerdown on DPP 5 using dpp_force_disable_cursor */ + if (!power_on) { + struct dpp *dpp5 = hws->ctx->dc->res_pool->dpps[dpp_inst]; + if (dpp5 && dpp5->funcs->dpp_force_disable_cursor) + dpp5->funcs->dpp_force_disable_cursor(dpp5); + } + break; default: BREAK_TO_DEBUGGER(); @@ -3055,8 +3063,6 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) link_enc->transmitter - TRANSMITTER_UNIPHY_A); } - link_hwss->setup_stream_attribute(pipe_ctx); - if (dc->res_pool->dccg->funcs->set_pixel_rate_div) dc->res_pool->dccg->funcs->set_pixel_rate_div( dc->res_pool->dccg, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index f02edc9371b0..2fbc22afb89c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -974,8 +974,6 @@ void dcn401_enable_stream(struct pipe_ctx *pipe_ctx) } } - link_hwss->setup_stream_attribute(pipe_ctx); - if (dc->res_pool->dccg->funcs->set_pixel_rate_div) { dc->res_pool->dccg->funcs->set_pixel_rate_div( dc->res_pool->dccg, @@ -3675,6 +3673,8 @@ void dcn401_update_dchubp_dpp_sequence(struct dc *dc, pipe_ctx->update_flags.bits.scaler || viewport_changed == true) && pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { + hwss_add_abort_cursor_offload_update(seq_state, dc, pipe_ctx); + hwss_add_set_cursor_attribute(seq_state, dc, pipe_ctx); /* Step 15: Cursor position setup */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h index 3772b4aa11cc..8ed9eea40c56 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h @@ -696,6 +696,11 @@ struct hubp_program_mcache_id_and_split_coordinate_params { struct mcache_regs_struct *mcache_regs; }; +struct abort_cursor_offload_update_params { + struct dc *dc; + struct pipe_ctx *pipe_ctx; +}; + struct set_cursor_attribute_params { struct dc *dc; struct pipe_ctx *pipe_ctx; @@ -842,6 +847,7 @@ union block_sequence_params { struct mpc_insert_plane_params mpc_insert_plane_params; struct dpp_set_scaler_params dpp_set_scaler_params; struct hubp_mem_program_viewport_params hubp_mem_program_viewport_params; + struct abort_cursor_offload_update_params abort_cursor_offload_update_params; struct set_cursor_attribute_params set_cursor_attribute_params; struct set_cursor_position_params set_cursor_position_params; struct set_cursor_sdr_white_level_params set_cursor_sdr_white_level_params; @@ -960,6 +966,7 @@ enum block_sequence_func { MPC_INSERT_PLANE, DPP_SET_SCALER, HUBP_MEM_PROGRAM_VIEWPORT, + ABORT_CURSOR_OFFLOAD_UPDATE, SET_CURSOR_ATTRIBUTE, SET_CURSOR_POSITION, SET_CURSOR_SDR_WHITE_LEVEL, @@ -1565,6 +1572,8 @@ void hwss_dpp_set_scaler(union block_sequence_params *params); void hwss_hubp_mem_program_viewport(union block_sequence_params *params); +void hwss_abort_cursor_offload_update(union block_sequence_params *params); + void hwss_set_cursor_attribute(union block_sequence_params *params); void hwss_set_cursor_position(union block_sequence_params *params); @@ -1961,6 +1970,10 @@ void hwss_add_hubp_mem_program_viewport(struct block_sequence_state *seq_state, const struct rect *viewport, const struct rect *viewport_c); +void hwss_add_abort_cursor_offload_update(struct block_sequence_state *seq_state, + struct dc *dc, + struct pipe_ctx *pipe_ctx); + void hwss_add_set_cursor_attribute(struct block_sequence_state *seq_state, struct dc *dc, struct pipe_ctx *pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h index 5e2813e9ae2f..a61d12ec61bc 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h @@ -75,11 +75,36 @@ */ #define MAX_LINK_ENCODERS (MAX_DIG_LINK_ENCODERS + MAX_DAC_LINK_ENCODERS) -#define MAX_DIG_LINK_ENCODERS 7 #define MAX_DWB_PIPES 1 #define MAX_HPO_DP2_ENCODERS 4 #define MAX_HPO_DP2_LINK_ENCODERS 4 +/* Pipe topology snapshot structures */ +#define MAX_TOPOLOGY_SNAPSHOTS 4 + +struct pipe_topology_line { + bool is_phantom_pipe; + int plane_idx; + int slice_idx; + int stream_idx; + int dpp_inst; + int opp_inst; + int tg_inst; +}; + +struct pipe_topology_snapshot { + struct pipe_topology_line pipe_log_lines[MAX_PIPES]; + int line_count; + uint64_t timestamp_us; + int stream_count; + int phantom_stream_count; +}; + +struct pipe_topology_history { + struct pipe_topology_snapshot snapshots[MAX_TOPOLOGY_SNAPSHOTS]; + int current_snapshot_index; +}; + struct gamma_curve { uint32_t offset; uint32_t segments_num; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index d163360a2bf6..6d31f4967f1a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -1224,8 +1224,6 @@ static bool detect_link_and_local_sink(struct dc_link *link, break; } - sink->edid_caps.analog &= dc_connector_supports_analog(link->link_id.id); - // Check if edid is the same if ((prev_sink) && (edid_status == EDID_THE_SAME || edid_status == EDID_OK)) diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 4ddcdc222913..6ae134147617 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -2226,7 +2226,11 @@ static enum dc_status enable_link( { enum dc_status status = DC_ERROR_UNEXPECTED; struct dc_stream_state *stream = pipe_ctx->stream; - struct dc_link *link = stream->link; + struct dc_link *link = NULL; + + if (stream == NULL) + return DC_ERROR_UNEXPECTED; + link = stream->link; /* There's some scenarios where driver is unloaded with display * still enabled. When driver is reloaded, it may cause a display @@ -2374,8 +2378,7 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) set_avmute(pipe_ctx, true); } - if (!dc_is_rgb_signal(pipe_ctx->stream->signal)) - dc->hwss.disable_audio_stream(pipe_ctx); + dc->hwss.disable_audio_stream(pipe_ctx); update_psp_stream_config(pipe_ctx, true); dc->hwss.blank_stream(pipe_ctx); @@ -2464,6 +2467,7 @@ void link_set_dpms_on( struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; enum otg_out_mux_dest otg_out_dest = OUT_MUX_DIO; struct vpg *vpg = pipe_ctx->stream_res.stream_enc->vpg; + const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); bool apply_edp_fast_boot_optimization = pipe_ctx->stream->apply_edp_fast_boot_optimization; @@ -2508,6 +2512,8 @@ void link_set_dpms_on( pipe_ctx->stream_res.tg->funcs->set_out_mux(pipe_ctx->stream_res.tg, otg_out_dest); } + link_hwss->setup_stream_attribute(pipe_ctx); + pipe_ctx->stream->apply_edp_fast_boot_optimization = false; // Enable VPG before building infoframe @@ -2660,8 +2666,7 @@ void link_set_dpms_on( enable_stream_features(pipe_ctx); update_psp_stream_config(pipe_ctx, false); - if (!dc_is_rgb_signal(pipe_ctx->stream->signal)) - dc->hwss.enable_audio_stream(pipe_ctx); + dc->hwss.enable_audio_stream(pipe_ctx); if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) { set_avmute(pipe_ctx, false); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 7989baf3843c..a6e2b0821969 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -529,16 +529,16 @@ static bool construct_phy(struct dc_link *link, enc_init_data.transmitter = translate_encoder_to_transmitter(enc_init_data.encoder); enc_init_data.analog_engine = find_analog_engine(link); - if (!transmitter_supported(enc_init_data.transmitter) && - !analog_engine_supported(enc_init_data.analog_engine)) { - DC_LOG_WARNING("link_id %d has unsupported encoder\n", link->link_id.id); - return false; - } - link->ep_type = DISPLAY_ENDPOINT_PHY; DC_LOG_DC("BIOS object table - link_id: %d", link->link_id.id); + if (!transmitter_supported(enc_init_data.transmitter) && + !analog_engine_supported(enc_init_data.analog_engine)) { + DC_LOG_WARNING("link_id %d has unsupported encoder\n", link->link_id.id); + goto unsupported_fail; + } + if (bios->funcs->get_disp_connector_caps_info) { bios->funcs->get_disp_connector_caps_info(bios, link->link_id, &disp_connect_caps_info); link->is_internal_display = disp_connect_caps_info.INTERNAL_DISPLAY; @@ -787,6 +787,7 @@ static bool construct_phy(struct dc_link *link, link->psr_settings.psr_vtotal_control_support = false; link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; + link->replay_settings.config.replay_version = DC_REPLAY_VERSION_UNSUPPORTED; DC_LOG_DC("BIOS object table - %s finished successfully.\n", __func__); return true; @@ -805,6 +806,7 @@ static bool construct_phy(struct dc_link *link, link->hpd_gpio = NULL; } +unsupported_fail: DC_LOG_DC("BIOS object table - %s failed.\n", __func__); return false; } @@ -868,6 +870,7 @@ static bool construct_dpia(struct dc_link *link, /* TODO: Create link encoder */ link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; + link->replay_settings.config.replay_version = DC_REPLAY_VERSION_UNSUPPORTED; return true; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 750147c52c8a..ad90a0106938 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1713,7 +1713,7 @@ static bool retrieve_link_cap(struct dc_link *link) union edp_configuration_cap edp_config_cap; union dp_downstream_port_present ds_port = { 0 }; enum dc_status status = DC_ERROR_UNEXPECTED; - uint32_t read_dpcd_retry_cnt = 3; + uint32_t read_dpcd_retry_cnt = 20; int i; struct dp_sink_hw_fw_revision dp_hw_fw_revision; const uint32_t post_oui_delay = 30; // 30ms @@ -1756,12 +1756,13 @@ static bool retrieve_link_cap(struct dc_link *link) } dpcd_set_source_specific_data(link); - /* Sink may need to configure internals based on vendor, so allow some - * time before proceeding with possibly vendor specific transactions - */ - msleep(post_oui_delay); for (i = 0; i < read_dpcd_retry_cnt; i++) { + /* + * Sink may need to configure internals based on vendor, so allow some + * time before proceeding with possibly vendor specific transactions + */ + msleep(post_oui_delay); status = core_link_read_dpcd( link, DP_DPCD_REV, @@ -2091,6 +2092,11 @@ static bool retrieve_link_cap(struct dc_link *link) link->dpcd_caps.max_uncompressed_pixel_rate_cap.raw, sizeof(link->dpcd_caps.max_uncompressed_pixel_rate_cap.raw)); + core_link_read_dpcd(link, + DP_PANEL_REPLAY_CAPABILITY_SUPPORT, + &link->dpcd_caps.pr_caps_supported.raw, + sizeof(link->dpcd_caps.pr_caps_supported.raw)); + /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); if (status != DC_OK) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 9391c75a30e5..c56e69eb27ef 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -949,7 +949,7 @@ bool edp_set_replay_allow_active(struct dc_link *link, const bool *allow_active, /* Set power optimization flag */ if (power_opts && link->replay_settings.replay_power_opt_active != *power_opts) { if (replay != NULL && link->replay_settings.replay_feature_enabled && - replay->funcs->replay_set_power_opt) { + replay->funcs->replay_set_power_opt) { replay->funcs->replay_set_power_opt(replay, *power_opts, panel_inst); link->replay_settings.replay_power_opt_active = *power_opts; } @@ -984,7 +984,117 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state) return true; } -bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream) +static bool edp_setup_panel_replay(struct dc_link *link, const struct dc_stream_state *stream) +{ + /* To-do: Setup Replay */ + struct dc *dc; + struct dmub_replay *replay; + int i; + unsigned int panel_inst; + struct replay_context replay_context = { 0 }; + unsigned int lineTimeInNs = 0; + + union panel_replay_enable_and_configuration_1 pr_config_1 = { 0 }; + union panel_replay_enable_and_configuration_2 pr_config_2 = { 0 }; + + union dpcd_alpm_configuration alpm_config; + + replay_context.controllerId = CONTROLLER_ID_UNDEFINED; + + if (!link) + return false; + + //Clear Panel Replay enable & config + dm_helpers_dp_write_dpcd(link->ctx, link, + DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_1, + (uint8_t *)&(pr_config_1.raw), sizeof(uint8_t)); + + dm_helpers_dp_write_dpcd(link->ctx, link, + DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_2, + (uint8_t *)&(pr_config_2.raw), sizeof(uint8_t)); + + if (!(link->replay_settings.config.replay_supported)) + return false; + + dc = link->ctx->dc; + + //not sure should keep or not + replay = dc->res_pool->replay; + + if (!replay) + return false; + + if (!dc_get_edp_link_panel_inst(dc, link, &panel_inst)) + return false; + + replay_context.aux_inst = link->ddc->ddc_pin->hw_info.ddc_channel; + replay_context.digbe_inst = link->link_enc->transmitter; + replay_context.digfe_inst = link->link_enc->preferred_engine; + + for (i = 0; i < MAX_PIPES; i++) { + if (dc->current_state->res_ctx.pipe_ctx[i].stream + == stream) { + /* dmcu -1 for all controller id values, + * therefore +1 here + */ + replay_context.controllerId = + dc->current_state->res_ctx.pipe_ctx[i].stream_res.tg->inst + 1; + break; + } + } + + lineTimeInNs = + ((stream->timing.h_total * 1000000) / + (stream->timing.pix_clk_100hz / 10)) + 1; + + replay_context.line_time_in_ns = lineTimeInNs; + + link->replay_settings.replay_feature_enabled = + replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst); + + if (link->replay_settings.replay_feature_enabled) { + pr_config_1.bits.PANEL_REPLAY_ENABLE = 1; + pr_config_1.bits.PANEL_REPLAY_CRC_ENABLE = 1; + pr_config_1.bits.IRQ_HPD_ASSDP_MISSING = 1; + pr_config_1.bits.IRQ_HPD_VSCSDP_UNCORRECTABLE_ERROR = 1; + pr_config_1.bits.IRQ_HPD_RFB_ERROR = 1; + pr_config_1.bits.IRQ_HPD_ACTIVE_FRAME_CRC_ERROR = 1; + pr_config_1.bits.PANEL_REPLAY_SELECTIVE_UPDATE_ENABLE = 1; + pr_config_1.bits.PANEL_REPLAY_EARLY_TRANSPORT_ENABLE = 1; + + pr_config_2.bits.SINK_REFRESH_RATE_UNLOCK_GRANTED = 0; + pr_config_2.bits.SU_Y_GRANULARITY_EXT_VALUE_ENABLED = 0; + pr_config_2.bits.SU_REGION_SCAN_LINE_CAPTURE_INDICATION = 0; + + dm_helpers_dp_write_dpcd(link->ctx, link, + DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_1, + (uint8_t *)&(pr_config_1.raw), sizeof(uint8_t)); + + dm_helpers_dp_write_dpcd(link->ctx, link, + DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_2, + (uint8_t *)&(pr_config_2.raw), sizeof(uint8_t)); + + //ALPM Setup + memset(&alpm_config, 0, sizeof(alpm_config)); + alpm_config.bits.ENABLE = link->replay_settings.config.alpm_mode != DC_ALPM_UNSUPPORTED ? 1 : 0; + + if (link->replay_settings.config.alpm_mode == DC_ALPM_AUXLESS) { + alpm_config.bits.ALPM_MODE_SEL = 1; + alpm_config.bits.ACDS_PERIOD_DURATION = 1; + } + + dm_helpers_dp_write_dpcd( + link->ctx, + link, + DP_RECEIVER_ALPM_CONFIG, + &alpm_config.raw, + sizeof(alpm_config.raw)); + } + + return true; +} + +static bool edp_setup_freesync_replay(struct dc_link *link, const struct dc_stream_state *stream) { /* To-do: Setup Replay */ struct dc *dc; @@ -1080,6 +1190,18 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream return true; } +bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream) +{ + if (!link) + return false; + if (link->replay_settings.config.replay_version == DC_VESA_PANEL_REPLAY) + return edp_setup_panel_replay(link, stream); + else if (link->replay_settings.config.replay_version == DC_FREESYNC_REPLAY) + return edp_setup_freesync_replay(link, stream); + else + return false; +} + /* * This is general Interface for Replay to set an 32 bit variable to dmub * replay_FW_Message_type: Indicates which instruction or variable pass to DMUB diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h index 0fc66487d800..e1fa2e80a15a 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h @@ -227,7 +227,8 @@ void dcn401_prepare_mcache_programming(struct dc *dc, struct dc_state *context); #define LE_DCN401_REG_LIST_RI(id) \ LE_DCN3_REG_LIST_RI(id), \ SRI_ARR(DP_DPHY_INTERNAL_CTRL, DP, id), \ - SRI_ARR(DIG_BE_CLK_CNTL, DIG, id) + SRI_ARR(DIG_BE_CLK_CNTL, DIG, id),\ + SR_ARR(DIO_CLK_CNTL, id) /* DPP */ #define DPP_REG_LIST_DCN401_COMMON_RI(id) \ diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c index 6ffc74fc9dcd..ad088d70e189 100644 --- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c @@ -44,11 +44,6 @@ static void virtual_stream_encoder_dvi_set_stream_attribute( struct dc_crtc_timing *crtc_timing, bool is_dual_link) {} -static void virtual_stream_encoder_lvds_set_stream_attribute( - struct stream_encoder *enc, - struct dc_crtc_timing *crtc_timing) -{} - static void virtual_stream_encoder_set_throttled_vcp_size( struct stream_encoder *enc, struct fixed31_32 avg_time_slots_per_mtp) @@ -120,8 +115,6 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = { virtual_stream_encoder_hdmi_set_stream_attribute, .dvi_set_stream_attribute = virtual_stream_encoder_dvi_set_stream_attribute, - .lvds_set_stream_attribute = - virtual_stream_encoder_lvds_set_stream_attribute, .set_throttled_vcp_size = virtual_stream_encoder_set_throttled_vcp_size, .update_hdmi_info_packets = 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 377a449fbf8f..3f2a0ed02c59 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -2647,6 +2647,7 @@ struct dmub_cmd_fams2_global_config { union dmub_cmd_fams2_config { struct dmub_cmd_fams2_global_config global; +// coverity[cert_dcl37_c_violation:FALSE] errno.h, stddef.h, stdint.h not included in atombios.h struct dmub_fams2_stream_static_state stream; //v0 union { struct dmub_fams2_cmd_stream_static_base_state base; diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h index de8f3cfed6c8..07b937b92efc 100644 --- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h +++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h @@ -30,6 +30,22 @@ #ifndef DP_SINK_HW_REVISION_START // can remove this once the define gets into linux drm_dp_helper.h #define DP_SINK_HW_REVISION_START 0x409 #endif +/* Panel Replay*/ +#ifndef DP_PANEL_REPLAY_CAPABILITY_SUPPORT // can remove this once the define gets into linux drm_dp_helper.h +#define DP_PANEL_REPLAY_CAPABILITY_SUPPORT 0x0b0 +#endif /* DP_PANEL_REPLAY_CAPABILITY_SUPPORT */ +#ifndef DP_PANEL_REPLAY_CAPABILITY // can remove this once the define gets into linux drm_dp_helper.h +#define DP_PANEL_REPLAY_CAPABILITY 0x0b1 +#endif /* DP_PANEL_REPLAY_CAPABILITY */ +#ifndef DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_1 // can remove this once the define gets into linux drm_dp_helper.h +#define DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_1 0x1b0 +#endif /* DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_1 */ +#ifndef DP_PANEL_REPLAY_ENABLE // can remove this once the define gets into linux drm_dp_helper.h +#define DP_PANEL_REPLAY_ENABLE (1 << 0) +#endif /* DP_PANEL_REPLAY_ENABLE */ +#ifndef DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_2 // can remove this once the define gets into linux drm_dp_helper.h +#define DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_2 0x1b1 +#endif /* DP_PANEL_REPLAY_ENABLE_AND_CONFIGURATION_2 */ enum dpcd_revision { DPCD_REV_10 = 0x10, diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 88b5b716a084..fd139b219bf9 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -1037,6 +1037,9 @@ void calculate_replay_link_off_frame_count(struct dc_link *link, uint8_t max_link_off_frame_count = 0; uint16_t max_deviation_line = 0, pixel_deviation_per_line = 0; + if (!link || link->replay_settings.config.replay_version != DC_FREESYNC_REPLAY) + return; + max_deviation_line = link->dpcd_caps.pr_info.max_deviation_line; pixel_deviation_per_line = link->dpcd_caps.pr_info.pixel_deviation_per_line; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index c6f55d3522cd..79b174e5326d 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -1187,8 +1187,11 @@ int amdgpu_dpm_get_pp_table(struct amdgpu_device *adev, char **table) const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; int ret = 0; - if (!pp_funcs->get_pp_table) - return 0; + if (!table) + return -EINVAL; + + if (amdgpu_sriov_vf(adev) || !pp_funcs->get_pp_table || adev->scpm_enabled) + return -EOPNOTSUPP; mutex_lock(&adev->pm.mutex); ret = pp_funcs->get_pp_table(adev->powerplay.pp_handle, @@ -1715,7 +1718,10 @@ int amdgpu_dpm_set_pp_table(struct amdgpu_device *adev, const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; int ret = 0; - if (!pp_funcs->set_pp_table) + if (!buf || !size) + return -EINVAL; + + if (amdgpu_sriov_vf(adev) || !pp_funcs->set_pp_table || adev->scpm_enabled) return -EOPNOTSUPP; mutex_lock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 84ad3ee17907..65296a819e6a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2506,7 +2506,7 @@ static struct amdgpu_device_attr amdgpu_device_attrs[] = { AMDGPU_DEVICE_ATTR_RO(pp_num_states, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RO(pp_cur_state, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), AMDGPU_DEVICE_ATTR_RW(pp_force_state, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), - AMDGPU_DEVICE_ATTR_RW(pp_table, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF), + AMDGPU_DEVICE_ATTR_RW(pp_table, ATTR_FLAG_BASIC), AMDGPU_DEVICE_ATTR_RW(pp_dpm_sclk, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF, .attr_update = pp_dpm_clk_default_attr_update), AMDGPU_DEVICE_ATTR_RW(pp_dpm_mclk, ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF, @@ -2638,6 +2638,15 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ if (amdgpu_dpm_get_apu_thermal_limit(adev, &limit) == -EOPNOTSUPP) *states = ATTR_STATE_UNSUPPORTED; + } else if (DEVICE_ATTR_IS(pp_table)) { + int ret; + char *tmp = NULL; + + ret = amdgpu_dpm_get_pp_table(adev, &tmp); + if (ret == -EOPNOTSUPP || !tmp) + *states = ATTR_STATE_UNSUPPORTED; + else + *states = ATTR_STATE_SUPPORTED; } switch (gc_ver) { diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 76a5353d7f4a..3aaf3dd71868 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -631,9 +631,12 @@ static int pp_dpm_get_pp_table(void *handle, char **table) { struct pp_hwmgr *hwmgr = handle; - if (!hwmgr || !hwmgr->pm_en || !hwmgr->soft_pp_table) + if (!hwmgr || !hwmgr->pm_en || !table) return -EINVAL; + if (!hwmgr->soft_pp_table) + return -EOPNOTSUPP; + *table = (char *)hwmgr->soft_pp_table; return hwmgr->soft_pp_table_size; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 4a2c3ad0c38a..f51fa265230b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -634,7 +634,7 @@ static int smu_sys_get_pp_table(void *handle, return -EOPNOTSUPP; if (!smu_table->power_play_table && !smu_table->hardcode_pptable) - return -EINVAL; + return -EOPNOTSUPP; if (smu_table->hardcode_pptable) *table = smu_table->hardcode_pptable; @@ -1669,9 +1669,12 @@ static int smu_smc_hw_setup(struct smu_context *smu) if (adev->in_suspend && smu_is_dpm_running(smu)) { dev_info(adev->dev, "dpm has been enabled\n"); ret = smu_system_features_control(smu, true); - if (ret) + if (ret) { dev_err(adev->dev, "Failed system features control!\n"); - return ret; + return ret; + } + + return smu_enable_thermal_alert(smu); } break; default: 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 78e4186d06cc..b0d6487171d7 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 @@ -1022,7 +1022,12 @@ int smu_v11_0_enable_thermal_alert(struct smu_context *smu) int smu_v11_0_disable_thermal_alert(struct smu_context *smu) { - return amdgpu_irq_put(smu->adev, &smu->irq_source, 0); + int ret = 0; + + if (smu->smu_table.thermal_controller_type) + ret = amdgpu_irq_put(smu->adev, &smu->irq_source, 0); + + return ret; } static uint16_t convert_to_vddc(uint8_t vid) diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index be703d35f6b7..8bbae94804f8 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -44,10 +44,10 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, struct drm_fb_helper_surface_size *sizes) { struct drm_device *dev = fbh->dev; + struct fb_info *info = fbh->info; struct drm_mode_fb_cmd2 mode; struct armada_framebuffer *dfb; struct armada_gem_object *obj; - struct fb_info *info; int size, ret; void *ptr; @@ -91,12 +91,6 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, if (IS_ERR(dfb)) return PTR_ERR(dfb); - info = drm_fb_helper_alloc_info(fbh); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_fballoc; - } - info->fbops = &armada_fb_ops; info->fix.smem_start = obj->phys_addr; info->fix.smem_len = obj->obj.size; @@ -112,8 +106,4 @@ int armada_fbdev_driver_fbdev_probe(struct drm_fb_helper *fbh, (unsigned long long)obj->phys_addr); return 0; - - err_fballoc: - dfb->fb.funcs->destroy(&dfb->fb); - return ret; } diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 7be36a358e74..787e38c6c17d 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -298,13 +298,13 @@ static inline void __ast_write8_i(void __iomem *addr, u32 reg, u8 index, u8 val) __ast_write8(addr, reg + 1, val); } -static inline void __ast_write8_i_masked(void __iomem *addr, u32 reg, u8 index, u8 read_mask, +static inline void __ast_write8_i_masked(void __iomem *addr, u32 reg, u8 index, u8 preserve_mask, u8 val) { - u8 tmp = __ast_read8_i_masked(addr, reg, index, read_mask); + u8 tmp = __ast_read8_i_masked(addr, reg, index, preserve_mask); - tmp |= val; - __ast_write8_i(addr, reg, index, tmp); + val &= ~preserve_mask; + __ast_write8_i(addr, reg, index, tmp | val); } static inline u32 ast_read32(struct ast_device *ast, u32 reg) diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index aa7b1dcc5d70..0185f61e6e59 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -287,6 +287,7 @@ enum chip_id { ID_IT6610, ID_IT66121, + ID_IT66122, }; struct it66121_chip_info { @@ -312,7 +313,7 @@ struct it66121_ctx { u8 swl; bool auto_cts; } audio; - const struct it66121_chip_info *info; + enum chip_id id; }; static const struct regmap_range_cfg it66121_regmap_banks[] = { @@ -402,7 +403,7 @@ static int it66121_configure_afe(struct it66121_ctx *ctx, if (ret) return ret; - if (ctx->info->id == ID_IT66121) { + if (ctx->id == ID_IT66121 || ctx->id == ID_IT66122) { ret = regmap_write_bits(ctx->regmap, IT66121_AFE_IP_REG, IT66121_AFE_IP_EC1, 0); if (ret) @@ -428,7 +429,7 @@ static int it66121_configure_afe(struct it66121_ctx *ctx, if (ret) return ret; - if (ctx->info->id == ID_IT66121) { + if (ctx->id == ID_IT66121 || ctx->id == ID_IT66122) { ret = regmap_write_bits(ctx->regmap, IT66121_AFE_IP_REG, IT66121_AFE_IP_EC1, IT66121_AFE_IP_EC1); @@ -449,7 +450,7 @@ static int it66121_configure_afe(struct it66121_ctx *ctx, if (ret) return ret; - if (ctx->info->id == ID_IT6610) { + if (ctx->id == ID_IT6610) { ret = regmap_write_bits(ctx->regmap, IT66121_AFE_XP_REG, IT6610_AFE_XP_BYPASS, IT6610_AFE_XP_BYPASS); @@ -599,7 +600,7 @@ static int it66121_bridge_attach(struct drm_bridge *bridge, if (ret) return ret; - if (ctx->info->id == ID_IT66121) { + if (ctx->id == ID_IT66121 || ctx->id == ID_IT66122) { ret = regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG, IT66121_CLK_BANK_PWROFF_RCLK, 0); if (ret) @@ -748,7 +749,7 @@ static int it66121_bridge_check(struct drm_bridge *bridge, { struct it66121_ctx *ctx = container_of(bridge, struct it66121_ctx, bridge); - if (ctx->info->id == ID_IT6610) { + if (ctx->id == ID_IT6610) { /* The IT6610 only supports these settings */ bridge_state->input_bus_cfg.flags |= DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE; @@ -802,7 +803,7 @@ void it66121_bridge_mode_set(struct drm_bridge *bridge, if (regmap_write(ctx->regmap, IT66121_HDMI_MODE_REG, IT66121_HDMI_MODE_HDMI)) goto unlock; - if (ctx->info->id == ID_IT66121 && + if ((ctx->id == ID_IT66121 || ctx->id == ID_IT66122) && regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG, IT66121_CLK_BANK_PWROFF_TXCLK, IT66121_CLK_BANK_PWROFF_TXCLK)) { @@ -815,7 +816,7 @@ void it66121_bridge_mode_set(struct drm_bridge *bridge, if (it66121_configure_afe(ctx, adjusted_mode)) goto unlock; - if (ctx->info->id == ID_IT66121 && + if ((ctx->id == ID_IT66121 || ctx->id == ID_IT66122) && regmap_write_bits(ctx->regmap, IT66121_CLK_BANK_REG, IT66121_CLK_BANK_PWROFF_TXCLK, 0)) { goto unlock; @@ -1384,8 +1385,6 @@ static int it66121_audio_startup(struct device *dev, void *data) int ret; struct it66121_ctx *ctx = dev_get_drvdata(dev); - dev_dbg(dev, "%s\n", __func__); - mutex_lock(&ctx->lock); ret = it661221_audio_output_enable(ctx, true); if (ret) @@ -1401,8 +1400,6 @@ static void it66121_audio_shutdown(struct device *dev, void *data) int ret; struct it66121_ctx *ctx = dev_get_drvdata(dev); - dev_dbg(dev, "%s\n", __func__); - mutex_lock(&ctx->lock); ret = it661221_audio_output_enable(ctx, false); if (ret) @@ -1479,8 +1476,6 @@ static int it66121_audio_codec_init(struct it66121_ctx *ctx, struct device *dev) .no_capture_mute = 1, }; - dev_dbg(dev, "%s\n", __func__); - if (!of_property_present(dev->of_node, "#sound-dai-cells")) { dev_info(dev, "No \"#sound-dai-cells\", no audio\n"); return 0; @@ -1504,13 +1499,20 @@ static const char * const it66121_supplies[] = { "vcn33", "vcn18", "vrf12" }; +static const struct it66121_chip_info it66xx_chip_info[] = { + {.id = ID_IT6610, .vid = 0xca00, .pid = 0x0611 }, + {.id = ID_IT66121, .vid = 0x4954, .pid = 0x0612 }, + {.id = ID_IT66122, .vid = 0x4954, .pid = 0x0622 }, +}; + static int it66121_probe(struct i2c_client *client) { u32 revision_id, vendor_ids[2] = { 0 }, device_ids[2] = { 0 }; struct device_node *ep; - int ret; + int ret, i; struct it66121_ctx *ctx; struct device *dev = &client->dev; + const struct it66121_chip_info *chip_info; if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { dev_err(dev, "I2C check functionality failed.\n"); @@ -1528,7 +1530,6 @@ static int it66121_probe(struct i2c_client *client) ctx->dev = dev; ctx->client = client; - ctx->info = i2c_get_match_data(client); of_property_read_u32(ep, "bus-width", &ctx->bus_width); of_node_put(ep); @@ -1574,11 +1575,18 @@ static int it66121_probe(struct i2c_client *client) revision_id = FIELD_GET(IT66121_REVISION_MASK, device_ids[1]); device_ids[1] &= IT66121_DEVICE_ID1_MASK; - if ((vendor_ids[1] << 8 | vendor_ids[0]) != ctx->info->vid || - (device_ids[1] << 8 | device_ids[0]) != ctx->info->pid) { - return -ENODEV; + for (i = 0; i < ARRAY_SIZE(it66xx_chip_info); i++) { + chip_info = &it66xx_chip_info[i]; + if ((vendor_ids[1] << 8 | vendor_ids[0]) == chip_info->vid && + (device_ids[1] << 8 | device_ids[0]) == chip_info->pid) { + ctx->id = chip_info->id; + break; + } } + if (i == ARRAY_SIZE(it66xx_chip_info)) + return -ENODEV; + ctx->bridge.of_node = dev->of_node; ctx->bridge.type = DRM_MODE_CONNECTOR_HDMIA; ctx->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID; @@ -1612,28 +1620,18 @@ static void it66121_remove(struct i2c_client *client) mutex_destroy(&ctx->lock); } -static const struct it66121_chip_info it66121_chip_info = { - .id = ID_IT66121, - .vid = 0x4954, - .pid = 0x0612, -}; - -static const struct it66121_chip_info it6610_chip_info = { - .id = ID_IT6610, - .vid = 0xca00, - .pid = 0x0611, -}; - static const struct of_device_id it66121_dt_match[] = { - { .compatible = "ite,it66121", &it66121_chip_info }, - { .compatible = "ite,it6610", &it6610_chip_info }, + { .compatible = "ite,it6610" }, + { .compatible = "ite,it66121" }, + { .compatible = "ite,it66122" }, { } }; MODULE_DEVICE_TABLE(of, it66121_dt_match); static const struct i2c_device_id it66121_id[] = { - { "it66121", (kernel_ulong_t) &it66121_chip_info }, - { "it6610", (kernel_ulong_t) &it6610_chip_info }, + { .name = "it6610" }, + { .name = "it66121" }, + { .name = "it66122" }, { } }; MODULE_DEVICE_TABLE(i2c, it66121_id); diff --git a/drivers/gpu/drm/bridge/simple-bridge.c b/drivers/gpu/drm/bridge/simple-bridge.c index e4d0bc2200f8..2cd1847ba776 100644 --- a/drivers/gpu/drm/bridge/simple-bridge.c +++ b/drivers/gpu/drm/bridge/simple-bridge.c @@ -261,6 +261,16 @@ static const struct of_device_id simple_bridge_match[] = { .timings = &default_bridge_timings, .connector_type = DRM_MODE_CONNECTOR_VGA, }, + }, { + .compatible = "asl-tek,cs5263", + .data = &(const struct simple_bridge_info) { + .connector_type = DRM_MODE_CONNECTOR_HDMIA, + }, + }, { + .compatible = "parade,ps185hdm", + .data = &(const struct simple_bridge_info) { + .connector_type = DRM_MODE_CONNECTOR_HDMIA, + }, }, { .compatible = "radxa,ra620", .data = &(const struct simple_bridge_info) { diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c index 4ba7b339eff6..fe4c026280f0 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c @@ -868,8 +868,9 @@ static void dw_hdmi_qp_bridge_atomic_enable(struct drm_bridge *bridge, return; if (connector->display_info.is_hdmi) { - dev_dbg(hdmi->dev, "%s mode=HDMI rate=%llu\n", - __func__, conn_state->hdmi.tmds_char_rate); + dev_dbg(hdmi->dev, "%s mode=HDMI %s rate=%llu bpc=%u\n", __func__, + drm_hdmi_connector_get_output_format_name(conn_state->hdmi.output_format), + conn_state->hdmi.tmds_char_rate, conn_state->hdmi.output_bpc); op_mode = 0; hdmi->tmds_char_rate = conn_state->hdmi.tmds_char_rate; } else { @@ -1287,6 +1288,12 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, hdmi->bridge.vendor = "Synopsys"; hdmi->bridge.product = "DW HDMI QP TX"; + if (plat_data->supported_formats) + hdmi->bridge.supported_formats = plat_data->supported_formats; + + if (plat_data->max_bpc) + hdmi->bridge.max_bpc = plat_data->max_bpc; + hdmi->bridge.ddc = dw_hdmi_qp_i2c_adapter(hdmi); if (IS_ERR(hdmi->bridge.ddc)) return ERR_CAST(hdmi->bridge.ddc); diff --git a/drivers/gpu/drm/ci/gitlab-ci.yml b/drivers/gpu/drm/ci/gitlab-ci.yml index d502d146b177..56638814bb28 100644 --- a/drivers/gpu/drm/ci/gitlab-ci.yml +++ b/drivers/gpu/drm/ci/gitlab-ci.yml @@ -280,7 +280,7 @@ sanity: GIT_STRATEGY: none script: # ci-fairy check-commits --junit-xml=check-commits.xml - - ci-fairy check-merge-request --require-allow-collaboration --junit-xml=check-merge-request.xml + # - ci-fairy check-merge-request --require-allow-collaboration --junit-xml=check-merge-request.xml - | set -eu image_tags=( diff --git a/drivers/gpu/drm/clients/drm_client_setup.c b/drivers/gpu/drm/clients/drm_client_setup.c index 72480db1f00d..515aceac22b1 100644 --- a/drivers/gpu/drm/clients/drm_client_setup.c +++ b/drivers/gpu/drm/clients/drm_client_setup.c @@ -13,8 +13,8 @@ static char drm_client_default[16] = CONFIG_DRM_CLIENT_DEFAULT; module_param_string(active, drm_client_default, sizeof(drm_client_default), 0444); MODULE_PARM_DESC(active, - "Choose which drm client to start, default is" - CONFIG_DRM_CLIENT_DEFAULT "]"); + "Choose which drm client to start, default is " + CONFIG_DRM_CLIENT_DEFAULT); /** * drm_client_setup() - Setup in-kernel DRM clients diff --git a/drivers/gpu/drm/clients/drm_fbdev_client.c b/drivers/gpu/drm/clients/drm_fbdev_client.c index 47e5f27eee58..28951e392482 100644 --- a/drivers/gpu/drm/clients/drm_fbdev_client.c +++ b/drivers/gpu/drm/clients/drm_fbdev_client.c @@ -38,9 +38,11 @@ static void drm_fbdev_client_unregister(struct drm_client_dev *client) } } -static int drm_fbdev_client_restore(struct drm_client_dev *client) +static int drm_fbdev_client_restore(struct drm_client_dev *client, bool force) { - drm_fb_helper_lastclose(client->dev); + struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client); + + drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force); return 0; } diff --git a/drivers/gpu/drm/clients/drm_log.c b/drivers/gpu/drm/clients/drm_log.c index 19e55aa0ed74..4d3005273b27 100644 --- a/drivers/gpu/drm/clients/drm_log.c +++ b/drivers/gpu/drm/clients/drm_log.c @@ -315,6 +315,18 @@ static void drm_log_client_unregister(struct drm_client_dev *client) drm_client_release(client); } +static int drm_log_client_restore(struct drm_client_dev *client, bool force) +{ + int ret; + + if (force) + ret = drm_client_modeset_commit_locked(client); + else + ret = drm_client_modeset_commit(client); + + return ret; +} + static int drm_log_client_hotplug(struct drm_client_dev *client) { struct drm_log *dlog = client_to_drm_log(client); @@ -348,6 +360,7 @@ static const struct drm_client_funcs drm_log_client_funcs = { .owner = THIS_MODULE, .free = drm_log_client_free, .unregister = drm_log_client_unregister, + .restore = drm_log_client_restore, .hotplug = drm_log_client_hotplug, .suspend = drm_log_client_suspend, .resume = drm_log_client_resume, diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index e05820b18832..67e095e398a3 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -42,6 +42,7 @@ #include #include #include +#include #include "drm_crtc_internal.h" #include "drm_internal.h" @@ -107,6 +108,7 @@ void drm_atomic_state_default_release(struct drm_atomic_state *state) kfree(state->connectors); kfree(state->crtcs); kfree(state->planes); + kfree(state->colorops); kfree(state->private_objs); } EXPORT_SYMBOL(drm_atomic_state_default_release); @@ -138,6 +140,10 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state) sizeof(*state->planes), GFP_KERNEL); if (!state->planes) goto fail; + state->colorops = kcalloc(dev->mode_config.num_colorop, + sizeof(*state->colorops), GFP_KERNEL); + if (!state->colorops) + goto fail; /* * Because drm_atomic_state can be committed asynchronously we need our @@ -251,6 +257,20 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) state->planes[i].new_state = NULL; } + for (i = 0; i < config->num_colorop; i++) { + struct drm_colorop *colorop = state->colorops[i].ptr; + + if (!colorop) + continue; + + drm_colorop_atomic_destroy_state(colorop, + state->colorops[i].state); + state->colorops[i].ptr = NULL; + state->colorops[i].state = NULL; + state->colorops[i].old_state = NULL; + state->colorops[i].new_state = NULL; + } + for (i = 0; i < state->num_private_objs; i++) { struct drm_private_obj *obj = state->private_objs[i].ptr; @@ -572,6 +592,55 @@ drm_atomic_get_plane_state(struct drm_atomic_state *state, } EXPORT_SYMBOL(drm_atomic_get_plane_state); +/** + * drm_atomic_get_colorop_state - get colorop state + * @state: global atomic state object + * @colorop: colorop to get state object for + * + * This function returns the colorop state for the given colorop, allocating it + * if needed. It will also grab the relevant plane lock to make sure that the + * state is consistent. + * + * Returns: + * + * Either the allocated state or the error code encoded into the pointer. When + * the error is EDEADLK then the w/w mutex code has detected a deadlock and the + * entire atomic sequence must be restarted. All other errors are fatal. + */ +struct drm_colorop_state * +drm_atomic_get_colorop_state(struct drm_atomic_state *state, + struct drm_colorop *colorop) +{ + int ret, index = drm_colorop_index(colorop); + struct drm_colorop_state *colorop_state; + + WARN_ON(!state->acquire_ctx); + + colorop_state = drm_atomic_get_new_colorop_state(state, colorop); + if (colorop_state) + return colorop_state; + + ret = drm_modeset_lock(&colorop->plane->mutex, state->acquire_ctx); + if (ret) + return ERR_PTR(ret); + + colorop_state = drm_atomic_helper_colorop_duplicate_state(colorop); + if (!colorop_state) + return ERR_PTR(-ENOMEM); + + state->colorops[index].state = colorop_state; + state->colorops[index].ptr = colorop; + state->colorops[index].old_state = colorop->state; + state->colorops[index].new_state = colorop_state; + colorop_state->state = state; + + drm_dbg_atomic(colorop->dev, "Added [COLOROP:%d:%d] %p state to %p\n", + colorop->base.id, colorop->type, colorop_state, state); + + return colorop_state; +} +EXPORT_SYMBOL(drm_atomic_get_colorop_state); + static bool plane_switching_crtc(const struct drm_plane_state *old_plane_state, const struct drm_plane_state *new_plane_state) @@ -711,6 +780,46 @@ static int drm_atomic_plane_check(const struct drm_plane_state *old_plane_state, return 0; } +static void drm_atomic_colorop_print_state(struct drm_printer *p, + const struct drm_colorop_state *state) +{ + struct drm_colorop *colorop = state->colorop; + + drm_printf(p, "colorop[%u]:\n", colorop->base.id); + drm_printf(p, "\ttype=%s\n", drm_get_colorop_type_name(colorop->type)); + if (colorop->bypass_property) + drm_printf(p, "\tbypass=%u\n", state->bypass); + + switch (colorop->type) { + case DRM_COLOROP_1D_CURVE: + drm_printf(p, "\tcurve_1d_type=%s\n", + drm_get_colorop_curve_1d_type_name(state->curve_1d_type)); + break; + case DRM_COLOROP_1D_LUT: + drm_printf(p, "\tsize=%d\n", colorop->size); + drm_printf(p, "\tinterpolation=%s\n", + drm_get_colorop_lut1d_interpolation_name(colorop->lut1d_interpolation)); + drm_printf(p, "\tdata blob id=%d\n", state->data ? state->data->base.id : 0); + break; + case DRM_COLOROP_CTM_3X4: + drm_printf(p, "\tdata blob id=%d\n", state->data ? state->data->base.id : 0); + break; + case DRM_COLOROP_MULTIPLIER: + drm_printf(p, "\tmultiplier=%llu\n", state->multiplier); + break; + case DRM_COLOROP_3D_LUT: + drm_printf(p, "\tsize=%d\n", colorop->size); + drm_printf(p, "\tinterpolation=%s\n", + drm_get_colorop_lut3d_interpolation_name(colorop->lut3d_interpolation)); + drm_printf(p, "\tdata blob id=%d\n", state->data ? state->data->base.id : 0); + break; + default: + break; + } + + drm_printf(p, "\tnext=%d\n", colorop->next ? colorop->next->base.id : 0); +} + static void drm_atomic_plane_print_state(struct drm_printer *p, const struct drm_plane_state *state) { @@ -732,7 +841,8 @@ static void drm_atomic_plane_print_state(struct drm_printer *p, drm_printf(p, "\tcolor-range=%s\n", drm_get_color_range_name(state->color_range)); drm_printf(p, "\tcolor_mgmt_changed=%d\n", state->color_mgmt_changed); - + drm_printf(p, "\tcolor-pipeline=%d\n", + state->color_pipeline ? state->color_pipeline->base.id : 0); if (plane->funcs->atomic_print_state) plane->funcs->atomic_print_state(p, state); } @@ -1445,6 +1555,52 @@ drm_atomic_add_affected_planes(struct drm_atomic_state *state, } EXPORT_SYMBOL(drm_atomic_add_affected_planes); +/** + * drm_atomic_add_affected_colorops - add colorops for plane + * @state: atomic state + * @plane: DRM plane + * + * This function walks the current configuration and adds all colorops + * currently used by @plane to the atomic configuration @state. This is useful + * when an atomic commit also needs to check all currently enabled colorop on + * @plane, e.g. when changing the mode. It's also useful when re-enabling a plane + * to avoid special code to force-enable all colorops. + * + * Since acquiring a colorop state will always also acquire the w/w mutex of the + * current plane for that colorop (if there is any) adding all the colorop states for + * a plane will not reduce parallelism of atomic updates. + * + * Returns: + * 0 on success or can fail with -EDEADLK or -ENOMEM. When the error is EDEADLK + * then the w/w mutex code has detected a deadlock and the entire atomic + * sequence must be restarted. All other errors are fatal. + */ +int +drm_atomic_add_affected_colorops(struct drm_atomic_state *state, + struct drm_plane *plane) +{ + struct drm_colorop *colorop; + struct drm_colorop_state *colorop_state; + + WARN_ON(!drm_atomic_get_new_plane_state(state, plane)); + + drm_dbg_atomic(plane->dev, + "Adding all current colorops for [PLANE:%d:%s] to %p\n", + plane->base.id, plane->name, state); + + drm_for_each_colorop(colorop, plane->dev) { + if (colorop->plane != plane) + continue; + + colorop_state = drm_atomic_get_colorop_state(state, colorop); + if (IS_ERR(colorop_state)) + return PTR_ERR(colorop_state); + } + + return 0; +} +EXPORT_SYMBOL(drm_atomic_add_affected_colorops); + /** * drm_atomic_check_only - check whether a given config would work * @state: atomic configuration to check @@ -1843,6 +1999,7 @@ static void __drm_state_dump(struct drm_device *dev, struct drm_printer *p, bool take_locks) { struct drm_mode_config *config = &dev->mode_config; + struct drm_colorop *colorop; struct drm_plane *plane; struct drm_crtc *crtc; struct drm_connector *connector; @@ -1852,6 +2009,14 @@ static void __drm_state_dump(struct drm_device *dev, struct drm_printer *p, if (!drm_drv_uses_atomic_modeset(dev)) return; + list_for_each_entry(colorop, &config->colorop_list, head) { + if (take_locks) + drm_modeset_lock(&colorop->plane->mutex, NULL); + drm_atomic_colorop_print_state(p, colorop->state); + if (take_locks) + drm_modeset_unlock(&colorop->plane->mutex); + } + list_for_each_entry(plane, &config->plane_list, head) { if (take_locks) drm_modeset_lock(&plane->mutex, NULL); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index e641fcf8c568..10adac9397cf 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -3184,6 +3184,8 @@ int drm_atomic_helper_swap_state(struct drm_atomic_state *state, struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_plane *plane; struct drm_plane_state *old_plane_state, *new_plane_state; + struct drm_colorop *colorop; + struct drm_colorop_state *old_colorop_state, *new_colorop_state; struct drm_crtc_commit *commit; struct drm_private_obj *obj; struct drm_private_state *old_obj_state, *new_obj_state; @@ -3261,6 +3263,16 @@ int drm_atomic_helper_swap_state(struct drm_atomic_state *state, } } + for_each_oldnew_colorop_in_state(state, colorop, old_colorop_state, new_colorop_state, i) { + WARN_ON(colorop->state != old_colorop_state); + + old_colorop_state->state = state; + new_colorop_state->state = NULL; + + state->colorops[i].state = old_colorop_state; + colorop->state = new_colorop_state; + } + drm_panic_lock(state->dev, flags); for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { WARN_ON(plane->state != old_plane_state); diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c index 7142e163e618..cee6d8fc44ad 100644 --- a/drivers/gpu/drm/drm_atomic_state_helper.c +++ b/drivers/gpu/drm/drm_atomic_state_helper.c @@ -268,6 +268,11 @@ void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *plane_state, plane_state->color_range = val; } + if (plane->color_pipeline_property) { + /* default is always NULL, i.e., bypass */ + plane_state->color_pipeline = NULL; + } + if (plane->zpos_property) { if (!drm_object_property_get_default_value(&plane->base, plane->zpos_property, diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index b2cb5ae5a139..7320db4b8489 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include @@ -257,6 +258,34 @@ drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state, } EXPORT_SYMBOL(drm_atomic_set_fb_for_plane); +/** + * drm_atomic_set_colorop_for_plane - set colorop for plane + * @plane_state: atomic state object for the plane + * @colorop: colorop to use for the plane + * + * Helper function to select the color pipeline on a plane by setting + * it to the first drm_colorop element of the pipeline. + */ +void +drm_atomic_set_colorop_for_plane(struct drm_plane_state *plane_state, + struct drm_colorop *colorop) +{ + struct drm_plane *plane = plane_state->plane; + + if (colorop) + drm_dbg_atomic(plane->dev, + "Set [COLOROP:%d] for [PLANE:%d:%s] state %p\n", + colorop->base.id, plane->base.id, plane->name, + plane_state); + else + drm_dbg_atomic(plane->dev, + "Set [NOCOLOROP] for [PLANE:%d:%s] state %p\n", + plane->base.id, plane->name, plane_state); + + plane_state->color_pipeline = colorop; +} +EXPORT_SYMBOL(drm_atomic_set_colorop_for_plane); + /** * drm_atomic_set_crtc_for_connector - set CRTC for connector * @conn_state: atomic state object for the connector @@ -544,6 +573,16 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane, state->color_encoding = val; } else if (property == plane->color_range_property) { state->color_range = val; + } else if (property == plane->color_pipeline_property) { + /* find DRM colorop object */ + struct drm_colorop *colorop = NULL; + + colorop = drm_colorop_find(dev, file_priv, val); + + if (val && !colorop) + return -EACCES; + + drm_atomic_set_colorop_for_plane(state, colorop); } else if (property == config->prop_fb_damage_clips) { ret = drm_property_replace_blob_from_id(dev, &state->fb_damage_clips, @@ -626,6 +665,8 @@ drm_atomic_plane_get_property(struct drm_plane *plane, *val = state->color_encoding; } else if (property == plane->color_range_property) { *val = state->color_range; + } else if (property == plane->color_pipeline_property) { + *val = (state->color_pipeline) ? state->color_pipeline->base.id : 0; } else if (property == config->prop_fb_damage_clips) { *val = (state->fb_damage_clips) ? state->fb_damage_clips->base.id : 0; @@ -648,6 +689,96 @@ drm_atomic_plane_get_property(struct drm_plane *plane, return 0; } +static int drm_atomic_color_set_data_property(struct drm_colorop *colorop, + struct drm_colorop_state *state, + struct drm_property *property, + uint64_t val) +{ + ssize_t elem_size = -1; + ssize_t size = -1; + bool replaced = false; + + switch (colorop->type) { + case DRM_COLOROP_1D_LUT: + size = colorop->size * sizeof(struct drm_color_lut32); + break; + case DRM_COLOROP_CTM_3X4: + size = sizeof(struct drm_color_ctm_3x4); + break; + case DRM_COLOROP_3D_LUT: + size = colorop->size * colorop->size * colorop->size * + sizeof(struct drm_color_lut32); + break; + default: + /* should never get here */ + return -EINVAL; + } + + return drm_property_replace_blob_from_id(colorop->dev, + &state->data, + val, + size, + elem_size, + &replaced); +} + +static int drm_atomic_colorop_set_property(struct drm_colorop *colorop, + struct drm_colorop_state *state, + struct drm_file *file_priv, + struct drm_property *property, + uint64_t val) +{ + if (property == colorop->bypass_property) { + state->bypass = val; + } else if (property == colorop->lut1d_interpolation_property) { + colorop->lut1d_interpolation = val; + } else if (property == colorop->curve_1d_type_property) { + state->curve_1d_type = val; + } else if (property == colorop->multiplier_property) { + state->multiplier = val; + } else if (property == colorop->lut3d_interpolation_property) { + colorop->lut3d_interpolation = val; + } else if (property == colorop->data_property) { + return drm_atomic_color_set_data_property(colorop, state, + property, val); + } else { + drm_dbg_atomic(colorop->dev, + "[COLOROP:%d:%d] unknown property [PROP:%d:%s]\n", + colorop->base.id, colorop->type, + property->base.id, property->name); + return -EINVAL; + } + + return 0; +} + +static int +drm_atomic_colorop_get_property(struct drm_colorop *colorop, + const struct drm_colorop_state *state, + struct drm_property *property, uint64_t *val) +{ + if (property == colorop->type_property) + *val = colorop->type; + else if (property == colorop->bypass_property) + *val = state->bypass; + else if (property == colorop->lut1d_interpolation_property) + *val = colorop->lut1d_interpolation; + else if (property == colorop->curve_1d_type_property) + *val = state->curve_1d_type; + else if (property == colorop->multiplier_property) + *val = state->multiplier; + else if (property == colorop->size_property) + *val = colorop->size; + else if (property == colorop->lut3d_interpolation_property) + *val = colorop->lut3d_interpolation; + else if (property == colorop->data_property) + *val = (state->data) ? state->data->base.id : 0; + else + return -EINVAL; + + return 0; +} + static int drm_atomic_set_writeback_fb_for_connector( struct drm_connector_state *conn_state, struct drm_framebuffer *fb) @@ -914,6 +1045,15 @@ int drm_atomic_get_property(struct drm_mode_object *obj, plane->state, property, val); break; } + case DRM_MODE_OBJECT_COLOROP: { + struct drm_colorop *colorop = obj_to_colorop(obj); + + if (colorop->plane) + WARN_ON(!drm_modeset_is_locked(&colorop->plane->mutex)); + + ret = drm_atomic_colorop_get_property(colorop, colorop->state, property, val); + break; + } default: drm_dbg_atomic(dev, "[OBJECT:%d] has no properties\n", obj->id); ret = -EINVAL; @@ -1111,6 +1251,21 @@ int drm_atomic_set_property(struct drm_atomic_state *state, ret = drm_atomic_plane_set_property(plane, plane_state, file_priv, prop, prop_value); + + break; + } + case DRM_MODE_OBJECT_COLOROP: { + struct drm_colorop *colorop = obj_to_colorop(obj); + struct drm_colorop_state *colorop_state; + + colorop_state = drm_atomic_get_colorop_state(state, colorop); + if (IS_ERR(colorop_state)) { + ret = PTR_ERR(colorop_state); + break; + } + + ret = drm_atomic_colorop_set_property(colorop, colorop_state, + file_priv, prop, prop_value); break; } default: @@ -1450,6 +1605,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); state->acquire_ctx = &ctx; state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET); + state->plane_color_pipeline = file_priv->plane_color_pipeline; retry: copied_objs = 0; diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index 504ec5bdfa2c..a82d741e6630 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include diff --git a/drivers/gpu/drm/drm_client_event.c b/drivers/gpu/drm/drm_client_event.c index d25dc5250983..7b3e362f7926 100644 --- a/drivers/gpu/drm/drm_client_event.c +++ b/drivers/gpu/drm/drm_client_event.c @@ -102,7 +102,7 @@ void drm_client_dev_hotplug(struct drm_device *dev) } EXPORT_SYMBOL(drm_client_dev_hotplug); -void drm_client_dev_restore(struct drm_device *dev) +void drm_client_dev_restore(struct drm_device *dev, bool force) { struct drm_client_dev *client; int ret; @@ -115,7 +115,7 @@ void drm_client_dev_restore(struct drm_device *dev) if (!client->funcs || !client->funcs->restore) continue; - ret = client->funcs->restore(client); + ret = client->funcs->restore(client, force); drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret); if (!ret) /* The first one to return zero gets the privilege to restore */ break; diff --git a/drivers/gpu/drm/drm_client_sysrq.c b/drivers/gpu/drm/drm_client_sysrq.c new file mode 100644 index 000000000000..eea660096f1b --- /dev/null +++ b/drivers/gpu/drm/drm_client_sysrq.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +#include + +#include +#include +#include + +#include "drm_internal.h" + +#ifdef CONFIG_MAGIC_SYSRQ +static LIST_HEAD(drm_client_sysrq_dev_list); +static DEFINE_MUTEX(drm_client_sysrq_dev_lock); + +/* emergency restore, don't bother with error reporting */ +static void drm_client_sysrq_restore_work_fn(struct work_struct *ignored) +{ + struct drm_device *dev; + + guard(mutex)(&drm_client_sysrq_dev_lock); + + list_for_each_entry(dev, &drm_client_sysrq_dev_list, client_sysrq_list) { + if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) + continue; + + drm_client_dev_restore(dev, true); + } +} + +static DECLARE_WORK(drm_client_sysrq_restore_work, drm_client_sysrq_restore_work_fn); + +static void drm_client_sysrq_restore_handler(u8 ignored) +{ + schedule_work(&drm_client_sysrq_restore_work); +} + +static const struct sysrq_key_op drm_client_sysrq_restore_op = { + .handler = drm_client_sysrq_restore_handler, + .help_msg = "force-fb(v)", + .action_msg = "Restore framebuffer console", +}; + +void drm_client_sysrq_register(struct drm_device *dev) +{ + guard(mutex)(&drm_client_sysrq_dev_lock); + + if (list_empty(&drm_client_sysrq_dev_list)) + register_sysrq_key('v', &drm_client_sysrq_restore_op); + + list_add(&dev->client_sysrq_list, &drm_client_sysrq_dev_list); +} + +void drm_client_sysrq_unregister(struct drm_device *dev) +{ + guard(mutex)(&drm_client_sysrq_dev_lock); + + /* remove device from global restore list */ + if (!drm_WARN_ON(dev, list_empty(&dev->client_sysrq_list))) + list_del(&dev->client_sysrq_list); + + /* no devices left; unregister key */ + if (list_empty(&drm_client_sysrq_dev_list)) + unregister_sysrq_key('v', &drm_client_sysrq_restore_op); +} +#endif diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index 131c1c9ae92f..c598b99673fc 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -874,3 +874,46 @@ void drm_crtc_fill_palette_8(struct drm_crtc *crtc, drm_crtc_set_lut_func set_pa fill_palette_8(crtc, i, set_palette); } EXPORT_SYMBOL(drm_crtc_fill_palette_8); + +/** + * drm_color_lut32_check - check validity of extended lookup table + * @lut: property blob containing extended LUT to check + * @tests: bitmask of tests to run + * + * Helper to check whether a userspace-provided extended lookup table is valid and + * satisfies hardware requirements. Drivers pass a bitmask indicating which of + * the tests in &drm_color_lut_tests should be performed. + * + * Returns 0 on success, -EINVAL on failure. + */ +int drm_color_lut32_check(const struct drm_property_blob *lut, u32 tests) +{ + const struct drm_color_lut32 *entry; + int i; + + if (!lut || !tests) + return 0; + + entry = lut->data; + for (i = 0; i < drm_color_lut32_size(lut); i++) { + if (tests & DRM_COLOR_LUT_EQUAL_CHANNELS) { + if (entry[i].red != entry[i].blue || + entry[i].red != entry[i].green) { + DRM_DEBUG_KMS("All LUT entries must have equal r/g/b\n"); + return -EINVAL; + } + } + + if (i > 0 && tests & DRM_COLOR_LUT_NON_DECREASING) { + if (entry[i].red < entry[i - 1].red || + entry[i].green < entry[i - 1].green || + entry[i].blue < entry[i - 1].blue) { + DRM_DEBUG_KMS("LUT entries must never decrease.\n"); + return -EINVAL; + } + } + } + + return 0; +} +EXPORT_SYMBOL(drm_color_lut32_check); diff --git a/drivers/gpu/drm/drm_colorop.c b/drivers/gpu/drm/drm_colorop.c new file mode 100644 index 000000000000..44eb823585d2 --- /dev/null +++ b/drivers/gpu/drm/drm_colorop.c @@ -0,0 +1,599 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved. + * + * 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 +#include +#include +#include + +#include "drm_crtc_internal.h" + +/** + * DOC: overview + * + * When userspace signals the &DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE it + * should use the COLOR_PIPELINE plane property and associated colorops + * for any color operation on the &drm_plane. Setting of all old color + * properties, such as COLOR_ENCODING and COLOR_RANGE, will be rejected + * and the values of the properties will be ignored. + * + * Colorops are only advertised and valid for atomic drivers and atomic + * userspace that signals the &DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE + * client cap. + * + * A colorop represents a single color operation. Colorops are chained + * via the NEXT property and make up color pipelines. Color pipelines + * are advertised and selected via the COLOR_PIPELINE &drm_plane + * property. + * + * A colorop will be of a certain type, advertised by the read-only TYPE + * property. Each type of colorop will advertise a different set of + * properties and is programmed in a different manner. Types can be + * enumerated 1D curves, 1D LUTs, 3D LUTs, matrices, etc. See the + * &drm_colorop_type documentation for information on each type. + * + * If a colorop advertises the BYPASS property it can be bypassed. + * + * Information about colorop and color pipeline design decisions can be + * found at rfc/color_pipeline.rst, but note that this document will + * grow stale over time. + */ + +static const struct drm_prop_enum_list drm_colorop_type_enum_list[] = { + { DRM_COLOROP_1D_CURVE, "1D Curve" }, + { DRM_COLOROP_1D_LUT, "1D LUT" }, + { DRM_COLOROP_CTM_3X4, "3x4 Matrix"}, + { DRM_COLOROP_MULTIPLIER, "Multiplier"}, + { DRM_COLOROP_3D_LUT, "3D LUT"}, +}; + +static const char * const colorop_curve_1d_type_names[] = { + [DRM_COLOROP_1D_CURVE_SRGB_EOTF] = "sRGB EOTF", + [DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF] = "sRGB Inverse EOTF", + [DRM_COLOROP_1D_CURVE_PQ_125_EOTF] = "PQ 125 EOTF", + [DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF] = "PQ 125 Inverse EOTF", + [DRM_COLOROP_1D_CURVE_BT2020_INV_OETF] = "BT.2020 Inverse OETF", + [DRM_COLOROP_1D_CURVE_BT2020_OETF] = "BT.2020 OETF", + [DRM_COLOROP_1D_CURVE_GAMMA22] = "Gamma 2.2", + [DRM_COLOROP_1D_CURVE_GAMMA22_INV] = "Gamma 2.2 Inverse", +}; + +static const struct drm_prop_enum_list drm_colorop_lut1d_interpolation_list[] = { + { DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR, "Linear" }, +}; + + +static const struct drm_prop_enum_list drm_colorop_lut3d_interpolation_list[] = { + { DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL, "Tetrahedral" }, +}; + +/* Init Helpers */ + +static int drm_plane_colorop_init(struct drm_device *dev, struct drm_colorop *colorop, + struct drm_plane *plane, enum drm_colorop_type type, + uint32_t flags) +{ + struct drm_mode_config *config = &dev->mode_config; + struct drm_property *prop; + int ret = 0; + + ret = drm_mode_object_add(dev, &colorop->base, DRM_MODE_OBJECT_COLOROP); + if (ret) + return ret; + + colorop->base.properties = &colorop->properties; + colorop->dev = dev; + colorop->type = type; + colorop->plane = plane; + colorop->next = NULL; + + list_add_tail(&colorop->head, &config->colorop_list); + colorop->index = config->num_colorop++; + + /* add properties */ + + /* type */ + prop = drm_property_create_enum(dev, + DRM_MODE_PROP_IMMUTABLE, + "TYPE", drm_colorop_type_enum_list, + ARRAY_SIZE(drm_colorop_type_enum_list)); + + if (!prop) + return -ENOMEM; + + colorop->type_property = prop; + + drm_object_attach_property(&colorop->base, + colorop->type_property, + colorop->type); + + if (flags & DRM_COLOROP_FLAG_ALLOW_BYPASS) { + /* bypass */ + prop = drm_property_create_bool(dev, DRM_MODE_PROP_ATOMIC, + "BYPASS"); + if (!prop) + return -ENOMEM; + + colorop->bypass_property = prop; + drm_object_attach_property(&colorop->base, + colorop->bypass_property, + 1); + } + + /* next */ + prop = drm_property_create_object(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_ATOMIC, + "NEXT", DRM_MODE_OBJECT_COLOROP); + if (!prop) + return -ENOMEM; + colorop->next_property = prop; + drm_object_attach_property(&colorop->base, + colorop->next_property, + 0); + + return ret; +} + +/** + * drm_colorop_cleanup - Cleanup a drm_colorop object in color_pipeline + * + * @colorop: The drm_colorop object to be cleaned + */ +void drm_colorop_cleanup(struct drm_colorop *colorop) +{ + struct drm_device *dev = colorop->dev; + struct drm_mode_config *config = &dev->mode_config; + + list_del(&colorop->head); + config->num_colorop--; + + if (colorop->state && colorop->state->data) { + drm_property_blob_put(colorop->state->data); + colorop->state->data = NULL; + } + + kfree(colorop->state); +} +EXPORT_SYMBOL(drm_colorop_cleanup); + +/** + * drm_colorop_pipeline_destroy - Helper for color pipeline destruction + * + * @dev: - The drm_device containing the drm_planes with the color_pipelines + * + * Provides a default color pipeline destroy handler for drm_device. + */ +void drm_colorop_pipeline_destroy(struct drm_device *dev) +{ + struct drm_mode_config *config = &dev->mode_config; + struct drm_colorop *colorop, *next; + + list_for_each_entry_safe(colorop, next, &config->colorop_list, head) { + drm_colorop_cleanup(colorop); + kfree(colorop); + } +} +EXPORT_SYMBOL(drm_colorop_pipeline_destroy); + +/** + * drm_plane_colorop_curve_1d_init - Initialize a DRM_COLOROP_1D_CURVE + * + * @dev: DRM device + * @colorop: The drm_colorop object to initialize + * @plane: The associated drm_plane + * @supported_tfs: A bitfield of supported drm_plane_colorop_curve_1d_init enum values, + * created using BIT(curve_type) and combined with the OR '|' + * operator. + * @flags: bitmask of misc, see DRM_COLOROP_FLAG_* defines. + * @return zero on success, -E value on failure + */ +int drm_plane_colorop_curve_1d_init(struct drm_device *dev, struct drm_colorop *colorop, + struct drm_plane *plane, u64 supported_tfs, uint32_t flags) +{ + struct drm_prop_enum_list enum_list[DRM_COLOROP_1D_CURVE_COUNT]; + int i, len; + + struct drm_property *prop; + int ret; + + if (!supported_tfs) { + drm_err(dev, + "No supported TFs for new 1D curve colorop on [PLANE:%d:%s]\n", + plane->base.id, plane->name); + return -EINVAL; + } + + if ((supported_tfs & -BIT(DRM_COLOROP_1D_CURVE_COUNT)) != 0) { + drm_err(dev, "Unknown TF provided on [PLANE:%d:%s]\n", + plane->base.id, plane->name); + return -EINVAL; + } + + ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_1D_CURVE, flags); + if (ret) + return ret; + + len = 0; + for (i = 0; i < DRM_COLOROP_1D_CURVE_COUNT; i++) { + if ((supported_tfs & BIT(i)) == 0) + continue; + + enum_list[len].type = i; + enum_list[len].name = colorop_curve_1d_type_names[i]; + len++; + } + + if (WARN_ON(len <= 0)) + return -EINVAL; + + /* initialize 1D curve only attribute */ + prop = drm_property_create_enum(dev, DRM_MODE_PROP_ATOMIC, "CURVE_1D_TYPE", + enum_list, len); + + if (!prop) + return -ENOMEM; + + colorop->curve_1d_type_property = prop; + drm_object_attach_property(&colorop->base, colorop->curve_1d_type_property, + enum_list[0].type); + drm_colorop_reset(colorop); + + return 0; +} +EXPORT_SYMBOL(drm_plane_colorop_curve_1d_init); + +static int drm_colorop_create_data_prop(struct drm_device *dev, struct drm_colorop *colorop) +{ + struct drm_property *prop; + + /* data */ + prop = drm_property_create(dev, DRM_MODE_PROP_ATOMIC | DRM_MODE_PROP_BLOB, + "DATA", 0); + if (!prop) + return -ENOMEM; + + colorop->data_property = prop; + drm_object_attach_property(&colorop->base, + colorop->data_property, + 0); + + return 0; +} + +/** + * drm_plane_colorop_curve_1d_lut_init - Initialize a DRM_COLOROP_1D_LUT + * + * @dev: DRM device + * @colorop: The drm_colorop object to initialize + * @plane: The associated drm_plane + * @lut_size: LUT size supported by driver + * @interpolation: 1D LUT interpolation type + * @flags: bitmask of misc, see DRM_COLOROP_FLAG_* defines. + * @return zero on success, -E value on failure + */ +int drm_plane_colorop_curve_1d_lut_init(struct drm_device *dev, struct drm_colorop *colorop, + struct drm_plane *plane, uint32_t lut_size, + enum drm_colorop_lut1d_interpolation_type interpolation, + uint32_t flags) +{ + struct drm_property *prop; + int ret; + + ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_1D_LUT, flags); + if (ret) + return ret; + + /* initialize 1D LUT only attribute */ + /* LUT size */ + prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_ATOMIC, + "SIZE", 0, UINT_MAX); + if (!prop) + return -ENOMEM; + + colorop->size_property = prop; + drm_object_attach_property(&colorop->base, colorop->size_property, lut_size); + colorop->size = lut_size; + + /* interpolation */ + prop = drm_property_create_enum(dev, 0, "LUT1D_INTERPOLATION", + drm_colorop_lut1d_interpolation_list, + ARRAY_SIZE(drm_colorop_lut1d_interpolation_list)); + if (!prop) + return -ENOMEM; + + colorop->lut1d_interpolation_property = prop; + drm_object_attach_property(&colorop->base, prop, interpolation); + colorop->lut1d_interpolation = interpolation; + + /* data */ + ret = drm_colorop_create_data_prop(dev, colorop); + if (ret) + return ret; + + drm_colorop_reset(colorop); + + return 0; +} +EXPORT_SYMBOL(drm_plane_colorop_curve_1d_lut_init); + +int drm_plane_colorop_ctm_3x4_init(struct drm_device *dev, struct drm_colorop *colorop, + struct drm_plane *plane, uint32_t flags) +{ + int ret; + + ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_CTM_3X4, flags); + if (ret) + return ret; + + ret = drm_colorop_create_data_prop(dev, colorop); + if (ret) + return ret; + + drm_colorop_reset(colorop); + + return 0; +} +EXPORT_SYMBOL(drm_plane_colorop_ctm_3x4_init); + +/** + * drm_plane_colorop_mult_init - Initialize a DRM_COLOROP_MULTIPLIER + * + * @dev: DRM device + * @colorop: The drm_colorop object to initialize + * @plane: The associated drm_plane + * @flags: bitmask of misc, see DRM_COLOROP_FLAG_* defines. + * @return zero on success, -E value on failure + */ +int drm_plane_colorop_mult_init(struct drm_device *dev, struct drm_colorop *colorop, + struct drm_plane *plane, uint32_t flags) +{ + struct drm_property *prop; + int ret; + + ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_MULTIPLIER, flags); + if (ret) + return ret; + + prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "MULTIPLIER", 0, U64_MAX); + if (!prop) + return -ENOMEM; + + colorop->multiplier_property = prop; + drm_object_attach_property(&colorop->base, colorop->multiplier_property, 0); + + drm_colorop_reset(colorop); + + return 0; +} +EXPORT_SYMBOL(drm_plane_colorop_mult_init); + +int drm_plane_colorop_3dlut_init(struct drm_device *dev, struct drm_colorop *colorop, + struct drm_plane *plane, + uint32_t lut_size, + enum drm_colorop_lut3d_interpolation_type interpolation, + uint32_t flags) +{ + struct drm_property *prop; + int ret; + + ret = drm_plane_colorop_init(dev, colorop, plane, DRM_COLOROP_3D_LUT, flags); + if (ret) + return ret; + + /* LUT size */ + prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_ATOMIC, + "SIZE", 0, UINT_MAX); + if (!prop) + return -ENOMEM; + + colorop->size_property = prop; + drm_object_attach_property(&colorop->base, colorop->size_property, lut_size); + colorop->size = lut_size; + + /* interpolation */ + prop = drm_property_create_enum(dev, 0, "LUT3D_INTERPOLATION", + drm_colorop_lut3d_interpolation_list, + ARRAY_SIZE(drm_colorop_lut3d_interpolation_list)); + if (!prop) + return -ENOMEM; + + colorop->lut3d_interpolation_property = prop; + drm_object_attach_property(&colorop->base, prop, interpolation); + colorop->lut3d_interpolation = interpolation; + + /* data */ + ret = drm_colorop_create_data_prop(dev, colorop); + if (ret) + return ret; + + drm_colorop_reset(colorop); + + return 0; +} +EXPORT_SYMBOL(drm_plane_colorop_3dlut_init); + +static void __drm_atomic_helper_colorop_duplicate_state(struct drm_colorop *colorop, + struct drm_colorop_state *state) +{ + memcpy(state, colorop->state, sizeof(*state)); + + if (state->data) + drm_property_blob_get(state->data); + + state->bypass = true; +} + +struct drm_colorop_state * +drm_atomic_helper_colorop_duplicate_state(struct drm_colorop *colorop) +{ + struct drm_colorop_state *state; + + if (WARN_ON(!colorop->state)) + return NULL; + + state = kmalloc(sizeof(*state), GFP_KERNEL); + if (state) + __drm_atomic_helper_colorop_duplicate_state(colorop, state); + + return state; +} + +void drm_colorop_atomic_destroy_state(struct drm_colorop *colorop, + struct drm_colorop_state *state) +{ + kfree(state); +} + +/** + * __drm_colorop_state_reset - resets colorop state to default values + * @colorop_state: atomic colorop state, must not be NULL + * @colorop: colorop object, must not be NULL + * + * Initializes the newly allocated @colorop_state with default + * values. This is useful for drivers that subclass the CRTC state. + */ +static void __drm_colorop_state_reset(struct drm_colorop_state *colorop_state, + struct drm_colorop *colorop) +{ + u64 val; + + colorop_state->colorop = colorop; + colorop_state->bypass = true; + + if (colorop->curve_1d_type_property) { + drm_object_property_get_default_value(&colorop->base, + colorop->curve_1d_type_property, + &val); + colorop_state->curve_1d_type = val; + } +} + +/** + * __drm_colorop_reset - reset state on colorop + * @colorop: drm colorop + * @colorop_state: colorop state to assign + * + * Initializes the newly allocated @colorop_state and assigns it to + * the &drm_crtc->state pointer of @colorop, usually required when + * initializing the drivers or when called from the &drm_colorop_funcs.reset + * hook. + * + * This is useful for drivers that subclass the colorop state. + */ +static void __drm_colorop_reset(struct drm_colorop *colorop, + struct drm_colorop_state *colorop_state) +{ + if (colorop_state) + __drm_colorop_state_reset(colorop_state, colorop); + + colorop->state = colorop_state; +} + +void drm_colorop_reset(struct drm_colorop *colorop) +{ + kfree(colorop->state); + colorop->state = kzalloc(sizeof(*colorop->state), GFP_KERNEL); + + if (colorop->state) + __drm_colorop_reset(colorop, colorop->state); +} + +static const char * const colorop_type_name[] = { + [DRM_COLOROP_1D_CURVE] = "1D Curve", + [DRM_COLOROP_1D_LUT] = "1D LUT", + [DRM_COLOROP_CTM_3X4] = "3x4 Matrix", + [DRM_COLOROP_MULTIPLIER] = "Multiplier", + [DRM_COLOROP_3D_LUT] = "3D LUT", +}; + +static const char * const colorop_lu3d_interpolation_name[] = { + [DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL] = "Tetrahedral", +}; + +static const char * const colorop_lut1d_interpolation_name[] = { + [DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR] = "Linear", +}; + +const char *drm_get_colorop_type_name(enum drm_colorop_type type) +{ + if (WARN_ON(type >= ARRAY_SIZE(colorop_type_name))) + return "unknown"; + + return colorop_type_name[type]; +} + +const char *drm_get_colorop_curve_1d_type_name(enum drm_colorop_curve_1d_type type) +{ + if (WARN_ON(type >= ARRAY_SIZE(colorop_curve_1d_type_names))) + return "unknown"; + + return colorop_curve_1d_type_names[type]; +} + +/** + * drm_get_colorop_lut1d_interpolation_name: return a string for interpolation type + * @type: interpolation type to compute name of + * + * In contrast to the other drm_get_*_name functions this one here returns a + * const pointer and hence is threadsafe. + */ +const char *drm_get_colorop_lut1d_interpolation_name(enum drm_colorop_lut1d_interpolation_type type) +{ + if (WARN_ON(type >= ARRAY_SIZE(colorop_lut1d_interpolation_name))) + return "unknown"; + + return colorop_lut1d_interpolation_name[type]; +} + +/** + * drm_get_colorop_lut3d_interpolation_name - return a string for interpolation type + * @type: interpolation type to compute name of + * + * In contrast to the other drm_get_*_name functions this one here returns a + * const pointer and hence is threadsafe. + */ +const char *drm_get_colorop_lut3d_interpolation_name(enum drm_colorop_lut3d_interpolation_type type) +{ + if (WARN_ON(type >= ARRAY_SIZE(colorop_lu3d_interpolation_name))) + return "unknown"; + + return colorop_lu3d_interpolation_name[type]; +} + +/** + * drm_colorop_set_next_property - sets the next pointer + * @colorop: drm colorop + * @next: next colorop + * + * Should be used when constructing the color pipeline + */ +void drm_colorop_set_next_property(struct drm_colorop *colorop, struct drm_colorop *next) +{ + drm_object_property_set_value(&colorop->base, + colorop->next_property, + next ? next->base.id : 0); + colorop->next = next; +} +EXPORT_SYMBOL(drm_colorop_set_next_property); diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 272d6254ea47..4d6dc9ebfdb5 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -3439,6 +3439,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, * properties reflect the latest status. */ ret = drm_mode_object_get_properties(&connector->base, file_priv->atomic, + file_priv->plane_color_pipeline, (uint32_t __user *)(unsigned long)(out_resp->props_ptr), (uint64_t __user *)(unsigned long)(out_resp->prop_values_ptr), &out_resp->count_props); diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h index 89706aa8232f..c09409229644 100644 --- a/drivers/gpu/drm/drm_crtc_internal.h +++ b/drivers/gpu/drm/drm_crtc_internal.h @@ -163,6 +163,7 @@ struct drm_mode_object *__drm_mode_object_find(struct drm_device *dev, void drm_mode_object_unregister(struct drm_device *dev, struct drm_mode_object *object); int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic, + bool plane_color_pipeline, uint32_t __user *prop_ptr, uint64_t __user *prop_values, uint32_t *arg_count_props); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 8e3cb08241c8..2915118436ce 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -733,6 +733,7 @@ static int drm_dev_init(struct drm_device *dev, INIT_LIST_HEAD(&dev->filelist); INIT_LIST_HEAD(&dev->filelist_internal); INIT_LIST_HEAD(&dev->clientlist); + INIT_LIST_HEAD(&dev->client_sysrq_list); INIT_LIST_HEAD(&dev->vblank_event_list); spin_lock_init(&dev->event_lock); @@ -1100,6 +1101,7 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) goto err_unload; } drm_panic_register(dev); + drm_client_sysrq_register(dev); DRM_INFO("Initialized %s %d.%d.%d for %s on minor %d\n", driver->name, driver->major, driver->minor, @@ -1144,6 +1146,7 @@ void drm_dev_unregister(struct drm_device *dev) { dev->registered = false; + drm_client_sysrq_unregister(dev); drm_panic_unregister(dev); drm_client_dev_unregister(dev); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 53e9dc0543de..be790fc68707 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include @@ -255,6 +254,7 @@ __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, /** * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration * @fb_helper: driver-allocated fbdev helper, can be NULL + * @force: ignore present DRM master * * This helper should be called from fbdev emulation's &drm_client_funcs.restore * callback. It ensures that the user isn't greeted with a black screen when the @@ -263,48 +263,12 @@ __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, * Returns: * 0 on success, or a negative errno code otherwise. */ -int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) +int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, bool force) { - return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false); + return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force); } EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); -#ifdef CONFIG_MAGIC_SYSRQ -/* emergency restore, don't bother with error reporting */ -static void drm_fb_helper_restore_work_fn(struct work_struct *ignored) -{ - struct drm_fb_helper *helper; - - mutex_lock(&kernel_fb_helper_lock); - list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { - struct drm_device *dev = helper->dev; - - if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) - continue; - - mutex_lock(&helper->lock); - drm_client_modeset_commit_locked(&helper->client); - mutex_unlock(&helper->lock); - } - mutex_unlock(&kernel_fb_helper_lock); -} - -static DECLARE_WORK(drm_fb_helper_restore_work, drm_fb_helper_restore_work_fn); - -static void drm_fb_helper_sysrq(u8 dummy1) -{ - schedule_work(&drm_fb_helper_restore_work); -} - -static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { - .handler = drm_fb_helper_sysrq, - .help_msg = "force-fb(v)", - .action_msg = "Restore framebuffer console", -}; -#else -static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { }; -#endif - static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode) { struct drm_fb_helper *fb_helper = info->par; @@ -495,20 +459,7 @@ int drm_fb_helper_init(struct drm_device *dev, } EXPORT_SYMBOL(drm_fb_helper_init); -/** - * drm_fb_helper_alloc_info - allocate fb_info and some of its members - * @fb_helper: driver-allocated fbdev helper - * - * A helper to alloc fb_info and the member cmap. Called by the driver - * within the struct &drm_driver.fbdev_probe callback function. Drivers do - * not need to release the allocated fb_info structure themselves, this is - * automatically done when calling drm_fb_helper_fini(). - * - * RETURNS: - * fb_info pointer if things went okay, pointer containing error code - * otherwise - */ -struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) +static struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) { struct device *dev = fb_helper->dev->dev; struct fb_info *info; @@ -535,17 +486,8 @@ struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) framebuffer_release(info); return ERR_PTR(ret); } -EXPORT_SYMBOL(drm_fb_helper_alloc_info); -/** - * drm_fb_helper_release_info - release fb_info and its members - * @fb_helper: driver-allocated fbdev helper - * - * A helper to release fb_info and the member cmap. Drivers do not - * need to release the allocated fb_info structure themselves, this is - * automatically done when calling drm_fb_helper_fini(). - */ -void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) +static void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) { struct fb_info *info = fb_helper->info; @@ -558,7 +500,6 @@ void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) fb_dealloc_cmap(&info->cmap); framebuffer_release(info); } -EXPORT_SYMBOL(drm_fb_helper_release_info); /** * drm_fb_helper_unregister_info - unregister fb_info framebuffer device @@ -601,11 +542,8 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) drm_fb_helper_release_info(fb_helper); mutex_lock(&kernel_fb_helper_lock); - if (!list_empty(&fb_helper->kernel_fb_list)) { + if (!list_empty(&fb_helper->kernel_fb_list)) list_del(&fb_helper->kernel_fb_list); - if (list_empty(&kernel_fb_helper_list)) - unregister_sysrq_key('v', &sysrq_drm_fb_helper_restore_op); - } mutex_unlock(&kernel_fb_helper_lock); if (!fb_helper->client.funcs) @@ -1328,9 +1266,9 @@ int drm_fb_helper_set_par(struct fb_info *info) * the KDSET IOCTL with KD_TEXT, and only after that drops the master * status when exiting. * - * In the past this was caught by drm_fb_helper_lastclose(), but on - * modern systems where logind always keeps a drm fd open to orchestrate - * the vt switching, this doesn't work. + * In the past this was caught by drm_fb_helper_restore_fbdev_mode_unlocked(), + * but on modern systems where logind always keeps a drm fd open to + * orchestrate the vt switching, this doesn't work. * * To not break the userspace ABI we have this special case here, which * is only used for the above case. Everything else uses the normal @@ -1809,6 +1747,11 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) height = dev->mode_config.max_height; drm_client_modeset_probe(&fb_helper->client, width, height); + + info = drm_fb_helper_alloc_info(fb_helper); + if (IS_ERR(info)) + return PTR_ERR(info); + ret = drm_fb_helper_single_fb_probe(fb_helper); if (ret < 0) { if (ret == -EAGAIN) { @@ -1817,13 +1760,12 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) } mutex_unlock(&fb_helper->lock); - return ret; + goto err_drm_fb_helper_release_info; } drm_setup_crtcs_fb(fb_helper); fb_helper->deferred_setup = false; - info = fb_helper->info; info->var.pixclock = 0; /* Need to drop locks to avoid recursive deadlock in @@ -1839,13 +1781,14 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) info->node, info->fix.id); mutex_lock(&kernel_fb_helper_lock); - if (list_empty(&kernel_fb_helper_list)) - register_sysrq_key('v', &sysrq_drm_fb_helper_restore_op); - list_add(&fb_helper->kernel_fb_list, &kernel_fb_helper_list); mutex_unlock(&kernel_fb_helper_lock); return 0; + +err_drm_fb_helper_release_info: + drm_fb_helper_release_info(fb_helper); + return ret; } /** @@ -1955,16 +1898,3 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) return 0; } EXPORT_SYMBOL(drm_fb_helper_hotplug_event); - -/** - * drm_fb_helper_lastclose - DRM driver lastclose helper for fbdev emulation - * @dev: DRM device - * - * This function is obsolete. Call drm_fb_helper_restore_fbdev_mode_unlocked() - * instead. - */ -void drm_fb_helper_lastclose(struct drm_device *dev) -{ - drm_fb_helper_restore_fbdev_mode_unlocked(dev->fb_helper); -} -EXPORT_SYMBOL(drm_fb_helper_lastclose); diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c index 12a8f5a5ada5..9412d9fdd74b 100644 --- a/drivers/gpu/drm/drm_fbdev_dma.c +++ b/drivers/gpu/drm/drm_fbdev_dma.c @@ -269,9 +269,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; + struct fb_info *info = fb_helper->info; struct drm_client_buffer *buffer; struct drm_framebuffer *fb; - struct fb_info *info; u32 format; struct iosys_map map; int ret; @@ -301,12 +301,6 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->buffer = buffer; fb_helper->fb = fb; - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_client_buffer_vunmap; - } - drm_fb_helper_fill_info(info, fb_helper, sizes); if (fb->funcs->dirty) @@ -314,12 +308,10 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper, else ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes); if (ret) - goto err_drm_fb_helper_release_info; + goto err_drm_client_buffer_vunmap; return 0; -err_drm_fb_helper_release_info: - drm_fb_helper_release_info(fb_helper); err_drm_client_buffer_vunmap: fb_helper->fb = NULL; fb_helper->buffer = NULL; diff --git a/drivers/gpu/drm/drm_fbdev_shmem.c b/drivers/gpu/drm/drm_fbdev_shmem.c index ac2b22e05cd6..458c899b5d4f 100644 --- a/drivers/gpu/drm/drm_fbdev_shmem.c +++ b/drivers/gpu/drm/drm_fbdev_shmem.c @@ -135,10 +135,10 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; + struct fb_info *info = fb_helper->info; struct drm_client_buffer *buffer; struct drm_gem_shmem_object *shmem; struct drm_framebuffer *fb; - struct fb_info *info; u32 format; struct iosys_map map; int ret; @@ -168,12 +168,6 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->buffer = buffer; fb_helper->fb = fb; - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_client_buffer_vunmap; - } - drm_fb_helper_fill_info(info, fb_helper, sizes); info->fbops = &drm_fbdev_shmem_fb_ops; @@ -194,12 +188,10 @@ int drm_fbdev_shmem_driver_fbdev_probe(struct drm_fb_helper *fb_helper, info->fbdefio = &fb_helper->fbdefio; ret = fb_deferred_io_init(info); if (ret) - goto err_drm_fb_helper_release_info; + goto err_drm_client_buffer_vunmap; return 0; -err_drm_fb_helper_release_info: - drm_fb_helper_release_info(fb_helper); err_drm_client_buffer_vunmap: fb_helper->fb = NULL; fb_helper->buffer = NULL; diff --git a/drivers/gpu/drm/drm_fbdev_ttm.c b/drivers/gpu/drm/drm_fbdev_ttm.c index c7ad779ba590..160bc35d8738 100644 --- a/drivers/gpu/drm/drm_fbdev_ttm.c +++ b/drivers/gpu/drm/drm_fbdev_ttm.c @@ -174,8 +174,8 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper, { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; + struct fb_info *info = fb_helper->info; struct drm_client_buffer *buffer; - struct fb_info *info; size_t screen_size; void *screen_buffer; u32 format; @@ -203,12 +203,6 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper, goto err_drm_client_buffer_delete; } - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_vfree; - } - drm_fb_helper_fill_info(info, fb_helper, sizes); info->fbops = &drm_fbdev_ttm_fb_ops; @@ -225,12 +219,10 @@ int drm_fbdev_ttm_driver_fbdev_probe(struct drm_fb_helper *fb_helper, info->fbdefio = &fb_helper->fbdefio; ret = fb_deferred_io_init(info); if (ret) - goto err_drm_fb_helper_release_info; + goto err_vfree; return 0; -err_drm_fb_helper_release_info: - drm_fb_helper_release_info(fb_helper); err_vfree: vfree(screen_buffer); err_drm_client_buffer_delete: diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index eebd1a05ee97..be5e617ceb9f 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -405,7 +405,7 @@ EXPORT_SYMBOL(drm_open); static void drm_lastclose(struct drm_device *dev) { - drm_client_dev_restore(dev); + drm_client_dev_restore(dev, false); if (dev_is_pci(dev->dev)) vga_switcheroo_process_delayed_switch(); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index a1a9c828938b..efc79bbf3c73 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -783,7 +783,6 @@ static int objects_lookup(struct drm_file *filp, u32 *handle, int count, int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles, int count, struct drm_gem_object ***objs_out) { - struct drm_device *dev = filp->minor->dev; struct drm_gem_object **objs; u32 *handles; int ret; @@ -798,20 +797,11 @@ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles, *objs_out = objs; - handles = kvmalloc_array(count, sizeof(u32), GFP_KERNEL); - if (!handles) { - ret = -ENOMEM; - goto out; - } - - if (copy_from_user(handles, bo_handles, count * sizeof(u32))) { - ret = -EFAULT; - drm_dbg_core(dev, "Failed to copy in GEM handles\n"); - goto out; - } + handles = vmemdup_array_user(bo_handles, count, sizeof(u32)); + if (IS_ERR(handles)) + return PTR_ERR(handles); ret = objects_lookup(filp, handles, count, objs); -out: kvfree(handles); return ret; diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index cbb029cc656a..569d41a65a0b 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -310,8 +310,12 @@ EXPORT_SYMBOL(drm_gem_destroy_shadow_plane_state); void __drm_gem_reset_shadow_plane(struct drm_plane *plane, struct drm_shadow_plane_state *shadow_plane_state) { - __drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base); - drm_format_conv_state_init(&shadow_plane_state->fmtcnv_state); + if (shadow_plane_state) { + __drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base); + drm_format_conv_state_init(&shadow_plane_state->fmtcnv_state); + } else { + __drm_atomic_helper_plane_reset(plane, NULL); + } } EXPORT_SYMBOL(__drm_gem_reset_shadow_plane); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 5a3bed48ab1f..f893b1e3a596 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -56,6 +56,17 @@ static inline void drm_client_debugfs_init(struct drm_device *dev) { } #endif +/* drm_client_sysrq.c */ +#if defined(CONFIG_DRM_CLIENT) && defined(CONFIG_MAGIC_SYSRQ) +void drm_client_sysrq_register(struct drm_device *dev); +void drm_client_sysrq_unregister(struct drm_device *dev); +#else +static inline void drm_client_sysrq_register(struct drm_device *dev) +{ } +static inline void drm_client_sysrq_unregister(struct drm_device *dev) +{ } +#endif + /* drm_file.c */ extern struct mutex drm_global_mutex; bool drm_dev_needs_global_mutex(struct drm_device *dev); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index d8a24875a7ba..ff193155129e 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -373,6 +373,13 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv) return -EINVAL; file_priv->supports_virtualized_cursor_plane = req->value; break; + case DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE: + if (!file_priv->atomic) + return -EINVAL; + if (req->value > 1) + return -EINVAL; + file_priv->plane_color_pipeline = req->value; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c index 25f376869b3a..d12db9b0bab8 100644 --- a/drivers/gpu/drm/drm_mode_config.c +++ b/drivers/gpu/drm/drm_mode_config.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "drm_crtc_internal.h" @@ -192,11 +193,15 @@ int drm_mode_getresources(struct drm_device *dev, void *data, void drm_mode_config_reset(struct drm_device *dev) { struct drm_crtc *crtc; + struct drm_colorop *colorop; struct drm_plane *plane; struct drm_encoder *encoder; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; + drm_for_each_colorop(colorop, dev) + drm_colorop_reset(colorop); + drm_for_each_plane(plane, dev) if (plane->funcs->reset) plane->funcs->reset(plane); @@ -437,6 +442,7 @@ int drmm_mode_config_init(struct drm_device *dev) INIT_LIST_HEAD(&dev->mode_config.property_list); INIT_LIST_HEAD(&dev->mode_config.property_blob_list); INIT_LIST_HEAD(&dev->mode_config.plane_list); + INIT_LIST_HEAD(&dev->mode_config.colorop_list); INIT_LIST_HEAD(&dev->mode_config.privobj_list); idr_init_base(&dev->mode_config.object_idr, 1); idr_init_base(&dev->mode_config.tile_idr, 1); @@ -458,6 +464,7 @@ int drmm_mode_config_init(struct drm_device *dev) dev->mode_config.num_crtc = 0; dev->mode_config.num_encoder = 0; dev->mode_config.num_total_plane = 0; + dev->mode_config.num_colorop = 0; if (IS_ENABLED(CONFIG_LOCKDEP)) { struct drm_modeset_acquire_ctx modeset_ctx; diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index e943205a2394..b45d501b10c8 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "drm_crtc_internal.h" @@ -386,6 +387,7 @@ EXPORT_SYMBOL(drm_object_property_get_default_value); /* helper for getconnector and getproperties ioctls */ int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic, + bool plane_color_pipeline, uint32_t __user *prop_ptr, uint64_t __user *prop_values, uint32_t *arg_count_props) @@ -399,6 +401,21 @@ int drm_mode_object_get_properties(struct drm_mode_object *obj, bool atomic, if ((prop->flags & DRM_MODE_PROP_ATOMIC) && !atomic) continue; + if (plane_color_pipeline && obj->type == DRM_MODE_OBJECT_PLANE) { + struct drm_plane *plane = obj_to_plane(obj); + + if (prop == plane->color_encoding_property || + prop == plane->color_range_property) + continue; + } + + if (!plane_color_pipeline && obj->type == DRM_MODE_OBJECT_PLANE) { + struct drm_plane *plane = obj_to_plane(obj); + + if (prop == plane->color_pipeline_property) + continue; + } + if (*arg_count_props > count) { ret = __drm_object_property_get_value(obj, prop, &val); if (ret) @@ -457,6 +474,7 @@ int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data, } ret = drm_mode_object_get_properties(obj, file_priv->atomic, + file_priv->plane_color_pipeline, (uint32_t __user *)(unsigned long)(arg->props_ptr), (uint64_t __user *)(unsigned long)(arg->prop_values_ptr), &arg->count_props); diff --git a/drivers/gpu/drm/drm_panic.c b/drivers/gpu/drm/drm_panic.c index 1d6312fa1429..d4b6ea42db0f 100644 --- a/drivers/gpu/drm/drm_panic.c +++ b/drivers/gpu/drm/drm_panic.c @@ -174,6 +174,33 @@ static void drm_panic_write_pixel24(void *vaddr, unsigned int offset, u32 color) *p = color & 0xff; } +/* + * Special case if the pixel crosses page boundaries + */ +static void drm_panic_write_pixel24_xpage(void *vaddr, struct page *next_page, + unsigned int offset, u32 color) +{ + u8 *vaddr2; + u8 *p = vaddr + offset; + + vaddr2 = kmap_local_page_try_from_panic(next_page); + + *p++ = color & 0xff; + color >>= 8; + + if (offset == PAGE_SIZE - 1) + p = vaddr2; + + *p++ = color & 0xff; + color >>= 8; + + if (offset == PAGE_SIZE - 2) + p = vaddr2; + + *p = color & 0xff; + kunmap_local(vaddr2); +} + static void drm_panic_write_pixel32(void *vaddr, unsigned int offset, u32 color) { u32 *p = vaddr + offset; @@ -231,7 +258,14 @@ static void drm_panic_blit_page(struct page **pages, unsigned int dpitch, page = new_page; vaddr = kmap_local_page_try_from_panic(pages[page]); } - if (vaddr) + if (!vaddr) + continue; + + // Special case for 24bit, as a pixel might cross page boundaries + if (cpp == 3 && offset + 3 > PAGE_SIZE) + drm_panic_write_pixel24_xpage(vaddr, pages[page + 1], + offset, fg32); + else drm_panic_write_pixel(vaddr, offset, fg32, cpp); } } @@ -321,7 +355,15 @@ static void drm_panic_fill_page(struct page **pages, unsigned int dpitch, page = new_page; vaddr = kmap_local_page_try_from_panic(pages[page]); } - drm_panic_write_pixel(vaddr, offset, color, cpp); + if (!vaddr) + continue; + + // Special case for 24bit, as a pixel might cross page boundaries + if (cpp == 3 && offset + 3 > PAGE_SIZE) + drm_panic_write_pixel24_xpage(vaddr, pages[page + 1], + offset, color); + else + drm_panic_write_pixel(vaddr, offset, color, cpp); } } if (vaddr) @@ -429,6 +471,9 @@ static void drm_panic_logo_rect(struct drm_rect *rect, const struct font_desc *f static void drm_panic_logo_draw(struct drm_scanout_buffer *sb, struct drm_rect *rect, const struct font_desc *font, u32 fg_color) { + if (rect->x2 > sb->width || rect->y2 > sb->height) + return; + if (logo_mono) drm_panic_blit(sb, rect, logo_mono->data, DIV_ROUND_UP(drm_rect_width(rect), 8), 1, fg_color); @@ -477,7 +522,7 @@ static int draw_line_with_wrap(struct drm_scanout_buffer *sb, const struct font_ struct drm_panic_line *line, int yoffset, u32 fg_color) { int chars_per_row = sb->width / font->width; - struct drm_rect r_txt = DRM_RECT_INIT(0, yoffset, sb->width, sb->height); + struct drm_rect r_txt = DRM_RECT_INIT(0, yoffset, sb->width, font->height); struct drm_panic_line line_wrap; if (line->len > chars_per_row) { @@ -520,7 +565,7 @@ static void draw_panic_static_kmsg(struct drm_scanout_buffer *sb) struct drm_panic_line line; int yoffset; - if (!font) + if (!font || font->width > sb->width) return; yoffset = sb->height - font->height - (sb->height % font->height) / 2; @@ -733,7 +778,10 @@ static int _draw_panic_static_qr_code(struct drm_scanout_buffer *sb) pr_debug("QR width %d and scale %d\n", qr_width, scale); r_qr_canvas = DRM_RECT_INIT(0, 0, qr_canvas_width * scale, qr_canvas_width * scale); - v_margin = (sb->height - drm_rect_height(&r_qr_canvas) - drm_rect_height(&r_msg)) / 5; + v_margin = sb->height - drm_rect_height(&r_qr_canvas) - drm_rect_height(&r_msg); + if (v_margin < 0) + return -ENOSPC; + v_margin /= 5; drm_rect_translate(&r_qr_canvas, (sb->width - r_qr_canvas.x2) / 2, 2 * v_margin); r_qr = DRM_RECT_INIT(r_qr_canvas.x1 + QR_MARGIN * scale, r_qr_canvas.y1 + QR_MARGIN * scale, @@ -746,7 +794,7 @@ static int _draw_panic_static_qr_code(struct drm_scanout_buffer *sb) /* Fill with the background color, and draw text on top */ drm_panic_fill(sb, &r_screen, bg_color); - if (!drm_rect_overlap(&r_logo, &r_msg) && !drm_rect_overlap(&r_logo, &r_qr)) + if (!drm_rect_overlap(&r_logo, &r_msg) && !drm_rect_overlap(&r_logo, &r_qr_canvas)) drm_panic_logo_draw(sb, &r_logo, font, fg_color); draw_txt_rectangle(sb, font, panic_msg, panic_msg_lines, true, &r_msg, fg_color); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 38f82391bfda..f6cfa8ac090c 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -1820,3 +1820,62 @@ int drm_plane_add_size_hints_property(struct drm_plane *plane, return 0; } EXPORT_SYMBOL(drm_plane_add_size_hints_property); + +/** + * drm_plane_create_color_pipeline_property - create a new color pipeline + * property + * + * @plane: drm plane + * @pipelines: list of pipelines + * @num_pipelines: number of pipelines + * + * Create the COLOR_PIPELINE plane property to specific color pipelines on + * the plane. + * + * RETURNS: + * Zero for success or -errno + */ +int drm_plane_create_color_pipeline_property(struct drm_plane *plane, + const struct drm_prop_enum_list *pipelines, + int num_pipelines) +{ + struct drm_prop_enum_list *all_pipelines; + struct drm_property *prop; + int len = 0; + int i; + + all_pipelines = kcalloc(num_pipelines + 1, + sizeof(*all_pipelines), + GFP_KERNEL); + + if (!all_pipelines) { + drm_err(plane->dev, "failed to allocate color pipeline\n"); + return -ENOMEM; + } + + /* Create default Bypass color pipeline */ + all_pipelines[len].type = 0; + all_pipelines[len].name = "Bypass"; + len++; + + /* Add all other color pipelines */ + for (i = 0; i < num_pipelines; i++, len++) { + all_pipelines[len].type = pipelines[i].type; + all_pipelines[len].name = pipelines[i].name; + } + + prop = drm_property_create_enum(plane->dev, DRM_MODE_PROP_ATOMIC, + "COLOR_PIPELINE", + all_pipelines, len); + if (IS_ERR(prop)) { + kfree(all_pipelines); + return PTR_ERR(prop); + } + + drm_object_attach_property(&plane->base, prop, 0); + plane->color_pipeline_property = prop; + + kfree(all_pipelines); + return 0; +} +EXPORT_SYMBOL(drm_plane_create_color_pipeline_property); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c index d4f1307d574f..ad5e6f7b23f9 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c @@ -348,7 +348,7 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, u32 exec_state, u32 link_target, link_dwords; bool switch_context = gpu->exec_state != exec_state; bool switch_mmu_context = gpu->mmu_context != mmu_context; - unsigned int new_flush_seq = READ_ONCE(gpu->mmu_context->flush_seq); + unsigned int new_flush_seq = READ_ONCE(mmu_context->flush_seq); bool need_flush = switch_mmu_context || gpu->flush_seq != new_flush_seq; bool has_blt = !!(gpu->identity.minor_features5 & chipMinorFeatures5_BLT_ENGINE); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index a9d35e8fca6a..637927818dfe 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -58,18 +58,11 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, struct drm_fb_helper_surface_size *sizes, struct exynos_drm_gem *exynos_gem) { - struct fb_info *fbi; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = helper->fb; unsigned int size = fb->width * fb->height * fb->format->cpp[0]; unsigned long offset; - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - DRM_DEV_ERROR(to_dma_dev(helper->dev), - "failed to allocate fb info.\n"); - return PTR_ERR(fbi); - } - fbi->fbops = &exynos_drm_fb_ops; drm_fb_helper_fill_info(fbi, helper, sizes); diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c index bc92fa24a1e2..c26926babc2a 100644 --- a/drivers/gpu/drm/gma500/fbdev.c +++ b/drivers/gpu/drm/gma500/fbdev.c @@ -108,7 +108,7 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct drm_device *dev = fb_helper->dev; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); - struct fb_info *info; + struct fb_info *info = fb_helper->info; struct drm_framebuffer *fb; struct drm_mode_fb_cmd2 mode_cmd = { }; int size; @@ -167,12 +167,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, fb_helper->funcs = &psb_fbdev_fb_helper_funcs; fb_helper->fb = fb; - info = drm_fb_helper_alloc_info(fb_helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto err_drm_framebuffer_unregister_private; - } - info->fbops = &psb_fbdev_fb_ops; /* Accessed stolen memory directly */ @@ -196,10 +190,6 @@ int psb_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, return 0; -err_drm_framebuffer_unregister_private: - drm_framebuffer_unregister_private(fb); - drm_framebuffer_cleanup(fb); - kfree(fb); err_drm_gem_object_put: drm_gem_object_put(obj); return ret; diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 49c86a0d44f9..7c89e5e0a277 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -426,7 +426,7 @@ obj-$(CONFIG_DRM_I915_GVT_KVMGT) += kvmgt.o # # Enable locally for CONFIG_DRM_I915_WERROR=y. See also scripts/Makefile.build ifdef CONFIG_DRM_I915_WERROR - cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none -Werror $< + cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none -Werror $< endif # header test diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index e5449c41cfa1..9cd03e2adeb2 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -267,8 +267,8 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct intel_display *display = to_intel_display(helper->dev); struct intel_fbdev *ifbdev = to_intel_fbdev(helper); struct intel_framebuffer *fb = ifbdev->fb; + struct fb_info *info = helper->info; struct ref_tracker *wakeref; - struct fb_info *info; struct i915_vma *vma; unsigned long flags = 0; bool prealloc = false; @@ -318,13 +318,6 @@ int intel_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto out_unlock; } - info = drm_fb_helper_alloc_info(helper); - if (IS_ERR(info)) { - drm_err(display->drm, "Failed to allocate fb_info (%pe)\n", info); - ret = PTR_ERR(info); - goto out_unpin; - } - helper->funcs = &intel_fb_helper_funcs; helper->fb = &fb->base; diff --git a/drivers/gpu/drm/imagination/Kconfig b/drivers/gpu/drm/imagination/Kconfig index 682dd2633d0c..0482bfcefdde 100644 --- a/drivers/gpu/drm/imagination/Kconfig +++ b/drivers/gpu/drm/imagination/Kconfig @@ -7,6 +7,7 @@ config DRM_POWERVR depends on DRM depends on MMU depends on PM + depends on POWER_SEQUENCING || !POWER_SEQUENCING select DRM_EXEC select DRM_GEM_SHMEM_HELPER select DRM_SCHED diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c index 61fab3698807..6fbf505d2801 100644 --- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c +++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c @@ -25,19 +25,18 @@ struct imx_parallel_display_encoder { struct drm_encoder encoder; - struct drm_bridge bridge; - struct imx_parallel_display *pd; }; struct imx_parallel_display { struct device *dev; u32 bus_format; struct drm_bridge *next_bridge; + struct drm_bridge bridge; }; static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b) { - return container_of(b, struct imx_parallel_display_encoder, bridge)->pd; + return container_of(b, struct imx_parallel_display, bridge); } static const u32 imx_pd_bus_fmts[] = { @@ -195,15 +194,13 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) if (IS_ERR(imxpd_encoder)) return PTR_ERR(imxpd_encoder); - imxpd_encoder->pd = imxpd; encoder = &imxpd_encoder->encoder; - bridge = &imxpd_encoder->bridge; + bridge = &imxpd->bridge; ret = imx_drm_encoder_parse_of(drm, encoder, imxpd->dev->of_node); if (ret) return ret; - bridge->funcs = &imx_pd_bridge_funcs; drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); connector = drm_bridge_connector_init(drm, encoder); @@ -228,9 +225,10 @@ static int imx_pd_probe(struct platform_device *pdev) u32 bus_format = 0; const char *fmt; - imxpd = devm_kzalloc(dev, sizeof(*imxpd), GFP_KERNEL); - if (!imxpd) - return -ENOMEM; + imxpd = devm_drm_bridge_alloc(dev, struct imx_parallel_display, bridge, + &imx_pd_bridge_funcs); + if (IS_ERR(imxpd)) + return PTR_ERR(imxpd); /* port@1 is the output port */ imxpd->next_bridge = devm_drm_of_get_bridge(dev, np, 1, 0); @@ -258,6 +256,8 @@ static int imx_pd_probe(struct platform_device *pdev) platform_set_drvdata(pdev, imxpd); + devm_drm_bridge_add(dev, &imxpd->bridge); + return component_add(dev, &imx_pd_ops); } diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index e47debd60619..96188bf9274a 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -30,9 +30,30 @@ config DRM_MEDIATEK_DP help DRM/KMS Display Port driver for MediaTek SoCs. +config DRM_MEDIATEK_HDMI_COMMON + tristate + depends on DRM_MEDIATEK + select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HELPER + select SND_SOC_HDMI_CODEC if SND_SOC + help + MediaTek SoC HDMI common library + config DRM_MEDIATEK_HDMI tristate "DRM HDMI Support for Mediatek SoCs" depends on DRM_MEDIATEK - select SND_SOC_HDMI_CODEC if SND_SOC + select DRM_MEDIATEK_HDMI_COMMON help DRM/KMS HDMI driver for Mediatek SoCs + +config DRM_MEDIATEK_HDMI_V2 + tristate "DRM HDMI v2 IP support for MediaTek SoCs" + depends on DRM_MEDIATEK + select DRM_MEDIATEK_HDMI_COMMON + help + Say yes here to enable support for the HDMIv2 IP and related + DDCv2 as found in the MediaTek MT8195, MT8188 SoCs and other + variants. + This driver can also be built as a module. If so, the HDMIv2 + module will be called "mtk_hdmi_v2", and the DDCv2 module + will be called "mtk_hdmi_ddc_v2". diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile index 43afd0a26d14..e0ac49b07d50 100644 --- a/drivers/gpu/drm/mediatek/Makefile +++ b/drivers/gpu/drm/mediatek/Makefile @@ -21,8 +21,11 @@ mediatek-drm-y := mtk_crtc.o \ obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o +obj-$(CONFIG_DRM_MEDIATEK_HDMI_COMMON) += mtk_hdmi_common.o obj-$(CONFIG_DRM_MEDIATEK_HDMI) += mtk_cec.o obj-$(CONFIG_DRM_MEDIATEK_HDMI) += mtk_hdmi.o obj-$(CONFIG_DRM_MEDIATEK_HDMI) += mtk_hdmi_ddc.o +obj-$(CONFIG_DRM_MEDIATEK_HDMI_V2) += mtk_hdmi_v2.o +obj-$(CONFIG_DRM_MEDIATEK_HDMI_V2) += mtk_hdmi_ddc_v2.o obj-$(CONFIG_DRM_MEDIATEK_DP) += mtk_dp.o diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index 68646a61f74d..991cdb3d7d5f 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -284,6 +284,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) unsigned int i; unsigned long flags; + /* release GCE HW usage and start autosuspend */ + pm_runtime_mark_last_busy(cmdq_cl->chan->mbox->dev); + pm_runtime_put_autosuspend(cmdq_cl->chan->mbox->dev); + if (data->sta < 0) return; @@ -619,6 +623,9 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank) mtk_crtc->config_updating = false; spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (pm_runtime_resume_and_get(mtk_crtc->cmdq_client.chan->mbox->dev) < 0) + goto update_config_out; + mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle); mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); goto update_config_out; diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c index ac6620e10262..9672ea1f91a2 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c @@ -621,15 +621,27 @@ int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev) return ret; } -int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, +static void mtk_ddp_comp_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + +static void mtk_ddp_comp_clk_put(void *_clk) +{ + struct clk *clk = _clk; + + clk_put(clk); +} + +int mtk_ddp_comp_init(struct device *dev, struct device_node *node, struct mtk_ddp_comp *comp, unsigned int comp_id) { struct platform_device *comp_pdev; enum mtk_ddp_comp_type type; struct mtk_ddp_comp_dev *priv; -#if IS_REACHABLE(CONFIG_MTK_CMDQ) int ret; -#endif if (comp_id >= DDP_COMPONENT_DRM_ID_MAX) return -EINVAL; @@ -651,6 +663,10 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, } comp->dev = &comp_pdev->dev; + ret = devm_add_action_or_reset(dev, mtk_ddp_comp_put_device, comp->dev); + if (ret) + return ret; + if (type == MTK_DISP_AAL || type == MTK_DISP_BLS || type == MTK_DISP_CCORR || @@ -666,15 +682,22 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp, type == MTK_DSI) return 0; - priv = devm_kzalloc(comp->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - priv->regs = of_iomap(node, 0); + priv->regs = devm_of_iomap(dev, node, 0, NULL); + if (IS_ERR(priv->regs)) + return PTR_ERR(priv->regs); + priv->clk = of_clk_get(node, 0); if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); + ret = devm_add_action_or_reset(dev, mtk_ddp_comp_clk_put, priv->clk); + if (ret) + return ret; + #if IS_REACHABLE(CONFIG_MTK_CMDQ) ret = cmdq_dev_get_client_reg(comp->dev, &priv->cmdq_reg, 0); if (ret) diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h index 7289b3dcf22f..3f3d43f4330d 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h @@ -350,7 +350,7 @@ static inline void mtk_ddp_comp_encoder_index_set(struct mtk_ddp_comp *comp) int mtk_ddp_comp_get_id(struct device_node *node, enum mtk_ddp_comp_type comp_type); int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev); -int mtk_ddp_comp_init(struct device_node *comp_node, struct mtk_ddp_comp *comp, +int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node, struct mtk_ddp_comp *comp, unsigned int comp_id); enum mtk_ddp_comp_type mtk_ddp_comp_get_type(unsigned int comp_id); void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value, diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c b/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c index 10d60d2c2a56..6d7bf4afa78d 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ccorr.c @@ -80,27 +80,6 @@ void mtk_ccorr_stop(struct device *dev) writel_relaxed(0x0, ccorr->regs + DISP_CCORR_EN); } -/* Converts a DRM S31.32 value to the HW S1.n format. */ -static u16 mtk_ctm_s31_32_to_s1_n(u64 in, u32 n) -{ - u16 r; - - /* Sign bit. */ - r = in & BIT_ULL(63) ? BIT(n + 1) : 0; - - if ((in & GENMASK_ULL(62, 33)) > 0) { - /* identity value 0x100000000 -> 0x400(mt8183), */ - /* identity value 0x100000000 -> 0x800(mt8192), */ - /* if bigger this, set it to max 0x7ff. */ - r |= GENMASK(n, 0); - } else { - /* take the n+1 most important bits. */ - r |= (in >> (32 - n)) & GENMASK(n, 0); - } - - return r; -} - void mtk_ccorr_ctm_set(struct device *dev, struct drm_crtc_state *state) { struct mtk_disp_ccorr *ccorr = dev_get_drvdata(dev); @@ -119,7 +98,7 @@ void mtk_ccorr_ctm_set(struct device *dev, struct drm_crtc_state *state) input = ctm->matrix; for (i = 0; i < ARRAY_SIZE(coeffs); i++) - coeffs[i] = mtk_ctm_s31_32_to_s1_n(input[i], matrix_bits); + coeffs[i] = drm_color_ctm_s31_32_to_qm_n(input[i], 2, matrix_bits); mtk_ddp_write(cmdq_pkt, coeffs[0] << 16 | coeffs[1], &ccorr->cmdq_reg, ccorr->regs, DISP_CCORR_COEF_0); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c index fe97bb97e004..c0af3e3b51d5 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c @@ -527,6 +527,13 @@ bool mtk_ovl_adaptor_is_comp_present(struct device_node *node) type == OVL_ADAPTOR_TYPE_PADDING; } +static void ovl_adaptor_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int ovl_adaptor_comp_init(struct device *dev, struct component_match **match) { struct mtk_disp_ovl_adaptor *priv = dev_get_drvdata(dev); @@ -560,6 +567,11 @@ static int ovl_adaptor_comp_init(struct device *dev, struct component_match **ma if (!comp_pdev) return -EPROBE_DEFER; + ret = devm_add_action_or_reset(dev, ovl_adaptor_put_device, + &comp_pdev->dev); + if (ret) + return ret; + priv->ovl_adaptor_comp[id] = &comp_pdev->dev; drm_of_component_match_add(dev, match, component_compare_of, node); diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index bef6eeb30d3e..b0b1e158600f 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -2087,6 +2087,7 @@ static int mtk_dp_dt_parse(struct mtk_dp *mtk_dp, endpoint = of_graph_get_endpoint_by_regs(pdev->dev.of_node, 1, -1); len = of_property_count_elems_of_size(endpoint, "data-lanes", sizeof(u32)); + of_node_put(endpoint); if (len < 0 || len > 4 || len == 3) { dev_err(dev, "invalid data lane size: %d\n", len); return -EINVAL; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index eb5537f0ac90..a94c51a83261 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -686,10 +686,6 @@ static int mtk_drm_bind(struct device *dev) for (i = 0; i < private->data->mmsys_dev_num; i++) private->all_drm_private[i]->drm = NULL; err_put_dev: - for (i = 0; i < private->data->mmsys_dev_num; i++) { - /* For device_find_child in mtk_drm_get_all_priv() */ - put_device(private->all_drm_private[i]->dev); - } put_device(private->mutex_dev); return ret; } @@ -697,18 +693,12 @@ static int mtk_drm_bind(struct device *dev) static void mtk_drm_unbind(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); - int i; /* for multi mmsys dev, unregister drm dev in mmsys master */ if (private->drm_master) { drm_dev_unregister(private->drm); mtk_drm_kms_deinit(private->drm); drm_dev_put(private->drm); - - for (i = 0; i < private->data->mmsys_dev_num; i++) { - /* For device_find_child in mtk_drm_get_all_priv() */ - put_device(private->all_drm_private[i]->dev); - } put_device(private->mutex_dev); } private->mtk_drm_bound = false; @@ -1133,7 +1123,7 @@ static int mtk_drm_probe(struct platform_device *pdev) (void *)private->mmsys_dev, sizeof(*private->mmsys_dev)); private->ddp_comp[DDP_COMPONENT_DRM_OVL_ADAPTOR].dev = &ovl_adaptor->dev; - mtk_ddp_comp_init(NULL, &private->ddp_comp[DDP_COMPONENT_DRM_OVL_ADAPTOR], + mtk_ddp_comp_init(dev, NULL, &private->ddp_comp[DDP_COMPONENT_DRM_OVL_ADAPTOR], DDP_COMPONENT_DRM_OVL_ADAPTOR); component_match_add(dev, &match, compare_dev, &ovl_adaptor->dev); } @@ -1199,7 +1189,7 @@ static int mtk_drm_probe(struct platform_device *pdev) node); } - ret = mtk_ddp_comp_init(node, &private->ddp_comp[comp_id], comp_id); + ret = mtk_ddp_comp_init(dev, node, &private->ddp_comp[comp_id], comp_id); if (ret) { of_node_put(node); goto err_node; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index b766dd5e6c8d..0face4dcaa36 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -31,6 +31,7 @@ #include #include "mtk_cec.h" +#include "mtk_hdmi_common.h" #include "mtk_hdmi_regs.h" #define NCTS_BYTES 7 @@ -43,143 +44,6 @@ enum mtk_hdmi_clk_id { MTK_HDMI_CLK_COUNT }; -enum hdmi_aud_input_type { - HDMI_AUD_INPUT_I2S = 0, - HDMI_AUD_INPUT_SPDIF, -}; - -enum hdmi_aud_i2s_fmt { - HDMI_I2S_MODE_RJT_24BIT = 0, - HDMI_I2S_MODE_RJT_16BIT, - HDMI_I2S_MODE_LJT_24BIT, - HDMI_I2S_MODE_LJT_16BIT, - HDMI_I2S_MODE_I2S_24BIT, - HDMI_I2S_MODE_I2S_16BIT -}; - -enum hdmi_aud_mclk { - HDMI_AUD_MCLK_128FS, - HDMI_AUD_MCLK_192FS, - HDMI_AUD_MCLK_256FS, - HDMI_AUD_MCLK_384FS, - HDMI_AUD_MCLK_512FS, - HDMI_AUD_MCLK_768FS, - HDMI_AUD_MCLK_1152FS, -}; - -enum hdmi_aud_channel_type { - HDMI_AUD_CHAN_TYPE_1_0 = 0, - HDMI_AUD_CHAN_TYPE_1_1, - HDMI_AUD_CHAN_TYPE_2_0, - HDMI_AUD_CHAN_TYPE_2_1, - HDMI_AUD_CHAN_TYPE_3_0, - HDMI_AUD_CHAN_TYPE_3_1, - HDMI_AUD_CHAN_TYPE_4_0, - HDMI_AUD_CHAN_TYPE_4_1, - HDMI_AUD_CHAN_TYPE_5_0, - HDMI_AUD_CHAN_TYPE_5_1, - HDMI_AUD_CHAN_TYPE_6_0, - HDMI_AUD_CHAN_TYPE_6_1, - HDMI_AUD_CHAN_TYPE_7_0, - HDMI_AUD_CHAN_TYPE_7_1, - HDMI_AUD_CHAN_TYPE_3_0_LRS, - HDMI_AUD_CHAN_TYPE_3_1_LRS, - HDMI_AUD_CHAN_TYPE_4_0_CLRS, - HDMI_AUD_CHAN_TYPE_4_1_CLRS, - HDMI_AUD_CHAN_TYPE_6_1_CS, - HDMI_AUD_CHAN_TYPE_6_1_CH, - HDMI_AUD_CHAN_TYPE_6_1_OH, - HDMI_AUD_CHAN_TYPE_6_1_CHR, - HDMI_AUD_CHAN_TYPE_7_1_LH_RH, - HDMI_AUD_CHAN_TYPE_7_1_LSR_RSR, - HDMI_AUD_CHAN_TYPE_7_1_LC_RC, - HDMI_AUD_CHAN_TYPE_7_1_LW_RW, - HDMI_AUD_CHAN_TYPE_7_1_LSD_RSD, - HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS, - HDMI_AUD_CHAN_TYPE_7_1_LHS_RHS, - HDMI_AUD_CHAN_TYPE_7_1_CS_CH, - HDMI_AUD_CHAN_TYPE_7_1_CS_OH, - HDMI_AUD_CHAN_TYPE_7_1_CS_CHR, - HDMI_AUD_CHAN_TYPE_7_1_CH_OH, - HDMI_AUD_CHAN_TYPE_7_1_CH_CHR, - HDMI_AUD_CHAN_TYPE_7_1_OH_CHR, - HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS_LSR_RSR, - HDMI_AUD_CHAN_TYPE_6_0_CS, - HDMI_AUD_CHAN_TYPE_6_0_CH, - HDMI_AUD_CHAN_TYPE_6_0_OH, - HDMI_AUD_CHAN_TYPE_6_0_CHR, - HDMI_AUD_CHAN_TYPE_7_0_LH_RH, - HDMI_AUD_CHAN_TYPE_7_0_LSR_RSR, - HDMI_AUD_CHAN_TYPE_7_0_LC_RC, - HDMI_AUD_CHAN_TYPE_7_0_LW_RW, - HDMI_AUD_CHAN_TYPE_7_0_LSD_RSD, - HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS, - HDMI_AUD_CHAN_TYPE_7_0_LHS_RHS, - HDMI_AUD_CHAN_TYPE_7_0_CS_CH, - HDMI_AUD_CHAN_TYPE_7_0_CS_OH, - HDMI_AUD_CHAN_TYPE_7_0_CS_CHR, - HDMI_AUD_CHAN_TYPE_7_0_CH_OH, - HDMI_AUD_CHAN_TYPE_7_0_CH_CHR, - HDMI_AUD_CHAN_TYPE_7_0_OH_CHR, - HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS_LSR_RSR, - HDMI_AUD_CHAN_TYPE_8_0_LH_RH_CS, - HDMI_AUD_CHAN_TYPE_UNKNOWN = 0xFF -}; - -enum hdmi_aud_channel_swap_type { - HDMI_AUD_SWAP_LR, - HDMI_AUD_SWAP_LFE_CC, - HDMI_AUD_SWAP_LSRS, - HDMI_AUD_SWAP_RLS_RRS, - HDMI_AUD_SWAP_LR_STATUS, -}; - -struct hdmi_audio_param { - enum hdmi_audio_coding_type aud_codec; - enum hdmi_audio_sample_size aud_sample_size; - enum hdmi_aud_input_type aud_input_type; - enum hdmi_aud_i2s_fmt aud_i2s_fmt; - enum hdmi_aud_mclk aud_mclk; - enum hdmi_aud_channel_type aud_input_chan_type; - struct hdmi_codec_params codec_params; -}; - -struct mtk_hdmi_conf { - bool tz_disabled; - bool cea_modes_only; - unsigned long max_mode_clock; -}; - -struct mtk_hdmi { - struct drm_bridge bridge; - struct drm_bridge *next_bridge; - struct drm_connector *curr_conn;/* current connector (only valid when 'enabled') */ - struct device *dev; - const struct mtk_hdmi_conf *conf; - struct phy *phy; - struct device *cec_dev; - struct i2c_adapter *ddc_adpt; - struct clk *clk[MTK_HDMI_CLK_COUNT]; - struct drm_display_mode mode; - bool dvi_mode; - struct regmap *sys_regmap; - unsigned int sys_offset; - struct regmap *regs; - struct platform_device *audio_pdev; - struct hdmi_audio_param aud_param; - bool audio_enable; - bool powered; - bool enabled; - hdmi_codec_plugged_cb plugged_cb; - struct device *codec_dev; - struct mutex update_plugged_status_lock; -}; - -static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b) -{ - return container_of(b, struct mtk_hdmi, bridge); -} - static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black) { regmap_update_bits(hdmi->regs, VIDEO_CFG_4, @@ -600,88 +464,6 @@ static void mtk_hdmi_hw_aud_set_mclk(struct mtk_hdmi *hdmi, regmap_write(hdmi->regs, GRL_CFG5, val); } -struct hdmi_acr_n { - unsigned int clock; - unsigned int n[3]; -}; - -/* Recommended N values from HDMI specification, tables 7-1 to 7-3 */ -static const struct hdmi_acr_n hdmi_rec_n_table[] = { - /* Clock, N: 32kHz 44.1kHz 48kHz */ - { 25175, { 4576, 7007, 6864 } }, - { 74176, { 11648, 17836, 11648 } }, - { 148352, { 11648, 8918, 5824 } }, - { 296703, { 5824, 4459, 5824 } }, - { 297000, { 3072, 4704, 5120 } }, - { 0, { 4096, 6272, 6144 } }, /* all other TMDS clocks */ -}; - -/** - * hdmi_recommended_n() - Return N value recommended by HDMI specification - * @freq: audio sample rate in Hz - * @clock: rounded TMDS clock in kHz - */ -static unsigned int hdmi_recommended_n(unsigned int freq, unsigned int clock) -{ - const struct hdmi_acr_n *recommended; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(hdmi_rec_n_table) - 1; i++) { - if (clock == hdmi_rec_n_table[i].clock) - break; - } - recommended = hdmi_rec_n_table + i; - - switch (freq) { - case 32000: - return recommended->n[0]; - case 44100: - return recommended->n[1]; - case 48000: - return recommended->n[2]; - case 88200: - return recommended->n[1] * 2; - case 96000: - return recommended->n[2] * 2; - case 176400: - return recommended->n[1] * 4; - case 192000: - return recommended->n[2] * 4; - default: - return (128 * freq) / 1000; - } -} - -static unsigned int hdmi_mode_clock_to_hz(unsigned int clock) -{ - switch (clock) { - case 25175: - return 25174825; /* 25.2/1.001 MHz */ - case 74176: - return 74175824; /* 74.25/1.001 MHz */ - case 148352: - return 148351648; /* 148.5/1.001 MHz */ - case 296703: - return 296703297; /* 297/1.001 MHz */ - default: - return clock * 1000; - } -} - -static unsigned int hdmi_expected_cts(unsigned int audio_sample_rate, - unsigned int tmds_clock, unsigned int n) -{ - return DIV_ROUND_CLOSEST_ULL((u64)hdmi_mode_clock_to_hz(tmds_clock) * n, - 128 * audio_sample_rate); -} - -static void mtk_hdmi_get_ncts(unsigned int sample_rate, unsigned int clock, - unsigned int *n, unsigned int *cts) -{ - *n = hdmi_recommended_n(sample_rate, clock); - *cts = hdmi_expected_cts(sample_rate, clock, *n); -} - static void do_hdmi_hw_aud_set_ncts(struct mtk_hdmi *hdmi, unsigned int n, unsigned int cts) { @@ -1072,20 +854,6 @@ static const char * const mtk_hdmi_clk_names[MTK_HDMI_CLK_COUNT] = { [MTK_HDMI_CLK_AUD_SPDIF] = "spdif", }; -static int mtk_hdmi_get_all_clk(struct mtk_hdmi *hdmi, - struct device_node *np) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mtk_hdmi_clk_names); i++) { - hdmi->clk[i] = of_clk_get_by_name(np, - mtk_hdmi_clk_names[i]); - if (IS_ERR(hdmi->clk[i])) - return PTR_ERR(hdmi->clk[i]); - } - return 0; -} - static int mtk_hdmi_clk_enable_audio(struct mtk_hdmi *hdmi) { int ret; @@ -1230,13 +998,6 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge, return 0; } -static bool mtk_hdmi_bridge_mode_fixup(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - return true; -} - static void mtk_hdmi_bridge_atomic_disable(struct drm_bridge *bridge, struct drm_atomic_state *state) { @@ -1268,28 +1029,6 @@ static void mtk_hdmi_bridge_atomic_post_disable(struct drm_bridge *bridge, hdmi->powered = false; } -static void mtk_hdmi_bridge_mode_set(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adjusted_mode) -{ - struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); - - dev_dbg(hdmi->dev, "cur info: name:%s, hdisplay:%d\n", - adjusted_mode->name, adjusted_mode->hdisplay); - dev_dbg(hdmi->dev, "hsync_start:%d,hsync_end:%d, htotal:%d", - adjusted_mode->hsync_start, adjusted_mode->hsync_end, - adjusted_mode->htotal); - dev_dbg(hdmi->dev, "hskew:%d, vdisplay:%d\n", - adjusted_mode->hskew, adjusted_mode->vdisplay); - dev_dbg(hdmi->dev, "vsync_start:%d, vsync_end:%d, vtotal:%d", - adjusted_mode->vsync_start, adjusted_mode->vsync_end, - adjusted_mode->vtotal); - dev_dbg(hdmi->dev, "vscan:%d, flag:%d\n", - adjusted_mode->vscan, adjusted_mode->flags); - - drm_mode_copy(&hdmi->mode, adjusted_mode); -} - static void mtk_hdmi_bridge_atomic_pre_enable(struct drm_bridge *bridge, struct drm_atomic_state *state) { @@ -1345,169 +1084,10 @@ static const struct drm_bridge_funcs mtk_hdmi_bridge_funcs = { .edid_read = mtk_hdmi_bridge_edid_read, }; -static int mtk_hdmi_get_cec_dev(struct mtk_hdmi *hdmi, struct device *dev, struct device_node *np) -{ - struct platform_device *cec_pdev; - struct device_node *cec_np; - int ret; - - ret = mtk_hdmi_get_all_clk(hdmi, np); - if (ret) - return dev_err_probe(dev, ret, "Failed to get clocks\n"); - - /* The CEC module handles HDMI hotplug detection */ - cec_np = of_get_compatible_child(np->parent, "mediatek,mt8173-cec"); - if (!cec_np) - return dev_err_probe(dev, -EINVAL, "Failed to find CEC node\n"); - - cec_pdev = of_find_device_by_node(cec_np); - if (!cec_pdev) { - dev_err(hdmi->dev, "Waiting for CEC device %pOF\n", - cec_np); - of_node_put(cec_np); - return -EPROBE_DEFER; - } - of_node_put(cec_np); - - /* - * The mediatek,syscon-hdmi property contains a phandle link to the - * MMSYS_CONFIG device and the register offset of the HDMI_SYS_CFG - * registers it contains. - */ - hdmi->sys_regmap = syscon_regmap_lookup_by_phandle_args(np, "mediatek,syscon-hdmi", - 1, &hdmi->sys_offset); - if (IS_ERR(hdmi->sys_regmap)) - return dev_err_probe(dev, PTR_ERR(hdmi->sys_regmap), - "Failed to get system configuration registers\n"); - - hdmi->cec_dev = &cec_pdev->dev; - return 0; -} - -static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, - struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; - struct device_node *remote, *i2c_np; - int ret; - - ret = mtk_hdmi_get_all_clk(hdmi, np); - if (ret) - return dev_err_probe(dev, ret, "Failed to get clocks\n"); - - hdmi->regs = device_node_to_regmap(dev->of_node); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); - - remote = of_graph_get_remote_node(np, 1, 0); - if (!remote) - return -EINVAL; - - if (!of_device_is_compatible(remote, "hdmi-connector")) { - hdmi->next_bridge = of_drm_find_bridge(remote); - if (!hdmi->next_bridge) { - dev_err(dev, "Waiting for external bridge\n"); - of_node_put(remote); - return -EPROBE_DEFER; - } - } - - i2c_np = of_parse_phandle(remote, "ddc-i2c-bus", 0); - of_node_put(remote); - if (!i2c_np) - return dev_err_probe(dev, -EINVAL, "No ddc-i2c-bus in connector\n"); - - hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np); - of_node_put(i2c_np); - if (!hdmi->ddc_adpt) - return dev_err_probe(dev, -EINVAL, "Failed to get ddc i2c adapter by node\n"); - - ret = mtk_hdmi_get_cec_dev(hdmi, dev, np); - if (ret) - return ret; - - return 0; -} - /* * HDMI audio codec callbacks */ -static int mtk_hdmi_audio_params(struct mtk_hdmi *hdmi, - struct hdmi_codec_daifmt *daifmt, - struct hdmi_codec_params *params) -{ - struct hdmi_audio_param aud_params = { 0 }; - unsigned int chan = params->cea.channels; - - dev_dbg(hdmi->dev, "%s: %u Hz, %d bit, %d channels\n", __func__, - params->sample_rate, params->sample_width, chan); - - if (!hdmi->bridge.encoder) - return -ENODEV; - - switch (chan) { - case 2: - aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_2_0; - break; - case 4: - aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_4_0; - break; - case 6: - aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_5_1; - break; - case 8: - aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_7_1; - break; - default: - dev_err(hdmi->dev, "channel[%d] not supported!\n", chan); - return -EINVAL; - } - - switch (params->sample_rate) { - case 32000: - case 44100: - case 48000: - case 88200: - case 96000: - case 176400: - case 192000: - break; - default: - dev_err(hdmi->dev, "rate[%d] not supported!\n", - params->sample_rate); - return -EINVAL; - } - - switch (daifmt->fmt) { - case HDMI_I2S: - aud_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; - aud_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; - aud_params.aud_input_type = HDMI_AUD_INPUT_I2S; - aud_params.aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT; - aud_params.aud_mclk = HDMI_AUD_MCLK_128FS; - break; - case HDMI_SPDIF: - aud_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; - aud_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; - aud_params.aud_input_type = HDMI_AUD_INPUT_SPDIF; - break; - default: - dev_err(hdmi->dev, "%s: Invalid DAI format %d\n", __func__, - daifmt->fmt); - return -EINVAL; - } - memcpy(&aud_params.codec_params, params, sizeof(aud_params.codec_params)); - memcpy(&hdmi->aud_param, &aud_params, sizeof(aud_params)); - - dev_dbg(hdmi->dev, "codec:%d, input:%d, channel:%d, fs:%d\n", - aud_params.aud_codec, aud_params.aud_input_type, - aud_params.aud_input_chan_type, aud_params.codec_params.sample_rate); - - return 0; -} - static int mtk_hdmi_audio_hw_params(struct device *dev, void *data, struct hdmi_codec_daifmt *daifmt, struct hdmi_codec_params *params) @@ -1555,26 +1135,6 @@ mtk_hdmi_audio_mute(struct device *dev, void *data, return 0; } -static int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size_t len) -{ - struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - - if (hdmi->enabled) - memcpy(buf, hdmi->curr_conn->eld, min(sizeof(hdmi->curr_conn->eld), len)); - else - memset(buf, 0, len); - return 0; -} - -static void mtk_hdmi_audio_set_plugged_cb(struct mtk_hdmi *hdmi, hdmi_codec_plugged_cb fn, - struct device *codec_dev) -{ - mutex_lock(&hdmi->update_plugged_status_lock); - hdmi->plugged_cb = fn; - hdmi->codec_dev = codec_dev; - mutex_unlock(&hdmi->update_plugged_status_lock); -} - static int mtk_hdmi_audio_hook_plugged_cb(struct device *dev, void *data, hdmi_codec_plugged_cb fn, struct device *codec_dev) @@ -1596,92 +1156,21 @@ static const struct hdmi_codec_ops mtk_hdmi_audio_codec_ops = { .hook_plugged_cb = mtk_hdmi_audio_hook_plugged_cb, }; -static void mtk_hdmi_unregister_audio_driver(void *data) -{ - platform_device_unregister(data); -} - -static int mtk_hdmi_register_audio_driver(struct device *dev) -{ - struct mtk_hdmi *hdmi = dev_get_drvdata(dev); - struct hdmi_audio_param *aud_param = &hdmi->aud_param; - struct hdmi_codec_pdata codec_data = { - .ops = &mtk_hdmi_audio_codec_ops, - .max_i2s_channels = 2, - .i2s = 1, - .data = hdmi, - .no_capture_mute = 1, - }; - int ret; - - aud_param->aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; - aud_param->aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; - aud_param->aud_input_type = HDMI_AUD_INPUT_I2S; - aud_param->aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT; - aud_param->aud_mclk = HDMI_AUD_MCLK_128FS; - aud_param->aud_input_chan_type = HDMI_AUD_CHAN_TYPE_2_0; - - hdmi->audio_pdev = platform_device_register_data(dev, - HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &codec_data, - sizeof(codec_data)); - if (IS_ERR(hdmi->audio_pdev)) - return PTR_ERR(hdmi->audio_pdev); - - ret = devm_add_action_or_reset(dev, mtk_hdmi_unregister_audio_driver, - hdmi->audio_pdev); - if (ret) - return ret; - - return 0; -} - static int mtk_hdmi_probe(struct platform_device *pdev) { struct mtk_hdmi *hdmi; - struct device *dev = &pdev->dev; int ret; - hdmi = devm_drm_bridge_alloc(dev, struct mtk_hdmi, bridge, - &mtk_hdmi_bridge_funcs); + hdmi = mtk_hdmi_common_probe(pdev); if (IS_ERR(hdmi)) return PTR_ERR(hdmi); - hdmi->dev = dev; - hdmi->conf = of_device_get_match_data(dev); - - ret = mtk_hdmi_dt_parse_pdata(hdmi, pdev); - if (ret) - return ret; - - hdmi->phy = devm_phy_get(dev, "hdmi"); - if (IS_ERR(hdmi->phy)) - return dev_err_probe(dev, PTR_ERR(hdmi->phy), - "Failed to get HDMI PHY\n"); - - mutex_init(&hdmi->update_plugged_status_lock); - platform_set_drvdata(pdev, hdmi); - - ret = mtk_hdmi_register_audio_driver(dev); - if (ret) - return dev_err_probe(dev, ret, - "Failed to register audio driver\n"); - - hdmi->bridge.of_node = pdev->dev.of_node; - hdmi->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID - | DRM_BRIDGE_OP_HPD; - hdmi->bridge.type = DRM_MODE_CONNECTOR_HDMIA; - hdmi->bridge.vendor = "MediaTek"; - hdmi->bridge.product = "On-Chip HDMI"; - - ret = devm_drm_bridge_add(dev, &hdmi->bridge); - if (ret) - return dev_err_probe(dev, ret, "Failed to add bridge\n"); + if (!hdmi->cec_dev) + return dev_err_probe(hdmi->dev, -ENODEV, "CEC is required by HDMIv1\n"); ret = mtk_hdmi_clk_enable_audio(hdmi); if (ret) - return dev_err_probe(dev, ret, + return dev_err_probe(hdmi->dev, ret, "Failed to enable audio clocks\n"); return 0; @@ -1712,19 +1201,32 @@ static __maybe_unused int mtk_hdmi_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(mtk_hdmi_pm_ops, mtk_hdmi_suspend, mtk_hdmi_resume); +static const struct mtk_hdmi_ver_conf mtk_hdmi_v1_ver_conf = { + .bridge_funcs = &mtk_hdmi_bridge_funcs, + .codec_ops = &mtk_hdmi_audio_codec_ops, + .mtk_hdmi_clock_names = mtk_hdmi_clk_names, + .num_clocks = ARRAY_SIZE(mtk_hdmi_clk_names) +}; + static const struct mtk_hdmi_conf mtk_hdmi_conf_mt2701 = { .tz_disabled = true, + .ver_conf = &mtk_hdmi_v1_ver_conf }; static const struct mtk_hdmi_conf mtk_hdmi_conf_mt8167 = { - .max_mode_clock = 148500, .cea_modes_only = true, + .max_mode_clock = 148500, + .ver_conf = &mtk_hdmi_v1_ver_conf +}; + +static const struct mtk_hdmi_conf mtk_hdmi_conf_mt8173 = { + .ver_conf = &mtk_hdmi_v1_ver_conf }; static const struct of_device_id mtk_hdmi_of_ids[] = { { .compatible = "mediatek,mt2701-hdmi", .data = &mtk_hdmi_conf_mt2701 }, { .compatible = "mediatek,mt8167-hdmi", .data = &mtk_hdmi_conf_mt8167 }, - { .compatible = "mediatek,mt8173-hdmi" }, + { .compatible = "mediatek,mt8173-hdmi", .data = &mtk_hdmi_conf_mt8173 }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, mtk_hdmi_of_ids); @@ -1744,3 +1246,4 @@ MODULE_AUTHOR("Jie Qiu "); MODULE_DESCRIPTION("MediaTek HDMI Driver"); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS("DRM_MTK_HDMI_V1"); +MODULE_IMPORT_NS("DRM_MTK_HDMI"); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_common.c b/drivers/gpu/drm/mediatek/mtk_hdmi_common.c new file mode 100644 index 000000000000..e78eb0876f16 --- /dev/null +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_common.c @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2014 MediaTek Inc. + * Copyright (c) 2024 Collabora Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mtk_hdmi_common.h" + +struct hdmi_acr_n { + unsigned int clock; + unsigned int n[3]; +}; + +/* Recommended N values from HDMI specification, tables 7-1 to 7-3 */ +static const struct hdmi_acr_n hdmi_rec_n_table[] = { + /* Clock, N: 32kHz 44.1kHz 48kHz */ + { 25175, { 4576, 7007, 6864 } }, + { 74176, { 11648, 17836, 11648 } }, + { 148352, { 11648, 8918, 5824 } }, + { 296703, { 5824, 4459, 5824 } }, + { 297000, { 3072, 4704, 5120 } }, + { 0, { 4096, 6272, 6144 } }, /* all other TMDS clocks */ +}; + +/** + * hdmi_recommended_n() - Return N value recommended by HDMI specification + * @freq: audio sample rate in Hz + * @clock: rounded TMDS clock in kHz + */ +static unsigned int hdmi_recommended_n(unsigned int freq, unsigned int clock) +{ + const struct hdmi_acr_n *recommended; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(hdmi_rec_n_table) - 1; i++) { + if (clock == hdmi_rec_n_table[i].clock) + break; + } + recommended = hdmi_rec_n_table + i; + + switch (freq) { + case 32000: + return recommended->n[0]; + case 44100: + return recommended->n[1]; + case 48000: + return recommended->n[2]; + case 88200: + return recommended->n[1] * 2; + case 96000: + return recommended->n[2] * 2; + case 176400: + return recommended->n[1] * 4; + case 192000: + return recommended->n[2] * 4; + default: + return (128 * freq) / 1000; + } +} + +static unsigned int hdmi_mode_clock_to_hz(unsigned int clock) +{ + switch (clock) { + case 25175: + return 25174825; /* 25.2/1.001 MHz */ + case 74176: + return 74175824; /* 74.25/1.001 MHz */ + case 148352: + return 148351648; /* 148.5/1.001 MHz */ + case 296703: + return 296703297; /* 297/1.001 MHz */ + default: + return clock * 1000; + } +} + +static unsigned int hdmi_expected_cts(unsigned int audio_sample_rate, + unsigned int tmds_clock, unsigned int n) +{ + return DIV_ROUND_CLOSEST_ULL((u64)hdmi_mode_clock_to_hz(tmds_clock) * n, + 128 * audio_sample_rate); +} + +void mtk_hdmi_get_ncts(unsigned int sample_rate, unsigned int clock, + unsigned int *n, unsigned int *cts) +{ + *n = hdmi_recommended_n(sample_rate, clock); + *cts = hdmi_expected_cts(sample_rate, clock, *n); +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_get_ncts, "DRM_MTK_HDMI"); + +int mtk_hdmi_audio_params(struct mtk_hdmi *hdmi, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) +{ + struct hdmi_audio_param aud_params = { 0 }; + unsigned int chan = params->cea.channels; + + dev_dbg(hdmi->dev, "%s: %u Hz, %d bit, %d channels\n", __func__, + params->sample_rate, params->sample_width, chan); + + if (!hdmi->bridge.encoder) + return -ENODEV; + + switch (chan) { + case 2: + aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_2_0; + break; + case 4: + aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_4_0; + break; + case 6: + aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_5_1; + break; + case 8: + aud_params.aud_input_chan_type = HDMI_AUD_CHAN_TYPE_7_1; + break; + default: + dev_err(hdmi->dev, "channel[%d] not supported!\n", chan); + return -EINVAL; + } + + switch (params->sample_rate) { + case 32000: + case 44100: + case 48000: + case 88200: + case 96000: + case 176400: + case 192000: + break; + default: + dev_err(hdmi->dev, "rate[%d] not supported!\n", + params->sample_rate); + return -EINVAL; + } + + switch (daifmt->fmt) { + case HDMI_I2S: + aud_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; + aud_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; + aud_params.aud_input_type = HDMI_AUD_INPUT_I2S; + aud_params.aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT; + aud_params.aud_mclk = HDMI_AUD_MCLK_128FS; + break; + case HDMI_SPDIF: + aud_params.aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; + aud_params.aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; + aud_params.aud_input_type = HDMI_AUD_INPUT_SPDIF; + break; + default: + dev_err(hdmi->dev, "%s: Invalid DAI format %d\n", __func__, + daifmt->fmt); + return -EINVAL; + } + memcpy(&aud_params.codec_params, params, sizeof(aud_params.codec_params)); + memcpy(&hdmi->aud_param, &aud_params, sizeof(aud_params)); + + dev_dbg(hdmi->dev, "codec:%d, input:%d, channel:%d, fs:%d\n", + aud_params.aud_codec, aud_params.aud_input_type, + aud_params.aud_input_chan_type, aud_params.codec_params.sample_rate); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_audio_params, "DRM_MTK_HDMI"); + +int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size_t len) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + if (hdmi->enabled) + memcpy(buf, hdmi->curr_conn->eld, min(sizeof(hdmi->curr_conn->eld), len)); + else + memset(buf, 0, len); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_audio_get_eld, "DRM_MTK_HDMI"); + +void mtk_hdmi_audio_set_plugged_cb(struct mtk_hdmi *hdmi, hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + mutex_lock(&hdmi->update_plugged_status_lock); + hdmi->plugged_cb = fn; + hdmi->codec_dev = codec_dev; + mutex_unlock(&hdmi->update_plugged_status_lock); +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_audio_set_plugged_cb, "DRM_MTK_HDMI"); + +static int mtk_hdmi_get_all_clk(struct mtk_hdmi *hdmi, struct device_node *np, + const char * const *clock_names, size_t num_clocks) +{ + int i; + + for (i = 0; i < num_clocks; i++) { + hdmi->clk[i] = of_clk_get_by_name(np, clock_names[i]); + + if (IS_ERR(hdmi->clk[i])) + return PTR_ERR(hdmi->clk[i]); + } + + return 0; +} + +bool mtk_hdmi_bridge_mode_fixup(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + return true; +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_bridge_mode_fixup, "DRM_MTK_HDMI"); + +void mtk_hdmi_bridge_mode_set(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + dev_dbg(hdmi->dev, "cur info: name:%s, hdisplay:%d\n", + adjusted_mode->name, adjusted_mode->hdisplay); + dev_dbg(hdmi->dev, "hsync_start:%d,hsync_end:%d, htotal:%d", + adjusted_mode->hsync_start, adjusted_mode->hsync_end, + adjusted_mode->htotal); + dev_dbg(hdmi->dev, "hskew:%d, vdisplay:%d\n", + adjusted_mode->hskew, adjusted_mode->vdisplay); + dev_dbg(hdmi->dev, "vsync_start:%d, vsync_end:%d, vtotal:%d", + adjusted_mode->vsync_start, adjusted_mode->vsync_end, + adjusted_mode->vtotal); + dev_dbg(hdmi->dev, "vscan:%d, flag:%d\n", + adjusted_mode->vscan, adjusted_mode->flags); + + drm_mode_copy(&hdmi->mode, adjusted_mode); +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_bridge_mode_set, "DRM_MTK_HDMI"); + +static void mtk_hdmi_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + +static int mtk_hdmi_get_cec_dev(struct mtk_hdmi *hdmi, struct device *dev, struct device_node *np) +{ + struct platform_device *cec_pdev; + struct device_node *cec_np; + int ret; + + /* The CEC module handles HDMI hotplug detection */ + cec_np = of_get_compatible_child(np->parent, "mediatek,mt8173-cec"); + if (!cec_np) + return dev_err_probe(dev, -EOPNOTSUPP, "Failed to find CEC node\n"); + + cec_pdev = of_find_device_by_node(cec_np); + if (!cec_pdev) { + dev_err(hdmi->dev, "Waiting for CEC device %pOF\n", cec_np); + of_node_put(cec_np); + return -EPROBE_DEFER; + } + of_node_put(cec_np); + + ret = devm_add_action_or_reset(dev, mtk_hdmi_put_device, &cec_pdev->dev); + if (ret) + return ret; + + /* + * The mediatek,syscon-hdmi property contains a phandle link to the + * MMSYS_CONFIG device and the register offset of the HDMI_SYS_CFG + * registers it contains. + */ + hdmi->sys_regmap = syscon_regmap_lookup_by_phandle_args(np, "mediatek,syscon-hdmi", + 1, &hdmi->sys_offset); + if (IS_ERR(hdmi->sys_regmap)) + return dev_err_probe(dev, PTR_ERR(hdmi->sys_regmap), + "Failed to get system configuration registers\n"); + + hdmi->cec_dev = &cec_pdev->dev; + return 0; +} + +static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, struct platform_device *pdev, + const char * const *clk_names, size_t num_clocks) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct device_node *remote, *i2c_np; + int ret; + + ret = mtk_hdmi_get_all_clk(hdmi, np, clk_names, num_clocks); + if (ret) + return dev_err_probe(dev, ret, "Failed to get clocks\n"); + + hdmi->irq = platform_get_irq(pdev, 0); + if (!hdmi->irq) + return hdmi->irq; + + hdmi->regs = device_node_to_regmap(dev->of_node); + if (IS_ERR(hdmi->regs)) + return PTR_ERR(hdmi->regs); + + remote = of_graph_get_remote_node(np, 1, 0); + if (!remote) + return -EINVAL; + + if (!of_device_is_compatible(remote, "hdmi-connector")) { + hdmi->next_bridge = of_drm_find_bridge(remote); + if (!hdmi->next_bridge) { + dev_err(dev, "Waiting for external bridge\n"); + of_node_put(remote); + return -EPROBE_DEFER; + } + } + + i2c_np = of_parse_phandle(remote, "ddc-i2c-bus", 0); + of_node_put(remote); + if (!i2c_np) + return dev_err_probe(dev, -EINVAL, "No ddc-i2c-bus in connector\n"); + + hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np); + of_node_put(i2c_np); + if (!hdmi->ddc_adpt) + return dev_err_probe(dev, -EPROBE_DEFER, "Failed to get ddc i2c adapter by node\n"); + + ret = devm_add_action_or_reset(dev, mtk_hdmi_put_device, &hdmi->ddc_adpt->dev); + if (ret) + return ret; + + ret = mtk_hdmi_get_cec_dev(hdmi, dev, np); + if (ret == -EOPNOTSUPP) + dev_info(dev, "CEC support unavailable: node not found\n"); + else if (ret) + return ret; + + return 0; +} + +static void mtk_hdmi_unregister_audio_driver(void *data) +{ + platform_device_unregister(data); +} + +static int mtk_hdmi_register_audio_driver(struct device *dev) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + struct hdmi_audio_param *aud_param = &hdmi->aud_param; + struct hdmi_codec_pdata codec_data = { + .ops = hdmi->conf->ver_conf->codec_ops, + .max_i2s_channels = 2, + .i2s = 1, + .data = hdmi, + .no_capture_mute = 1, + }; + int ret; + + aud_param->aud_codec = HDMI_AUDIO_CODING_TYPE_PCM; + aud_param->aud_sample_size = HDMI_AUDIO_SAMPLE_SIZE_16; + aud_param->aud_input_type = HDMI_AUD_INPUT_I2S; + aud_param->aud_i2s_fmt = HDMI_I2S_MODE_I2S_24BIT; + aud_param->aud_mclk = HDMI_AUD_MCLK_128FS; + aud_param->aud_input_chan_type = HDMI_AUD_CHAN_TYPE_2_0; + + hdmi->audio_pdev = platform_device_register_data(dev, + HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &codec_data, + sizeof(codec_data)); + if (IS_ERR(hdmi->audio_pdev)) + return PTR_ERR(hdmi->audio_pdev); + + ret = devm_add_action_or_reset(dev, mtk_hdmi_unregister_audio_driver, + hdmi->audio_pdev); + if (ret) + return ret; + + return 0; +} + +struct mtk_hdmi *mtk_hdmi_common_probe(struct platform_device *pdev) +{ + const struct mtk_hdmi_ver_conf *ver_conf; + const struct mtk_hdmi_conf *hdmi_conf; + struct device *dev = &pdev->dev; + struct mtk_hdmi *hdmi; + int ret; + + hdmi_conf = of_device_get_match_data(dev); + if (!hdmi_conf) + return ERR_PTR(-ENODEV); + + ver_conf = hdmi_conf->ver_conf; + + hdmi = devm_drm_bridge_alloc(dev, struct mtk_hdmi, bridge, + ver_conf->bridge_funcs); + if (IS_ERR(hdmi)) + return hdmi; + + hdmi->dev = dev; + hdmi->conf = hdmi_conf; + + hdmi->clk = devm_kcalloc(dev, ver_conf->num_clocks, sizeof(*hdmi->clk), GFP_KERNEL); + if (!hdmi->clk) + return ERR_PTR(-ENOMEM); + + ret = mtk_hdmi_dt_parse_pdata(hdmi, pdev, ver_conf->mtk_hdmi_clock_names, + ver_conf->num_clocks); + if (ret) + return ERR_PTR(ret); + + hdmi->phy = devm_phy_get(dev, "hdmi"); + if (IS_ERR(hdmi->phy)) + return dev_err_cast_probe(dev, hdmi->phy, "Failed to get HDMI PHY\n"); + + mutex_init(&hdmi->update_plugged_status_lock); + platform_set_drvdata(pdev, hdmi); + + ret = mtk_hdmi_register_audio_driver(dev); + if (ret) + return dev_err_ptr_probe(dev, ret, "Cannot register HDMI Audio driver\n"); + + hdmi->bridge.of_node = pdev->dev.of_node; + hdmi->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID + | DRM_BRIDGE_OP_HPD; + + if (ver_conf->bridge_funcs->hdmi_write_infoframe && + ver_conf->bridge_funcs->hdmi_clear_infoframe) + hdmi->bridge.ops |= DRM_BRIDGE_OP_HDMI; + + hdmi->bridge.type = DRM_MODE_CONNECTOR_HDMIA; + hdmi->bridge.ddc = hdmi->ddc_adpt; + hdmi->bridge.vendor = "MediaTek"; + hdmi->bridge.product = "On-Chip HDMI"; + hdmi->bridge.interlace_allowed = ver_conf->interlace_allowed; + + ret = devm_drm_bridge_add(dev, &hdmi->bridge); + if (ret) + return dev_err_ptr_probe(dev, ret, "Failed to add bridge\n"); + + return hdmi; +} +EXPORT_SYMBOL_NS_GPL(mtk_hdmi_common_probe, "DRM_MTK_HDMI"); + +MODULE_AUTHOR("AngeloGioacchino Del Regno "); +MODULE_DESCRIPTION("MediaTek HDMI Common Library"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_common.h b/drivers/gpu/drm/mediatek/mtk_hdmi_common.h new file mode 100644 index 000000000000..de5e064585f8 --- /dev/null +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_common.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + * Copyright (c) 2024 Collabora Ltd. + */ + +#ifndef _MTK_HDMI_COMMON_H +#define _MTK_HDMI_COMMON_H + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +enum hdmi_aud_input_type { + HDMI_AUD_INPUT_I2S = 0, + HDMI_AUD_INPUT_SPDIF, +}; + +enum hdmi_aud_i2s_fmt { + HDMI_I2S_MODE_RJT_24BIT = 0, + HDMI_I2S_MODE_RJT_16BIT, + HDMI_I2S_MODE_LJT_24BIT, + HDMI_I2S_MODE_LJT_16BIT, + HDMI_I2S_MODE_I2S_24BIT, + HDMI_I2S_MODE_I2S_16BIT +}; + +enum hdmi_aud_mclk { + HDMI_AUD_MCLK_128FS, + HDMI_AUD_MCLK_192FS, + HDMI_AUD_MCLK_256FS, + HDMI_AUD_MCLK_384FS, + HDMI_AUD_MCLK_512FS, + HDMI_AUD_MCLK_768FS, + HDMI_AUD_MCLK_1152FS, +}; + +enum hdmi_aud_channel_type { + HDMI_AUD_CHAN_TYPE_1_0 = 0, + HDMI_AUD_CHAN_TYPE_1_1, + HDMI_AUD_CHAN_TYPE_2_0, + HDMI_AUD_CHAN_TYPE_2_1, + HDMI_AUD_CHAN_TYPE_3_0, + HDMI_AUD_CHAN_TYPE_3_1, + HDMI_AUD_CHAN_TYPE_4_0, + HDMI_AUD_CHAN_TYPE_4_1, + HDMI_AUD_CHAN_TYPE_5_0, + HDMI_AUD_CHAN_TYPE_5_1, + HDMI_AUD_CHAN_TYPE_6_0, + HDMI_AUD_CHAN_TYPE_6_1, + HDMI_AUD_CHAN_TYPE_7_0, + HDMI_AUD_CHAN_TYPE_7_1, + HDMI_AUD_CHAN_TYPE_3_0_LRS, + HDMI_AUD_CHAN_TYPE_3_1_LRS, + HDMI_AUD_CHAN_TYPE_4_0_CLRS, + HDMI_AUD_CHAN_TYPE_4_1_CLRS, + HDMI_AUD_CHAN_TYPE_6_1_CS, + HDMI_AUD_CHAN_TYPE_6_1_CH, + HDMI_AUD_CHAN_TYPE_6_1_OH, + HDMI_AUD_CHAN_TYPE_6_1_CHR, + HDMI_AUD_CHAN_TYPE_7_1_LH_RH, + HDMI_AUD_CHAN_TYPE_7_1_LSR_RSR, + HDMI_AUD_CHAN_TYPE_7_1_LC_RC, + HDMI_AUD_CHAN_TYPE_7_1_LW_RW, + HDMI_AUD_CHAN_TYPE_7_1_LSD_RSD, + HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS, + HDMI_AUD_CHAN_TYPE_7_1_LHS_RHS, + HDMI_AUD_CHAN_TYPE_7_1_CS_CH, + HDMI_AUD_CHAN_TYPE_7_1_CS_OH, + HDMI_AUD_CHAN_TYPE_7_1_CS_CHR, + HDMI_AUD_CHAN_TYPE_7_1_CH_OH, + HDMI_AUD_CHAN_TYPE_7_1_CH_CHR, + HDMI_AUD_CHAN_TYPE_7_1_OH_CHR, + HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS_LSR_RSR, + HDMI_AUD_CHAN_TYPE_6_0_CS, + HDMI_AUD_CHAN_TYPE_6_0_CH, + HDMI_AUD_CHAN_TYPE_6_0_OH, + HDMI_AUD_CHAN_TYPE_6_0_CHR, + HDMI_AUD_CHAN_TYPE_7_0_LH_RH, + HDMI_AUD_CHAN_TYPE_7_0_LSR_RSR, + HDMI_AUD_CHAN_TYPE_7_0_LC_RC, + HDMI_AUD_CHAN_TYPE_7_0_LW_RW, + HDMI_AUD_CHAN_TYPE_7_0_LSD_RSD, + HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS, + HDMI_AUD_CHAN_TYPE_7_0_LHS_RHS, + HDMI_AUD_CHAN_TYPE_7_0_CS_CH, + HDMI_AUD_CHAN_TYPE_7_0_CS_OH, + HDMI_AUD_CHAN_TYPE_7_0_CS_CHR, + HDMI_AUD_CHAN_TYPE_7_0_CH_OH, + HDMI_AUD_CHAN_TYPE_7_0_CH_CHR, + HDMI_AUD_CHAN_TYPE_7_0_OH_CHR, + HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS_LSR_RSR, + HDMI_AUD_CHAN_TYPE_8_0_LH_RH_CS, + HDMI_AUD_CHAN_TYPE_UNKNOWN = 0xFF +}; + +enum hdmi_aud_channel_swap_type { + HDMI_AUD_SWAP_LR, + HDMI_AUD_SWAP_LFE_CC, + HDMI_AUD_SWAP_LSRS, + HDMI_AUD_SWAP_RLS_RRS, + HDMI_AUD_SWAP_LR_STATUS, +}; + +struct hdmi_audio_param { + enum hdmi_audio_coding_type aud_codec; + enum hdmi_audio_sample_size aud_sample_size; + enum hdmi_aud_input_type aud_input_type; + enum hdmi_aud_i2s_fmt aud_i2s_fmt; + enum hdmi_aud_mclk aud_mclk; + enum hdmi_aud_channel_type aud_input_chan_type; + struct hdmi_codec_params codec_params; +}; + +enum hdmi_hpd_state { + HDMI_PLUG_OUT = 0, + HDMI_PLUG_IN_AND_SINK_POWER_ON, + HDMI_PLUG_IN_ONLY, +}; + +struct mtk_hdmi_ver_conf { + const struct drm_bridge_funcs *bridge_funcs; + const struct hdmi_codec_ops *codec_ops; + const char * const *mtk_hdmi_clock_names; + int num_clocks; + bool interlace_allowed; +}; + +struct mtk_hdmi_conf { + const struct mtk_hdmi_ver_conf *ver_conf; + bool tz_disabled; + bool cea_modes_only; + unsigned long max_mode_clock; + u32 reg_hdmi_tx_cfg; +}; + +struct mtk_hdmi { + struct drm_bridge bridge; + struct drm_bridge *next_bridge; + struct drm_connector *curr_conn;/* current connector (only valid when 'enabled') */ + struct device *dev; + const struct mtk_hdmi_conf *conf; + struct phy *phy; + struct device *cec_dev; + struct i2c_adapter *ddc_adpt; + struct clk **clk; + struct drm_display_mode mode; + bool dvi_mode; + struct regmap *sys_regmap; + unsigned int sys_offset; + struct regmap *regs; + struct platform_device *audio_pdev; + struct hdmi_audio_param aud_param; + bool audio_enable; + bool powered; + bool enabled; + unsigned int irq; + enum hdmi_hpd_state hpd; + hdmi_codec_plugged_cb plugged_cb; + struct device *codec_dev; + struct mutex update_plugged_status_lock; +}; + +static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b) +{ + return container_of(b, struct mtk_hdmi, bridge); +} + + +int mtk_hdmi_audio_get_eld(struct device *dev, void *data, uint8_t *buf, size_t len); +void mtk_hdmi_audio_set_plugged_cb(struct mtk_hdmi *hdmi, hdmi_codec_plugged_cb fn, + struct device *codec_dev); +int mtk_hdmi_audio_params(struct mtk_hdmi *hdmi, struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params); +void mtk_hdmi_get_ncts(unsigned int sample_rate, unsigned int clock, + unsigned int *n, unsigned int *cts); +bool mtk_hdmi_bridge_mode_fixup(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); +void mtk_hdmi_bridge_mode_set(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode); +struct mtk_hdmi *mtk_hdmi_common_probe(struct platform_device *pdev); +#endif /* _MTK_HDMI_COMMON_H */ diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c new file mode 100644 index 000000000000..b844e2c10f28 --- /dev/null +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c @@ -0,0 +1,396 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MediaTek HDMI v2 Display Data Channel Driver + * + * Copyright (c) 2021 MediaTek Inc. + * Copyright (c) 2021 BayLibre, SAS + * Copyright (c) 2024 Collabora Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "mtk_hdmi_common.h" +#include "mtk_hdmi_regs_v2.h" + +#define DDC2_DLY_CNT 572 /* BIM=208M/(v*4) = 90Khz */ +#define DDC2_DLY_CNT_EDID 832 /* BIM=208M/(v*4) = 62.5Khz */ +#define SI2C_ADDR_READ 0xf4 +#define SCDC_I2C_SLAVE_ADDRESS 0x54 + +struct mtk_hdmi_ddc { + struct device *dev; + struct regmap *regs; + struct clk *clk; + struct i2c_adapter adap; +}; + +static int mtk_ddc_check_and_rise_low_bus(struct mtk_hdmi_ddc *ddc) +{ + u32 val; + + regmap_read(ddc->regs, HDCP2X_DDCM_STATUS, &val); + if (val & DDC_I2C_BUS_LOW) { + regmap_update_bits(ddc->regs, DDC_CTRL, DDC_CTRL_CMD, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_CLOCK_SCL)); + usleep_range(250, 300); + } + + if (val & DDC_I2C_NO_ACK) { + u32 ddc_ctrl, hpd_ddc_ctrl, hpd_ddc_status; + + regmap_read(ddc->regs, DDC_CTRL, &ddc_ctrl); + regmap_read(ddc->regs, HPD_DDC_CTRL, &hpd_ddc_ctrl); + regmap_read(ddc->regs, HPD_DDC_STATUS, &hpd_ddc_status); + } + + if (val & DDC_I2C_NO_ACK) + return -EIO; + + return 0; +} + +static int mtk_ddc_wr_one(struct mtk_hdmi_ddc *ddc, u16 addr_id, + u16 offset_id, u8 *wr_data) +{ + u32 val; + int ret; + + /* If down, rise bus for write operation */ + mtk_ddc_check_and_rise_low_bus(ddc); + + regmap_update_bits(ddc->regs, HPD_DDC_CTRL, HPD_DDC_DELAY_CNT, + FIELD_PREP(HPD_DDC_DELAY_CNT, DDC2_DLY_CNT)); + + if (wr_data) { + regmap_write(ddc->regs, SI2C_CTRL, + FIELD_PREP(SI2C_ADDR, SI2C_ADDR_READ) | + FIELD_PREP(SI2C_WDATA, *wr_data) | + SI2C_WR); + } + + regmap_write(ddc->regs, DDC_CTRL, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_SEQ_WRITE) | + FIELD_PREP(DDC_CTRL_DIN_CNT, wr_data == NULL ? 0 : 1) | + FIELD_PREP(DDC_CTRL_OFFSET, offset_id) | + FIELD_PREP(DDC_CTRL_ADDR, addr_id)); + usleep_range(1000, 1250); + + ret = regmap_read_poll_timeout(ddc->regs, HPD_DDC_STATUS, val, + !(val & DDC_I2C_IN_PROG), 500, 1000); + if (ret) { + dev_err(ddc->dev, "DDC I2C write timeout\n"); + return ret; + } + + /* The I2C bus might be down after WR operation: rise it again */ + ret = mtk_ddc_check_and_rise_low_bus(ddc); + if (ret) { + dev_err(ddc->dev, "Error during write operation: No ACK\n"); + return ret; + } + + return 0; +} + +static int mtk_ddcm_read_hdmi(struct mtk_hdmi_ddc *ddc, u16 uc_dev, + u8 addr, u8 *puc_value, u16 data_cnt) +{ + u16 dly_cnt, i, uc_idx; + u32 rem, temp_length, uc_read_count, val; + u64 loop_counter; + int ret; + + mtk_ddc_check_and_rise_low_bus(ddc); + + regmap_update_bits(ddc->regs, DDC_CTRL, DDC_CTRL_CMD, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_CLEAR_FIFO)); + + if (data_cnt >= 16) { + temp_length = 16; + loop_counter = data_cnt; + + rem = do_div(loop_counter, temp_length); + if (rem) + loop_counter++; + } else { + temp_length = data_cnt; + loop_counter = 1; + } + + if (uc_dev >= DDC_ADDR) + dly_cnt = DDC2_DLY_CNT_EDID; + else + dly_cnt = DDC2_DLY_CNT; + + regmap_update_bits(ddc->regs, HPD_DDC_CTRL, HPD_DDC_DELAY_CNT, + FIELD_PREP(HPD_DDC_DELAY_CNT, dly_cnt)); + + for (i = 0; i < loop_counter; i++) { + rem = data_cnt % 16; + + if (i > 0 && i == (loop_counter - 1) && rem) + temp_length = rem; + + /* 0x51 - 0x53: Flow control */ + if (uc_dev > DDC_ADDR && uc_dev <= 0x53) { + regmap_update_bits(ddc->regs, SCDC_CTRL, SCDC_DDC_SEGMENT, + FIELD_PREP(SCDC_DDC_SEGMENT, uc_dev - DDC_ADDR)); + + regmap_write(ddc->regs, DDC_CTRL, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_ENH_READ_NOACK) | + FIELD_PREP(DDC_CTRL_DIN_CNT, temp_length) | + FIELD_PREP(DDC_CTRL_OFFSET, addr + i * temp_length) | + FIELD_PREP(DDC_CTRL_ADDR, DDC_ADDR)); + } else { + u16 offset; + + if (addr != 0x43) + offset = i * 16; + else + offset = 0; + + regmap_write(ddc->regs, DDC_CTRL, + FIELD_PREP(DDC_CTRL_CMD, DDC_CMD_SEQ_READ_NOACK) | + FIELD_PREP(DDC_CTRL_DIN_CNT, temp_length) | + FIELD_PREP(DDC_CTRL_OFFSET, addr + offset) | + FIELD_PREP(DDC_CTRL_ADDR, uc_dev)); + } + usleep_range(5000, 5500); + + ret = regmap_read_poll_timeout(ddc->regs, HPD_DDC_STATUS, val, + !(val & DDC_I2C_IN_PROG), 1000, + 500 * (temp_length + 5)); + if (ret) { + dev_err(ddc->dev, "Timeout waiting for DDC I2C\n"); + return ret; + } + + ret = mtk_ddc_check_and_rise_low_bus(ddc); + if (ret) { + dev_err(ddc->dev, "Error during read operation: No ACK\n"); + return ret; + } + + for (uc_idx = 0; uc_idx < temp_length; uc_idx++) { + unsigned int read_idx = i * 16 + uc_idx; + + regmap_write(ddc->regs, SI2C_CTRL, + FIELD_PREP(SI2C_ADDR, SI2C_ADDR_READ) | + SI2C_RD); + + regmap_read(ddc->regs, HPD_DDC_STATUS, &val); + puc_value[read_idx] = FIELD_GET(DDC_DATA_OUT, val); + + regmap_write(ddc->regs, SI2C_CTRL, + FIELD_PREP(SI2C_ADDR, SI2C_ADDR_READ) | + SI2C_CONFIRM_READ); + + /* + * If HDMI IP gets reset during EDID read, DDC read + * operation will fail and its delay counter will be + * reset to 400. + */ + regmap_read(ddc->regs, HPD_DDC_CTRL, &val); + if (FIELD_GET(HPD_DDC_DELAY_CNT, val) < DDC2_DLY_CNT) + return 0; + + uc_read_count = read_idx + 1; + } + } + if (uc_read_count > U8_MAX) + dev_warn(ddc->dev, "Invalid read data count %u\n", uc_read_count); + + return uc_read_count; +} + +static int mtk_hdmi_fg_ddc_data_read(struct mtk_hdmi_ddc *ddc, u16 b_dev, + u8 data_addr, u16 data_cnt, u8 *pr_data) +{ + int read_data_cnt; + u16 req_data_cnt; + + if (!data_cnt) { + dev_err(ddc->dev, "Invalid DDCM read request\n"); + return -EINVAL; + } + + req_data_cnt = U8_MAX - data_addr + 1; + if (req_data_cnt > data_cnt) + req_data_cnt = data_cnt; + + regmap_set_bits(ddc->regs, HDCP2X_POL_CTRL, HDCP2X_DIS_POLL_EN); + + read_data_cnt = mtk_ddcm_read_hdmi(ddc, b_dev, data_addr, pr_data, req_data_cnt); + + if (read_data_cnt < 0) + return read_data_cnt; + else if (read_data_cnt != req_data_cnt) + return -EINVAL; + + return 0; +} + +static int mtk_hdmi_ddc_fg_data_write(struct mtk_hdmi_ddc *ddc, u16 b_dev, + u8 data_addr, u16 data_cnt, u8 *pr_data) +{ + int i, ret; + + regmap_set_bits(ddc->regs, HDCP2X_POL_CTRL, HDCP2X_DIS_POLL_EN); + /* + * In case there is no payload data, just do a single write for the + * address only + */ + if (data_cnt == 0) + return mtk_ddc_wr_one(ddc, b_dev, data_addr, NULL); + + i = 0; + do { + ret = mtk_ddc_wr_one(ddc, b_dev, data_addr + i, pr_data + i); + if (ret) + return ret; + } while (++i < data_cnt); + + return 0; +} + +static int mtk_hdmi_ddc_v2_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num) +{ + struct mtk_hdmi_ddc *ddc; + u8 offset = 0; + int i, ret; + + ddc = adapter->algo_data; + + for (i = 0; i < num; i++) { + struct i2c_msg *msg = &msgs[i]; + + if (!msg->buf) { + dev_err(ddc->dev, "No message buffer\n"); + return -EINVAL; + } + + if (msg->flags & I2C_M_RD) { + /* + * The underlying DDC hardware always issues a write request + * that assigns the read offset as part of the read operation, + * therefore, use the `offset` value assigned in the previous + * write request from drm_edid + */ + ret = mtk_hdmi_fg_ddc_data_read(ddc, msg->addr, offset, + msg->len, &msg->buf[0]); + if (ret) + return ret; + } else { + /* + * The HW needs the data offset, found in buf[0], in the + * DDC_CTRL register, and each byte of data, starting at + * buf[1], goes in the SI2C_WDATA register. + */ + ret = mtk_hdmi_ddc_fg_data_write(ddc, msg->addr, msg->buf[0], + msg->len - 1, &msg->buf[1]); + if (ret) + return ret; + + /* + * Store the offset value requested by drm_edid or by + * scdc to use in subsequent read requests. + */ + if ((msg->addr == DDC_ADDR || msg->addr == SCDC_I2C_SLAVE_ADDRESS) && + msg->len == 1) { + offset = msg->buf[0]; + } + } + } + + return i; +} + +static u32 mtk_hdmi_ddc_v2_func(struct i2c_adapter *adapter) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm mtk_hdmi_ddc_v2_algorithm = { + .master_xfer = mtk_hdmi_ddc_v2_xfer, + .functionality = mtk_hdmi_ddc_v2_func, +}; + +static int mtk_hdmi_ddc_v2_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_hdmi_ddc *ddc; + int ret; + + ddc = devm_kzalloc(dev, sizeof(*ddc), GFP_KERNEL); + if (!ddc) + return -ENOMEM; + + ddc->dev = dev; + ddc->regs = device_node_to_regmap(dev->parent->of_node); + if (IS_ERR_OR_NULL(ddc->regs)) + return dev_err_probe(dev, + IS_ERR(ddc->regs) ? PTR_ERR(ddc->regs) : -EINVAL, + "Cannot get regmap\n"); + + ddc->clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(ddc->clk)) + return dev_err_probe(dev, PTR_ERR(ddc->clk), "Cannot get DDC clock\n"); + + strscpy(ddc->adap.name, "mediatek-hdmi-ddc-v2", sizeof(ddc->adap.name)); + ddc->adap.owner = THIS_MODULE; + ddc->adap.algo = &mtk_hdmi_ddc_v2_algorithm; + ddc->adap.retries = 3; + ddc->adap.dev.of_node = dev->of_node; + ddc->adap.algo_data = ddc; + ddc->adap.dev.parent = &pdev->dev; + + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Cannot enable Runtime PM\n"); + + pm_runtime_get_sync(dev); + + ret = devm_i2c_add_adapter(dev, &ddc->adap); + if (ret < 0) + return dev_err_probe(dev, ret, "Cannot add DDC I2C adapter\n"); + + platform_set_drvdata(pdev, ddc); + return 0; +} + +static const struct of_device_id mtk_hdmi_ddc_v2_match[] = { + { .compatible = "mediatek,mt8195-hdmi-ddc" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, mtk_hdmi_ddc_v2_match); + +struct platform_driver mtk_hdmi_ddc_v2_driver = { + .probe = mtk_hdmi_ddc_v2_probe, + .driver = { + .name = "mediatek-hdmi-ddc-v2", + .of_match_table = mtk_hdmi_ddc_v2_match, + }, +}; +module_platform_driver(mtk_hdmi_ddc_v2_driver); + +MODULE_AUTHOR("AngeloGioacchino Del Regno "); +MODULE_AUTHOR("Can Zeng "); +MODULE_DESCRIPTION("MediaTek HDMIv2 DDC Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_regs_v2.h b/drivers/gpu/drm/mediatek/mtk_hdmi_regs_v2.h new file mode 100644 index 000000000000..521b35c7e14d --- /dev/null +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_regs_v2.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + * Copyright (c) 2021 BayLibre, SAS + * Copyright (c) 2024 Collabora Ltd. + * AngeloGioacchino Del Regno + */ + +#ifndef _MTK_HDMI_REGS_H +#define _MTK_HDMI_REGS_H + +/* HDMI_TOP Config */ +#define TOP_CFG00 0x000 +#define HDMI2_ON BIT(2) +#define HDMI_MODE_HDMI BIT(3) +#define SCR_ON BIT(4) +#define TMDS_PACK_MODE GENMASK(9, 8) +#define TMDS_PACK_MODE_8BPP 0 +#define TMDS_PACK_MODE_10BPP 1 +#define TMDS_PACK_MODE_12BPP 2 +#define TMDS_PACK_MODE_16BPP 3 +#define DEEPCOLOR_PKT_EN BIT(12) +#define HDMI_ABIST_VIDEO_FORMAT GENMASK(21, 16) +#define HDMI_ABIST_ENABLE BIT(31) +#define TOP_CFG01 0x004 +#define CP_SET_MUTE_EN BIT(0) +#define CP_CLR_MUTE_EN BIT(1) +#define NULL_PKT_EN BIT(2) +#define NULL_PKT_VSYNC_HIGH_EN BIT(3) + +/* HDMI_TOP Audio: Channel Mapping */ +#define TOP_AUD_MAP 0x00c +#define SD0_MAP GENMASK(2, 0) +#define SD1_MAP GENMASK(6, 4) +#define SD2_MAP GENMASK(10, 8) +#define SD3_MAP GENMASK(14, 12) +#define SD4_MAP GENMASK(18, 16) +#define SD5_MAP GENMASK(22, 20) +#define SD6_MAP GENMASK(26, 24) +#define SD7_MAP GENMASK(30, 28) + +/* Auxiliary Video Information (AVI) Infoframe */ +#define TOP_AVI_HEADER 0x024 +#define TOP_AVI_PKT00 0x028 +#define TOP_AVI_PKT01 0x02C +#define TOP_AVI_PKT02 0x030 +#define TOP_AVI_PKT03 0x034 +#define TOP_AVI_PKT04 0x038 +#define TOP_AVI_PKT05 0x03C + +/* Audio Interface Infoframe */ +#define TOP_AIF_HEADER 0x040 +#define TOP_AIF_PKT00 0x044 +#define TOP_AIF_PKT01 0x048 +#define TOP_AIF_PKT02 0x04c +#define TOP_AIF_PKT03 0x050 + +/* Audio SPDIF Infoframe */ +#define TOP_SPDIF_HEADER 0x054 +#define TOP_SPDIF_PKT00 0x058 +#define TOP_SPDIF_PKT01 0x05c +#define TOP_SPDIF_PKT02 0x060 +#define TOP_SPDIF_PKT03 0x064 +#define TOP_SPDIF_PKT04 0x068 +#define TOP_SPDIF_PKT05 0x06c +#define TOP_SPDIF_PKT06 0x070 +#define TOP_SPDIF_PKT07 0x074 + +/* Infoframes Configuration */ +#define TOP_INFO_EN 0x01c +#define AVI_EN BIT(0) +#define SPD_EN BIT(1) +#define AUD_EN BIT(2) +#define CP_EN BIT(5) +#define VSIF_EN BIT(11) +#define AVI_EN_WR BIT(16) +#define SPD_EN_WR BIT(17) +#define AUD_EN_WR BIT(18) +#define CP_EN_WR BIT(21) +#define VSIF_EN_WR BIT(27) +#define TOP_INFO_RPT 0x020 +#define AVI_RPT_EN BIT(0) +#define SPD_RPT_EN BIT(1) +#define AUD_RPT_EN BIT(2) +#define CP_RPT_EN BIT(5) +#define VSIF_RPT_EN BIT(11) + +/* Vendor Specific Infoframe */ +#define TOP_VSIF_HEADER 0x174 +#define TOP_VSIF_PKT00 0x178 +#define TOP_VSIF_PKT01 0x17c +#define TOP_VSIF_PKT02 0x180 +#define TOP_VSIF_PKT03 0x184 +#define TOP_VSIF_PKT04 0x188 +#define TOP_VSIF_PKT05 0x18c +#define TOP_VSIF_PKT06 0x190 +#define TOP_VSIF_PKT07 0x194 + +/* HDMI_TOP Misc */ +#define TOP_MISC_CTLR 0x1a4 +#define DEEP_COLOR_ADD BIT(4) + +/* Hardware interrupts */ +#define TOP_INT_STA00 0x1a8 +#define TOP_INT_ENABLE00 0x1b0 +#define HTPLG_R_INT BIT(0) +#define HTPLG_F_INT BIT(1) +#define PORD_R_INT BIT(2) +#define PORD_F_INT BIT(3) +#define HDMI_VSYNC_INT BIT(4) +#define HDMI_AUDIO_INT BIT(5) +#define HDCP2X_RX_REAUTH_REQ_DDCM_INT BIT(25) +#define TOP_INT_ENABLE01 0x1b4 +#define TOP_INT_CLR00 0x1b8 +#define TOP_INT_CLR01 0x1bc + + +/* Video Mute */ +#define TOP_VMUTE_CFG1 0x1c8 +#define REG_VMUTE_EN BIT(16) + +/* HDMI Audio IP */ +#define AIP_CTRL 0x400 +#define CTS_SW_SEL BIT(0) +#define CTS_REQ_EN BIT(1) +#define MCLK_EN BIT(2) +#define NO_MCLK_CTSGEN_SEL BIT(3) +#define AUD_IN_EN BIT(8) +#define AUD_SEL_OWRT BIT(9) +#define SPDIF_EN BIT(13) +#define HBRA_ON BIT(14) +#define DSD_EN BIT(15) +#define I2S_EN GENMASK(19, 16) +#define HBR_FROM_SPDIF BIT(20) +#define CTS_CAL_N4 BIT(23) +#define SPDIF_INTERNAL_MODULE BIT(24) +#define AIP_N_VAL 0x404 +#define AIP_CTS_SVAL 0x408 +#define AIP_SPDIF_CTRL 0x40c +#define WR_1UI_LOCK BIT(0) +#define FS_OVERRIDE_WRITE BIT(1) +#define WR_2UI_LOCK BIT(2) +#define MAX_1UI_WRITE GENMASK(15, 8) +#define MAX_2UI_SPDIF_WRITE GENMASK(23, 16) +#define MAX_2UI_I2S_HI_WRITE GENMASK(23, 20) +#define MAX_2UI_I2S_LFE_CC_SWAP BIT(1) +#define MAX_2UI_I2S_LO_WRITE GENMASK(19, 16) +#define AUD_ERR_THRESH GENMASK(29, 24) +#define I2S2DSD_EN BIT(30) +#define AIP_I2S_CTRL 0x410 +#define FIFO0_MAP GENMASK(1, 0) +#define FIFO1_MAP GENMASK(3, 2) +#define FIFO2_MAP GENMASK(5, 4) +#define FIFO3_MAP GENMASK(7, 6) +#define I2S_1ST_BIT_NOSHIFT BIT(8) +#define I2S_DATA_DIR_LSB BIT(9) +#define JUSTIFY_RIGHT BIT(10) +#define WS_HIGH BIT(11) +#define VBIT_COMPRESSED BIT(12) +#define CBIT_ORDER_SAME BIT(13) +#define SCK_EDGE_RISE BIT(14) +#define AIP_I2S_CHST0 0x414 +#define AIP_I2S_CHST1 0x418 +#define AIP_TXCTRL 0x424 +#define RST4AUDIO BIT(0) +#define RST4AUDIO_FIFO BIT(1) +#define RST4AUDIO_ACR BIT(2) +#define AUD_LAYOUT_1 BIT(4) +#define AUD_MUTE_FIFO_EN BIT(5) +#define AUD_PACKET_DROP BIT(6) +#define DSD_MUTE_EN BIT(7) +#define AIP_TPI_CTRL 0x428 +#define TPI_AUDIO_LOOKUP_EN BIT(2) + +/* Video downsampling configuration */ +#define VID_DOWNSAMPLE_CONFIG 0x8d0 +#define C444_C422_CONFIG_ENABLE BIT(0) +#define C422_C420_CONFIG_ENABLE BIT(4) +#define C422_C420_CONFIG_BYPASS BIT(5) +#define C422_C420_CONFIG_OUT_CB_OR_CR BIT(6) +#define VID_OUT_FORMAT 0x8fc +#define OUTPUT_FORMAT_DEMUX_420_ENABLE BIT(10) + +/* HDCP registers */ +#define HDCP_TOP_CTRL 0xc00 +#define HDCP2X_CTRL_0 0xc20 +#define HDCP2X_EN BIT(0) +#define HDCP2X_ENCRYPT_EN BIT(7) +#define HDCP2X_HPD_OVR BIT(10) +#define HDCP2X_HPD_SW BIT(11) +#define HDCP2X_POL_CTRL 0xc54 +#define HDCP2X_DIS_POLL_EN BIT(16) +#define HDCP1X_CTRL 0xcd0 +#define HDCP1X_ENC_EN BIT(6) + +/* HDMI DDC registers */ +#define HPD_DDC_CTRL 0xc08 +#define HPD_DDC_DELAY_CNT GENMASK(31, 16) +#define HPD_DDC_HPD_DBNC_EN BIT(2) +#define HPD_DDC_PORD_DBNC_EN BIT(3) +#define DDC_CTRL 0xc10 +#define DDC_CTRL_ADDR GENMASK(7, 1) +#define DDC_CTRL_OFFSET GENMASK(15, 8) +#define DDC_CTRL_DIN_CNT GENMASK(25, 16) +#define DDC_CTRL_CMD GENMASK(31, 28) +#define SCDC_CTRL 0xc18 +#define SCDC_DDC_SEGMENT GENMASK(15, 8) +#define HPD_DDC_STATUS 0xc60 +#define HPD_STATE GENMASK(1, 0) +#define HPD_STATE_CONNECTED 2 +#define HPD_PIN_STA BIT(4) +#define PORD_PIN_STA BIT(5) +#define DDC_I2C_IN_PROG BIT(13) +#define DDC_DATA_OUT GENMASK(23, 16) +#define SI2C_CTRL 0xcac +#define SI2C_WR BIT(0) +#define SI2C_RD BIT(1) +#define SI2C_CONFIRM_READ BIT(2) +#define SI2C_WDATA GENMASK(15, 8) +#define SI2C_ADDR GENMASK(23, 16) + +/* HDCP DDC registers */ +#define HDCP2X_DDCM_STATUS 0xc68 +#define DDC_I2C_NO_ACK BIT(10) +#define DDC_I2C_BUS_LOW BIT(11) + +/* HDMI TX registers */ +#define HDMITX_CONFIG_MT8188 0xea0 +#define HDMITX_CONFIG_MT8195 0x900 +#define HDMI_YUV420_MODE BIT(10) +#define HDMITX_SW_HPD BIT(29) +#define HDMITX_SW_RSTB BIT(31) + +/** + * enum mtk_hdmi_ddc_v2_cmds - DDC_CMD register commands + * @DDC_CMD_READ_NOACK: Current address read with no ACK on last byte + * @DDC_CMD_READ: Current address read with ACK on last byte + * @DDC_CMD_SEQ_READ_NOACK: Sequential read with no ACK on last byte + * @DDC_CMD_SEQ_READ: Sequential read with ACK on last byte + * @DDC_CMD_ENH_READ_NOACK: Enhanced read with no ACK on last byte + * @DDC_CMD_ENH_READ: Enhanced read with ACK on last byte + * @DDC_CMD_SEQ_WRITE_NOACK: Sequential write ignoring ACK on last byte + * @DDC_CMD_SEQ_WRITE: Sequential write requiring ACK on last byte + * @DDC_CMD_RSVD: Reserved for future use + * @DDC_CMD_CLEAR_FIFO: Clear DDC I2C FIFO + * @DDC_CMD_CLOCK_SCL: Start clocking DDC I2C SCL + * @DDC_CMD_ABORT_XFER: Abort DDC I2C transaction + */ +enum mtk_hdmi_ddc_v2_cmds { + DDC_CMD_READ_NOACK = 0x0, + DDC_CMD_READ, + DDC_CMD_SEQ_READ_NOACK, + DDC_CMD_SEQ_READ, + DDC_CMD_ENH_READ_NOACK, + DDC_CMD_ENH_READ, + DDC_CMD_SEQ_WRITE_NOACK, + DDC_CMD_SEQ_WRITE = 0x07, + DDC_CMD_CLEAR_FIFO = 0x09, + DDC_CMD_CLOCK_SCL = 0x0a, + DDC_CMD_ABORT_XFER = 0x0f +}; + +#endif /* _MTK_HDMI_REGS_H */ diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c new file mode 100644 index 000000000000..c272e1e74b7d --- /dev/null +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c @@ -0,0 +1,1521 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MediaTek HDMI v2 IP driver + * + * Copyright (c) 2022 MediaTek Inc. + * Copyright (c) 2022 BayLibre, SAS + * Copyright (c) 2024 Collabora Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "mtk_hdmi_common.h" +#include "mtk_hdmi_regs_v2.h" + +#define MTK_HDMI_V2_CLOCK_MIN 27000 +#define MTK_HDMI_V2_CLOCK_MAX 594000 + +#define HPD_PORD_HWIRQS (HTPLG_R_INT | HTPLG_F_INT | PORD_F_INT | PORD_R_INT) + +enum mtk_hdmi_v2_clk_id { + MTK_HDMI_V2_CLK_HDCP_SEL, + MTK_HDMI_V2_CLK_HDCP_24M_SEL, + MTK_HDMI_V2_CLK_VPP_SPLIT_HDMI, + MTK_HDMI_V2_CLK_HDMI_APB_SEL, + MTK_HDMI_V2_CLK_COUNT, +}; + +const char *const mtk_hdmi_v2_clk_names[MTK_HDMI_V2_CLK_COUNT] = { + [MTK_HDMI_V2_CLK_HDMI_APB_SEL] = "bus", + [MTK_HDMI_V2_CLK_HDCP_SEL] = "hdcp", + [MTK_HDMI_V2_CLK_HDCP_24M_SEL] = "hdcp24m", + [MTK_HDMI_V2_CLK_VPP_SPLIT_HDMI] = "hdmi-split", +}; + +static inline void mtk_hdmi_v2_hwirq_disable(struct mtk_hdmi *hdmi) +{ + regmap_write(hdmi->regs, TOP_INT_ENABLE00, 0); + regmap_write(hdmi->regs, TOP_INT_ENABLE01, 0); +} + +static inline void mtk_hdmi_v2_enable_hpd_pord_irq(struct mtk_hdmi *hdmi, bool enable) +{ + if (enable) + regmap_set_bits(hdmi->regs, TOP_INT_ENABLE00, HPD_PORD_HWIRQS); + else + regmap_clear_bits(hdmi->regs, TOP_INT_ENABLE00, HPD_PORD_HWIRQS); +} + +static inline void mtk_hdmi_v2_set_sw_hpd(struct mtk_hdmi *hdmi, bool enable) +{ + if (enable) { + regmap_set_bits(hdmi->regs, hdmi->conf->reg_hdmi_tx_cfg, HDMITX_SW_HPD); + regmap_set_bits(hdmi->regs, HDCP2X_CTRL_0, HDCP2X_HPD_OVR); + regmap_set_bits(hdmi->regs, HDCP2X_CTRL_0, HDCP2X_HPD_SW); + } else { + regmap_clear_bits(hdmi->regs, HDCP2X_CTRL_0, HDCP2X_HPD_OVR); + regmap_clear_bits(hdmi->regs, HDCP2X_CTRL_0, HDCP2X_HPD_SW); + regmap_clear_bits(hdmi->regs, hdmi->conf->reg_hdmi_tx_cfg, HDMITX_SW_HPD); + } +} + +static inline void mtk_hdmi_v2_enable_scrambling(struct mtk_hdmi *hdmi, bool enable) +{ + struct drm_scdc *scdc = &hdmi->curr_conn->display_info.hdmi.scdc; + + if (enable) + regmap_set_bits(hdmi->regs, TOP_CFG00, SCR_ON | HDMI2_ON); + else + regmap_clear_bits(hdmi->regs, TOP_CFG00, SCR_ON | HDMI2_ON); + + if (scdc->supported) { + if (scdc->scrambling.supported) + drm_scdc_set_scrambling(hdmi->curr_conn, enable); + drm_scdc_set_high_tmds_clock_ratio(hdmi->curr_conn, enable); + } +} + +static void mtk_hdmi_v2_hw_vid_mute(struct mtk_hdmi *hdmi, bool enable) +{ + /* If enabled, sends a black image */ + if (enable) + regmap_set_bits(hdmi->regs, TOP_VMUTE_CFG1, REG_VMUTE_EN); + else + regmap_clear_bits(hdmi->regs, TOP_VMUTE_CFG1, REG_VMUTE_EN); +} + +static void mtk_hdmi_v2_hw_aud_mute(struct mtk_hdmi *hdmi, bool enable) +{ + u32 aip, val; + + if (!enable) { + regmap_clear_bits(hdmi->regs, AIP_TXCTRL, AUD_MUTE_FIFO_EN); + return; + } + + regmap_read(hdmi->regs, AIP_CTRL, &aip); + + val = AUD_MUTE_FIFO_EN; + if (aip & DSD_EN) + val |= DSD_MUTE_EN; + + regmap_update_bits(hdmi->regs, AIP_TXCTRL, val, val); +} + +static void mtk_hdmi_v2_hw_reset(struct mtk_hdmi *hdmi) +{ + regmap_clear_bits(hdmi->regs, hdmi->conf->reg_hdmi_tx_cfg, HDMITX_SW_RSTB); + udelay(5); + regmap_set_bits(hdmi->regs, hdmi->conf->reg_hdmi_tx_cfg, HDMITX_SW_RSTB); +} + +static inline u32 mtk_hdmi_v2_format_hw_packet(const u8 *buffer, u8 len) +{ + unsigned short i; + u32 val = 0; + + for (i = 0; i < len; i++) + val |= buffer[i] << (i * 8); + + return val; +} + +static void mtk_hdmi_v2_hw_write_audio_infoframe(struct mtk_hdmi *hdmi, const u8 *buffer) +{ + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, AUD_EN | AUD_EN_WR); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, AUD_RPT_EN); + + regmap_write(hdmi->regs, TOP_AIF_HEADER, mtk_hdmi_v2_format_hw_packet(&buffer[0], 3)); + regmap_write(hdmi->regs, TOP_AIF_PKT00, mtk_hdmi_v2_format_hw_packet(&buffer[3], 3)); + regmap_write(hdmi->regs, TOP_AIF_PKT01, mtk_hdmi_v2_format_hw_packet(&buffer[7], 2)); + regmap_write(hdmi->regs, TOP_AIF_PKT02, 0); + regmap_write(hdmi->regs, TOP_AIF_PKT03, 0); + + regmap_set_bits(hdmi->regs, TOP_INFO_RPT, AUD_RPT_EN); + regmap_set_bits(hdmi->regs, TOP_INFO_EN, AUD_EN | AUD_EN_WR); +} + +static void mtk_hdmi_v2_hw_write_avi_infoframe(struct mtk_hdmi *hdmi, const u8 *buffer) +{ + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, AVI_EN_WR | AVI_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, AVI_RPT_EN); + + regmap_write(hdmi->regs, TOP_AVI_HEADER, mtk_hdmi_v2_format_hw_packet(&buffer[0], 3)); + regmap_write(hdmi->regs, TOP_AVI_PKT00, mtk_hdmi_v2_format_hw_packet(&buffer[3], 4)); + regmap_write(hdmi->regs, TOP_AVI_PKT01, mtk_hdmi_v2_format_hw_packet(&buffer[7], 3)); + regmap_write(hdmi->regs, TOP_AVI_PKT02, mtk_hdmi_v2_format_hw_packet(&buffer[10], 4)); + regmap_write(hdmi->regs, TOP_AVI_PKT03, mtk_hdmi_v2_format_hw_packet(&buffer[14], 3)); + regmap_write(hdmi->regs, TOP_AVI_PKT04, 0); + regmap_write(hdmi->regs, TOP_AVI_PKT05, 0); + + regmap_set_bits(hdmi->regs, TOP_INFO_RPT, AVI_RPT_EN); + regmap_set_bits(hdmi->regs, TOP_INFO_EN, AVI_EN_WR | AVI_EN); +} + +static void mtk_hdmi_v2_hw_write_spd_infoframe(struct mtk_hdmi *hdmi, const u8 *buffer) +{ + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, SPD_EN_WR | SPD_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, SPD_RPT_EN); + + regmap_write(hdmi->regs, TOP_SPDIF_HEADER, mtk_hdmi_v2_format_hw_packet(&buffer[0], 3)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT00, mtk_hdmi_v2_format_hw_packet(&buffer[3], 4)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT01, mtk_hdmi_v2_format_hw_packet(&buffer[7], 3)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT02, mtk_hdmi_v2_format_hw_packet(&buffer[10], 4)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT03, mtk_hdmi_v2_format_hw_packet(&buffer[14], 3)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT04, mtk_hdmi_v2_format_hw_packet(&buffer[17], 4)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT05, mtk_hdmi_v2_format_hw_packet(&buffer[21], 3)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT06, mtk_hdmi_v2_format_hw_packet(&buffer[24], 4)); + regmap_write(hdmi->regs, TOP_SPDIF_PKT07, buffer[28]); + + regmap_set_bits(hdmi->regs, TOP_INFO_EN, SPD_EN_WR | SPD_EN); + regmap_set_bits(hdmi->regs, TOP_INFO_RPT, SPD_RPT_EN); +} + +static void mtk_hdmi_v2_hw_write_vendor_infoframe(struct mtk_hdmi *hdmi, const u8 *buffer) +{ + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, VSIF_EN_WR | VSIF_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, VSIF_RPT_EN); + + regmap_write(hdmi->regs, TOP_VSIF_HEADER, mtk_hdmi_v2_format_hw_packet(&buffer[0], 3)); + regmap_write(hdmi->regs, TOP_VSIF_PKT00, mtk_hdmi_v2_format_hw_packet(&buffer[3], 4)); + regmap_write(hdmi->regs, TOP_VSIF_PKT01, mtk_hdmi_v2_format_hw_packet(&buffer[7], 2)); + regmap_write(hdmi->regs, TOP_VSIF_PKT02, 0); + regmap_write(hdmi->regs, TOP_VSIF_PKT03, 0); + regmap_write(hdmi->regs, TOP_VSIF_PKT04, 0); + regmap_write(hdmi->regs, TOP_VSIF_PKT05, 0); + regmap_write(hdmi->regs, TOP_VSIF_PKT06, 0); + regmap_write(hdmi->regs, TOP_VSIF_PKT07, 0); + + regmap_set_bits(hdmi->regs, TOP_INFO_EN, VSIF_EN_WR | VSIF_EN); + regmap_set_bits(hdmi->regs, TOP_INFO_RPT, VSIF_RPT_EN); +} + +static void mtk_hdmi_yuv420_downsampling(struct mtk_hdmi *hdmi, bool enable) +{ + u32 val; + + regmap_read(hdmi->regs, VID_DOWNSAMPLE_CONFIG, &val); + + if (enable) { + regmap_set_bits(hdmi->regs, hdmi->conf->reg_hdmi_tx_cfg, HDMI_YUV420_MODE); + + val |= C444_C422_CONFIG_ENABLE | C422_C420_CONFIG_ENABLE; + val |= C422_C420_CONFIG_OUT_CB_OR_CR; + val &= ~C422_C420_CONFIG_BYPASS; + regmap_write(hdmi->regs, VID_DOWNSAMPLE_CONFIG, val); + + regmap_set_bits(hdmi->regs, VID_OUT_FORMAT, OUTPUT_FORMAT_DEMUX_420_ENABLE); + } else { + regmap_clear_bits(hdmi->regs, hdmi->conf->reg_hdmi_tx_cfg, HDMI_YUV420_MODE); + + val &= ~(C444_C422_CONFIG_ENABLE | C422_C420_CONFIG_ENABLE); + val &= ~C422_C420_CONFIG_OUT_CB_OR_CR; + val |= C422_C420_CONFIG_BYPASS; + regmap_write(hdmi->regs, VID_DOWNSAMPLE_CONFIG, val); + + regmap_clear_bits(hdmi->regs, VID_OUT_FORMAT, OUTPUT_FORMAT_DEMUX_420_ENABLE); + } +} + +static int mtk_hdmi_v2_setup_audio_infoframe(struct mtk_hdmi *hdmi) +{ + struct hdmi_codec_params *params = &hdmi->aud_param.codec_params; + struct hdmi_audio_infoframe frame; + u8 buffer[14]; + ssize_t ret; + + memcpy(&frame, ¶ms->cea, sizeof(frame)); + + ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer)); + if (ret < 0) + return ret; + + mtk_hdmi_v2_hw_write_audio_infoframe(hdmi, buffer); + + return 0; +} + +static inline void mtk_hdmi_v2_hw_gcp_avmute(struct mtk_hdmi *hdmi, bool mute) +{ + u32 val; + + regmap_read(hdmi->regs, TOP_CFG01, &val); + val &= ~(CP_CLR_MUTE_EN | CP_SET_MUTE_EN); + + if (mute) { + val |= CP_SET_MUTE_EN; + val &= ~CP_CLR_MUTE_EN; + } else { + val |= CP_CLR_MUTE_EN; + val &= ~CP_SET_MUTE_EN; + } + regmap_write(hdmi->regs, TOP_CFG01, val); + + regmap_set_bits(hdmi->regs, TOP_INFO_RPT, CP_RPT_EN); + regmap_set_bits(hdmi->regs, TOP_INFO_EN, CP_EN | CP_EN_WR); +} + +static void mtk_hdmi_v2_hw_ncts_enable(struct mtk_hdmi *hdmi, bool enable) +{ + if (enable) + regmap_set_bits(hdmi->regs, AIP_CTRL, CTS_SW_SEL); + else + regmap_clear_bits(hdmi->regs, AIP_CTRL, CTS_SW_SEL); +} + +static void mtk_hdmi_v2_hw_aud_set_channel_status(struct mtk_hdmi *hdmi) +{ + u8 *ch_status = hdmi->aud_param.codec_params.iec.status; + + /* Only the first 5 to 7 bytes of Channel Status contain useful information */ + regmap_write(hdmi->regs, AIP_I2S_CHST0, mtk_hdmi_v2_format_hw_packet(&ch_status[0], 4)); + regmap_write(hdmi->regs, AIP_I2S_CHST1, mtk_hdmi_v2_format_hw_packet(&ch_status[4], 3)); +} + +static void mtk_hdmi_v2_hw_aud_set_ncts(struct mtk_hdmi *hdmi, + unsigned int sample_rate, + unsigned int clock) +{ + unsigned int n, cts; + + mtk_hdmi_get_ncts(sample_rate, clock, &n, &cts); + + regmap_write(hdmi->regs, AIP_N_VAL, n); + regmap_write(hdmi->regs, AIP_CTS_SVAL, cts); +} + +static void mtk_hdmi_v2_hw_aud_enable(struct mtk_hdmi *hdmi, bool enable) +{ + if (enable) + regmap_clear_bits(hdmi->regs, AIP_TXCTRL, AUD_PACKET_DROP); + else + regmap_set_bits(hdmi->regs, AIP_TXCTRL, AUD_PACKET_DROP); +} + +static u32 mtk_hdmi_v2_aud_output_channel_map(u8 sd0, u8 sd1, u8 sd2, u8 sd3, + u8 sd4, u8 sd5, u8 sd6, u8 sd7) +{ + u32 val; + + /* + * Each of the Output Channels (0-7) can be mapped to get their input + * from any of the available Input Channels (0-7): this function + * takes input channel numbers and formats a value that must then + * be written to the TOP_AUD_MAP hardware register by the caller. + */ + val = FIELD_PREP(SD0_MAP, sd0) | FIELD_PREP(SD1_MAP, sd1); + val |= FIELD_PREP(SD2_MAP, sd2) | FIELD_PREP(SD3_MAP, sd3); + val |= FIELD_PREP(SD4_MAP, sd4) | FIELD_PREP(SD5_MAP, sd5); + val |= FIELD_PREP(SD6_MAP, sd6) | FIELD_PREP(SD7_MAP, sd7); + + return val; +} + +static void mtk_hdmi_audio_dsd_config(struct mtk_hdmi *hdmi, + unsigned char chnum, bool dsd_bypass) +{ + u32 channel_map; + + regmap_update_bits(hdmi->regs, AIP_CTRL, SPDIF_EN | DSD_EN | HBRA_ON, DSD_EN); + regmap_set_bits(hdmi->regs, AIP_TXCTRL, DSD_MUTE_EN); + + if (dsd_bypass) + channel_map = mtk_hdmi_v2_aud_output_channel_map(0, 2, 4, 6, 1, 3, 5, 7); + else + channel_map = mtk_hdmi_v2_aud_output_channel_map(0, 5, 1, 0, 3, 2, 4, 0); + + regmap_write(hdmi->regs, TOP_AUD_MAP, channel_map); + regmap_clear_bits(hdmi->regs, AIP_SPDIF_CTRL, I2S2DSD_EN); +} + +static inline void mtk_hdmi_v2_hw_i2s_fifo_map(struct mtk_hdmi *hdmi, u32 fifo_mapping) +{ + regmap_update_bits(hdmi->regs, AIP_I2S_CTRL, + FIFO0_MAP | FIFO1_MAP | FIFO2_MAP | FIFO3_MAP, fifo_mapping); +} + +static inline void mtk_hdmi_v2_hw_i2s_ch_number(struct mtk_hdmi *hdmi, u8 chnum) +{ + regmap_update_bits(hdmi->regs, AIP_CTRL, I2S_EN, FIELD_PREP(I2S_EN, chnum)); +} + +static void mtk_hdmi_v2_hw_i2s_ch_mapping(struct mtk_hdmi *hdmi, u8 chnum, u8 mapping) +{ + u32 fifo_map; + u8 bdata; + + switch (chnum) { + default: + case 2: + bdata = 0x1; + break; + case 3: + bdata = 0x3; + break; + case 6: + if (mapping == 0x0e) { + bdata = 0xf; + break; + } + fallthrough; + case 5: + bdata = 0x7; + break; + case 7: + case 8: + bdata = 0xf; + break; + } + + /* Assign default FIFO mapping: SD0 to FIFO0, SD1 to FIFO1, etc. */ + fifo_map = FIELD_PREP(FIFO0_MAP, 0) | FIELD_PREP(FIFO1_MAP, 1); + fifo_map |= FIELD_PREP(FIFO2_MAP, 2) | FIELD_PREP(FIFO3_MAP, 3); + mtk_hdmi_v2_hw_i2s_fifo_map(hdmi, fifo_map); + mtk_hdmi_v2_hw_i2s_ch_number(hdmi, bdata); + + /* + * Set HDMI Audio packet layout indicator: + * Layout 0 is for two channels + * Layout 1 is for up to eight channels + */ + if (chnum == 2) + regmap_set_bits(hdmi->regs, AIP_TXCTRL, AUD_LAYOUT_1); + else + regmap_clear_bits(hdmi->regs, AIP_TXCTRL, AUD_LAYOUT_1); +} + +static void mtk_hdmi_i2s_data_fmt(struct mtk_hdmi *hdmi, unsigned char fmt) +{ + u32 val; + + regmap_read(hdmi->regs, AIP_I2S_CTRL, &val); + val &= ~(WS_HIGH | I2S_1ST_BIT_NOSHIFT | JUSTIFY_RIGHT); + + switch (fmt) { + case HDMI_I2S_MODE_RJT_24BIT: + case HDMI_I2S_MODE_RJT_16BIT: + val |= (WS_HIGH | I2S_1ST_BIT_NOSHIFT | JUSTIFY_RIGHT); + break; + case HDMI_I2S_MODE_LJT_24BIT: + case HDMI_I2S_MODE_LJT_16BIT: + val |= (WS_HIGH | I2S_1ST_BIT_NOSHIFT); + break; + case HDMI_I2S_MODE_I2S_24BIT: + case HDMI_I2S_MODE_I2S_16BIT: + default: + break; + } + + regmap_write(hdmi->regs, AIP_I2S_CTRL, val); +} + +static inline void mtk_hdmi_i2s_sck_edge_rise(struct mtk_hdmi *hdmi, bool rise) +{ + if (rise) + regmap_set_bits(hdmi->regs, AIP_I2S_CTRL, SCK_EDGE_RISE); + else + regmap_clear_bits(hdmi->regs, AIP_I2S_CTRL, SCK_EDGE_RISE); +} + +static inline void mtk_hdmi_i2s_cbit_order(struct mtk_hdmi *hdmi, unsigned int cbit) +{ + regmap_update_bits(hdmi->regs, AIP_I2S_CTRL, CBIT_ORDER_SAME, cbit); +} + +static inline void mtk_hdmi_i2s_vbit(struct mtk_hdmi *hdmi, unsigned int vbit) +{ + /* V bit: 0 for PCM, 1 for Compressed data */ + regmap_update_bits(hdmi->regs, AIP_I2S_CTRL, VBIT_COMPRESSED, vbit); +} + +static inline void mtk_hdmi_i2s_data_direction(struct mtk_hdmi *hdmi, unsigned int is_lsb) +{ + regmap_update_bits(hdmi->regs, AIP_I2S_CTRL, I2S_DATA_DIR_LSB, is_lsb); +} + +static inline void mtk_hdmi_v2_hw_audio_type(struct mtk_hdmi *hdmi, unsigned int spdif_i2s) +{ + regmap_update_bits(hdmi->regs, AIP_CTRL, SPDIF_EN, FIELD_PREP(SPDIF_EN, spdif_i2s)); +} + +static u8 mtk_hdmi_v2_get_i2s_ch_mapping(struct mtk_hdmi *hdmi, u8 channel_type) +{ + switch (channel_type) { + case HDMI_AUD_CHAN_TYPE_1_1: + case HDMI_AUD_CHAN_TYPE_2_1: + return 0x01; + case HDMI_AUD_CHAN_TYPE_3_0: + return 0x02; + case HDMI_AUD_CHAN_TYPE_3_1: + return 0x03; + case HDMI_AUD_CHAN_TYPE_3_0_LRS: + case HDMI_AUD_CHAN_TYPE_4_0: + return 0x08; + case HDMI_AUD_CHAN_TYPE_5_1: + return 0x0b; + case HDMI_AUD_CHAN_TYPE_4_1_CLRS: + case HDMI_AUD_CHAN_TYPE_6_0: + case HDMI_AUD_CHAN_TYPE_6_0_CS: + case HDMI_AUD_CHAN_TYPE_6_0_CH: + case HDMI_AUD_CHAN_TYPE_6_0_OH: + case HDMI_AUD_CHAN_TYPE_6_0_CHR: + return 0x0e; + case HDMI_AUD_CHAN_TYPE_1_0: + case HDMI_AUD_CHAN_TYPE_2_0: + case HDMI_AUD_CHAN_TYPE_3_1_LRS: + case HDMI_AUD_CHAN_TYPE_4_1: + case HDMI_AUD_CHAN_TYPE_5_0: + case HDMI_AUD_CHAN_TYPE_4_0_CLRS: + case HDMI_AUD_CHAN_TYPE_6_1: + case HDMI_AUD_CHAN_TYPE_6_1_CS: + case HDMI_AUD_CHAN_TYPE_6_1_CH: + case HDMI_AUD_CHAN_TYPE_6_1_OH: + case HDMI_AUD_CHAN_TYPE_6_1_CHR: + case HDMI_AUD_CHAN_TYPE_7_0: + case HDMI_AUD_CHAN_TYPE_7_0_LH_RH: + case HDMI_AUD_CHAN_TYPE_7_0_LSR_RSR: + case HDMI_AUD_CHAN_TYPE_7_0_LC_RC: + case HDMI_AUD_CHAN_TYPE_7_0_LW_RW: + case HDMI_AUD_CHAN_TYPE_7_0_LSD_RSD: + case HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS: + case HDMI_AUD_CHAN_TYPE_7_0_LHS_RHS: + case HDMI_AUD_CHAN_TYPE_7_0_CS_CH: + case HDMI_AUD_CHAN_TYPE_7_0_CS_OH: + case HDMI_AUD_CHAN_TYPE_7_0_CS_CHR: + case HDMI_AUD_CHAN_TYPE_7_0_CH_OH: + case HDMI_AUD_CHAN_TYPE_7_0_CH_CHR: + case HDMI_AUD_CHAN_TYPE_7_0_OH_CHR: + case HDMI_AUD_CHAN_TYPE_7_0_LSS_RSS_LSR_RSR: + case HDMI_AUD_CHAN_TYPE_8_0_LH_RH_CS: + case HDMI_AUD_CHAN_TYPE_7_1: + case HDMI_AUD_CHAN_TYPE_7_1_LH_RH: + case HDMI_AUD_CHAN_TYPE_7_1_LSR_RSR: + case HDMI_AUD_CHAN_TYPE_7_1_LC_RC: + case HDMI_AUD_CHAN_TYPE_7_1_LW_RW: + case HDMI_AUD_CHAN_TYPE_7_1_LSD_RSD: + case HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS: + case HDMI_AUD_CHAN_TYPE_7_1_LHS_RHS: + case HDMI_AUD_CHAN_TYPE_7_1_CS_CH: + case HDMI_AUD_CHAN_TYPE_7_1_CS_OH: + case HDMI_AUD_CHAN_TYPE_7_1_CS_CHR: + case HDMI_AUD_CHAN_TYPE_7_1_CH_OH: + case HDMI_AUD_CHAN_TYPE_7_1_CH_CHR: + case HDMI_AUD_CHAN_TYPE_7_1_OH_CHR: + case HDMI_AUD_CHAN_TYPE_7_1_LSS_RSS_LSR_RSR: + default: + return 0; + } + + return 0; +} + +static inline void mtk_hdmi_v2_hw_i2s_ch_swap(struct mtk_hdmi *hdmi) +{ + regmap_update_bits(hdmi->regs, AIP_SPDIF_CTRL, MAX_2UI_I2S_HI_WRITE, + FIELD_PREP(MAX_2UI_I2S_HI_WRITE, MAX_2UI_I2S_LFE_CC_SWAP)); +} + +static void mtk_hdmi_hbr_config(struct mtk_hdmi *hdmi, bool dsd_bypass) +{ + const u32 hbr_mask = SPDIF_EN | DSD_EN | HBRA_ON; + + if (dsd_bypass) { + regmap_update_bits(hdmi->regs, AIP_CTRL, hbr_mask, HBRA_ON); + regmap_set_bits(hdmi->regs, AIP_CTRL, I2S_EN); + } else { + regmap_update_bits(hdmi->regs, AIP_CTRL, hbr_mask, SPDIF_EN); + regmap_set_bits(hdmi->regs, AIP_CTRL, SPDIF_INTERNAL_MODULE); + regmap_set_bits(hdmi->regs, AIP_CTRL, HBR_FROM_SPDIF); + regmap_set_bits(hdmi->regs, AIP_CTRL, CTS_CAL_N4); + } +} + +static inline void mtk_hdmi_v2_hw_spdif_config(struct mtk_hdmi *hdmi) +{ + regmap_clear_bits(hdmi->regs, AIP_SPDIF_CTRL, WR_1UI_LOCK); + regmap_clear_bits(hdmi->regs, AIP_SPDIF_CTRL, FS_OVERRIDE_WRITE); + regmap_clear_bits(hdmi->regs, AIP_SPDIF_CTRL, WR_2UI_LOCK); + + regmap_update_bits(hdmi->regs, AIP_SPDIF_CTRL, MAX_1UI_WRITE, + FIELD_PREP(MAX_1UI_WRITE, 4)); + regmap_update_bits(hdmi->regs, AIP_SPDIF_CTRL, MAX_2UI_SPDIF_WRITE, + FIELD_PREP(MAX_2UI_SPDIF_WRITE, 9)); + regmap_update_bits(hdmi->regs, AIP_SPDIF_CTRL, AUD_ERR_THRESH, + FIELD_PREP(AUD_ERR_THRESH, 4)); + + regmap_set_bits(hdmi->regs, AIP_SPDIF_CTRL, I2S2DSD_EN); +} + +static void mtk_hdmi_v2_aud_set_input(struct mtk_hdmi *hdmi) +{ + struct hdmi_audio_param *aud_param = &hdmi->aud_param; + struct hdmi_codec_params *codec_params = &aud_param->codec_params; + u8 i2s_ch_map; + u32 out_ch_map; + + /* Write the default output channel map. CH0 maps to SD0, CH1 maps to SD1, etc */ + out_ch_map = mtk_hdmi_v2_aud_output_channel_map(0, 1, 2, 3, 4, 5, 6, 7); + regmap_write(hdmi->regs, TOP_AUD_MAP, out_ch_map); + + regmap_update_bits(hdmi->regs, AIP_SPDIF_CTRL, MAX_2UI_I2S_HI_WRITE, 0); + regmap_clear_bits(hdmi->regs, AIP_CTRL, + SPDIF_EN | DSD_EN | HBRA_ON | CTS_CAL_N4 | + HBR_FROM_SPDIF | SPDIF_INTERNAL_MODULE); + regmap_clear_bits(hdmi->regs, AIP_TXCTRL, DSD_MUTE_EN | AUD_LAYOUT_1); + + if (aud_param->aud_input_type == HDMI_AUD_INPUT_I2S) { + switch (aud_param->aud_codec) { + case HDMI_AUDIO_CODING_TYPE_DTS_HD: + case HDMI_AUDIO_CODING_TYPE_MLP: + mtk_hdmi_i2s_data_fmt(hdmi, aud_param->aud_i2s_fmt); + mtk_hdmi_hbr_config(hdmi, true); + break; + case HDMI_AUDIO_CODING_TYPE_DSD: + mtk_hdmi_audio_dsd_config(hdmi, codec_params->channels, 0); + mtk_hdmi_v2_hw_i2s_ch_mapping(hdmi, codec_params->channels, 1); + break; + default: + mtk_hdmi_i2s_data_fmt(hdmi, aud_param->aud_i2s_fmt); + mtk_hdmi_i2s_sck_edge_rise(hdmi, true); + mtk_hdmi_i2s_cbit_order(hdmi, CBIT_ORDER_SAME); + mtk_hdmi_i2s_vbit(hdmi, 0); /* PCM data */ + mtk_hdmi_i2s_data_direction(hdmi, 0); /* MSB first */ + mtk_hdmi_v2_hw_audio_type(hdmi, HDMI_AUD_INPUT_I2S); + i2s_ch_map = mtk_hdmi_v2_get_i2s_ch_mapping(hdmi, + aud_param->aud_input_chan_type); + mtk_hdmi_v2_hw_i2s_ch_mapping(hdmi, codec_params->channels, i2s_ch_map); + mtk_hdmi_v2_hw_i2s_ch_swap(hdmi); + } + } else { + if (codec_params->sample_rate == 768000 && + (aud_param->aud_codec == HDMI_AUDIO_CODING_TYPE_DTS_HD || + aud_param->aud_codec == HDMI_AUDIO_CODING_TYPE_MLP)) { + mtk_hdmi_hbr_config(hdmi, false); + } else { + mtk_hdmi_v2_hw_spdif_config(hdmi); + mtk_hdmi_v2_hw_i2s_ch_mapping(hdmi, 2, 0); + } + } +} + +static inline void mtk_hdmi_v2_hw_audio_input_enable(struct mtk_hdmi *hdmi, bool ena) +{ + if (ena) + regmap_set_bits(hdmi->regs, AIP_CTRL, AUD_IN_EN); + else + regmap_clear_bits(hdmi->regs, AIP_CTRL, AUD_IN_EN); +} + +static void mtk_hdmi_v2_aip_ctrl_init(struct mtk_hdmi *hdmi) +{ + regmap_set_bits(hdmi->regs, AIP_CTRL, + AUD_SEL_OWRT | NO_MCLK_CTSGEN_SEL | MCLK_EN | CTS_REQ_EN); + regmap_clear_bits(hdmi->regs, AIP_TPI_CTRL, TPI_AUDIO_LOOKUP_EN); +} + +static void mtk_hdmi_v2_audio_reset(struct mtk_hdmi *hdmi, bool reset) +{ + const u32 arst_bits = RST4AUDIO | RST4AUDIO_FIFO | RST4AUDIO_ACR; + + if (reset) + regmap_set_bits(hdmi->regs, AIP_TXCTRL, arst_bits); + else + regmap_clear_bits(hdmi->regs, AIP_TXCTRL, arst_bits); +} + +static void mtk_hdmi_v2_aud_output_config(struct mtk_hdmi *hdmi, + struct drm_display_mode *display_mode) +{ + /* Shut down and reset the HDMI Audio HW to avoid glitching */ + mtk_hdmi_v2_hw_aud_mute(hdmi, true); + mtk_hdmi_v2_hw_aud_enable(hdmi, false); + mtk_hdmi_v2_audio_reset(hdmi, true); + + /* Configure the main hardware params and get out of reset */ + mtk_hdmi_v2_aip_ctrl_init(hdmi); + mtk_hdmi_v2_aud_set_input(hdmi); + mtk_hdmi_v2_hw_aud_set_channel_status(hdmi); + mtk_hdmi_v2_setup_audio_infoframe(hdmi); + mtk_hdmi_v2_hw_audio_input_enable(hdmi, true); + mtk_hdmi_v2_audio_reset(hdmi, false); + + /* Ignore N/CTS packet transmission requests and configure */ + mtk_hdmi_v2_hw_ncts_enable(hdmi, false); + mtk_hdmi_v2_hw_aud_set_ncts(hdmi, hdmi->aud_param.codec_params.sample_rate, + display_mode->clock); + + /* Wait for the HW to apply settings */ + usleep_range(25, 50); + + /* Hardware is fully configured: enable TX of N/CTS pkts and unmute */ + mtk_hdmi_v2_hw_ncts_enable(hdmi, true); + mtk_hdmi_v2_hw_aud_enable(hdmi, true); + mtk_hdmi_v2_hw_aud_mute(hdmi, false); +} + +static void mtk_hdmi_v2_change_video_resolution(struct mtk_hdmi *hdmi, + struct drm_connector_state *conn_state) +{ + mtk_hdmi_v2_hw_reset(hdmi); + mtk_hdmi_v2_set_sw_hpd(hdmi, true); + udelay(2); + + regmap_write(hdmi->regs, HDCP_TOP_CTRL, 0); + + /* + * Enable HDCP reauthentication interrupt: the HW uses this internally + * for the HPD state machine even if HDCP encryption is not enabled. + */ + regmap_set_bits(hdmi->regs, TOP_INT_ENABLE00, HDCP2X_RX_REAUTH_REQ_DDCM_INT); + + /* Enable hotplug and pord interrupts */ + mtk_hdmi_v2_enable_hpd_pord_irq(hdmi, true); + + /* Force enabling HDCP HPD */ + regmap_set_bits(hdmi->regs, HDCP2X_CTRL_0, HDCP2X_HPD_OVR); + regmap_set_bits(hdmi->regs, HDCP2X_CTRL_0, HDCP2X_HPD_SW); + + /* Set 8 bits per pixel */ + regmap_update_bits(hdmi->regs, TOP_CFG00, TMDS_PACK_MODE, + FIELD_PREP(TMDS_PACK_MODE, TMDS_PACK_MODE_8BPP)); + /* Disable generating deepcolor packets */ + regmap_clear_bits(hdmi->regs, TOP_CFG00, DEEPCOLOR_PKT_EN); + /* Disable adding deepcolor information to the general packet */ + regmap_clear_bits(hdmi->regs, TOP_MISC_CTLR, DEEP_COLOR_ADD); + + if (hdmi->curr_conn->display_info.is_hdmi) + regmap_set_bits(hdmi->regs, TOP_CFG00, HDMI_MODE_HDMI); + else + regmap_clear_bits(hdmi->regs, TOP_CFG00, HDMI_MODE_HDMI); + + udelay(5); + mtk_hdmi_v2_hw_vid_mute(hdmi, true); + mtk_hdmi_v2_hw_aud_mute(hdmi, true); + mtk_hdmi_v2_hw_gcp_avmute(hdmi, false); + + regmap_update_bits(hdmi->regs, TOP_CFG01, + NULL_PKT_VSYNC_HIGH_EN | NULL_PKT_EN, NULL_PKT_VSYNC_HIGH_EN); + usleep_range(100, 150); + + /* Enable scrambling if tmds clock is 340MHz or more */ + mtk_hdmi_v2_enable_scrambling(hdmi, hdmi->mode.clock >= 340 * KILO); + + switch (conn_state->hdmi.output_format) { + default: + case HDMI_COLORSPACE_RGB: + case HDMI_COLORSPACE_YUV444: + /* Disable YUV420 downsampling for RGB and YUV444 */ + mtk_hdmi_yuv420_downsampling(hdmi, false); + break; + case HDMI_COLORSPACE_YUV422: + /* + * YUV420 downsampling is special and needs a bit of setup + * so we disable everything there before doing anything else. + * + * YUV422 downsampling instead just needs one bit to be set. + */ + mtk_hdmi_yuv420_downsampling(hdmi, false); + regmap_set_bits(hdmi->regs, VID_DOWNSAMPLE_CONFIG, + C444_C422_CONFIG_ENABLE); + break; + case HDMI_COLORSPACE_YUV420: + mtk_hdmi_yuv420_downsampling(hdmi, true); + break; + }; +} + +static void mtk_hdmi_v2_output_set_display_mode(struct mtk_hdmi *hdmi, + struct drm_connector_state *conn_state, + struct drm_display_mode *mode) +{ + union phy_configure_opts opts = { + .dp = { .link_rate = hdmi->mode.clock * KILO } + }; + int ret; + + ret = phy_configure(hdmi->phy, &opts); + if (ret) + dev_err(hdmi->dev, "Setting clock=%d failed: %d", mode->clock, ret); + + mtk_hdmi_v2_change_video_resolution(hdmi, conn_state); + mtk_hdmi_v2_aud_output_config(hdmi, mode); +} + +static int mtk_hdmi_v2_clk_enable(struct mtk_hdmi *hdmi) +{ + int ret; + + ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_V2_CLK_HDCP_SEL]); + if (ret) + return ret; + + ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_V2_CLK_HDCP_24M_SEL]); + if (ret) + goto disable_hdcp_clk; + + ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_V2_CLK_HDMI_APB_SEL]); + if (ret) + goto disable_hdcp_24m_clk; + + ret = clk_prepare_enable(hdmi->clk[MTK_HDMI_V2_CLK_VPP_SPLIT_HDMI]); + if (ret) + goto disable_bus_clk; + + return 0; + +disable_bus_clk: + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_HDMI_APB_SEL]); +disable_hdcp_24m_clk: + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_HDCP_24M_SEL]); +disable_hdcp_clk: + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_HDCP_SEL]); + + return ret; +} + +static void mtk_hdmi_v2_clk_disable(struct mtk_hdmi *hdmi) +{ + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_VPP_SPLIT_HDMI]); + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_HDMI_APB_SEL]); + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_HDCP_24M_SEL]); + clk_disable_unprepare(hdmi->clk[MTK_HDMI_V2_CLK_HDCP_SEL]); +} + +static enum hdmi_hpd_state mtk_hdmi_v2_hpd_pord_status(struct mtk_hdmi *hdmi) +{ + u8 hpd_pin_sta, pord_pin_sta; + u32 hpd_status; + + regmap_read(hdmi->regs, HPD_DDC_STATUS, &hpd_status); + hpd_pin_sta = FIELD_GET(HPD_PIN_STA, hpd_status); + pord_pin_sta = FIELD_GET(PORD_PIN_STA, hpd_status); + + /* + * Inform that the cable is plugged in (hpd_pin_sta) so that the + * sink can be powered on by switching the 5V VBUS as required by + * the HDMI spec for reading EDID and for HDMI Audio registers to + * be accessible. + * + * PORD detection succeeds only when the cable is plugged in and + * the sink is powered on: reaching that state means that the + * communication with the sink can be started. + * + * Please note that when the cable is plugged out the HPD pin will + * be the first one to fall, while PORD may still be in rise state + * for a few more milliseconds, so we decide HDMI_PLUG_OUT without + * checking PORD at all (we check only HPD falling for that). + */ + if (hpd_pin_sta && pord_pin_sta) + return HDMI_PLUG_IN_AND_SINK_POWER_ON; + else if (hpd_pin_sta) + return HDMI_PLUG_IN_ONLY; + else + return HDMI_PLUG_OUT; +} + +static irqreturn_t mtk_hdmi_v2_isr(int irq, void *arg) +{ + struct mtk_hdmi *hdmi = arg; + unsigned int irq_sta; + int ret = IRQ_HANDLED; + + regmap_read(hdmi->regs, TOP_INT_STA00, &irq_sta); + + /* Handle Hotplug Detection interrupts */ + if (irq_sta & HPD_PORD_HWIRQS) { + /* + * Disable the HPD/PORD IRQs now and until thread done to + * avoid interrupt storm that could happen with bad cables + */ + mtk_hdmi_v2_enable_hpd_pord_irq(hdmi, false); + ret = IRQ_WAKE_THREAD; + + /* Clear HPD/PORD irqs to avoid unwanted retriggering */ + regmap_write(hdmi->regs, TOP_INT_CLR00, HPD_PORD_HWIRQS); + regmap_write(hdmi->regs, TOP_INT_CLR00, 0); + } + + return ret; +} + +static irqreturn_t __mtk_hdmi_v2_isr_thread(struct mtk_hdmi *hdmi) +{ + enum hdmi_hpd_state hpd; + + hpd = mtk_hdmi_v2_hpd_pord_status(hdmi); + if (hpd != hdmi->hpd) { + struct drm_encoder *encoder = hdmi->bridge.encoder; + + hdmi->hpd = hpd; + + if (encoder && encoder->dev) + drm_helper_hpd_irq_event(hdmi->bridge.encoder->dev); + } + + mtk_hdmi_v2_enable_hpd_pord_irq(hdmi, true); + return IRQ_HANDLED; +} + +static irqreturn_t mtk_hdmi_v2_isr_thread(int irq, void *arg) +{ + struct mtk_hdmi *hdmi = arg; + + /* + * Debounce HDMI monitor HPD status. + * Empirical testing shows that 30ms is enough wait + */ + msleep(30); + + return __mtk_hdmi_v2_isr_thread(hdmi); +} + +static int mtk_hdmi_v2_enable(struct mtk_hdmi *hdmi) +{ + bool was_active = pm_runtime_active(hdmi->dev); + int ret; + + ret = pm_runtime_resume_and_get(hdmi->dev); + if (ret) { + dev_err(hdmi->dev, "Cannot resume HDMI\n"); + return ret; + } + + ret = mtk_hdmi_v2_clk_enable(hdmi); + if (ret) { + pm_runtime_put(hdmi->dev); + return ret; + } + + if (!was_active) { + mtk_hdmi_v2_hw_reset(hdmi); + mtk_hdmi_v2_set_sw_hpd(hdmi, true); + } + + return 0; +} + +static void mtk_hdmi_v2_disable(struct mtk_hdmi *hdmi) +{ + mtk_hdmi_v2_clk_disable(hdmi); + pm_runtime_put_sync(hdmi->dev); +} + +/* + * Bridge callbacks + */ + +static int mtk_hdmi_v2_bridge_attach(struct drm_bridge *bridge, + struct drm_encoder *encoder, + enum drm_bridge_attach_flags flags) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + int ret; + + if (!(flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR)) { + DRM_ERROR("The flag DRM_BRIDGE_ATTACH_NO_CONNECTOR must be supplied\n"); + return -EINVAL; + } + if (hdmi->next_bridge) { + ret = drm_bridge_attach(encoder, hdmi->next_bridge, bridge, flags); + if (ret) + return ret; + } + + ret = mtk_hdmi_v2_enable(hdmi); + if (ret) + return ret; + + /* Enable Hotplug and Pord pins internal debouncing */ + regmap_set_bits(hdmi->regs, HPD_DDC_CTRL, + HPD_DDC_HPD_DBNC_EN | HPD_DDC_PORD_DBNC_EN); + + irq_clear_status_flags(hdmi->irq, IRQ_NOAUTOEN); + enable_irq(hdmi->irq); + + /* + * Check if any HDMI monitor was connected before probing this driver + * and/or attaching the bridge, without debouncing: if so, we want to + * notify the DRM so that we start outputting an image ASAP. + * Note that calling the ISR thread function will also perform a HW + * registers write that enables both the HPD and Pord interrupts. + */ + __mtk_hdmi_v2_isr_thread(hdmi); + + mtk_hdmi_v2_disable(hdmi); + + return 0; +} + +static void mtk_hdmi_v2_bridge_detach(struct drm_bridge *bridge) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + WARN_ON(pm_runtime_active(hdmi->dev)); + + /* The controller is already powered off, just disable irq here */ + disable_irq(hdmi->irq); +} + +static void mtk_hdmi_v2_handle_plugged_change(struct mtk_hdmi *hdmi, bool plugged) +{ + mutex_lock(&hdmi->update_plugged_status_lock); + if (hdmi->plugged_cb && hdmi->codec_dev) + hdmi->plugged_cb(hdmi->codec_dev, plugged); + mutex_unlock(&hdmi->update_plugged_status_lock); +} + +static void mtk_hdmi_v2_bridge_pre_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + struct drm_connector_state *conn_state; + union phy_configure_opts opts = { + .dp = { .link_rate = hdmi->mode.clock * KILO } + }; + int ret; + + /* Power on the controller before trying to write to registers */ + ret = mtk_hdmi_v2_enable(hdmi); + if (WARN_ON(ret)) + return; + + /* Retrieve the connector through the atomic state */ + hdmi->curr_conn = drm_atomic_get_new_connector_for_encoder(state, bridge->encoder); + + conn_state = drm_atomic_get_new_connector_state(state, hdmi->curr_conn); + if (WARN_ON(!conn_state)) + return; + + /* + * Preconfigure the HDMI controller and the HDMI PHY at pre_enable + * stage to make sure that this IP is ready and clocked before the + * mtk_dpi gets powered on and before it enables the output. + */ + mtk_hdmi_v2_output_set_display_mode(hdmi, conn_state, &hdmi->mode); + + /* Reconfigure phy clock link with appropriate rate */ + phy_configure(hdmi->phy, &opts); + + /* Power on the PHY here to make sure that DPI_HDMI is clocked */ + phy_power_on(hdmi->phy); + + hdmi->powered = true; +} + +static void mtk_hdmi_v2_bridge_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + int ret; + + if (WARN_ON(!hdmi->powered)) + return; + + ret = drm_atomic_helper_connector_hdmi_update_infoframes(hdmi->curr_conn, state); + if (ret) + dev_err(hdmi->dev, "Could not update infoframes: %d\n", ret); + + mtk_hdmi_v2_hw_vid_mute(hdmi, false); + + /* signal the connect event to audio codec */ + mtk_hdmi_v2_handle_plugged_change(hdmi, true); + + hdmi->enabled = true; +} + +static void mtk_hdmi_v2_bridge_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + if (!hdmi->enabled) + return; + + mtk_hdmi_v2_hw_gcp_avmute(hdmi, true); + msleep(50); + mtk_hdmi_v2_hw_vid_mute(hdmi, true); + mtk_hdmi_v2_hw_aud_mute(hdmi, true); + msleep(50); + + hdmi->enabled = false; +} + +static void mtk_hdmi_v2_bridge_post_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + if (!hdmi->powered) + return; + + phy_power_off(hdmi->phy); + hdmi->powered = false; + + /* signal the disconnect event to audio codec */ + mtk_hdmi_v2_handle_plugged_change(hdmi, false); + + /* Power off */ + mtk_hdmi_v2_disable(hdmi); +} + +static enum drm_connector_status mtk_hdmi_v2_bridge_detect(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + return hdmi->hpd != HDMI_PLUG_OUT ? + connector_status_connected : connector_status_disconnected; +} + +static const struct drm_edid *mtk_hdmi_v2_bridge_edid_read(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + return drm_edid_read(connector); +} + +static void mtk_hdmi_v2_hpd_enable(struct drm_bridge *bridge) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + int ret; + + ret = mtk_hdmi_v2_enable(hdmi); + if (ret) { + dev_err(hdmi->dev, "Cannot power on controller for HPD: %d\n", ret); + return; + } + + mtk_hdmi_v2_enable_hpd_pord_irq(hdmi, true); +} + +static void mtk_hdmi_v2_hpd_disable(struct drm_bridge *bridge) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + mtk_hdmi_v2_enable_hpd_pord_irq(hdmi, false); + mtk_hdmi_v2_disable(hdmi); +} + +static int mtk_hdmi_v2_hdmi_tmds_char_rate_valid(const struct drm_bridge *bridge, + const struct drm_display_mode *mode, + unsigned long long tmds_rate) +{ + if (mode->clock < MTK_HDMI_V2_CLOCK_MIN) + return MODE_CLOCK_LOW; + else if (mode->clock > MTK_HDMI_V2_CLOCK_MAX) + return MODE_CLOCK_HIGH; + else + return MODE_OK; +} + +static int mtk_hdmi_v2_hdmi_clear_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + switch (type) { + case HDMI_INFOFRAME_TYPE_AUDIO: + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, AUD_EN_WR | AUD_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, AUD_RPT_EN); + break; + case HDMI_INFOFRAME_TYPE_AVI: + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, AVI_EN_WR | AVI_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, AVI_RPT_EN); + break; + case HDMI_INFOFRAME_TYPE_SPD: + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, SPD_EN_WR | SPD_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, SPD_RPT_EN); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + regmap_clear_bits(hdmi->regs, TOP_INFO_EN, VSIF_EN_WR | VSIF_EN); + regmap_clear_bits(hdmi->regs, TOP_INFO_RPT, VSIF_RPT_EN); + break; + case HDMI_INFOFRAME_TYPE_DRM: + default: + break; + }; + + return 0; +} + +static int mtk_hdmi_v2_hdmi_write_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type, + const u8 *buffer, size_t len) +{ + struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); + + switch (type) { + case HDMI_INFOFRAME_TYPE_AUDIO: + mtk_hdmi_v2_hw_write_audio_infoframe(hdmi, buffer); + break; + case HDMI_INFOFRAME_TYPE_AVI: + mtk_hdmi_v2_hw_write_avi_infoframe(hdmi, buffer); + break; + case HDMI_INFOFRAME_TYPE_SPD: + mtk_hdmi_v2_hw_write_spd_infoframe(hdmi, buffer); + break; + case HDMI_INFOFRAME_TYPE_VENDOR: + mtk_hdmi_v2_hw_write_vendor_infoframe(hdmi, buffer); + break; + case HDMI_INFOFRAME_TYPE_DRM: + default: + dev_err(hdmi->dev, "Unsupported HDMI infoframe type %u\n", type); + break; + }; + + return 0; +} + +static int mtk_hdmi_v2_set_abist(struct mtk_hdmi *hdmi, bool enable) +{ + struct drm_display_mode *mode = &hdmi->mode; + int abist_format = -EINVAL; + bool interlaced; + + if (!enable) { + regmap_clear_bits(hdmi->regs, TOP_CFG00, HDMI_ABIST_ENABLE); + return 0; + } + + if (!mode->hdisplay || !mode->vdisplay) + return -EINVAL; + + interlaced = mode->flags & DRM_MODE_FLAG_INTERLACE; + + switch (mode->hdisplay) { + case 720: + if (mode->vdisplay == 480) + abist_format = 2; + else if (mode->vdisplay == 576) + abist_format = 11; + break; + case 1280: + if (mode->vdisplay == 720) + abist_format = 3; + break; + case 1440: + if (mode->vdisplay == 480) + abist_format = interlaced ? 5 : 9; + else if (mode->vdisplay == 576) + abist_format = interlaced ? 14 : 18; + break; + case 1920: + if (mode->vdisplay == 1080) + abist_format = interlaced ? 4 : 10; + break; + case 3840: + if (mode->vdisplay == 2160) + abist_format = 25; + break; + case 4096: + if (mode->vdisplay == 2160) + abist_format = 26; + break; + default: + break; + } + if (abist_format < 0) + return abist_format; + + regmap_update_bits(hdmi->regs, TOP_CFG00, HDMI_ABIST_VIDEO_FORMAT, + FIELD_PREP(HDMI_ABIST_VIDEO_FORMAT, abist_format)); + regmap_set_bits(hdmi->regs, TOP_CFG00, HDMI_ABIST_ENABLE); + return 0; +} + +static int mtk_hdmi_v2_debug_abist_show(struct seq_file *m, void *arg) +{ + struct mtk_hdmi *hdmi = m->private; + bool en; + u32 val; + int ret; + + if (!hdmi) + return -EINVAL; + + ret = regmap_read(hdmi->regs, TOP_CFG00, &val); + if (ret) + return ret; + + en = FIELD_GET(HDMI_ABIST_ENABLE, val); + + seq_printf(m, "HDMI Automated Built-In Self Test: %s\n", + en ? "Enabled" : "Disabled"); + + return 0; +} + +static ssize_t mtk_hdmi_v2_debug_abist_write(struct file *file, + const char __user *ubuf, + size_t len, loff_t *offp) +{ + struct seq_file *m = file->private_data; + int ret; + u32 en; + + if (!m || !m->private || *offp) + return -EINVAL; + + ret = kstrtouint_from_user(ubuf, len, 0, &en); + if (ret) + return ret; + + if (en < 0 || en > 1) + return -EINVAL; + + mtk_hdmi_v2_set_abist((struct mtk_hdmi *)m->private, en); + return len; +} + +static int mtk_hdmi_v2_debug_abist_open(struct inode *inode, struct file *file) +{ + return single_open(file, mtk_hdmi_v2_debug_abist_show, inode->i_private); +} + +static const struct file_operations mtk_hdmi_debug_abist_fops = { + .owner = THIS_MODULE, + .open = mtk_hdmi_v2_debug_abist_open, + .read = seq_read, + .write = mtk_hdmi_v2_debug_abist_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static void mtk_hdmi_v2_debugfs_init(struct drm_bridge *bridge, struct dentry *root) +{ + struct mtk_hdmi *dpi = hdmi_ctx_from_bridge(bridge); + + debugfs_create_file("hdmi_abist", 0640, root, dpi, &mtk_hdmi_debug_abist_fops); +} + +static const struct drm_bridge_funcs mtk_v2_hdmi_bridge_funcs = { + .attach = mtk_hdmi_v2_bridge_attach, + .detach = mtk_hdmi_v2_bridge_detach, + .mode_fixup = mtk_hdmi_bridge_mode_fixup, + .mode_set = mtk_hdmi_bridge_mode_set, + .atomic_pre_enable = mtk_hdmi_v2_bridge_pre_enable, + .atomic_enable = mtk_hdmi_v2_bridge_enable, + .atomic_disable = mtk_hdmi_v2_bridge_disable, + .atomic_post_disable = mtk_hdmi_v2_bridge_post_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .detect = mtk_hdmi_v2_bridge_detect, + .edid_read = mtk_hdmi_v2_bridge_edid_read, + .hpd_enable = mtk_hdmi_v2_hpd_enable, + .hpd_disable = mtk_hdmi_v2_hpd_disable, + .hdmi_tmds_char_rate_valid = mtk_hdmi_v2_hdmi_tmds_char_rate_valid, + .hdmi_clear_infoframe = mtk_hdmi_v2_hdmi_clear_infoframe, + .hdmi_write_infoframe = mtk_hdmi_v2_hdmi_write_infoframe, + .debugfs_init = mtk_hdmi_v2_debugfs_init, +}; + +/* + * HDMI audio codec callbacks + */ +static int mtk_hdmi_v2_audio_hook_plugged_cb(struct device *dev, void *data, + hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + bool plugged; + + if (!hdmi) + return -ENODEV; + + mtk_hdmi_audio_set_plugged_cb(hdmi, fn, codec_dev); + plugged = (hdmi->hpd == HDMI_PLUG_IN_AND_SINK_POWER_ON); + mtk_hdmi_v2_handle_plugged_change(hdmi, plugged); + + return 0; +} + +static int mtk_hdmi_v2_audio_hw_params(struct device *dev, void *data, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + if (hdmi->audio_enable) { + mtk_hdmi_audio_params(hdmi, daifmt, params); + mtk_hdmi_v2_aud_output_config(hdmi, &hdmi->mode); + } + return 0; +} + +static int mtk_hdmi_v2_audio_startup(struct device *dev, void *data) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + mtk_hdmi_v2_hw_aud_enable(hdmi, true); + hdmi->audio_enable = true; + + return 0; +} + +static void mtk_hdmi_v2_audio_shutdown(struct device *dev, void *data) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + hdmi->audio_enable = false; + mtk_hdmi_v2_hw_aud_enable(hdmi, false); +} + +static int mtk_hdmi_v2_audio_mute(struct device *dev, void *data, bool enable, int dir) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + mtk_hdmi_v2_hw_aud_mute(hdmi, enable); + + return 0; +} + +static const struct hdmi_codec_ops mtk_hdmi_v2_audio_codec_ops = { + .hw_params = mtk_hdmi_v2_audio_hw_params, + .audio_startup = mtk_hdmi_v2_audio_startup, + .audio_shutdown = mtk_hdmi_v2_audio_shutdown, + .mute_stream = mtk_hdmi_v2_audio_mute, + .get_eld = mtk_hdmi_audio_get_eld, + .hook_plugged_cb = mtk_hdmi_v2_audio_hook_plugged_cb, +}; + +static __maybe_unused int mtk_hdmi_v2_suspend(struct device *dev) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + mtk_hdmi_v2_disable(hdmi); + + return 0; +} + +static __maybe_unused int mtk_hdmi_v2_resume(struct device *dev) +{ + struct mtk_hdmi *hdmi = dev_get_drvdata(dev); + + return mtk_hdmi_v2_enable(hdmi); +} + +static SIMPLE_DEV_PM_OPS(mtk_hdmi_v2_pm_ops, mtk_hdmi_v2_suspend, mtk_hdmi_v2_resume); + +static const struct mtk_hdmi_ver_conf mtk_hdmi_conf_v2 = { + .bridge_funcs = &mtk_v2_hdmi_bridge_funcs, + .codec_ops = &mtk_hdmi_v2_audio_codec_ops, + .mtk_hdmi_clock_names = mtk_hdmi_v2_clk_names, + .num_clocks = MTK_HDMI_V2_CLK_COUNT, + .interlace_allowed = true, +}; + +static const struct mtk_hdmi_conf mtk_hdmi_conf_mt8188 = { + .ver_conf = &mtk_hdmi_conf_v2, + .reg_hdmi_tx_cfg = HDMITX_CONFIG_MT8188 +}; + +static const struct mtk_hdmi_conf mtk_hdmi_conf_mt8195 = { + .ver_conf = &mtk_hdmi_conf_v2, + .reg_hdmi_tx_cfg = HDMITX_CONFIG_MT8195 +}; + +static int mtk_hdmi_v2_probe(struct platform_device *pdev) +{ + struct mtk_hdmi *hdmi; + int ret; + + /* Populate HDMI sub-devices if present */ + ret = devm_of_platform_populate(&pdev->dev); + if (ret) + return ret; + + hdmi = mtk_hdmi_common_probe(pdev); + if (IS_ERR(hdmi)) + return PTR_ERR(hdmi); + + hdmi->hpd = HDMI_PLUG_OUT; + + /* Disable all HW interrupts at probe stage */ + mtk_hdmi_v2_hwirq_disable(hdmi); + + /* + * In case bootloader leaves HDMI enabled before booting, make + * sure that any interrupt that was left is cleared by setting + * all bits in the INT_CLR registers for all 32+19 interrupts. + */ + regmap_write(hdmi->regs, TOP_INT_CLR00, GENMASK(31, 0)); + regmap_write(hdmi->regs, TOP_INT_CLR01, GENMASK(18, 0)); + + /* Restore interrupt clearing registers to zero */ + regmap_write(hdmi->regs, TOP_INT_CLR00, 0); + regmap_write(hdmi->regs, TOP_INT_CLR01, 0); + + /* + * Install the ISR but keep it disabled: as the interrupts are + * being set up in the .bridge_attach() callback which will + * enable both the right HW IRQs and the ISR. + */ + irq_set_status_flags(hdmi->irq, IRQ_NOAUTOEN); + ret = devm_request_threaded_irq(&pdev->dev, hdmi->irq, mtk_hdmi_v2_isr, + mtk_hdmi_v2_isr_thread, + IRQ_TYPE_LEVEL_HIGH, + dev_name(&pdev->dev), hdmi); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Cannot request IRQ\n"); + + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Cannot enable Runtime PM\n"); + + return 0; +} + +static void mtk_hdmi_v2_remove(struct platform_device *pdev) +{ + struct mtk_hdmi *hdmi = platform_get_drvdata(pdev); + + i2c_put_adapter(hdmi->ddc_adpt); +} + +static const struct of_device_id mtk_drm_hdmi_v2_of_ids[] = { + { .compatible = "mediatek,mt8188-hdmi-tx", .data = &mtk_hdmi_conf_mt8188 }, + { .compatible = "mediatek,mt8195-hdmi-tx", .data = &mtk_hdmi_conf_mt8195 }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, mtk_drm_hdmi_v2_of_ids); + +static struct platform_driver mtk_hdmi_v2_driver = { + .probe = mtk_hdmi_v2_probe, + .remove = mtk_hdmi_v2_remove, + .driver = { + .name = "mediatek-drm-hdmi-v2", + .of_match_table = mtk_drm_hdmi_v2_of_ids, + .pm = &mtk_hdmi_v2_pm_ops, + }, +}; +module_platform_driver(mtk_hdmi_v2_driver); + +MODULE_AUTHOR("AngeloGioacchino Del Regno >"); +MODULE_DESCRIPTION("MediaTek HDMIv2 Driver"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("DRM_MTK_HDMI"); diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index c22166476423..5043e0377270 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -22,9 +22,6 @@ static const u64 modifiers[] = { DRM_FORMAT_MOD_LINEAR, - DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | - AFBC_FORMAT_MOD_SPLIT | - AFBC_FORMAT_MOD_SPARSE), DRM_FORMAT_MOD_INVALID, }; @@ -72,26 +69,7 @@ static bool mtk_plane_format_mod_supported(struct drm_plane *plane, uint32_t format, uint64_t modifier) { - if (modifier == DRM_FORMAT_MOD_LINEAR) - return true; - - if (modifier != DRM_FORMAT_MOD_ARM_AFBC( - AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | - AFBC_FORMAT_MOD_SPLIT | - AFBC_FORMAT_MOD_SPARSE)) - return false; - - if (format != DRM_FORMAT_XRGB8888 && - format != DRM_FORMAT_ARGB8888 && - format != DRM_FORMAT_BGRX8888 && - format != DRM_FORMAT_BGRA8888 && - format != DRM_FORMAT_ABGR8888 && - format != DRM_FORMAT_XBGR8888 && - format != DRM_FORMAT_RGB888 && - format != DRM_FORMAT_BGR888) - return false; - - return true; + return modifier == DRM_FORMAT_MOD_LINEAR; } static void mtk_plane_destroy_state(struct drm_plane *plane, diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 0c0dfb25f01b..8aa7d07303fb 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -24,6 +24,7 @@ adreno-y := \ adreno/a6xx_gmu.o \ adreno/a6xx_hfi.o \ adreno/a6xx_preempt.o \ + adreno/a8xx_gpu.o \ adreno-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \ @@ -201,6 +202,7 @@ ADRENO_HEADERS = \ generated/a6xx_perfcntrs.xml.h \ generated/a7xx_enums.xml.h \ generated/a7xx_perfcntrs.xml.h \ + generated/a8xx_enums.xml.h \ generated/a6xx_gmu.xml.h \ generated/adreno_common.xml.h \ generated/adreno_pm4.xml.h \ diff --git a/drivers/gpu/drm/msm/adreno/a2xx_catalog.c b/drivers/gpu/drm/msm/adreno/a2xx_catalog.c index 5ddd015f930d..e9dbf3ddf89e 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a2xx_gpu.h" static const struct adreno_info a2xx_gpus[] = { { @@ -19,7 +20,7 @@ static const struct adreno_info a2xx_gpus[] = { }, .gmem = SZ_256K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a2xx_gpu_init, + .funcs = &a2xx_gpu_funcs, }, { /* a200 on i.mx51 has only 128kib gmem */ .chip_ids = ADRENO_CHIP_IDS(0x02000001), .family = ADRENO_2XX_GEN1, @@ -30,7 +31,7 @@ static const struct adreno_info a2xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a2xx_gpu_init, + .funcs = &a2xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x02020000), .family = ADRENO_2XX_GEN2, @@ -41,7 +42,7 @@ static const struct adreno_info a2xx_gpus[] = { }, .gmem = SZ_512K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a2xx_gpu_init, + .funcs = &a2xx_gpu_funcs, } }; DECLARE_ADRENO_GPULIST(a2xx); diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index ec38db45d8a3..1b1ee14b65cf 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -234,7 +234,7 @@ static int a2xx_hw_init(struct msm_gpu *gpu) * word (0x20xxxx for A200, 0x220xxx for A220, 0x225xxx for A225). * Older firmware files, which lack protection support, have 0 instead. */ - if (ptr[1] == 0) { + if (ptr[1] == 0 && !a2xx_gpu->protection_disabled) { dev_warn(gpu->dev->dev, "Legacy firmware detected, disabling protection support\n"); a2xx_gpu->protection_disabled = true; @@ -486,39 +486,18 @@ static u32 a2xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr; } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a2xx_hw_init, - .pm_suspend = msm_gpu_pm_suspend, - .pm_resume = msm_gpu_pm_resume, - .recover = a2xx_recover, - .submit = a2xx_submit, - .active_ring = adreno_active_ring, - .irq = a2xx_irq, - .destroy = a2xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = adreno_show, -#endif - .gpu_state_get = a2xx_gpu_state_get, - .gpu_state_put = adreno_gpu_state_put, - .create_vm = a2xx_create_vm, - .get_rptr = a2xx_get_rptr, - }, -}; - static const struct msm_gpu_perfcntr perfcntrs[] = { /* TODO */ }; -struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) { struct a2xx_gpu *a2xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; int ret; if (!pdev) { @@ -539,7 +518,7 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) gpu->perfcntrs = perfcntrs; gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs); - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, 1); if (ret) goto fail; @@ -558,3 +537,26 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } + +const struct adreno_gpu_funcs a2xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a2xx_hw_init, + .pm_suspend = msm_gpu_pm_suspend, + .pm_resume = msm_gpu_pm_resume, + .recover = a2xx_recover, + .submit = a2xx_submit, + .active_ring = adreno_active_ring, + .irq = a2xx_irq, + .destroy = a2xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_state_get = a2xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + .create_vm = a2xx_create_vm, + .get_rptr = a2xx_get_rptr, + }, + .init = a2xx_gpu_init, +}; diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.h b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h index 53702f19990f..162ef98951f5 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h @@ -19,6 +19,8 @@ struct a2xx_gpu { }; #define to_a2xx_gpu(x) container_of(x, struct a2xx_gpu, base) +extern const struct adreno_gpu_funcs a2xx_gpu_funcs; + struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu); void a2xx_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base, dma_addr_t *tran_error); diff --git a/drivers/gpu/drm/msm/adreno/a3xx_catalog.c b/drivers/gpu/drm/msm/adreno/a3xx_catalog.c index 1498e6532f62..6ae8716fc08a 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a3xx_gpu.h" static const struct adreno_info a3xx_gpus[] = { { @@ -18,7 +19,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x03000520), .family = ADRENO_3XX, @@ -29,7 +30,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_256K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x03000600), .family = ADRENO_3XX, @@ -40,7 +41,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x03000620), .family = ADRENO_3XX, @@ -51,7 +52,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS( 0x03020000, @@ -66,7 +67,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_512K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS( 0x03030000, @@ -81,7 +82,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_1M, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, } }; DECLARE_ADRENO_GPULIST(a3xx); diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index a956cd79195e..f22d33e99e81 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -508,29 +508,6 @@ static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr; } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a3xx_hw_init, - .pm_suspend = msm_gpu_pm_suspend, - .pm_resume = msm_gpu_pm_resume, - .recover = a3xx_recover, - .submit = a3xx_submit, - .active_ring = adreno_active_ring, - .irq = a3xx_irq, - .destroy = a3xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = adreno_show, -#endif - .gpu_busy = a3xx_gpu_busy, - .gpu_state_get = a3xx_gpu_state_get, - .gpu_state_put = adreno_gpu_state_put, - .create_vm = adreno_create_vm, - .get_rptr = a3xx_get_rptr, - }, -}; - static const struct msm_gpu_perfcntr perfcntrs[] = { { REG_A3XX_SP_PERFCOUNTER6_SELECT, REG_A3XX_RBBM_PERFCTR_SP_6_LO, SP_ALU_ACTIVE_CYCLES, "ALUACTIVE" }, @@ -538,13 +515,14 @@ static const struct msm_gpu_perfcntr perfcntrs[] = { SP_FS_FULL_ALU_INSTRUCTIONS, "ALUFULL" }, }; -struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) { struct a3xx_gpu *a3xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; struct icc_path *ocmem_icc_path; struct icc_path *icc_path; int ret; @@ -569,7 +547,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = a3xx_registers; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, 1); if (ret) goto fail; @@ -613,3 +591,27 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } + +const struct adreno_gpu_funcs a3xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a3xx_hw_init, + .pm_suspend = msm_gpu_pm_suspend, + .pm_resume = msm_gpu_pm_resume, + .recover = a3xx_recover, + .submit = a3xx_submit, + .active_ring = adreno_active_ring, + .irq = a3xx_irq, + .destroy = a3xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_busy = a3xx_gpu_busy, + .gpu_state_get = a3xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + .create_vm = adreno_create_vm, + .get_rptr = a3xx_get_rptr, + }, + .init = a3xx_gpu_init, +}; diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h index c555fb13e0d7..3d4ec9dbd918 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h @@ -23,4 +23,6 @@ struct a3xx_gpu { }; #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base) +extern const struct adreno_gpu_funcs a3xx_gpu_funcs; + #endif /* __A3XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a4xx_catalog.c b/drivers/gpu/drm/msm/adreno/a4xx_catalog.c index 09f9f228b75e..9192586f7ef0 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a4xx_gpu.h" static const struct adreno_info a4xx_gpus[] = { { @@ -19,7 +20,7 @@ static const struct adreno_info a4xx_gpus[] = { }, .gmem = SZ_256K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a4xx_gpu_init, + .funcs = &a4xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x04020000), .family = ADRENO_4XX, @@ -30,7 +31,7 @@ static const struct adreno_info a4xx_gpus[] = { }, .gmem = (SZ_1M + SZ_512K), .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a4xx_gpu_init, + .funcs = &a4xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x04030002), .family = ADRENO_4XX, @@ -41,7 +42,7 @@ static const struct adreno_info a4xx_gpus[] = { }, .gmem = (SZ_1M + SZ_512K), .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a4xx_gpu_init, + .funcs = &a4xx_gpu_funcs, } }; DECLARE_ADRENO_GPULIST(a4xx); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 83f6329accba..db06c06067ae 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -627,37 +627,14 @@ static u32 a4xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr; } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a4xx_hw_init, - .pm_suspend = a4xx_pm_suspend, - .pm_resume = a4xx_pm_resume, - .recover = a4xx_recover, - .submit = a4xx_submit, - .active_ring = adreno_active_ring, - .irq = a4xx_irq, - .destroy = a4xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = adreno_show, -#endif - .gpu_busy = a4xx_gpu_busy, - .gpu_state_get = a4xx_gpu_state_get, - .gpu_state_put = adreno_gpu_state_put, - .create_vm = adreno_create_vm, - .get_rptr = a4xx_get_rptr, - }, - .get_timestamp = a4xx_get_timestamp, -}; - -struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) { struct a4xx_gpu *a4xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; struct icc_path *ocmem_icc_path; struct icc_path *icc_path; int ret; @@ -680,7 +657,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) gpu->perfcntrs = NULL; gpu->num_perfcntrs = 0; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, 1); if (ret) goto fail; @@ -726,3 +703,28 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } + +const struct adreno_gpu_funcs a4xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a4xx_hw_init, + .pm_suspend = a4xx_pm_suspend, + .pm_resume = a4xx_pm_resume, + .recover = a4xx_recover, + .submit = a4xx_submit, + .active_ring = adreno_active_ring, + .irq = a4xx_irq, + .destroy = a4xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_busy = a4xx_gpu_busy, + .gpu_state_get = a4xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + .create_vm = adreno_create_vm, + .get_rptr = a4xx_get_rptr, + }, + .init = a4xx_gpu_init, + .get_timestamp = a4xx_get_timestamp, +}; diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h index a01448cba2ea..71b164439f62 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h @@ -20,4 +20,6 @@ struct a4xx_gpu { }; #define to_a4xx_gpu(x) container_of(x, struct a4xx_gpu, base) +extern const struct adreno_gpu_funcs a4xx_gpu_funcs; + #endif /* __A4XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a5xx_catalog.c b/drivers/gpu/drm/msm/adreno/a5xx_catalog.c index b48a636d8237..babd320f3b73 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a5xx_gpu.h" static const struct adreno_info a5xx_gpus[] = { { @@ -21,7 +22,7 @@ static const struct adreno_info a5xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x05000600), .family = ADRENO_5XX, @@ -38,7 +39,7 @@ static const struct adreno_info a5xx_gpus[] = { .inactive_period = 250, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a506_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS(0x05000800), @@ -55,7 +56,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a508_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS(0x05000900), @@ -72,7 +73,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, /* Adreno 509 uses the same ZAP as 512 */ .zapfw = "a512_zap.mdt", }, { @@ -89,7 +90,7 @@ static const struct adreno_info a5xx_gpus[] = { * the GDSC which appears to make it grumpy */ .inactive_period = 250, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x05010200), .family = ADRENO_5XX, @@ -105,7 +106,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a512_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS( @@ -127,7 +128,7 @@ static const struct adreno_info a5xx_gpus[] = { .inactive_period = 250, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_FAULT_DETECT_MASK, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a530_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS(0x05040001), @@ -145,7 +146,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a540_zap.mdt", } }; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 4a04dc43a8e6..56eaff2ee4e4 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1691,34 +1691,6 @@ static uint32_t a5xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr = gpu_read(gpu, REG_A5XX_CP_RB_RPTR); } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a5xx_hw_init, - .ucode_load = a5xx_ucode_load, - .pm_suspend = a5xx_pm_suspend, - .pm_resume = a5xx_pm_resume, - .recover = a5xx_recover, - .submit = a5xx_submit, - .active_ring = a5xx_active_ring, - .irq = a5xx_irq, - .destroy = a5xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = a5xx_show, -#endif -#if defined(CONFIG_DEBUG_FS) - .debugfs_init = a5xx_debugfs_init, -#endif - .gpu_busy = a5xx_gpu_busy, - .gpu_state_get = a5xx_gpu_state_get, - .gpu_state_put = a5xx_gpu_state_put, - .create_vm = adreno_create_vm, - .get_rptr = a5xx_get_rptr, - }, - .get_timestamp = a5xx_get_timestamp, -}; - static void check_speed_bin(struct device *dev) { struct nvmem_cell *cell; @@ -1751,7 +1723,7 @@ static void check_speed_bin(struct device *dev) devm_pm_opp_set_supported_hw(dev, &val, 1); } -struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; @@ -1781,7 +1753,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) if (config->info->revn == 510) nr_rings = 1; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, nr_rings); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, nr_rings); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); @@ -1806,3 +1778,32 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) return gpu; } + +const struct adreno_gpu_funcs a5xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a5xx_hw_init, + .ucode_load = a5xx_ucode_load, + .pm_suspend = a5xx_pm_suspend, + .pm_resume = a5xx_pm_resume, + .recover = a5xx_recover, + .submit = a5xx_submit, + .active_ring = a5xx_active_ring, + .irq = a5xx_irq, + .destroy = a5xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = a5xx_show, +#endif +#if defined(CONFIG_DEBUG_FS) + .debugfs_init = a5xx_debugfs_init, +#endif + .gpu_busy = a5xx_gpu_busy, + .gpu_state_get = a5xx_gpu_state_get, + .gpu_state_put = a5xx_gpu_state_put, + .create_vm = adreno_create_vm, + .get_rptr = a5xx_get_rptr, + }, + .init = a5xx_gpu_init, + .get_timestamp = a5xx_get_timestamp, +}; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 9c0d701fe4b8..407bb950d350 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -133,6 +133,7 @@ struct a5xx_preempt_record { */ #define A5XX_PREEMPT_COUNTER_SIZE (16 * 4) +extern const struct adreno_gpu_funcs a5xx_gpu_funcs; int a5xx_power_init(struct msm_gpu *gpu); void a5xx_gpmu_ucode_init(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 44df6410bce1..29107b362346 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -672,6 +672,14 @@ static const u32 a690_protect_regs[] = { }; DECLARE_ADRENO_PROTECT(a690_protect, 48); +static const struct adreno_reglist a640_gbif[] = { + { REG_A6XX_GBIF_QSB_SIDE0, 0x00071620 }, + { REG_A6XX_GBIF_QSB_SIDE1, 0x00071620 }, + { REG_A6XX_GBIF_QSB_SIDE2, 0x00071620 }, + { REG_A6XX_GBIF_QSB_SIDE3, 0x00071620 }, + { }, +}; + static const struct adreno_info a6xx_gpus[] = { { .chip_ids = ADRENO_CHIP_IDS(0x06010000), @@ -683,11 +691,12 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = (SZ_128K + SZ_4K), .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gmuwrapper_funcs, .zapfw = "a610_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a612_hwcg, .protect = &a630_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00080000, }, @@ -705,6 +714,22 @@ static const struct adreno_info a6xx_gpus[] = { { 157, 3 }, { 127, 4 }, ), + }, { + .chip_ids = ADRENO_CHIP_IDS(0x06010200), + .family = ADRENO_6XX_GEN1, + .fw = { + [ADRENO_FW_SQE] = "a630_sqe.fw", + [ADRENO_FW_GMU] = "a612_rgmu.bin", + }, + .gmem = (SZ_128K + SZ_4K), + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .funcs = &a6xx_gmuwrapper_funcs, + .a6xx = &(const struct a6xx_info) { + .hwcg = a612_hwcg, + .protect = &a630_protect, + .gmu_cgc_mode = 0x00000022, + .prim_fifo_threshold = 0x00080000, + }, }, { .chip_ids = ADRENO_CHIP_IDS(0x06010500), .family = ADRENO_6XX_GEN1, @@ -716,7 +741,7 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = SZ_512K, .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -747,7 +772,7 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -774,7 +799,7 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .protect = &a630_protect, .gmu_cgc_mode = 0x00000222, @@ -797,7 +822,7 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = SZ_512K, .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -822,7 +847,7 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = SZ_512K, .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -847,7 +872,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -873,11 +898,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a620_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a620_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00010000, }, @@ -896,10 +922,11 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a690_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00010000, .bcms = (const struct a6xx_bcm[]) { @@ -933,7 +960,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a630_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a630_hwcg, @@ -953,7 +980,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a640_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a640_hwcg, @@ -977,11 +1004,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a650_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a650_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00300200, }, @@ -1003,11 +1031,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a660_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a660_hwcg, .protect = &a660_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020000, .prim_fifo_threshold = 0x00300200, }, @@ -1022,10 +1051,11 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a690_hwcg, .protect = &a660_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00300200, }, @@ -1045,11 +1075,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a660_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a660_hwcg, .protect = &a660_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00200200, }, @@ -1072,7 +1103,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a640_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a640_hwcg, @@ -1091,11 +1122,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a690_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a690_hwcg, .protect = &a690_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00800200, }, @@ -1426,11 +1458,12 @@ static const struct adreno_info a7xx_gpus[] = { .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gmuwrapper_funcs, .zapfw = "a702_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a702_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x0000c000, }, @@ -1452,12 +1485,13 @@ static const struct adreno_info a7xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .zapfw = "a730_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a730_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020000, }, .preempt_record_size = 2860 * SZ_1K, @@ -1473,12 +1507,13 @@ static const struct adreno_info a7xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .zapfw = "a740_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x7020100, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { @@ -1507,12 +1542,13 @@ static const struct adreno_info a7xx_gpus[] = { ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION | ADRENO_QUIRK_IFPC, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, .ifpc_reglist = &a750_ifpc_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x7050001, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { @@ -1548,12 +1584,13 @@ static const struct adreno_info a7xx_gpus[] = { ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION | ADRENO_QUIRK_IFPC, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .zapfw = "gen70900_zap.mbn", .a6xx = &(const struct a6xx_info) { .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, .ifpc_reglist = &a750_ifpc_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x7090100, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { @@ -1581,11 +1618,12 @@ static const struct adreno_info a7xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x70f0000, .gmu_cgc_mode = 0x00020222, .bcms = (const struct a6xx_bcm[]) { @@ -1612,6 +1650,306 @@ static const struct adreno_info a7xx_gpus[] = { }; DECLARE_ADRENO_GPULIST(a7xx); +static const struct adreno_reglist_pipe x285_nonctxt_regs[] = { + { REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) }, + { REG_A8XX_GRAS_DBG_ECO_CNTL, 0x00000800, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_GRAS_TSEFE_DBG_ECO_CNTL, 0x00200000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A6XX_PC_AUTO_VERTEX_STRIDE, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_VIS_STREAM_CNTL, 0x10010000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CONTEXT_SWITCH_STABILIZE_CNTL_1, 0x00000002, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_1, 0x00000003, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_2, 0x00000200, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_3, 0x00500000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_4, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_RB_GC_GMEM_PROTECT, 0x15000000, BIT(PIPE_BR) }, + { REG_A8XX_RB_RESOLVE_PREFETCH_CNTL, 0x00000007, BIT(PIPE_BR) }, + { REG_A8XX_RB_CMP_DBG_ECO_CNTL, 0x00004000, BIT(PIPE_BR) }, + { REG_A8XX_RBBM_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_SLICE_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL2, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_INTERFACE_HANG_INT_CNTL, 0x0fffffff, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x22122212, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_CGC_P2S_CNTL, 0x00000040, BIT(PIPE_NONE) }, + { REG_A7XX_SP_CHICKEN_BITS_2, 0x00820800, BIT(PIPE_NONE) }, + { REG_A7XX_SP_CHICKEN_BITS_3, 0x00300000, BIT(PIPE_NONE) }, + { REG_A6XX_SP_PERFCTR_SHADER_MASK, 0x0000003f, BIT(PIPE_NONE) }, + /* Disable CS dead batch merge */ + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL_2, BIT(31), BIT(PIPE_NONE) }, + { REG_A7XX_SP_HLSQ_TIMEOUT_THRESHOLD_DP, 0x00000080, BIT(PIPE_NONE) }, + { REG_A7XX_SP_READ_SEL, 0x0001ff00, BIT(PIPE_NONE) }, + { REG_A6XX_TPL1_DBG_ECO_CNTL, 0x10000000, BIT(PIPE_NONE) }, + /* BIT(26): Disable final clamp for bicubic filtering */ + { REG_A6XX_TPL1_DBG_ECO_CNTL1, 0x00000720, BIT(PIPE_NONE) }, + { REG_A6XX_UCHE_MODE_CNTL, 0x80080000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_MODE_CNTL, 0x00001000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_CACHE_WAYS, 0x00000800, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_GBIF_GX_CONFIG, 0x010240e0, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_VARB_IDLE_TIMEOUT, 0x00000020, BIT(PIPE_NONE) }, + { REG_A7XX_VFD_DBG_ECO_CNTL, 0x00008000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BV_THRESHOLD, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BR_THRESHOLD, 0x00600060, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BUSY_REQ_CNT, 0x00200020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_LP_REQ_CNT, 0x00000020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VPC_FLATSHADE_MODE_CNTL, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { }, +}; + +static const u32 x285_protect_regs[] = { + A6XX_PROTECT_RDONLY(0x00008, 0x039b), + A6XX_PROTECT_RDONLY(0x003b4, 0x008b), + A6XX_PROTECT_NORDWR(0x00440, 0x001f), + A6XX_PROTECT_RDONLY(0x00580, 0x005f), + A6XX_PROTECT_NORDWR(0x005e0, 0x011f), + A6XX_PROTECT_RDONLY(0x0074a, 0x0005), + A6XX_PROTECT_RDONLY(0x00759, 0x0026), + A6XX_PROTECT_RDONLY(0x00789, 0x0000), + A6XX_PROTECT_RDONLY(0x0078c, 0x0013), + A6XX_PROTECT_NORDWR(0x00800, 0x0029), + A6XX_PROTECT_NORDWR(0x0082c, 0x0000), + A6XX_PROTECT_NORDWR(0x00837, 0x00af), + A6XX_PROTECT_RDONLY(0x008e7, 0x00c9), + A6XX_PROTECT_NORDWR(0x008ec, 0x00c3), + A6XX_PROTECT_NORDWR(0x009b1, 0x0250), + A6XX_PROTECT_RDONLY(0x00ce0, 0x0001), + A6XX_PROTECT_RDONLY(0x00df0, 0x0000), + A6XX_PROTECT_NORDWR(0x00df1, 0x0000), + A6XX_PROTECT_NORDWR(0x00e01, 0x0000), + A6XX_PROTECT_NORDWR(0x00e03, 0x1fff), + A6XX_PROTECT_NORDWR(0x03c00, 0x00c5), + A6XX_PROTECT_RDONLY(0x03cc6, 0x0039), + A6XX_PROTECT_NORDWR(0x03d00, 0x1fff), + A6XX_PROTECT_NORDWR(0x08600, 0x01ff), + A6XX_PROTECT_NORDWR(0x08e00, 0x00ff), + A6XX_PROTECT_RDONLY(0x08f00, 0x0000), + A6XX_PROTECT_NORDWR(0x08f01, 0x01be), + A6XX_PROTECT_NORDWR(0x09600, 0x01ff), + A6XX_PROTECT_RDONLY(0x0981a, 0x02e5), + A6XX_PROTECT_NORDWR(0x09e00, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a600, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a82e, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae00, 0x0006), + A6XX_PROTECT_NORDWR(0x0ae08, 0x0006), + A6XX_PROTECT_NORDWR(0x0ae10, 0x00bf), + A6XX_PROTECT_RDONLY(0x0aed0, 0x002f), + A6XX_PROTECT_NORDWR(0x0af00, 0x027f), + A6XX_PROTECT_NORDWR(0x0b600, 0x1fff), + A6XX_PROTECT_NORDWR(0x0dc00, 0x1fff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff), + A6XX_PROTECT_NORDWR(0x18400, 0x003f), + A6XX_PROTECT_RDONLY(0x18440, 0x013f), + A6XX_PROTECT_NORDWR(0x18580, 0x1fff), + A6XX_PROTECT_NORDWR(0x1b400, 0x1fff), + A6XX_PROTECT_NORDWR(0x1f400, 0x0477), + A6XX_PROTECT_RDONLY(0x1f878, 0x0507), + A6XX_PROTECT_NORDWR(0x1f930, 0x0329), + A6XX_PROTECT_NORDWR(0x1fd80, 0x1fff), + A6XX_PROTECT_NORDWR(0x27800, 0x007f), + A6XX_PROTECT_RDONLY(0x27880, 0x0385), + A6XX_PROTECT_NORDWR(0x27882, 0x000a), + A6XX_PROTECT_NORDWR(0x27c06, 0x0000), +}; + +DECLARE_ADRENO_PROTECT(x285_protect, 64); + +static const struct adreno_reglist_pipe a840_nonctxt_regs[] = { + { REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) }, + { REG_A8XX_GRAS_DBG_ECO_CNTL, 0x00000800, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_GRAS_TSEFE_DBG_ECO_CNTL, 0x00200000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A6XX_PC_AUTO_VERTEX_STRIDE, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_VIS_STREAM_CNTL, 0x10010000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CONTEXT_SWITCH_STABILIZE_CNTL_1, 0x00000002, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_1, 0x00000003, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_2, 0x00000200, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_3, 0x00500000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_4, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + /* Disable Dead Draw Merge scheme on RB-HLSQ */ + { REG_A6XX_RB_RBP_CNTL, BIT(5), BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A7XX_RB_CCU_CNTL, 0x00000068, BIT(PIPE_BR) }, + /* Partially enable perf clear, Disable DINT to c/z be data forwarding */ + { REG_A7XX_RB_CCU_DBG_ECO_CNTL, 0x00002200, BIT(PIPE_BR) }, + { REG_A8XX_RB_GC_GMEM_PROTECT, 0x12000000, BIT(PIPE_BR) }, + { REG_A8XX_RB_RESOLVE_PREFETCH_CNTL, 0x00000007, BIT(PIPE_BR) }, + { REG_A8XX_RB_CMP_DBG_ECO_CNTL, 0x00004000, BIT(PIPE_BR) }, + { REG_A8XX_RBBM_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_SLICE_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_POWER_UP_RESET_SW_OVERRIDE, 0x70809060, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_POWER_UP_RESET_SW_BV_OVERRIDE, 0x30000000, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL2, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_INTERFACE_HANG_INT_CNTL, 0x0fffffff, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x22122212, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_CGC_P2S_CNTL, 0x00000040, BIT(PIPE_NONE) }, + /* Disable mode_switch optimization in UMAS */ + { REG_A6XX_SP_CHICKEN_BITS, BIT(24) | BIT(26), BIT(PIPE_NONE) }, + /* Disable LPAC large-LM mode */ + { REG_A8XX_SP_SS_CHICKEN_BITS_0, BIT(3), BIT(PIPE_NONE) }, + /* Disable PS out of order retire */ + { REG_A7XX_SP_CHICKEN_BITS_2, 0x00c21800, BIT(PIPE_NONE) }, + { REG_A7XX_SP_CHICKEN_BITS_3, 0x00300000, BIT(PIPE_NONE) }, + /* Disable SP2TP info attribute */ + { REG_A8XX_SP_CHICKEN_BITS_4, 0x00000002, BIT(PIPE_NONE) }, + { REG_A6XX_SP_PERFCTR_SHADER_MASK, 0x0000003f, BIT(PIPE_NONE) }, + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL, BIT(14), BIT(PIPE_NONE) }, + /* Ignore HLSQ shared constant feedback from SP */ + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL_1, BIT(17), BIT(PIPE_NONE) }, + /* Disable CS dead batch merge */ + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL_2, BIT(24), BIT(PIPE_NONE) }, + { REG_A8XX_SP_HLSQ_DBG_ECO_CNTL_3, BIT(7), BIT(PIPE_NONE) }, + { REG_A7XX_SP_HLSQ_TIMEOUT_THRESHOLD_DP, 0x00000080, BIT(PIPE_NONE) }, + { REG_A7XX_SP_READ_SEL, 0x0001ff00, BIT(PIPE_NONE) }, + { REG_A6XX_TPL1_DBG_ECO_CNTL, 0x10100000, BIT(PIPE_NONE) }, + /* BIT(26): Disable final clamp for bicubic filtering */ + { REG_A6XX_TPL1_DBG_ECO_CNTL1, 0x04000720, BIT(PIPE_NONE) }, + { REG_A6XX_UCHE_MODE_CNTL, 0x80080000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_MODE_CNTL, 0x00001000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_CACHE_WAYS, 0x00000800, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_GBIF_GX_CONFIG, 0x010240e0, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_VARB_IDLE_TIMEOUT, 0x00000020, BIT(PIPE_NONE) }, + { REG_A7XX_VFD_DBG_ECO_CNTL, 0x00008000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BV_THRESHOLD, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BR_THRESHOLD, 0x00600060, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BUSY_REQ_CNT, 0x00200020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_LP_REQ_CNT, 0x00000020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VPC_FLATSHADE_MODE_CNTL, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { }, +}; + +static const u32 a840_protect_regs[] = { + A6XX_PROTECT_RDONLY(0x00008, 0x039b), + A6XX_PROTECT_RDONLY(0x003b4, 0x008b), + A6XX_PROTECT_NORDWR(0x00440, 0x001f), + A6XX_PROTECT_RDONLY(0x00580, 0x005f), + A6XX_PROTECT_NORDWR(0x005e0, 0x011f), + A6XX_PROTECT_RDONLY(0x0074a, 0x0005), + A6XX_PROTECT_RDONLY(0x00759, 0x001b), + A6XX_PROTECT_NORDWR(0x00775, 0x000a), + A6XX_PROTECT_RDONLY(0x00789, 0x0000), + A6XX_PROTECT_RDONLY(0x0078c, 0x0013), + A6XX_PROTECT_NORDWR(0x00800, 0x0029), + A6XX_PROTECT_NORDWR(0x00837, 0x00af), + A6XX_PROTECT_RDONLY(0x008e7, 0x00c9), + A6XX_PROTECT_NORDWR(0x008ec, 0x00c3), + A6XX_PROTECT_NORDWR(0x009b1, 0x0250), + A6XX_PROTECT_NORDWR(0x00c07, 0x0008), + A6XX_PROTECT_RDONLY(0x00ce0, 0x0001), + A6XX_PROTECT_RDONLY(0x00df0, 0x0000), + A6XX_PROTECT_NORDWR(0x00df1, 0x0000), + A6XX_PROTECT_NORDWR(0x00e01, 0x0000), + A6XX_PROTECT_NORDWR(0x00e03, 0x1fff), + A6XX_PROTECT_NORDWR(0x03c00, 0x00c5), + A6XX_PROTECT_RDONLY(0x03cc6, 0x0039), + A6XX_PROTECT_NORDWR(0x03d00, 0x1fff), + A6XX_PROTECT_NORDWR(0x08600, 0x01ff), + A6XX_PROTECT_NORDWR(0x08e00, 0x00ff), + A6XX_PROTECT_RDONLY(0x08f00, 0x0000), + A6XX_PROTECT_NORDWR(0x08f01, 0x01be), + A6XX_PROTECT_NORDWR(0x09600, 0x01ff), + A6XX_PROTECT_RDONLY(0x0981a, 0x02e5), + A6XX_PROTECT_NORDWR(0x09e00, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a600, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a82e, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae00, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae02, 0x0004), + A6XX_PROTECT_NORDWR(0x0ae08, 0x0006), + A6XX_PROTECT_NORDWR(0x0ae10, 0x00bf), + A6XX_PROTECT_RDONLY(0x0aed0, 0x002f), + A6XX_PROTECT_NORDWR(0x0af00, 0x027f), + A6XX_PROTECT_NORDWR(0x0b600, 0x1fff), + A6XX_PROTECT_NORDWR(0x0dc00, 0x1fff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff), + A6XX_PROTECT_NORDWR(0x18400, 0x003f), + A6XX_PROTECT_RDONLY(0x18440, 0x013f), + A6XX_PROTECT_NORDWR(0x18580, 0x1fff), + A6XX_PROTECT_NORDWR(0x1b400, 0x1fff), + A6XX_PROTECT_NORDWR(0x1f400, 0x0477), + A6XX_PROTECT_RDONLY(0x1f878, 0x0507), + A6XX_PROTECT_NORDWR(0x1f930, 0x0329), + A6XX_PROTECT_NORDWR(0x1fd80, 0x1fff), + A6XX_PROTECT_NORDWR(0x27800, 0x007f), + A6XX_PROTECT_RDONLY(0x27880, 0x0385), + A6XX_PROTECT_NORDWR(0x27882, 0x0009), + A6XX_PROTECT_NORDWR(0x27c06, 0x0000), +}; +DECLARE_ADRENO_PROTECT(a840_protect, 15); + +static const struct adreno_reglist a840_gbif[] = { + { REG_A6XX_GBIF_QSB_SIDE0, 0x00071e20 }, + { REG_A6XX_GBIF_QSB_SIDE1, 0x00071e20 }, + { REG_A6XX_GBIF_QSB_SIDE2, 0x00071e20 }, + { REG_A6XX_GBIF_QSB_SIDE3, 0x00071e20 }, + { REG_A8XX_GBIF_CX_CONFIG, 0x20023000 }, + { }, +}; + +static const struct adreno_info a8xx_gpus[] = { + { + .chip_ids = ADRENO_CHIP_IDS(0x44070001), + .family = ADRENO_8XX_GEN2, + .fw = { + [ADRENO_FW_SQE] = "gen80100_sqe.fw", + [ADRENO_FW_GMU] = "gen80100_gmu.bin", + }, + .gmem = 21 * SZ_1M, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .funcs = &a8xx_gpu_funcs, + .a6xx = &(const struct a6xx_info) { + .protect = &x285_protect, + .nonctxt_reglist = x285_nonctxt_regs, + .gbif_cx = a840_gbif, + .max_slices = 4, + .gmu_chipid = 0x8010100, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(2), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, + }, + }, { + .chip_ids = ADRENO_CHIP_IDS(0x44050a01), + .family = ADRENO_8XX_GEN2, + .fw = { + [ADRENO_FW_SQE] = "gen80200_sqe.fw", + [ADRENO_FW_GMU] = "gen80200_gmu.bin", + [ADRENO_FW_AQE] = "gen80200_aqe.fw", + }, + .gmem = 18 * SZ_1M, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .funcs = &a8xx_gpu_funcs, + .a6xx = &(const struct a6xx_info) { + .protect = &a840_protect, + .nonctxt_reglist = a840_nonctxt_regs, + .gbif_cx = a840_gbif, + .max_slices = 3, + .gmu_chipid = 0x8020100, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(2), + .perfmode_bw = 10687500, + }, + { /* sentinel */ }, + }, + }, + .preempt_record_size = 19708 * SZ_1K, + } +}; + +DECLARE_ADRENO_GPULIST(a8xx); + static inline __always_unused void __build_asserts(void) { BUILD_BUG_ON(a630_protect.count > a630_protect.count_max); @@ -1619,4 +1957,5 @@ static inline __always_unused void __build_asserts(void) BUILD_BUG_ON(a660_protect.count > a660_protect.count_max); BUILD_BUG_ON(a690_protect.count > a690_protect.count_max); BUILD_BUG_ON(a730_protect.count > a730_protect.count_max); + BUILD_BUG_ON(a840_protect.count > a840_protect.count_max); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index fc62fef2fed8..5903cd891b49 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -224,14 +224,19 @@ unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu) static bool a6xx_gmu_check_idle_level(struct a6xx_gmu *gmu) { - u32 val; + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int local = gmu->idle_level; + u32 val; /* SPTP and IFPC both report as IFPC */ if (gmu->idle_level == GMU_IDLE_STATE_SPTP) local = GMU_IDLE_STATE_IFPC; - val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + if (adreno_is_a8xx(adreno_gpu)) + val = gmu_read(gmu, REG_A8XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + else + val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); if (val == local) { if (gmu->idle_level != GMU_IDLE_STATE_IFPC || @@ -269,7 +274,9 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) /* Set the log wptr index * note: downstream saves the value in poweroff and restores it here */ - if (adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(gmu, REG_A8XX_GMU_GENERAL_9, 0); + else if (adreno_is_a7xx(adreno_gpu)) gmu_write(gmu, REG_A7XX_GMU_GENERAL_9, 0); else gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_RESP, 0); @@ -350,12 +357,18 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = { /* Trigger a OOB (out of band) request to the GMU */ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int ret; u32 val; int request, ack; WARN_ON_ONCE(!mutex_is_locked(&gmu->lock)); + /* Skip OOB calls since RGMU is not enabled */ + if (adreno_has_rgmu(adreno_gpu)) + return 0; + if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits)) return -EINVAL; @@ -376,9 +389,23 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) /* Trigger the equested OOB operation */ gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << request); - /* Wait for the acknowledge interrupt */ - ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, - val & (1 << ack), 100, 10000); + do { + /* Wait for the acknowledge interrupt */ + ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, + val & (1 << ack), 100, 10000); + + if (!ret) + break; + + if (completion_done(&a6xx_gpu->base.fault_coredump_done)) + break; + + /* We may timeout because the GMU is temporarily wedged from + * pending faults from the GPU and we are taking a devcoredump. + * Wait until the MMU is resumed and try again. + */ + wait_for_completion(&a6xx_gpu->base.fault_coredump_done); + } while (true); if (ret) DRM_DEV_ERROR(gmu->dev, @@ -395,10 +422,16 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) /* Clear a pending OOB state in the GMU */ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int bit; WARN_ON_ONCE(!mutex_is_locked(&gmu->lock)); + /* Skip OOB calls since RGMU is not enabled */ + if (adreno_has_rgmu(adreno_gpu)) + return; + if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits)) return; @@ -485,17 +518,25 @@ static void a6xx_gemnoc_workaround(struct a6xx_gmu *gmu) * in the power down sequence not being fully executed. That in turn can * prevent CX_GDSC from collapsing. Assert Qactive to avoid this. */ - if (adreno_is_a621(adreno_gpu) || adreno_is_7c3(adreno_gpu)) - gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, BIT(0)); + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(gmu, REG_A8XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, BIT(0)); + else if (adreno_is_a7xx(adreno_gpu) || (adreno_is_a621(adreno_gpu) || + adreno_is_7c3(adreno_gpu))) + gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, BIT(0)); } /* Let the GMU know that we are about to go into slumber */ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int ret; /* Disable the power counter so the GMU isn't busy */ - gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0); + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0); + else + gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0); /* Disable SPTP_PC if the CPU is responsible for it */ if (gmu->idle_level < GMU_IDLE_STATE_SPTP) @@ -522,10 +563,9 @@ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu) } out: - a6xx_gemnoc_workaround(gmu); - /* Put fence into allow mode */ gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + a6xx_gemnoc_workaround(gmu); return ret; } @@ -561,16 +601,22 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu) static void a6xx_rpmh_stop(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + u32 bitmask = BIT(16); int ret; u32 val; if (test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status)) return; + if (adreno_is_a840(adreno_gpu)) + bitmask = BIT(30); + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1); ret = gmu_poll_timeout_rscc(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0, - val, val & (1 << 16), 100, 10000); + val, val & bitmask, 100, 10000); if (ret) DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n"); @@ -584,22 +630,24 @@ static inline void pdc_write(void __iomem *ptr, u32 offset, u32 value) writel(value, ptr + (offset << 2)); } -static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, - const char *name); - static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, 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"); u32 seqmem0_drv0_reg = REG_A6XX_RSCC_SEQ_MEM_0_DRV0; void __iomem *seqptr = NULL; uint32_t pdc_address_offset; + void __iomem *pdcptr; bool pdc_in_aop = false; + /* On A8x and above, RPMH/PDC configurations are entirely configured in AOP */ + if (adreno_is_a8xx(adreno_gpu)) + return; + + pdcptr = devm_platform_ioremap_resource_byname(pdev, "gmu_pdc"); if (IS_ERR(pdcptr)) - goto err; + return; if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) @@ -612,9 +660,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) pdc_address_offset = 0x30080; if (!pdc_in_aop) { - seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq"); + seqptr = devm_platform_ioremap_resource_byname(pdev, "gmu_pdc_seq"); if (IS_ERR(seqptr)) - goto err; + return; } /* Disable SDE clock gating */ @@ -704,12 +752,6 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) /* ensure no writes happen before the uCode is fully written */ wmb(); - -err: - if (!IS_ERR_OR_NULL(pdcptr)) - iounmap(pdcptr); - if (!IS_ERR_OR_NULL(seqptr)) - iounmap(seqptr); } /* @@ -732,7 +774,7 @@ static void a6xx_gmu_power_config(struct a6xx_gmu *gmu) gmu_write(gmu, REG_A6XX_GMU_DCACHE_CONFIG, 0x1); /* A7xx knows better by default! */ - if (adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) return; gmu_write(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0x9c40400); @@ -780,6 +822,9 @@ static bool fw_block_mem(struct a6xx_gmu_bo *bo, const struct block_header *blk) return true; } +#define NEXT_BLK(blk) \ + ((const struct block_header *)((const char *)(blk) + sizeof(*(blk)) + (blk)->size)) + static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); @@ -792,7 +837,9 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) u32 itcm_base = 0x00000000; u32 dtcm_base = 0x00040000; - if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a650_family(adreno_gpu) || + adreno_is_a7xx(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) dtcm_base = 0x10004000; if (gmu->legacy) { @@ -811,7 +858,7 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) for (blk = (const struct block_header *) fw_image->data; (const u8*) blk < fw_image->data + fw_image->size; - blk = (const struct block_header *) &blk->data[blk->size >> 2]) { + blk = NEXT_BLK(blk)) { if (blk->size == 0) continue; @@ -847,7 +894,9 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; const struct a6xx_info *a6xx_info = adreno_gpu->info->a6xx; + const struct adreno_reglist *gbif_cx = a6xx_info->gbif_cx; u32 fence_range_lower, fence_range_upper; u32 chipid = 0; int ret; @@ -856,12 +905,15 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) { gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, 1); gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FAL_INTF, 1); + } else if (adreno_is_a8xx(adreno_gpu)) { + gmu_write(gmu, REG_A8XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, 1); + gmu_write(gmu, REG_A8XX_GPU_GMU_CX_GMU_CX_FAL_INTF, 1); } /* Turn on TCM (Tightly Coupled Memory) retention */ if (adreno_is_a7xx(adreno_gpu)) a6xx_llc_write(a6xx_gpu, REG_A7XX_CX_MISC_TCM_RET_CNTL, 1); - else + else if (!adreno_is_a8xx(adreno_gpu)) gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1); ret = a6xx_rpmh_start(gmu); @@ -886,7 +938,10 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_ADDR, gmu->hfi.iova); gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_INFO, 1); - if (adreno_is_a7xx(adreno_gpu)) { + if (adreno_is_a8xx(adreno_gpu)) { + fence_range_upper = 0x32; + fence_range_lower = 0x8c0; + } else if (adreno_is_a7xx(adreno_gpu)) { fence_range_upper = 0x32; fence_range_lower = 0x8a0; } else { @@ -920,7 +975,12 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) chipid |= (adreno_gpu->chip_id << 8) & 0x0f00; /* patchid */ } - if (adreno_is_a7xx(adreno_gpu)) { + if (adreno_is_a8xx(adreno_gpu)) { + gmu_write(gmu, REG_A8XX_GMU_GENERAL_10, chipid); + gmu_write(gmu, REG_A8XX_GMU_GENERAL_8, + (gmu->log.iova & GENMASK(31, 12)) | + ((gmu->log.size / SZ_4K - 1) & GENMASK(7, 0))); + } else if (adreno_is_a7xx(adreno_gpu)) { gmu_write(gmu, REG_A7XX_GMU_GENERAL_10, chipid); gmu_write(gmu, REG_A7XX_GMU_GENERAL_8, (gmu->log.iova & GENMASK(31, 12)) | @@ -932,6 +992,15 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) gmu->log.iova | (gmu->log.size / SZ_4K - 1)); } + /* For A7x and newer, do the CX GBIF configurations before GMU wake up */ + for (int i = 0; (gbif_cx && gbif_cx[i].offset); i++) + gpu_write(gpu, gbif_cx[i].offset, gbif_cx[i].value); + + if (adreno_is_a8xx(adreno_gpu)) { + gpu_write(gpu, REG_A8XX_GBIF_CX_CONFIG, 0x20023000); + gmu_write(gmu, REG_A6XX_GMU_MRC_GBIF_QOS_CTRL, 0x33); + } + /* Set up the lowest idle level on the GMU */ a6xx_gmu_power_config(gmu); @@ -983,7 +1052,7 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) u32 val, seqmem_off = 0; /* The second spin of A7xx GPUs messed with some register offsets.. */ - if (adreno_is_a740_family(adreno_gpu)) + if (adreno_is_a740_family(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) seqmem_off = 4; /* Make sure there are no outstanding RPMh votes */ @@ -996,7 +1065,7 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS + seqmem_off, val, (val & 1), 100, 1000); - if (!adreno_is_a740_family(adreno_gpu)) + if (!adreno_is_a740_family(adreno_gpu) && !adreno_is_a8xx(adreno_gpu)) return; gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS4_DRV0_STATUS + seqmem_off, @@ -1024,7 +1093,10 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) * Turn off keep alive that might have been enabled by the hang * interrupt */ - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(&a6xx_gpu->gmu, REG_A8XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); + else + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); /* Flush all the queues */ a6xx_hfi_stop(gmu); @@ -1050,7 +1122,7 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) /* Halt the gmu cm3 core */ gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); - a6xx_bus_clear_pending_transactions(adreno_gpu, true); + adreno_gpu->funcs->bus_halt(adreno_gpu, true); /* Reset GPU core blocks */ a6xx_gpu_sw_reset(gpu, true); @@ -1119,6 +1191,9 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) return ret; } + /* Read the slice info on A8x GPUs */ + a8xx_gpu_get_slice_info(gpu); + /* Set the bus quota to a reasonable value for boot */ a6xx_gmu_set_initial_bw(gpu, gmu); @@ -1128,7 +1203,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) enable_irq(gmu->gmu_irq); /* Check to see if we are doing a cold or warm boot */ - if (adreno_is_a7xx(adreno_gpu)) { + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) { status = a6xx_llc_read(a6xx_gpu, REG_A7XX_CX_MISC_TCM_RET_CNTL) == 1 ? GMU_WARM_BOOT : GMU_COLD_BOOT; } else if (gmu->legacy) { @@ -1222,7 +1297,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) if (ret) goto force_off; - a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); + adreno_gpu->funcs->bus_halt(adreno_gpu, a6xx_gpu->hung); /* tell the GMU we want to slumber */ ret = a6xx_gmu_notify_slumber(gmu); @@ -1457,7 +1532,7 @@ static int a6xx_gmu_rpmh_bw_votes_init(struct adreno_gpu *adreno_gpu, vote = clamp(peak, 1, BCM_TCS_CMD_VOTE_MASK); /* GMUs on A7xx votes on both x & y */ - if (adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) data[bcm_index] = BCM_TCS_CMD(commit, true, vote, vote); else data[bcm_index] = BCM_TCS_CMD(commit, true, 0, vote); @@ -1489,13 +1564,14 @@ static unsigned int a6xx_gmu_get_arc_level(struct device *dev, } static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, - unsigned long *freqs, int freqs_count, const char *id) + unsigned long *freqs, int freqs_count, + const char *pri_id, const char *sec_id) { int i, j; const u16 *pri, *sec; size_t pri_count, sec_count; - pri = cmd_db_read_aux_data(id, &pri_count); + pri = cmd_db_read_aux_data(pri_id, &pri_count); if (IS_ERR(pri)) return PTR_ERR(pri); /* @@ -1506,13 +1582,7 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, if (!pri_count) return -EINVAL; - /* - * Some targets have a separate gfx mxc rail. So try to read that first and then fall back - * to regular mx rail if it is missing - */ - sec = cmd_db_read_aux_data("gmxc.lvl", &sec_count); - if (IS_ERR(sec) && sec != ERR_PTR(-EPROBE_DEFER)) - sec = cmd_db_read_aux_data("mx.lvl", &sec_count); + sec = cmd_db_read_aux_data(sec_id, &sec_count); if (IS_ERR(sec)) return PTR_ERR(sec); @@ -1566,6 +1636,57 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, return 0; } +static int a6xx_gmu_rpmh_dep_votes_init(struct device *dev, u32 *votes, + unsigned long *freqs, int freqs_count) +{ + const u16 *mx; + size_t count; + + mx = cmd_db_read_aux_data("mx.lvl", &count); + if (IS_ERR(mx)) + return PTR_ERR(mx); + /* + * The data comes back as an array of unsigned shorts so adjust the + * count accordingly + */ + count >>= 1; + if (!count) + return -EINVAL; + + /* Fix the vote for zero frequency */ + votes[0] = 0xffffffff; + + /* Construct a vote for rest of the corners */ + for (int i = 1; i < freqs_count; i++) { + unsigned int level = a6xx_gmu_get_arc_level(dev, freqs[i]); + u8 j, index = 0; + + /* Get the primary index that matches the arc level */ + for (j = 0; j < count; j++) { + if (mx[j] >= level) { + index = j; + break; + } + } + + if (j == count) { + DRM_DEV_ERROR(dev, + "Mx Level %u not found in the RPMh list\n", + level); + DRM_DEV_ERROR(dev, "Available levels:\n"); + for (j = 0; j < count; j++) + DRM_DEV_ERROR(dev, " %u\n", mx[j]); + + return -EINVAL; + } + + /* Construct the vote */ + votes[i] = (0x3fff << 14) | (index << 8) | (0xff); + } + + return 0; +} + /* * The GMU votes with the RPMh for itself and on behalf of the GPU but we need * to construct the list of votes on the CPU and send it over. Query the RPMh @@ -1580,15 +1701,27 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; + const char *sec_id; + const u16 *gmxc; int ret; + gmxc = cmd_db_read_aux_data("gmxc.lvl", NULL); + if (gmxc == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + /* If GMxC is present, prefer that as secondary rail for GX votes */ + sec_id = IS_ERR_OR_NULL(gmxc) ? "mx.lvl" : "gmxc.lvl"; + /* Build the GX votes */ ret = a6xx_gmu_rpmh_arc_votes_init(&gpu->pdev->dev, gmu->gx_arc_votes, - gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl"); + gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl", sec_id); /* Build the CX votes */ ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, - gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); + gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl", "mx.lvl"); + + ret |= a6xx_gmu_rpmh_dep_votes_init(gmu->dev, gmu->dep_arc_votes, + gmu->gpu_freqs, gmu->nr_gpu_freqs); /* Build the interconnect votes */ if (info->bcms && gmu->nr_gpu_bws > 1) @@ -1792,27 +1925,6 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu) return 0; } -static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, - const char *name) -{ - void __iomem *ret; - struct resource *res = platform_get_resource_byname(pdev, - IORESOURCE_MEM, name); - - if (!res) { - DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name); - return ERR_PTR(-EINVAL); - } - - ret = ioremap(res->start, resource_size(res)); - if (!ret) { - DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name); - return ERR_PTR(-EINVAL); - } - - return ret; -} - static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev, const char *name, irq_handler_t handler) { @@ -1863,7 +1975,6 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct a6xx_gmu *gmu = &a6xx_gpu->gmu; - struct platform_device *pdev = to_platform_device(gmu->dev); mutex_lock(&gmu->lock); if (!gmu->initialized) { @@ -1892,12 +2003,11 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) qmp_put(gmu->qmp); iounmap(gmu->mmio); - if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc")) - iounmap(gmu->rscc); gmu->mmio = NULL; gmu->rscc = NULL; - if (!adreno_has_gmu_wrapper(adreno_gpu)) { + if (!adreno_has_gmu_wrapper(adreno_gpu) && + !adreno_has_rgmu(adreno_gpu)) { a6xx_gmu_memory_free(gmu); free_irq(gmu->gmu_irq, gmu); @@ -1919,10 +2029,38 @@ static int cxpd_notifier_cb(struct notifier_block *nb, return 0; } +static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, + const char *name, resource_size_t *start) +{ + void __iomem *ret; + struct resource *res = platform_get_resource_byname(pdev, + IORESOURCE_MEM, name); + + if (!res) { + DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name); + return ERR_PTR(-EINVAL); + } + + ret = ioremap(res->start, resource_size(res)); + if (!ret) { + DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name); + return ERR_PTR(-EINVAL); + } + + if (start) + *start = res->start; + + return ret; +} + int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) { struct platform_device *pdev = of_find_device_by_node(node); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + resource_size_t start; + struct resource *res; int ret; if (!pdev) @@ -1939,13 +2077,29 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) /* Mark legacy for manual SPTPRAC control */ gmu->legacy = true; + /* RGMU requires clocks */ + ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks); + if (ret < 0) + goto err_clk; + + gmu->nr_clocks = ret; + /* Map the GMU registers */ - gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu"); + gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu", &start); if (IS_ERR(gmu->mmio)) { ret = PTR_ERR(gmu->mmio); goto err_mmio; } + res = platform_get_resource_byname(gpu->pdev, IORESOURCE_MEM, "kgsl_3d0_reg_memory"); + if (!res) { + ret = -EINVAL; + goto err_mmio; + } + + /* Identify gmu base offset from gpu base address */ + gmu->mmio_offset = (u32)(start - res->start); + gmu->cxpd = dev_pm_domain_attach_by_name(gmu->dev, "cx"); if (IS_ERR(gmu->cxpd)) { ret = PTR_ERR(gmu->cxpd); @@ -1978,6 +2132,7 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) err_mmio: iounmap(gmu->mmio); +err_clk: /* Drop reference taken in of_find_device_by_node */ put_device(gmu->dev); @@ -1986,10 +2141,13 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) { - struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; - struct a6xx_gmu *gmu = &a6xx_gpu->gmu; struct platform_device *pdev = of_find_device_by_node(node); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; struct device_link *link; + resource_size_t start; + struct resource *res; int ret; if (!pdev) @@ -2025,13 +2183,14 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) */ gmu->dummy.size = SZ_4K; if (adreno_is_a660_family(adreno_gpu) || - adreno_is_a7xx(adreno_gpu)) { + adreno_is_a7xx(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) { ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7, 0x60400000, "debug"); if (ret) goto err_memory; - gmu->dummy.size = SZ_8K; + gmu->dummy.size = SZ_16K; } /* Allocate memory for the GMU dummy page */ @@ -2042,7 +2201,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) /* Note that a650 family also includes a660 family: */ if (adreno_is_a650_family(adreno_gpu) || - adreno_is_a7xx(adreno_gpu)) { + adreno_is_a7xx(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) { ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache, SZ_16M - SZ_16K, 0x04000, "icache"); if (ret) @@ -2084,19 +2244,30 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) goto err_memory; /* Map the GMU registers */ - gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu"); + gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu", &start); if (IS_ERR(gmu->mmio)) { ret = PTR_ERR(gmu->mmio); goto err_memory; } + res = platform_get_resource_byname(gpu->pdev, IORESOURCE_MEM, "kgsl_3d0_reg_memory"); + if (!res) { + ret = -EINVAL; + goto err_mmio; + } + + /* Identify gmu base offset from gpu base address */ + gmu->mmio_offset = (u32)(start - res->start); + if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) { - gmu->rscc = a6xx_gmu_get_mmio(pdev, "rscc"); + gmu->rscc = devm_platform_ioremap_resource_byname(pdev, "rscc"); if (IS_ERR(gmu->rscc)) { ret = -ENODEV; goto err_mmio; } + } else if (adreno_is_a8xx(adreno_gpu)) { + gmu->rscc = gmu->mmio + 0x19000; } else { gmu->rscc = gmu->mmio + 0x23000; } @@ -2170,8 +2341,6 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) err_mmio: iounmap(gmu->mmio); - if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc")) - iounmap(gmu->rscc); free_irq(gmu->gmu_irq, gmu); free_irq(gmu->hfi_irq, gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 06cfc294016f..2af074c8e8cf 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -19,8 +19,8 @@ struct a6xx_gmu_bo { u64 iova; }; -#define GMU_MAX_GX_FREQS 16 -#define GMU_MAX_CX_FREQS 4 +#define GMU_MAX_GX_FREQS 32 +#define GMU_MAX_CX_FREQS 6 #define GMU_MAX_BCMS 3 struct a6xx_bcm { @@ -68,6 +68,7 @@ struct a6xx_gmu { struct drm_gpuvm *vm; void __iomem *mmio; + u32 mmio_offset; void __iomem *rscc; int hfi_irq; @@ -96,6 +97,7 @@ struct a6xx_gmu { int nr_gpu_freqs; unsigned long gpu_freqs[GMU_MAX_GX_FREQS]; u32 gx_arc_votes[GMU_MAX_GX_FREQS]; + u32 dep_arc_votes[GMU_MAX_GX_FREQS]; struct a6xx_hfi_acd_table acd_table; int nr_gpu_bws; @@ -130,20 +132,23 @@ struct a6xx_gmu { unsigned long status; }; +#define GMU_BYTE_OFFSET(gmu, offset) (((offset) << 2) - (gmu)->mmio_offset) + static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset) { - return readl(gmu->mmio + (offset << 2)); + /* The 'offset' is based on GPU's start address. Adjust it */ + return readl(gmu->mmio + GMU_BYTE_OFFSET(gmu, offset)); } static inline void gmu_write(struct a6xx_gmu *gmu, u32 offset, u32 value) { - writel(value, gmu->mmio + (offset << 2)); + writel(value, gmu->mmio + GMU_BYTE_OFFSET(gmu, offset)); } static inline void gmu_write_bulk(struct a6xx_gmu *gmu, u32 offset, const u32 *data, u32 size) { - memcpy_toio(gmu->mmio + (offset << 2), data, size); + memcpy_toio(gmu->mmio + GMU_BYTE_OFFSET(gmu, offset), data, size); wmb(); } @@ -160,17 +165,17 @@ static inline u64 gmu_read64(struct a6xx_gmu *gmu, u32 lo, u32 hi) { u64 val; - val = (u64) readl(gmu->mmio + (lo << 2)); - val |= ((u64) readl(gmu->mmio + (hi << 2)) << 32); + val = gmu_read(gmu, lo); + val |= ((u64) gmu_read(gmu, hi) << 32); return val; } #define gmu_poll_timeout(gmu, addr, val, cond, interval, timeout) \ - readl_poll_timeout((gmu)->mmio + ((addr) << 2), val, cond, \ - interval, timeout) + readl_poll_timeout((gmu)->mmio + (GMU_BYTE_OFFSET(gmu, addr)), val, \ + cond, interval, timeout) #define gmu_poll_timeout_atomic(gmu, addr, val, cond, interval, timeout) \ - readl_poll_timeout_atomic((gmu)->mmio + ((addr) << 2), val, cond, \ + readl_poll_timeout_atomic((gmu)->mmio + (GMU_BYTE_OFFSET(gmu, addr)), val, cond, \ interval, timeout) static inline u32 gmu_read_rscc(struct a6xx_gmu *gmu, u32 offset) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index b8f8ae940b55..0200a7e71cdf 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -157,7 +157,7 @@ static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) } } -static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -224,7 +224,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, submit->seqno - 1); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); - OUT_RING(ring, CP_SET_THREAD_BOTH); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH); /* Reset state used to synchronize BR and BV */ OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1); @@ -235,18 +235,31 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); - OUT_RING(ring, CP_SET_THREAD_BR); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH); + + OUT_PKT7(ring, CP_EVENT_WRITE, 1); + OUT_RING(ring, LRZ_FLUSH_INVALIDATE); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR); } if (!sysprof) { - if (!adreno_is_a7xx(adreno_gpu)) { + if (!(adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu))) { /* Turn off protected mode to write to special registers */ OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 0); } - OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); - OUT_RING(ring, 1); + if (adreno_is_a8xx(adreno_gpu)) { + OUT_PKT4(ring, REG_A8XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + OUT_PKT4(ring, REG_A8XX_RBBM_SLICE_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + } else { + OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + } } /* Execute the table update */ @@ -275,7 +288,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, * to make sure BV doesn't race ahead while BR is still switching * pagetables. */ - if (adreno_is_a7xx(&a6xx_gpu->base)) { + if (adreno_is_a7xx(&a6xx_gpu->base) || adreno_is_a8xx(&a6xx_gpu->base)) { OUT_PKT7(ring, CP_THREAD_CONTROL, 1); OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR); } @@ -289,20 +302,22 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, CACHE_INVALIDATE); if (!sysprof) { + u32 reg_status = adreno_is_a8xx(adreno_gpu) ? + REG_A8XX_RBBM_PERFCTR_SRAM_INIT_STATUS : + REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS; /* * Wait for SRAM clear after the pgtable update, so the * two can happen in parallel: */ OUT_PKT7(ring, CP_WAIT_REG_MEM, 6); OUT_RING(ring, CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ)); - OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_LO( - REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS)); + OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_LO(reg_status)); OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_HI(0)); OUT_RING(ring, CP_WAIT_REG_MEM_3_REF(0x1)); OUT_RING(ring, CP_WAIT_REG_MEM_4_MASK(0x1)); OUT_RING(ring, CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0)); - if (!adreno_is_a7xx(adreno_gpu)) { + if (!(adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu))) { /* Re-enable protected mode: */ OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); @@ -375,7 +390,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) rbmemptr_stats(ring, index, alwayson_end)); /* Write the fence to the scratch register */ - OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1); + OUT_PKT4(ring, REG_A6XX_CP_SCRATCH(2), 1); OUT_RING(ring, submit->seqno); /* @@ -440,6 +455,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct msm_ringbuffer *ring = submit->ring; + u32 rbbm_perfctr_cp0, cp_always_on_counter; unsigned int i, ibs = 0; adreno_check_and_reenable_stall(adreno_gpu); @@ -460,10 +476,16 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) if (gpu->nr_rings > 1) a6xx_emit_set_pseudo_reg(ring, a6xx_gpu, submit->queue); - get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0), - rbmemptr_stats(ring, index, cpcycles_start)); - get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER, - rbmemptr_stats(ring, index, alwayson_start)); + if (adreno_is_a8xx(adreno_gpu)) { + rbbm_perfctr_cp0 = REG_A8XX_RBBM_PERFCTR_CP(0); + cp_always_on_counter = REG_A8XX_CP_ALWAYS_ON_COUNTER; + } else { + rbbm_perfctr_cp0 = REG_A7XX_RBBM_PERFCTR_CP(0); + cp_always_on_counter = REG_A6XX_CP_ALWAYS_ON_COUNTER; + } + + get_stats_counter(ring, rbbm_perfctr_cp0, rbmemptr_stats(ring, index, cpcycles_start)); + get_stats_counter(ring, cp_always_on_counter, rbmemptr_stats(ring, index, alwayson_start)); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); OUT_RING(ring, CP_SET_THREAD_BOTH); @@ -510,14 +532,17 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, 0x00e); /* IB1LIST end */ } - get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0), - rbmemptr_stats(ring, index, cpcycles_end)); - get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER, - rbmemptr_stats(ring, index, alwayson_end)); + get_stats_counter(ring, rbbm_perfctr_cp0, rbmemptr_stats(ring, index, cpcycles_end)); + get_stats_counter(ring, cp_always_on_counter, rbmemptr_stats(ring, index, alwayson_end)); /* Write the fence to the scratch register */ - OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1); - OUT_RING(ring, submit->seqno); + if (adreno_is_a8xx(adreno_gpu)) { + OUT_PKT4(ring, REG_A8XX_CP_SCRATCH_GLOBAL(2), 1); + OUT_RING(ring, submit->seqno); + } else { + OUT_PKT4(ring, REG_A6XX_CP_SCRATCH(2), 1); + OUT_RING(ring, submit->seqno); + } OUT_PKT7(ring, CP_THREAD_CONTROL, 1); OUT_RING(ring, CP_SET_THREAD_BR); @@ -612,15 +637,26 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state) if (adreno_is_a630(adreno_gpu)) clock_cntl_on = 0x8aa8aa02; - else if (adreno_is_a610(adreno_gpu)) + else if (adreno_is_a610(adreno_gpu) || adreno_is_a612(adreno_gpu)) clock_cntl_on = 0xaaa8aa82; else if (adreno_is_a702(adreno_gpu)) clock_cntl_on = 0xaaaaaa82; else clock_cntl_on = 0x8aa8aa82; - cgc_delay = adreno_is_a615_family(adreno_gpu) ? 0x111 : 0x10111; - cgc_hyst = adreno_is_a615_family(adreno_gpu) ? 0x555 : 0x5555; + if (adreno_is_a612(adreno_gpu)) + cgc_delay = 0x11; + else if (adreno_is_a615_family(adreno_gpu)) + cgc_delay = 0x111; + else + cgc_delay = 0x10111; + + if (adreno_is_a612(adreno_gpu)) + cgc_hyst = 0x55; + else if (adreno_is_a615_family(adreno_gpu)) + cgc_hyst = 0x555; + else + cgc_hyst = 0x5555; gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL, state ? adreno_gpu->info->a6xx->gmu_cgc_mode : 0); @@ -706,14 +742,20 @@ static int a6xx_calc_ubwc_config(struct adreno_gpu *gpu) /* Copy the data into the internal struct to drop the const qualifier (temporarily) */ *cfg = *common_cfg; - cfg->ubwc_swizzle = 0x6; - cfg->highest_bank_bit = 15; + /* Use common config as is for A8x */ + if (!adreno_is_a8xx(gpu)) { + cfg->ubwc_swizzle = 0x6; + cfg->highest_bank_bit = 15; + } if (adreno_is_a610(gpu)) { cfg->highest_bank_bit = 13; cfg->ubwc_swizzle = 0x7; } + if (adreno_is_a612(gpu)) + cfg->highest_bank_bit = 14; + if (adreno_is_a618(gpu)) cfg->highest_bank_bit = 14; @@ -993,7 +1035,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, return false; /* A7xx is safe! */ - if (adreno_is_a7xx(adreno_gpu) || adreno_is_a702(adreno_gpu)) + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a702(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) return true; /* @@ -1076,6 +1118,23 @@ static int a6xx_ucode_load(struct msm_gpu *gpu) } } + if (!a6xx_gpu->aqe_bo && adreno_gpu->fw[ADRENO_FW_AQE]) { + a6xx_gpu->aqe_bo = adreno_fw_create_bo(gpu, + adreno_gpu->fw[ADRENO_FW_AQE], &a6xx_gpu->aqe_iova); + + if (IS_ERR(a6xx_gpu->aqe_bo)) { + int ret = PTR_ERR(a6xx_gpu->aqe_bo); + + a6xx_gpu->aqe_bo = NULL; + DRM_DEV_ERROR(&gpu->pdev->dev, + "Could not allocate AQE ucode: %d\n", ret); + + return ret; + } + + msm_gem_object_set_name(a6xx_gpu->aqe_bo, "aqefw"); + } + /* * Expanded APRIV and targets that support WHERE_AM_I both need a * privileged buffer to store the RPTR shadow @@ -1107,7 +1166,7 @@ static int a6xx_ucode_load(struct msm_gpu *gpu) return 0; } -static int a6xx_zap_shader_init(struct msm_gpu *gpu) +int a6xx_zap_shader_init(struct msm_gpu *gpu) { static bool loaded; int ret; @@ -1220,17 +1279,20 @@ static int hw_init(struct msm_gpu *gpu) /* enable hardware clockgating */ a6xx_set_hwcg(gpu, true); - /* VBIF/GBIF start*/ - if (adreno_is_a610_family(adreno_gpu) || - adreno_is_a640_family(adreno_gpu) || - adreno_is_a650_family(adreno_gpu) || - adreno_is_a7xx(adreno_gpu)) { + /* For gmuwrapper implementations, do the VBIF/GBIF CX configuration here */ + if (adreno_is_a610_family(adreno_gpu)) { gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620); gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620); gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620); gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE3, 0x00071620); - gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, - adreno_is_a7xx(adreno_gpu) ? 0x2120212 : 0x3); + } + + if (adreno_is_a610_family(adreno_gpu) || + adreno_is_a640_family(adreno_gpu) || + adreno_is_a650_family(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x3); + } else if (adreno_is_a7xx(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x2120212); } else { gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3); } @@ -1285,10 +1347,10 @@ static int hw_init(struct msm_gpu *gpu) } if (adreno_is_a660_family(adreno_gpu)) - gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020); + gpu_write(gpu, REG_A7XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020); /* Setting the mem pool size */ - if (adreno_is_a610(adreno_gpu)) { + if (adreno_is_a610(adreno_gpu) || adreno_is_a612(adreno_gpu)) { gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 48); gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 47); } else if (adreno_is_a702(adreno_gpu)) { @@ -1321,7 +1383,8 @@ static int hw_init(struct msm_gpu *gpu) a6xx_set_ubwc_config(gpu); /* Enable fault detection */ - if (adreno_is_a730(adreno_gpu) || + if (adreno_is_a612(adreno_gpu) || + adreno_is_a730(adreno_gpu) || adreno_is_a740_family(adreno_gpu)) gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0xcfffff); else if (adreno_is_a690(adreno_gpu)) @@ -1540,7 +1603,7 @@ static void a6xx_recover(struct msm_gpu *gpu) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gmu *gmu = &a6xx_gpu->gmu; - int i, active_submits; + int active_submits; adreno_dump_info(gpu); @@ -1548,10 +1611,6 @@ static void a6xx_recover(struct msm_gpu *gpu) /* Sometimes crashstate capture is skipped, so SQE should be halted here again */ gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); - for (i = 0; i < 8; i++) - DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i, - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i))); - if (hang_debug) a6xx_dump(gpu); @@ -1576,9 +1635,9 @@ static void a6xx_recover(struct msm_gpu *gpu) */ gpu->active_submits = 0; - if (adreno_has_gmu_wrapper(adreno_gpu)) { + if (adreno_has_gmu_wrapper(adreno_gpu) || adreno_has_rgmu(adreno_gpu)) { /* Drain the outstanding traffic on memory buses */ - a6xx_bus_clear_pending_transactions(adreno_gpu, true); + adreno_gpu->funcs->bus_halt(adreno_gpu, true); /* Reset the GPU to a clean state */ a6xx_gpu_sw_reset(gpu, true); @@ -1737,10 +1796,10 @@ static int a6xx_fault_handler(void *arg, unsigned long iova, int flags, void *da const char *block = "unknown"; u32 scratch[] = { - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(4)), - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(5)), - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(6)), - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(7)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(4)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(5)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(6)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(7)), }; if (info) @@ -2072,7 +2131,7 @@ static int a7xx_cx_mem_init(struct a6xx_gpu *a6xx_gpu) u32 fuse_val; int ret; - if (adreno_is_a750(adreno_gpu)) { + if (adreno_is_a750(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) { /* * Assume that if qcom scm isn't available, that whatever * replacement allows writing the fuse register ourselves. @@ -2098,9 +2157,9 @@ static int a7xx_cx_mem_init(struct a6xx_gpu *a6xx_gpu) return ret; /* - * On a750 raytracing may be disabled by the firmware, find out - * whether that's the case. The scm call above sets the fuse - * register. + * On A7XX_GEN3 and newer, raytracing may be disabled by the + * firmware, find out whether that's the case. The scm call + * above sets the fuse register. */ fuse_val = a6xx_llc_read(a6xx_gpu, REG_A7XX_CX_MISC_SW_FUSE_VALUE); @@ -2161,7 +2220,7 @@ void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_ void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert) { /* 11nm chips (e.g. ones with A610) have hw issues with the reset line! */ - if (adreno_is_a610(to_adreno_gpu(gpu))) + if (adreno_is_a610(to_adreno_gpu(gpu)) || adreno_is_a8xx(to_adreno_gpu(gpu))) return; gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, assert); @@ -2192,7 +2251,12 @@ static int a6xx_gmu_pm_resume(struct msm_gpu *gpu) msm_devfreq_resume(gpu); - adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate(a6xx_gpu) : a6xx_llc_activate(a6xx_gpu); + if (adreno_is_a8xx(adreno_gpu)) + a8xx_llc_activate(a6xx_gpu); + else if (adreno_is_a7xx(adreno_gpu)) + a7xx_llc_activate(a6xx_gpu); + else + a6xx_llc_activate(a6xx_gpu); return ret; } @@ -2229,6 +2293,12 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) if (ret) goto err_bulk_clk; + ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks); + if (ret) { + clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); + goto err_bulk_clk; + } + if (adreno_is_a619_holi(adreno_gpu)) a6xx_sptprac_enable(gmu); @@ -2242,8 +2312,10 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) err_set_opp: mutex_unlock(&a6xx_gpu->gmu.lock); - if (!ret) + if (!ret) { msm_devfreq_resume(gpu); + a6xx_llc_activate(a6xx_gpu); + } return ret; } @@ -2284,17 +2356,20 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) trace_msm_gpu_suspend(0); + a6xx_llc_deactivate(a6xx_gpu); + msm_devfreq_suspend(gpu); mutex_lock(&a6xx_gpu->gmu.lock); /* Drain the outstanding traffic on memory buses */ - a6xx_bus_clear_pending_transactions(adreno_gpu, true); + adreno_gpu->funcs->bus_halt(adreno_gpu, true); if (adreno_is_a619_holi(adreno_gpu)) a6xx_sptprac_disable(gmu); clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); + clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks); pm_runtime_put_sync(gmu->gxpd); dev_pm_opp_set_opp(&gpu->pdev->dev, NULL); @@ -2345,6 +2420,11 @@ static void a6xx_destroy(struct msm_gpu *gpu) drm_gem_object_put(a6xx_gpu->sqe_bo); } + if (a6xx_gpu->aqe_bo) { + msm_gem_unpin_iova(a6xx_gpu->aqe_bo, gpu->vm); + drm_gem_object_put(a6xx_gpu->aqe_bo); + } + if (a6xx_gpu->shadow_bo) { msm_gem_unpin_iova(a6xx_gpu->shadow_bo, gpu->vm); drm_gem_object_put(a6xx_gpu->shadow_bo); @@ -2527,7 +2607,105 @@ static int a6xx_set_supported_hw(struct device *dev, const struct adreno_info *i return 0; } -static const struct adreno_gpu_funcs funcs = { +static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) +{ + struct msm_drm_private *priv = dev->dev_private; + struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; + struct device_node *node; + struct a6xx_gpu *a6xx_gpu; + struct adreno_gpu *adreno_gpu; + struct msm_gpu *gpu; + extern int enable_preemption; + bool is_a7xx; + int ret, nr_rings = 1; + + a6xx_gpu = kzalloc(sizeof(*a6xx_gpu), GFP_KERNEL); + if (!a6xx_gpu) + return ERR_PTR(-ENOMEM); + + adreno_gpu = &a6xx_gpu->base; + gpu = &adreno_gpu->base; + + mutex_init(&a6xx_gpu->gmu.lock); + + adreno_gpu->registers = NULL; + + /* Check if there is a GMU phandle and set it up */ + node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); + /* FIXME: How do we gracefully handle this? */ + BUG_ON(!node); + + adreno_gpu->gmu_is_wrapper = of_device_is_compatible(node, "qcom,adreno-gmu-wrapper"); + + adreno_gpu->base.hw_apriv = + !!(config->info->quirks & ADRENO_QUIRK_HAS_HW_APRIV); + + /* gpu->info only gets assigned in adreno_gpu_init(). A8x is included intentionally */ + is_a7xx = config->info->family >= ADRENO_7XX_GEN1; + + a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx); + + ret = a6xx_set_supported_hw(&pdev->dev, config->info); + if (ret) { + a6xx_llc_slices_destroy(a6xx_gpu); + kfree(a6xx_gpu); + return ERR_PTR(ret); + } + + if ((enable_preemption == 1) || (enable_preemption == -1 && + (config->info->quirks & ADRENO_QUIRK_PREEMPTION))) + nr_rings = 4; + + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, nr_rings); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + + /* + * For now only clamp to idle freq for devices where this is known not + * to cause power supply issues: + */ + if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) + priv->gpu_clamp_to_idle = true; + + if (adreno_has_gmu_wrapper(adreno_gpu) || adreno_has_rgmu(adreno_gpu)) + ret = a6xx_gmu_wrapper_init(a6xx_gpu, node); + else + ret = a6xx_gmu_init(a6xx_gpu, node); + of_node_put(node); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) { + ret = a7xx_cx_mem_init(a6xx_gpu); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + } + + adreno_gpu->uche_trap_base = 0x1fffffffff000ull; + + msm_mmu_set_fault_handler(to_msm_vm(gpu->vm)->mmu, gpu, + adreno_gpu->funcs->mmu_fault_handler); + + ret = a6xx_calc_ubwc_config(adreno_gpu); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + + /* Set up the preemption specific bits and pieces for each ringbuffer */ + a6xx_preempt_init(gpu); + + return gpu; +} + +const struct adreno_gpu_funcs a6xx_gpu_funcs = { .base = { .get_param = adreno_get_param, .set_param = adreno_set_param, @@ -2554,12 +2732,14 @@ static const struct adreno_gpu_funcs funcs = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, - .sysprof_setup = a6xx_gmu_sysprof_setup, }, + .init = a6xx_gpu_init, .get_timestamp = a6xx_gmu_get_timestamp, + .bus_halt = a6xx_bus_clear_pending_transactions, + .mmu_fault_handler = a6xx_fault_handler, }; -static const struct adreno_gpu_funcs funcs_gmuwrapper = { +const struct adreno_gpu_funcs a6xx_gmuwrapper_funcs = { .base = { .get_param = adreno_get_param, .set_param = adreno_set_param, @@ -2585,10 +2765,13 @@ static const struct adreno_gpu_funcs funcs_gmuwrapper = { .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, }, + .init = a6xx_gpu_init, .get_timestamp = a6xx_get_timestamp, + .bus_halt = a6xx_bus_clear_pending_transactions, + .mmu_fault_handler = a6xx_fault_handler, }; -static const struct adreno_gpu_funcs funcs_a7xx = { +const struct adreno_gpu_funcs a7xx_gpu_funcs = { .base = { .get_param = adreno_get_param, .set_param = adreno_set_param, @@ -2615,111 +2798,36 @@ static const struct adreno_gpu_funcs funcs_a7xx = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, - .sysprof_setup = a6xx_gmu_sysprof_setup, }, + .init = a6xx_gpu_init, .get_timestamp = a6xx_gmu_get_timestamp, + .bus_halt = a6xx_bus_clear_pending_transactions, + .mmu_fault_handler = a6xx_fault_handler, }; -struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) -{ - struct msm_drm_private *priv = dev->dev_private; - struct platform_device *pdev = priv->gpu_pdev; - struct adreno_platform_config *config = pdev->dev.platform_data; - struct device_node *node; - struct a6xx_gpu *a6xx_gpu; - struct adreno_gpu *adreno_gpu; - struct msm_gpu *gpu; - extern int enable_preemption; - bool is_a7xx; - int ret; - - a6xx_gpu = kzalloc(sizeof(*a6xx_gpu), GFP_KERNEL); - if (!a6xx_gpu) - return ERR_PTR(-ENOMEM); - - adreno_gpu = &a6xx_gpu->base; - gpu = &adreno_gpu->base; - - mutex_init(&a6xx_gpu->gmu.lock); - - adreno_gpu->registers = NULL; - - /* Check if there is a GMU phandle and set it up */ - node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); - /* FIXME: How do we gracefully handle this? */ - BUG_ON(!node); - - adreno_gpu->gmu_is_wrapper = of_device_is_compatible(node, "qcom,adreno-gmu-wrapper"); - - adreno_gpu->base.hw_apriv = - !!(config->info->quirks & ADRENO_QUIRK_HAS_HW_APRIV); - - /* gpu->info only gets assigned in adreno_gpu_init() */ - is_a7xx = config->info->family == ADRENO_7XX_GEN1 || - config->info->family == ADRENO_7XX_GEN2 || - config->info->family == ADRENO_7XX_GEN3; - - a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx); - - ret = a6xx_set_supported_hw(&pdev->dev, config->info); - if (ret) { - a6xx_llc_slices_destroy(a6xx_gpu); - kfree(a6xx_gpu); - return ERR_PTR(ret); - } - - if ((enable_preemption == 1) || (enable_preemption == -1 && - (config->info->quirks & ADRENO_QUIRK_PREEMPTION))) - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 4); - else if (is_a7xx) - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 1); - else if (adreno_has_gmu_wrapper(adreno_gpu)) - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_gmuwrapper, 1); - else - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - - /* - * For now only clamp to idle freq for devices where this is known not - * to cause power supply issues: - */ - if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) - priv->gpu_clamp_to_idle = true; - - if (adreno_has_gmu_wrapper(adreno_gpu)) - ret = a6xx_gmu_wrapper_init(a6xx_gpu, node); - else - ret = a6xx_gmu_init(a6xx_gpu, node); - of_node_put(node); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - - if (adreno_is_a7xx(adreno_gpu)) { - ret = a7xx_cx_mem_init(a6xx_gpu); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - } - - adreno_gpu->uche_trap_base = 0x1fffffffff000ull; - - msm_mmu_set_fault_handler(to_msm_vm(gpu->vm)->mmu, gpu, - a6xx_fault_handler); - - ret = a6xx_calc_ubwc_config(adreno_gpu); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - - /* Set up the preemption specific bits and pieces for each ringbuffer */ - a6xx_preempt_init(gpu); - - return gpu; -} +const struct adreno_gpu_funcs a8xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a8xx_hw_init, + .ucode_load = a6xx_ucode_load, + .pm_suspend = a6xx_gmu_pm_suspend, + .pm_resume = a6xx_gmu_pm_resume, + .recover = a8xx_recover, + .submit = a7xx_submit, + .active_ring = a6xx_active_ring, + .irq = a8xx_irq, + .destroy = a6xx_destroy, + .gpu_busy = a8xx_gpu_busy, + .gpu_get_freq = a6xx_gmu_get_freq, + .gpu_set_freq = a6xx_gpu_set_freq, + .create_vm = a6xx_create_vm, + .create_private_vm = a6xx_create_private_vm, + .get_rptr = a6xx_get_rptr, + .progress = a8xx_progress, + }, + .init = a6xx_gpu_init, + .get_timestamp = a8xx_gmu_get_timestamp, + .bus_halt = a8xx_bus_clear_pending_transactions, + .mmu_fault_handler = a8xx_fault_handler, +}; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 0b17d36c36a9..6820216ec5fc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -46,6 +46,9 @@ struct a6xx_info { const struct adreno_protect *protect; const struct adreno_reglist_list *pwrup_reglist; const struct adreno_reglist_list *ifpc_reglist; + const struct adreno_reglist *gbif_cx; + const struct adreno_reglist_pipe *nonctxt_reglist; + u32 max_slices; u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; @@ -57,6 +60,8 @@ struct a6xx_gpu { struct drm_gem_object *sqe_bo; uint64_t sqe_iova; + struct drm_gem_object *aqe_bo; + uint64_t aqe_iova; struct msm_ringbuffer *cur_ring; struct msm_ringbuffer *next_ring; @@ -101,6 +106,11 @@ struct a6xx_gpu { void *htw_llc_slice; bool have_mmu500; bool hung; + + u32 cached_aperture; + spinlock_t aperture_lock; + + u32 slice_mask; }; #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base) @@ -216,6 +226,11 @@ struct a7xx_cp_smmu_info { #define A6XX_PROTECT_RDONLY(_reg, _len) \ ((((_len) & 0x3FFF) << 18) | ((_reg) & 0x3FFFF)) +extern const struct adreno_gpu_funcs a6xx_gpu_funcs; +extern const struct adreno_gpu_funcs a6xx_gmuwrapper_funcs; +extern const struct adreno_gpu_funcs a7xx_gpu_funcs; +extern const struct adreno_gpu_funcs a8xx_gpu_funcs; + static inline bool a6xx_has_gbif(struct adreno_gpu *gpu) { if(adreno_is_a630(gpu)) @@ -298,5 +313,19 @@ int a6xx_gpu_state_put(struct msm_gpu_state *state); void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off); void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert); int a6xx_fenced_write(struct a6xx_gpu *gpu, u32 offset, u64 value, u32 mask, bool is_64b); +void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +int a6xx_zap_shader_init(struct msm_gpu *gpu); +void a8xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off); +int a8xx_fault_handler(void *arg, unsigned long iova, int flags, void *data); +void a8xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +int a8xx_gmu_get_timestamp(struct msm_gpu *gpu, uint64_t *value); +u64 a8xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate); +int a8xx_gpu_feature_probe(struct msm_gpu *gpu); +void a8xx_gpu_get_slice_info(struct msm_gpu *gpu); +int a8xx_hw_init(struct msm_gpu *gpu); +irqreturn_t a8xx_irq(struct msm_gpu *gpu); +void a8xx_llc_activate(struct a6xx_gpu *a6xx_gpu); +bool a8xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +void a8xx_recover(struct msm_gpu *gpu); #endif /* __A6XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 4c7f3c642f6a..d2d6b2fd3cba 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1255,7 +1255,7 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, return; /* Set the fence to ALLOW mode so we can access the registers */ - gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2], &a6xx_state->gmu_registers[3], false); @@ -1596,7 +1596,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) /* Get the generic state from the adreno core */ adreno_gpu_state_get(gpu, &a6xx_state->base); - if (!adreno_has_gmu_wrapper(adreno_gpu)) { + if (!adreno_has_gmu_wrapper(adreno_gpu) && + !adreno_has_rgmu(adreno_gpu)) { a6xx_get_gmu_registers(gpu, a6xx_state); a6xx_state->gmu_log = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.log); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 1c18499b60bb..b49d8427b59e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -71,8 +71,8 @@ static const struct a6xx_cluster { u32 sel_val; } a6xx_clusters[] = { CLUSTER(CLUSTER_GRAS, a6xx_gras_cluster, 0, 0), - CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rac, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x0), - CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rbp, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x9), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rac, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 0x0), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rbp, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 0x9), CLUSTER(CLUSTER_PS, a6xx_ps_cluster, 0, 0), CLUSTER(CLUSTER_FE, a6xx_fe_cluster, 0, 0), CLUSTER(CLUSTER_PC_VS, a6xx_pc_vs_cluster, 0, 0), @@ -303,8 +303,8 @@ static const u32 a660_registers[] = { static const struct a6xx_registers a6xx_reglist[] = { REGS(a6xx_registers, 0, 0), REGS(a660_registers, 0, 0), - REGS(a6xx_rb_rac_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0), - REGS(a6xx_rb_rbp_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 9), + REGS(a6xx_rb_rac_registers, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 0), + REGS(a6xx_rb_rbp_registers, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 9), }; static const u32 a6xx_ahb_registers[] = { @@ -343,48 +343,48 @@ static const struct a6xx_registers a6xx_gbif_reglist = static const u32 a6xx_gmu_gx_registers[] = { /* GMU GX */ - 0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b, - 0x001e, 0x001e, 0x0020, 0x0023, 0x0026, 0x0026, 0x0028, 0x002b, - 0x002e, 0x002e, 0x0030, 0x0033, 0x0036, 0x0036, 0x0038, 0x003b, - 0x003e, 0x003e, 0x0040, 0x0043, 0x0046, 0x0046, 0x0080, 0x0084, - 0x0100, 0x012b, 0x0140, 0x0140, + 0x1a800, 0x1a800, 0x1a810, 0x1a813, 0x1a816, 0x1a816, 0x1a818, 0x1a81b, + 0x1a81e, 0x1a81e, 0x1a820, 0x1a823, 0x1a826, 0x1a826, 0x1a828, 0x1a82b, + 0x1a82e, 0x1a82e, 0x1a830, 0x1a833, 0x1a836, 0x1a836, 0x1a838, 0x1a83b, + 0x1a83e, 0x1a83e, 0x1a840, 0x1a843, 0x1a846, 0x1a846, 0x1a880, 0x1a884, + 0x1a900, 0x1a92b, 0x1a940, 0x1a940, }; static const u32 a6xx_gmu_cx_registers[] = { /* GMU CX */ - 0x4c00, 0x4c07, 0x4c10, 0x4c12, 0x4d00, 0x4d00, 0x4d07, 0x4d0a, - 0x5000, 0x5004, 0x5007, 0x5008, 0x500b, 0x500c, 0x500f, 0x501c, - 0x5024, 0x502a, 0x502d, 0x5030, 0x5040, 0x5053, 0x5087, 0x5089, - 0x50a0, 0x50a2, 0x50a4, 0x50af, 0x50c0, 0x50c3, 0x50d0, 0x50d0, - 0x50e4, 0x50e4, 0x50e8, 0x50ec, 0x5100, 0x5103, 0x5140, 0x5140, - 0x5142, 0x5144, 0x514c, 0x514d, 0x514f, 0x5151, 0x5154, 0x5154, - 0x5157, 0x5158, 0x515d, 0x515d, 0x5162, 0x5162, 0x5164, 0x5165, - 0x5180, 0x5186, 0x5190, 0x519e, 0x51c0, 0x51c0, 0x51c5, 0x51cc, - 0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201, + 0x1f400, 0x1f407, 0x1f410, 0x1f412, 0x1f500, 0x1f500, 0x1f507, 0x1f50a, + 0x1f800, 0x1f804, 0x1f807, 0x1f808, 0x1f80b, 0x1f80c, 0x1f80f, 0x1f81c, + 0x1f824, 0x1f82a, 0x1f82d, 0x1f830, 0x1f840, 0x1f853, 0x1f887, 0x1f889, + 0x1f8a0, 0x1f8a2, 0x1f8a4, 0x1f8af, 0x1f8c0, 0x1f8c3, 0x1f8d0, 0x1f8d0, + 0x1f8e4, 0x1f8e4, 0x1f8e8, 0x1f8ec, 0x1f900, 0x1f903, 0x1f940, 0x1f940, + 0x1f942, 0x1f944, 0x1f94c, 0x1f94d, 0x1f94f, 0x1f951, 0x1f954, 0x1f954, + 0x1f957, 0x1f958, 0x1f95d, 0x1f95d, 0x1f962, 0x1f962, 0x1f964, 0x1f965, + 0x1f980, 0x1f986, 0x1f990, 0x1f99e, 0x1f9c0, 0x1f9c0, 0x1f9c5, 0x1f9cc, + 0x1f9e0, 0x1f9e2, 0x1f9f0, 0x1f9f0, 0x1fa00, 0x1fa01, /* GMU AO */ - 0x9300, 0x9316, 0x9400, 0x9400, + 0x23b00, 0x23b16, 0x23c00, 0x23c00, }; static const u32 a6xx_gmu_gpucc_registers[] = { /* GPU CC */ - 0x9800, 0x9812, 0x9840, 0x9852, 0x9c00, 0x9c04, 0x9c07, 0x9c0b, - 0x9c15, 0x9c1c, 0x9c1e, 0x9c2d, 0x9c3c, 0x9c3d, 0x9c3f, 0x9c40, - 0x9c42, 0x9c49, 0x9c58, 0x9c5a, 0x9d40, 0x9d5e, 0xa000, 0xa002, - 0xa400, 0xa402, 0xac00, 0xac02, 0xb000, 0xb002, 0xb400, 0xb402, - 0xb800, 0xb802, + 0x24000, 0x24012, 0x24040, 0x24052, 0x24400, 0x24404, 0x24407, 0x2440b, + 0x24415, 0x2441c, 0x2441e, 0x2442d, 0x2443c, 0x2443d, 0x2443f, 0x24440, + 0x24442, 0x24449, 0x24458, 0x2445a, 0x24540, 0x2455e, 0x24800, 0x24802, + 0x24c00, 0x24c02, 0x25400, 0x25402, 0x25800, 0x25802, 0x25c00, 0x25c02, + 0x26000, 0x26002, /* GPU CC ACD */ - 0xbc00, 0xbc16, 0xbc20, 0xbc27, + 0x26400, 0x26416, 0x26420, 0x26427, }; static const u32 a621_gmu_gpucc_registers[] = { /* GPU CC */ - 0x9800, 0x980e, 0x9c00, 0x9c0e, 0xb000, 0xb004, 0xb400, 0xb404, - 0xb800, 0xb804, 0xbc00, 0xbc05, 0xbc14, 0xbc1d, 0xbc2a, 0xbc30, - 0xbc32, 0xbc32, 0xbc41, 0xbc55, 0xbc66, 0xbc68, 0xbc78, 0xbc7a, - 0xbc89, 0xbc8a, 0xbc9c, 0xbc9e, 0xbca0, 0xbca3, 0xbcb3, 0xbcb5, - 0xbcc5, 0xbcc7, 0xbcd6, 0xbcd8, 0xbce8, 0xbce9, 0xbcf9, 0xbcfc, - 0xbd0b, 0xbd0c, 0xbd1c, 0xbd1e, 0xbd40, 0xbd70, 0xbe00, 0xbe16, - 0xbe20, 0xbe2d, + 0x24000, 0x2400e, 0x24400, 0x2440e, 0x25800, 0x25804, 0x25c00, 0x25c04, + 0x26000, 0x26004, 0x26400, 0x26405, 0x26414, 0x2641d, 0x2642a, 0x26430, + 0x26432, 0x26432, 0x26441, 0x26455, 0x26466, 0x26468, 0x26478, 0x2647a, + 0x26489, 0x2648a, 0x2649c, 0x2649e, 0x264a0, 0x264a3, 0x264b3, 0x264b5, + 0x264c5, 0x264c7, 0x264d6, 0x264d8, 0x264e8, 0x264e9, 0x264f9, 0x264fc, + 0x2650b, 0x2650c, 0x2651c, 0x2651e, 0x26540, 0x26570, 0x26600, 0x26616, + 0x26620, 0x2662d, }; static const u32 a6xx_gmu_cx_rscc_registers[] = { @@ -575,7 +575,7 @@ struct gen7_sptp_cluster_registers { /* statetype: SP block state type for the cluster */ enum a7xx_statetype_id statetype; /* pipe_id: Pipe identifier */ - enum a7xx_pipe pipe_id; + enum adreno_pipe pipe_id; /* context_id: Context identifier */ int context_id; /* location_id: Location identifier */ @@ -801,10 +801,10 @@ static const char *a7xx_statetype_names[] = { }; static const char *a7xx_pipe_names[] = { - A7XX_NAME(A7XX_PIPE_NONE), - A7XX_NAME(A7XX_PIPE_BR), - A7XX_NAME(A7XX_PIPE_BV), - A7XX_NAME(A7XX_PIPE_LPAC), + A7XX_NAME(PIPE_NONE), + A7XX_NAME(PIPE_BR), + A7XX_NAME(PIPE_BV), + A7XX_NAME(PIPE_LPAC), }; static const char *a7xx_cluster_names[] = { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 550de6ad68ef..53cfdf4e6c34 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -23,6 +23,7 @@ static const char * const a6xx_hfi_msg_id[] = { HFI_MSG_ID(HFI_H2F_MSG_START), HFI_MSG_ID(HFI_H2F_FEATURE_CTRL), HFI_MSG_ID(HFI_H2F_MSG_CORE_FW_START), + HFI_MSG_ID(HFI_H2F_MSG_TABLE), HFI_MSG_ID(HFI_H2F_MSG_GX_BW_PERF_VOTE), HFI_MSG_ID(HFI_H2F_MSG_PREPARE_SLUMBER), }; @@ -105,10 +106,25 @@ static int a6xx_hfi_wait_for_msg_interrupt(struct a6xx_gmu *gmu, u32 id, u32 seq { int ret; u32 val; + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); - /* Wait for a response */ - ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, - val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 1000000); + do { + /* Wait for a response */ + ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, + val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 1000000); + + if (!ret) + break; + + if (completion_done(&a6xx_gpu->base.fault_coredump_done)) + break; + + /* We may timeout because the GMU is temporarily wedged from + * pending faults from the GPU and we are taking a devcoredump. + * Wait until the MMU is resumed and try again. + */ + wait_for_completion(&a6xx_gpu->base.fault_coredump_done); + } while (true); if (ret) { DRM_DEV_ERROR(gmu->dev, @@ -255,11 +271,63 @@ static int a6xx_hfi_send_perf_table_v1(struct a6xx_gmu *gmu) NULL, 0); } +static int a8xx_hfi_send_perf_table(struct a6xx_gmu *gmu) +{ + unsigned int num_gx_votes = 3, num_cx_votes = 2; + struct a6xx_hfi_table_entry *entry; + struct a6xx_hfi_table *tbl; + int ret, i; + u32 size; + + size = sizeof(*tbl) + (2 * sizeof(tbl->entry[0])) + + (gmu->nr_gpu_freqs * num_gx_votes * sizeof(gmu->gx_arc_votes[0])) + + (gmu->nr_gmu_freqs * num_cx_votes * sizeof(gmu->cx_arc_votes[0])); + tbl = kzalloc(size, GFP_KERNEL); + tbl->type = HFI_TABLE_GPU_PERF; + + /* First fill GX votes */ + entry = &tbl->entry[0]; + entry->count = gmu->nr_gpu_freqs; + entry->stride = num_gx_votes; + + for (i = 0; i < gmu->nr_gpu_freqs; i++) { + unsigned int base = i * entry->stride; + + entry->data[base+0] = gmu->gx_arc_votes[i]; + entry->data[base+1] = gmu->dep_arc_votes[i]; + entry->data[base+2] = gmu->gpu_freqs[i] / 1000; + } + + /* Then fill CX votes */ + entry = (struct a6xx_hfi_table_entry *) + &tbl->entry[0].data[gmu->nr_gpu_freqs * num_gx_votes]; + + entry->count = gmu->nr_gmu_freqs; + entry->stride = num_cx_votes; + + for (i = 0; i < gmu->nr_gmu_freqs; i++) { + unsigned int base = i * entry->stride; + + entry->data[base] = gmu->cx_arc_votes[i]; + entry->data[base+1] = gmu->gmu_freqs[i] / 1000; + } + + ret = a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_TABLE, tbl, size, NULL, 0); + + kfree(tbl); + return ret; +} + static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct a6xx_hfi_msg_perf_table msg = { 0 }; int i; + if (adreno_is_a8xx(adreno_gpu)) + return a8xx_hfi_send_perf_table(gmu); + msg.num_gpu_levels = gmu->nr_gpu_freqs; msg.num_gmu_levels = gmu->nr_gmu_freqs; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h index 653ef720e2da..6f9f74a0bc85 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h @@ -185,6 +185,23 @@ struct a6xx_hfi_msg_core_fw_start { u32 handle; }; +#define HFI_H2F_MSG_TABLE 15 + +struct a6xx_hfi_table_entry { + u32 count; + u32 stride; + u32 data[]; +}; + +struct a6xx_hfi_table { + u32 header; + u32 version; + u32 type; +#define HFI_TABLE_BW_VOTE 0 +#define HFI_TABLE_GPU_PERF 1 + struct a6xx_hfi_table_entry entry[]; +}; + #define HFI_H2F_MSG_GX_BW_PERF_VOTE 30 struct a6xx_hfi_gx_bw_perf_vote_cmd { diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c new file mode 100644 index 000000000000..30de078e9dfd --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c @@ -0,0 +1,1201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ + + +#include "msm_gem.h" +#include "msm_mmu.h" +#include "msm_gpu_trace.h" +#include "a6xx_gpu.h" +#include "a6xx_gmu.xml.h" + +#include +#include +#include +#include +#include + +#define GPU_PAS_ID 13 + +static void a8xx_aperture_slice_set(struct msm_gpu *gpu, enum adreno_pipe pipe, u32 slice) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u32 val; + + val = A8XX_CP_APERTURE_CNTL_HOST_PIPEID(pipe) | A8XX_CP_APERTURE_CNTL_HOST_SLICEID(slice); + + if (a6xx_gpu->cached_aperture == val) + return; + + gpu_write(gpu, REG_A8XX_CP_APERTURE_CNTL_HOST, val); + + a6xx_gpu->cached_aperture = val; +} + +static void a8xx_aperture_acquire(struct msm_gpu *gpu, enum adreno_pipe pipe, unsigned long *flags) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + spin_lock_irqsave(&a6xx_gpu->aperture_lock, *flags); + + a8xx_aperture_slice_set(gpu, pipe, 0); +} + +static void a8xx_aperture_release(struct msm_gpu *gpu, unsigned long flags) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + spin_unlock_irqrestore(&a6xx_gpu->aperture_lock, flags); +} + +static void a8xx_aperture_clear(struct msm_gpu *gpu) +{ + unsigned long flags; + + a8xx_aperture_acquire(gpu, PIPE_NONE, &flags); + a8xx_aperture_release(gpu, flags); +} + +static void a8xx_write_pipe(struct msm_gpu *gpu, enum adreno_pipe pipe, u32 offset, u32 data) +{ + unsigned long flags; + + a8xx_aperture_acquire(gpu, pipe, &flags); + gpu_write(gpu, offset, data); + a8xx_aperture_release(gpu, flags); +} + +static u32 a8xx_read_pipe_slice(struct msm_gpu *gpu, enum adreno_pipe pipe, u32 slice, u32 offset) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&a6xx_gpu->aperture_lock, flags); + a8xx_aperture_slice_set(gpu, pipe, slice); + val = gpu_read(gpu, offset); + spin_unlock_irqrestore(&a6xx_gpu->aperture_lock, flags); + + return val; +} + +void a8xx_gpu_get_slice_info(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; + u32 slice_mask; + + if (adreno_gpu->info->family < ADRENO_8XX_GEN1) + return; + + if (a6xx_gpu->slice_mask) + return; + + slice_mask = GENMASK(info->max_slices - 1, 0); + + /* GEN1 doesn't support partial slice configurations */ + if (adreno_gpu->info->family == ADRENO_8XX_GEN1) { + a6xx_gpu->slice_mask = slice_mask; + return; + } + + slice_mask &= a6xx_llc_read(a6xx_gpu, + REG_A8XX_CX_MISC_SLICE_ENABLE_FINAL); + + a6xx_gpu->slice_mask = slice_mask; + + /* Chip ID depends on the number of slices available. So update it */ + adreno_gpu->chip_id |= FIELD_PREP(GENMASK(7, 4), hweight32(slice_mask)); +} + +static u32 a8xx_get_first_slice(struct a6xx_gpu *a6xx_gpu) +{ + return ffs(a6xx_gpu->slice_mask) - 1; +} + +static inline bool _a8xx_check_idle(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + /* Check that the GMU is idle */ + if (!a6xx_gmu_isidle(&a6xx_gpu->gmu)) + return false; + + /* Check that the CX master is idle */ + if (gpu_read(gpu, REG_A8XX_RBBM_STATUS) & + ~A8XX_RBBM_STATUS_CP_AHB_BUSY_CX_MASTER) + return false; + + return !(gpu_read(gpu, REG_A8XX_RBBM_INT_0_STATUS) & + A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT); +} + +static bool a8xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + /* wait for CP to drain ringbuffer: */ + if (!adreno_idle(gpu, ring)) + return false; + + if (spin_until(_a8xx_check_idle(gpu))) { + DRM_ERROR( + "%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X rptr/wptr %d/%d\n", + gpu->name, __builtin_return_address(0), + gpu_read(gpu, REG_A8XX_RBBM_STATUS), + gpu_read(gpu, REG_A8XX_RBBM_INT_0_STATUS), + gpu_read(gpu, REG_A6XX_CP_RB_RPTR), + gpu_read(gpu, REG_A6XX_CP_RB_WPTR)); + return false; + } + + return true; +} + +void a8xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + uint32_t wptr; + unsigned long flags; + + spin_lock_irqsave(&ring->preempt_lock, flags); + + /* Copy the shadow to the actual register */ + ring->cur = ring->next; + + /* Make sure to wrap wptr if we need to */ + wptr = get_wptr(ring); + + /* Update HW if this is the current ring and we are not in preempt*/ + if (!a6xx_in_preempt(a6xx_gpu)) { + if (a6xx_gpu->cur_ring == ring) + gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr); + else + ring->restore_wptr = true; + } else { + ring->restore_wptr = true; + } + + spin_unlock_irqrestore(&ring->preempt_lock, flags); +} + +static void a8xx_set_hwcg(struct msm_gpu *gpu, bool state) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + u32 val; + + if (adreno_is_x285(adreno_gpu) && state) + gpu_write(gpu, REG_A8XX_RBBM_CGC_0_PC, 0x00000702); + + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL, + state ? adreno_gpu->info->a6xx->gmu_cgc_mode : 0); + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL, + state ? 0x110111 : 0); + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL, + state ? 0x55555 : 0); + + gpu_write(gpu, REG_A8XX_RBBM_CLOCK_CNTL_GLOBAL, 1); + gpu_write(gpu, REG_A8XX_RBBM_CGC_GLOBAL_LOAD_CMD, !!state); + + if (state) { + gpu_write(gpu, REG_A8XX_RBBM_CGC_P2S_TRIG_CMD, 1); + + if (gpu_poll_timeout(gpu, REG_A8XX_RBBM_CGC_P2S_STATUS, val, + val & A8XX_RBBM_CGC_P2S_STATUS_TXDONE, 1, 10)) { + dev_err(&gpu->pdev->dev, "RBBM_CGC_P2S_STATUS TXDONE Poll failed\n"); + return; + } + + gpu_write(gpu, REG_A8XX_RBBM_CLOCK_CNTL_GLOBAL, 0); + } else { + /* + * GMU enables clk gating in GBIF during boot up. So, + * override that here when hwcg feature is disabled + */ + gpu_rmw(gpu, REG_A8XX_GBIF_CX_CONFIG, BIT(0), 0); + } +} + +static void a8xx_set_cp_protect(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct adreno_protect *protect = adreno_gpu->info->a6xx->protect; + u32 cntl, final_cfg; + unsigned int i; + + cntl = A8XX_CP_PROTECT_CNTL_PIPE_ACCESS_PROT_EN | + A8XX_CP_PROTECT_CNTL_PIPE_ACCESS_FAULT_ON_VIOL_EN | + A8XX_CP_PROTECT_CNTL_PIPE_LAST_SPAN_INF_RANGE | + A8XX_CP_PROTECT_CNTL_PIPE_HALT_SQE_RANGE__MASK; + /* + * Enable access protection to privileged registers, fault on an access + * protect violation and select the last span to protect from the start + * address all the way to the end of the register address space + */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_CP_PROTECT_CNTL_PIPE, cntl); + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_CP_PROTECT_CNTL_PIPE, cntl); + + a8xx_aperture_clear(gpu); + + for (i = 0; i < protect->count; i++) { + /* Intentionally skip writing to some registers */ + if (protect->regs[i]) { + gpu_write(gpu, REG_A8XX_CP_PROTECT_GLOBAL(i), protect->regs[i]); + final_cfg = protect->regs[i]; + } + } + + /* + * Last span feature is only supported on PIPE specific register. + * So update those here + */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_CP_PROTECT_PIPE(protect->count_max), final_cfg); + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_CP_PROTECT_PIPE(protect->count_max), final_cfg); + + a8xx_aperture_clear(gpu); +} + +static void a8xx_set_ubwc_config(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct qcom_ubwc_cfg_data *cfg = adreno_gpu->ubwc_config; + u32 level2_swizzling_dis = !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL2); + u32 level3_swizzling_dis = !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL3); + bool rgba8888_lossless = false, fp16compoptdis = false; + bool yuvnotcomptofc = false, min_acc_len_64b = false; + bool rgb565_predicator = false, amsbc = false; + bool ubwc_mode = qcom_ubwc_get_ubwc_mode(cfg); + u32 ubwc_version = cfg->ubwc_enc_version; + u32 hbb, hbb_hi, hbb_lo, mode = 1; + u8 uavflagprd_inv = 2; + + switch (ubwc_version) { + case UBWC_5_0: + amsbc = true; + rgb565_predicator = true; + mode = 4; + break; + case UBWC_4_0: + amsbc = true; + rgb565_predicator = true; + fp16compoptdis = true; + rgba8888_lossless = true; + mode = 2; + break; + case UBWC_3_0: + amsbc = true; + mode = 1; + break; + default: + dev_err(&gpu->pdev->dev, "Unknown UBWC version: 0x%x\n", ubwc_version); + break; + } + + /* + * We subtract 13 from the highest bank bit (13 is the minimum value + * allowed by hw) and write the lowest two bits of the remaining value + * as hbb_lo and the one above it as hbb_hi to the hardware. + */ + WARN_ON(cfg->highest_bank_bit < 13); + hbb = cfg->highest_bank_bit - 13; + hbb_hi = hbb >> 2; + hbb_lo = hbb & 3; + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); + + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CCU_NC_MODE_CNTL, + yuvnotcomptofc << 6 | + hbb_hi << 3 | + hbb_lo << 1); + + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CMP_NC_MODE_CNTL, + mode << 15 | + yuvnotcomptofc << 6 | + rgba8888_lossless << 4 | + fp16compoptdis << 3 | + rgb565_predicator << 2 | + amsbc << 1 | + min_acc_len_64b); + + a8xx_aperture_clear(gpu); + + gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, + level3_swizzling_dis << 13 | + level2_swizzling_dis << 12 | + hbb_hi << 10 | + uavflagprd_inv << 4 | + min_acc_len_64b << 3 | + hbb_lo << 1 | ubwc_mode); + + gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, + level3_swizzling_dis << 7 | + level2_swizzling_dis << 6 | + hbb_hi << 4 | + min_acc_len_64b << 3 | + hbb_lo << 1 | ubwc_mode); +} + +static void a8xx_nonctxt_config(struct msm_gpu *gpu, u32 *gmem_protect) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; + const struct adreno_reglist_pipe *regs = info->nonctxt_reglist; + unsigned int pipe_id, i; + unsigned long flags; + + for (pipe_id = PIPE_NONE; pipe_id <= PIPE_DDE_BV; pipe_id++) { + /* We don't have support for LPAC yet */ + if (pipe_id == PIPE_LPAC) + continue; + + a8xx_aperture_acquire(gpu, pipe_id, &flags); + + for (i = 0; regs[i].offset; i++) { + if (!(BIT(pipe_id) & regs[i].pipe)) + continue; + + if (regs[i].offset == REG_A8XX_RB_GC_GMEM_PROTECT) + *gmem_protect = regs[i].value; + + gpu_write(gpu, regs[i].offset, regs[i].value); + } + + a8xx_aperture_release(gpu, flags); + } + + a8xx_aperture_clear(gpu); +} + +static int a8xx_cp_init(struct msm_gpu *gpu) +{ + struct msm_ringbuffer *ring = gpu->rb[0]; + u32 mask; + + /* Disable concurrent binning before sending CP init */ + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, BIT(27)); + + OUT_PKT7(ring, CP_ME_INIT, 4); + + /* Use multiple HW contexts */ + mask = BIT(0); + + /* Enable error detection */ + mask |= BIT(1); + + /* Set default reset state */ + mask |= BIT(3); + + /* Disable save/restore of performance counters across preemption */ + mask |= BIT(6); + + OUT_RING(ring, mask); + + /* Enable multiple hardware contexts */ + OUT_RING(ring, 0x00000003); + + /* Enable error detection */ + OUT_RING(ring, 0x20000000); + + /* Operation mode mask */ + OUT_RING(ring, 0x00000002); + + a6xx_flush(gpu, ring); + return a8xx_idle(gpu, ring) ? 0 : -EINVAL; +} + +#define A8XX_INT_MASK \ + (A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR | \ + A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \ + A6XX_RBBM_INT_0_MASK_RBBM_GPC_ERROR | \ + A6XX_RBBM_INT_0_MASK_CP_SW | \ + A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \ + A6XX_RBBM_INT_0_MASK_PM4CPINTERRUPT | \ + A6XX_RBBM_INT_0_MASK_CP_RB_DONE_TS | \ + A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \ + A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW | \ + A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT | \ + A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \ + A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR | \ + A6XX_RBBM_INT_0_MASK_TSBWRITEERROR | \ + A6XX_RBBM_INT_0_MASK_SWFUSEVIOLATION) + +#define A8XX_APRIV_MASK \ + (A8XX_CP_APRIV_CNTL_PIPE_ICACHE | \ + A8XX_CP_APRIV_CNTL_PIPE_RBFETCH | \ + A8XX_CP_APRIV_CNTL_PIPE_RBPRIVLEVEL | \ + A8XX_CP_APRIV_CNTL_PIPE_RBRPWB) + +#define A8XX_BR_APRIV_MASK \ + (A8XX_APRIV_MASK | \ + A8XX_CP_APRIV_CNTL_PIPE_CDREAD | \ + A8XX_CP_APRIV_CNTL_PIPE_CDWRITE) + +#define A8XX_CP_GLOBAL_INT_MASK \ + (A8XX_CP_GLOBAL_INT_MASK_HWFAULTBR | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTBV | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTLPAC | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTAQE0 | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTAQE1 | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTDDEBR | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTDDEBV | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBR | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBV | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTLPAC | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTAQE0 | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTAQE1 | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTDDEBR | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTDDEBV) + +#define A8XX_CP_INTERRUPT_STATUS_MASK_PIPE \ + (A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFRBWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFIB1WRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFIB2WRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFIB3WRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFSDSWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFMRBWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFVSDWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_OPCODEERROR | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VSDPARITYERROR | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_REGISTERPROTECTIONERROR | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_ILLEGALINSTRUCTION | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_SMMUFAULT | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESPCLIENT| \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESPTYPE | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESPREAD | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_RTWROVF | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_LRZRTWROVF | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_LRZRTREFCNTOVF | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_LRZRTCLRRESMISS) + +#define A8XX_CP_HW_FAULT_STATUS_MASK_PIPE \ + (A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFRBFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFIB1FAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFIB2FAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFIB3FAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFSDSFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFMRBFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFVSDFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_SQEREADBURSTOVF | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_EVENTENGINEOVF | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_UCODEERROR) + +static int hw_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + unsigned int pipe_id, i; + u32 gmem_protect = 0; + u64 gmem_range_min; + int ret; + + ret = a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + if (ret) + return ret; + + /* Clear the cached value to force aperture configuration next time */ + a6xx_gpu->cached_aperture = UINT_MAX; + a8xx_aperture_clear(gpu); + + /* Clear GBIF halt in case GX domain was not collapsed */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0); + gpu_read(gpu, REG_A6XX_GBIF_HALT); + + gpu_write(gpu, REG_A8XX_RBBM_GBIF_HALT, 0); + gpu_read(gpu, REG_A8XX_RBBM_GBIF_HALT); + + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0); + + /* + * Disable the trusted memory range - we don't actually supported secure + * memory rendering at this point in time and we don't want to block off + * part of the virtual memory space. + */ + gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE, 0x00000000); + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); + + /* Make all blocks contribute to the GPU BUSY perf counter */ + gpu_write(gpu, REG_A8XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff); + + /* Setup GMEM Range in UCHE */ + gmem_range_min = SZ_64M; + /* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */ + gpu_write64(gpu, REG_A8XX_UCHE_CCHE_GC_GMEM_RANGE_MIN, gmem_range_min); + gpu_write64(gpu, REG_A8XX_SP_HLSQ_GC_GMEM_RANGE_MIN, gmem_range_min); + + /* Setup UCHE Trap region */ + gpu_write64(gpu, REG_A8XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A8XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A8XX_UCHE_CCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A8XX_UCHE_CCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); + + /* Turn on performance counters */ + gpu_write(gpu, REG_A8XX_RBBM_PERFCTR_CNTL, 0x1); + gpu_write(gpu, REG_A8XX_RBBM_SLICE_PERFCTR_CNTL, 0x1); + + /* Turn on the IFPC counter (countable 4 on XOCLK1) */ + gmu_write(&a6xx_gpu->gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_SELECT_XOCLK_1, + FIELD_PREP(GENMASK(7, 0), 0x4)); + + /* Select CP0 to always count cycles */ + gpu_write(gpu, REG_A8XX_CP_PERFCTR_CP_SEL(0), 1); + + a8xx_set_ubwc_config(gpu); + + /* Set weights for bicubic filtering */ + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(0), 0); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(1), 0x3fe05ff4); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), 0x3fa0ebee); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), 0x3f5193ed); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), 0x3f0243f0); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(5), 0x00000000); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(6), 0x3fd093e8); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(7), 0x3f4133dc); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(8), 0x3ea1dfdb); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(9), 0x3e0283e0); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(10), 0x0000ac2b); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(11), 0x0000f01d); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(12), 0x00114412); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(13), 0x0021980a); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(14), 0x0051ec05); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(15), 0x0000380e); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(16), 0x3ff09001); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(17), 0x3fc10bfa); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(18), 0x3f9193f7); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(19), 0x3f7227f7); + + gpu_write(gpu, REG_A8XX_UCHE_CLIENT_PF, BIT(7) | 0x1); + + a8xx_nonctxt_config(gpu, &gmem_protect); + + /* Enable fault detection */ + gpu_write(gpu, REG_A8XX_RBBM_INTERFACE_HANG_INT_CNTL, BIT(30) | 0xcfffff); + gpu_write(gpu, REG_A8XX_RBBM_SLICE_INTERFACE_HANG_INT_CNTL, BIT(30)); + + /* Set up the CX GMU counter 0 to count busy ticks */ + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, 0xff000000); + + /* Enable the power counter */ + gmu_rmw(gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_SELECT_XOCLK_0, 0xff, BIT(5)); + gmu_write(gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1); + + /* Protect registers from the CP */ + a8xx_set_cp_protect(gpu); + + /* Enable the GMEM save/restore feature for preemption */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ENABLE, 1); + + for (pipe_id = PIPE_BR; pipe_id <= PIPE_DDE_BV; pipe_id++) { + u32 apriv_mask = A8XX_APRIV_MASK; + unsigned long flags; + + if (pipe_id == PIPE_LPAC) + continue; + + if (pipe_id == PIPE_BR) + apriv_mask = A8XX_BR_APRIV_MASK; + + a8xx_aperture_acquire(gpu, pipe_id, &flags); + gpu_write(gpu, REG_A8XX_CP_APRIV_CNTL_PIPE, apriv_mask); + gpu_write(gpu, REG_A8XX_CP_INTERRUPT_STATUS_MASK_PIPE, + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE); + gpu_write(gpu, REG_A8XX_CP_HW_FAULT_STATUS_MASK_PIPE, + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE); + a8xx_aperture_release(gpu, flags); + } + + a8xx_aperture_clear(gpu); + + /* Enable interrupts */ + gpu_write(gpu, REG_A8XX_CP_INTERRUPT_STATUS_MASK_GLOBAL, A8XX_CP_GLOBAL_INT_MASK); + gpu_write(gpu, REG_A8XX_RBBM_INT_0_MASK, A8XX_INT_MASK); + + ret = adreno_hw_init(gpu); + if (ret) + goto out; + + gpu_write64(gpu, REG_A8XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova); + if (a6xx_gpu->aqe_iova) + gpu_write64(gpu, REG_A8XX_CP_AQE_INSTR_BASE_0, a6xx_gpu->aqe_iova); + + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova); + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, MSM_GPU_RB_CNTL_DEFAULT); + + /* Configure the RPTR shadow if needed: */ + gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR, shadowptr(a6xx_gpu, gpu->rb[0])); + gpu_write64(gpu, REG_A8XX_CP_RB_RPTR_ADDR_BV, rbmemptr(gpu->rb[0], bv_rptr)); + + for (i = 0; i < gpu->nr_rings; i++) + a6xx_gpu->shadow[i] = 0; + + /* Always come up on rb 0 */ + a6xx_gpu->cur_ring = gpu->rb[0]; + + for (i = 0; i < gpu->nr_rings; i++) + gpu->rb[i]->cur_ctx_seqno = 0; + + /* Enable the SQE_to start the CP engine */ + gpu_write(gpu, REG_A8XX_CP_SQE_CNTL, 1); + + ret = a8xx_cp_init(gpu); + if (ret) + goto out; + + /* + * Try to load a zap shader into the secure world. If successful + * we can use the CP to switch out of secure mode. If not then we + * have no resource but to try to switch ourselves out manually. If we + * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will + * be blocked and a permissions violation will soon follow. + */ + ret = a6xx_zap_shader_init(gpu); + if (!ret) { + OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1); + OUT_RING(gpu->rb[0], 0x00000000); + + a6xx_flush(gpu, gpu->rb[0]); + if (!a8xx_idle(gpu, gpu->rb[0])) + return -EINVAL; + } else if (ret == -ENODEV) { + /* + * This device does not use zap shader (but print a warning + * just in case someone got their dt wrong.. hopefully they + * have a debug UART to realize the error of their ways... + * if you mess this up you are about to crash horribly) + */ + dev_warn_once(gpu->dev->dev, + "Zap shader not enabled - using SECVID_TRUST_CNTL instead\n"); + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0); + ret = 0; + } else { + return ret; + } + + /* + * GMEM_PROTECT register should be programmed after GPU is transitioned to + * non-secure mode + */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_GC_GMEM_PROTECT, gmem_protect); + WARN_ON(!gmem_protect); + a8xx_aperture_clear(gpu); + + /* Enable hardware clockgating */ + a8xx_set_hwcg(gpu, true); +out: + /* + * Tell the GMU that we are done touching the GPU and it can start power + * management + */ + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + + return ret; +} + +int a8xx_hw_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + int ret; + + mutex_lock(&a6xx_gpu->gmu.lock); + ret = hw_init(gpu); + mutex_unlock(&a6xx_gpu->gmu.lock); + + return ret; +} + +static void a8xx_dump(struct msm_gpu *gpu) +{ + DRM_DEV_INFO(&gpu->pdev->dev, "status: %08x\n", gpu_read(gpu, REG_A8XX_RBBM_STATUS)); + adreno_dump(gpu); +} + +void a8xx_recover(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + int active_submits; + + adreno_dump_info(gpu); + + if (hang_debug) + a8xx_dump(gpu); + + /* + * To handle recovery specific sequences during the rpm suspend we are + * about to trigger + */ + a6xx_gpu->hung = true; + + /* Halt SQE first */ + gpu_write(gpu, REG_A8XX_CP_SQE_CNTL, 3); + + pm_runtime_dont_use_autosuspend(&gpu->pdev->dev); + + /* active_submit won't change until we make a submission */ + mutex_lock(&gpu->active_lock); + active_submits = gpu->active_submits; + + /* + * Temporarily clear active_submits count to silence a WARN() in the + * runtime suspend cb + */ + gpu->active_submits = 0; + + reinit_completion(&gmu->pd_gate); + dev_pm_genpd_add_notifier(gmu->cxpd, &gmu->pd_nb); + dev_pm_genpd_synced_poweroff(gmu->cxpd); + + /* Drop the rpm refcount from active submits */ + if (active_submits) + pm_runtime_put(&gpu->pdev->dev); + + /* And the final one from recover worker */ + pm_runtime_put_sync(&gpu->pdev->dev); + + if (!wait_for_completion_timeout(&gmu->pd_gate, msecs_to_jiffies(1000))) + DRM_DEV_ERROR(&gpu->pdev->dev, "cx gdsc didn't collapse\n"); + + dev_pm_genpd_remove_notifier(gmu->cxpd); + + pm_runtime_use_autosuspend(&gpu->pdev->dev); + + if (active_submits) + pm_runtime_get(&gpu->pdev->dev); + + pm_runtime_get_sync(&gpu->pdev->dev); + + gpu->active_submits = active_submits; + mutex_unlock(&gpu->active_lock); + + msm_gpu_hw_init(gpu); + a6xx_gpu->hung = false; +} + +static const char *a8xx_uche_fault_block(struct msm_gpu *gpu, u32 mid) +{ + static const char * const uche_clients[] = { + "BR_VFD", "BR_SP", "BR_VSC", "BR_VPC", "BR_HLSQ", "BR_PC", "BR_LRZ", "BR_TP", + "BV_VFD", "BV_SP", "BV_VSC", "BV_VPC", "BV_HLSQ", "BV_PC", "BV_LRZ", "BV_TP", + "STCHE", + }; + static const char * const uche_clients_lpac[] = { + "-", "SP_LPAC", "-", "-", "HLSQ_LPAC", "-", "-", "TP_LPAC", + }; + u32 val; + + /* + * The source of the data depends on the mid ID read from FSYNR1. + * and the client ID read from the UCHE block + */ + val = gpu_read(gpu, REG_A8XX_UCHE_CLIENT_PF); + + val &= GENMASK(6, 0); + + /* mid=3 refers to BR or BV */ + if (mid == 3) { + if (val < ARRAY_SIZE(uche_clients)) + return uche_clients[val]; + else + return "UCHE"; + } + + /* mid=8 refers to LPAC */ + if (mid == 8) { + if (val < ARRAY_SIZE(uche_clients_lpac)) + return uche_clients_lpac[val]; + else + return "UCHE_LPAC"; + } + + return "Unknown"; +} + +static const char *a8xx_fault_block(struct msm_gpu *gpu, u32 id) +{ + switch (id) { + case 0x0: + return "CP"; + case 0x1: + return "UCHE: Unknown"; + case 0x2: + return "UCHE_LPAC: Unknown"; + case 0x3: + case 0x8: + return a8xx_uche_fault_block(gpu, id); + case 0x4: + return "CCU"; + case 0x5: + return "Flag cache"; + case 0x6: + return "PREFETCH"; + case 0x7: + return "GMU"; + case 0x9: + return "UCHE_HPAC"; + } + + return "Unknown"; +} + +int a8xx_fault_handler(void *arg, unsigned long iova, int flags, void *data) +{ + struct msm_gpu *gpu = arg; + struct adreno_smmu_fault_info *info = data; + const char *block = "unknown"; + + u32 scratch[] = { + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(0)), + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(1)), + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(2)), + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(3)), + }; + + if (info) + block = a8xx_fault_block(gpu, info->fsynr1 & 0xff); + + return adreno_fault_handler(gpu, iova, flags, info, block, scratch); +} + +static void a8xx_cp_hw_err_irq(struct msm_gpu *gpu) +{ + u32 status = gpu_read(gpu, REG_A8XX_CP_INTERRUPT_STATUS_GLOBAL); + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u32 slice = a8xx_get_first_slice(a6xx_gpu); + u32 hw_fault_mask = GENMASK(6, 0); + u32 sw_fault_mask = GENMASK(22, 16); + u32 pipe = 0; + + dev_err_ratelimited(&gpu->pdev->dev, "CP Fault Global INT status: 0x%x\n", status); + + if (status & (A8XX_CP_GLOBAL_INT_MASK_HWFAULTBR | + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBR)) + pipe |= BIT(PIPE_BR); + + if (status & (A8XX_CP_GLOBAL_INT_MASK_HWFAULTBV | + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBV)) + pipe |= BIT(PIPE_BV); + + if (!pipe) { + dev_err_ratelimited(&gpu->pdev->dev, "CP Fault Unknown pipe\n"); + goto out; + } + + for (unsigned int pipe_id = PIPE_NONE; pipe_id <= PIPE_DDE_BV; pipe_id++) { + if (!(BIT(pipe_id) & pipe)) + continue; + + if (hw_fault_mask & status) { + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_HW_FAULT_STATUS_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP HW FAULT pipe: %u status: 0x%x\n", pipe_id, status); + } + + if (sw_fault_mask & status) { + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_INTERRUPT_STATUS_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP SW FAULT pipe: %u status: 0x%x\n", pipe_id, status); + + if (status & BIT(8)) { + a8xx_write_pipe(gpu, pipe_id, REG_A8XX_CP_SQE_STAT_ADDR_PIPE, 1); + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_SQE_STAT_DATA_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP Opcode error, opcode=0x%x\n", status); + } + + if (status & BIT(10)) { + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_PROTECT_STATUS_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP REG PROTECT error, status=0x%x\n", status); + } + } + } + +out: + /* Turn off interrupts to avoid triggering recovery again */ + a8xx_aperture_clear(gpu); + gpu_write(gpu, REG_A8XX_CP_INTERRUPT_STATUS_MASK_GLOBAL, 0); + gpu_write(gpu, REG_A8XX_RBBM_INT_0_MASK, 0); + + kthread_queue_work(gpu->worker, &gpu->recover_work); +} + +static u32 gpu_periph_read(struct msm_gpu *gpu, u32 dbg_offset) +{ + gpu_write(gpu, REG_A8XX_CP_SQE_UCODE_DBG_ADDR_PIPE, dbg_offset); + + return gpu_read(gpu, REG_A8XX_CP_SQE_UCODE_DBG_DATA_PIPE); +} + +static u64 gpu_periph_read64(struct msm_gpu *gpu, u32 dbg_offset) +{ + u64 lo, hi; + + lo = gpu_periph_read(gpu, dbg_offset); + hi = gpu_periph_read(gpu, dbg_offset + 1); + + return (hi << 32) | lo; +} + +#define CP_PERIPH_IB1_BASE_LO 0x7005 +#define CP_PERIPH_IB1_BASE_HI 0x7006 +#define CP_PERIPH_IB1_SIZE 0x7007 +#define CP_PERIPH_IB1_OFFSET 0x7008 +#define CP_PERIPH_IB2_BASE_LO 0x7009 +#define CP_PERIPH_IB2_BASE_HI 0x700a +#define CP_PERIPH_IB2_SIZE 0x700b +#define CP_PERIPH_IB2_OFFSET 0x700c +#define CP_PERIPH_IB3_BASE_LO 0x700d +#define CP_PERIPH_IB3_BASE_HI 0x700e +#define CP_PERIPH_IB3_SIZE 0x700f +#define CP_PERIPH_IB3_OFFSET 0x7010 + +static void a8xx_fault_detect_irq(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu); + unsigned long flags; + + /* + * If stalled on SMMU fault, we could trip the GPU's hang detection, + * but the fault handler will trigger the devcore dump, and we want + * to otherwise resume normally rather than killing the submit, so + * just bail. + */ + if (gpu_read(gpu, REG_A8XX_RBBM_MISC_STATUS) & A8XX_RBBM_MISC_STATUS_SMMU_STALLED_ON_FAULT) + return; + + /* + * Force the GPU to stay on until after we finish + * collecting information + */ + if (!adreno_has_gmu_wrapper(adreno_gpu)) + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1); + + DRM_DEV_ERROR(&gpu->pdev->dev, + "gpu fault ring %d fence %x status %8.8X gfx_status %8.8X\n", + ring ? ring->id : -1, ring ? ring->fctx->last_fence : 0, + gpu_read(gpu, REG_A8XX_RBBM_STATUS), gpu_read(gpu, REG_A8XX_RBBM_GFX_STATUS)); + + a8xx_aperture_acquire(gpu, PIPE_BR, &flags); + + DRM_DEV_ERROR(&gpu->pdev->dev, + "BR: status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x ib3 %16.16llX/%4.4x\n", + gpu_read(gpu, REG_A8XX_RBBM_GFX_BR_STATUS), + gpu_read(gpu, REG_A6XX_CP_RB_RPTR), + gpu_read(gpu, REG_A6XX_CP_RB_WPTR), + gpu_periph_read64(gpu, CP_PERIPH_IB1_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB1_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB2_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB2_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB3_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB3_OFFSET)); + + a8xx_aperture_release(gpu, flags); + a8xx_aperture_acquire(gpu, PIPE_BV, &flags); + + DRM_DEV_ERROR(&gpu->pdev->dev, + "BV: status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x ib3 %16.16llX/%4.4x\n", + gpu_read(gpu, REG_A8XX_RBBM_GFX_BV_STATUS), + gpu_read(gpu, REG_A8XX_CP_RB_RPTR_BV), + gpu_read(gpu, REG_A6XX_CP_RB_WPTR), + gpu_periph_read64(gpu, CP_PERIPH_IB1_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB1_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB2_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB2_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB3_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB3_OFFSET)); + + a8xx_aperture_release(gpu, flags); + a8xx_aperture_clear(gpu); + + /* Turn off the hangcheck timer to keep it from bothering us */ + timer_delete(&gpu->hangcheck_timer); + + kthread_queue_work(gpu->worker, &gpu->recover_work); +} + +static void a8xx_sw_fuse_violation_irq(struct msm_gpu *gpu) +{ + u32 status; + + status = gpu_read(gpu, REG_A8XX_RBBM_SW_FUSE_INT_STATUS); + gpu_write(gpu, REG_A8XX_RBBM_SW_FUSE_INT_MASK, 0); + + dev_err_ratelimited(&gpu->pdev->dev, "SW fuse violation status=%8.8x\n", status); + + /* + * Ignore FASTBLEND violations, because the HW will silently fall back + * to legacy blending. + */ + if (status & (A7XX_CX_MISC_SW_FUSE_VALUE_RAYTRACING | + A7XX_CX_MISC_SW_FUSE_VALUE_LPAC)) { + timer_delete(&gpu->hangcheck_timer); + + kthread_queue_work(gpu->worker, &gpu->recover_work); + } +} + +irqreturn_t a8xx_irq(struct msm_gpu *gpu) +{ + struct msm_drm_private *priv = gpu->dev->dev_private; + u32 status = gpu_read(gpu, REG_A8XX_RBBM_INT_0_STATUS); + + gpu_write(gpu, REG_A8XX_RBBM_INT_CLEAR_CMD, status); + + if (priv->disable_err_irq) + status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS; + + if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT) + a8xx_fault_detect_irq(gpu); + + if (status & A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR) { + u32 rl0, rl1; + + rl0 = gpu_read(gpu, REG_A8XX_CP_RL_ERROR_DETAILS_0); + rl1 = gpu_read(gpu, REG_A8XX_CP_RL_ERROR_DETAILS_1); + dev_err_ratelimited(&gpu->pdev->dev, + "CP | AHB bus error RL_ERROR_0: %x, RL_ERROR_1: %x\n", rl0, rl1); + } + + if (status & A6XX_RBBM_INT_0_MASK_CP_HW_ERROR) + a8xx_cp_hw_err_irq(gpu); + + if (status & A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW) + dev_err_ratelimited(&gpu->pdev->dev, "RBBM | ATB ASYNC overflow\n"); + + if (status & A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW) + dev_err_ratelimited(&gpu->pdev->dev, "RBBM | ATB bus overflow\n"); + + if (status & A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS) + dev_err_ratelimited(&gpu->pdev->dev, "UCHE | Out of bounds access\n"); + + if (status & A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR) + dev_err_ratelimited(&gpu->pdev->dev, "UCHE | Trap interrupt\n"); + + if (status & A6XX_RBBM_INT_0_MASK_SWFUSEVIOLATION) + a8xx_sw_fuse_violation_irq(gpu); + + if (status & A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS) { + msm_gpu_retire(gpu); + a6xx_preempt_trigger(gpu); + } + + if (status & A6XX_RBBM_INT_0_MASK_CP_SW) + a6xx_preempt_irq(gpu); + + return IRQ_HANDLED; +} + +void a8xx_llc_activate(struct a6xx_gpu *a6xx_gpu) +{ + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + + if (!llcc_slice_activate(a6xx_gpu->llc_slice)) { + u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice); + + gpu_scid &= GENMASK(5, 0); + + gpu_write(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, + FIELD_PREP(GENMASK(29, 24), gpu_scid) | + FIELD_PREP(GENMASK(23, 18), gpu_scid) | + FIELD_PREP(GENMASK(17, 12), gpu_scid) | + FIELD_PREP(GENMASK(11, 6), gpu_scid) | + FIELD_PREP(GENMASK(5, 0), gpu_scid)); + + gpu_write(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, + FIELD_PREP(GENMASK(27, 22), gpu_scid) | + FIELD_PREP(GENMASK(21, 16), gpu_scid) | + FIELD_PREP(GENMASK(15, 10), gpu_scid) | + BIT(8)); + } + + llcc_slice_activate(a6xx_gpu->htw_llc_slice); +} + +#define GBIF_CLIENT_HALT_MASK BIT(0) +#define GBIF_ARB_HALT_MASK BIT(1) +#define VBIF_XIN_HALT_CTRL0_MASK GENMASK(3, 0) +#define VBIF_RESET_ACK_MASK 0xF0 +#define GPR0_GBIF_HALT_REQUEST 0x1E0 + +void a8xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if (gx_off) { + /* Halt the gx side of GBIF */ + gpu_write(gpu, REG_A8XX_RBBM_GBIF_HALT, 1); + spin_until(gpu_read(gpu, REG_A8XX_RBBM_GBIF_HALT_ACK) & 1); + } + + /* Halt new client requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); + + /* Halt all AXI requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); + + /* The GBIF halt needs to be explicitly cleared */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); +} + +int a8xx_gmu_get_timestamp(struct msm_gpu *gpu, uint64_t *value) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + mutex_lock(&a6xx_gpu->gmu.lock); + + /* Force the GPU power on so we can read this register */ + a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); + + *value = gpu_read64(gpu, REG_A8XX_CP_ALWAYS_ON_COUNTER); + + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); + + mutex_unlock(&a6xx_gpu->gmu.lock); + + return 0; +} + +u64 a8xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u64 busy_cycles; + + /* 19.2MHz */ + *out_sample_rate = 19200000; + + busy_cycles = gmu_read64(&a6xx_gpu->gmu, + REG_A8XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L, + REG_A8XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H); + + return busy_cycles; +} + +bool a8xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + return true; +} diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 28f744f3caf7..554d746f115b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -34,6 +34,7 @@ extern const struct adreno_gpulist a4xx_gpulist; extern const struct adreno_gpulist a5xx_gpulist; extern const struct adreno_gpulist a6xx_gpulist; extern const struct adreno_gpulist a7xx_gpulist; +extern const struct adreno_gpulist a8xx_gpulist; static const struct adreno_gpulist *gpulists[] = { &a2xx_gpulist, @@ -42,6 +43,7 @@ static const struct adreno_gpulist *gpulists[] = { &a5xx_gpulist, &a6xx_gpulist, &a7xx_gpulist, + &a8xx_gpulist, }; static const struct adreno_info *adreno_info(uint32_t chip_id) @@ -235,7 +237,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) priv->has_cached_coherent = !!(info->quirks & ADRENO_QUIRK_HAS_CACHED_COHERENT); - gpu = info->init(drm); + gpu = info->funcs->init(drm); if (IS_ERR(gpu)) { dev_warn(drm->dev, "failed to load adreno gpu\n"); return PTR_ERR(gpu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h index 04b49d385f9d..d513e03fef08 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h @@ -82,85 +82,85 @@ static const u32 gen7_0_0_debugbus_blocks[] = { }; static const struct gen7_shader_block gen7_0_0_shader_blocks[] = { - {A7XX_TP0_TMO_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_SMO_DATA, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_1, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_0_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_1_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_2_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_3_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_4_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_5_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_6_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_7_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_CB_RAM, 0x390, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_TAG, 0x90, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_2, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_TMO_TAG, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_SMO_TAG, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_STATE_DATA, 0x40, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_HWAVE_RAM, 0x100, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_L0_INST_BUF, 0x50, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_8_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_9_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_10_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_11_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_12_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_1, 0x200, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_TP0_TMO_DATA, 0x200, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_SMO_DATA, 0x80, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_1, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_0_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_1_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_2_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_3_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_4_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_5_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_6_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_7_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_CB_RAM, 0x390, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_TAG, 0x90, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_2, 0x200, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_TMO_TAG, 0x80, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_SMO_TAG, 0x80, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_STATE_DATA, 0x40, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_HWAVE_RAM, 0x100, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_L0_INST_BUF, 0x50, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_8_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_9_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_10_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_11_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_12_DATA, 0x200, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_1, 0x200, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, }; static const u32 gen7_0_0_pre_crashdumper_gpu_registers[] = { @@ -303,7 +303,7 @@ static const u32 gen7_0_0_noncontext_rb_rbp_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_noncontext_rb_rbp_pipe_br_registers), 8)); -/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: A7XX_PIPE_BR */ +/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: PIPE_BR */ static const u32 gen7_0_0_gras_cluster_gras_pipe_br_registers[] = { 0x08000, 0x08008, 0x08010, 0x08092, 0x08094, 0x08099, 0x0809b, 0x0809d, 0x080a0, 0x080a7, 0x080af, 0x080f1, 0x080f4, 0x080f6, 0x080f8, 0x080fa, @@ -313,7 +313,7 @@ static const u32 gen7_0_0_gras_cluster_gras_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_gras_cluster_gras_pipe_br_registers), 8)); -/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: A7XX_PIPE_BV */ +/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: PIPE_BV */ static const u32 gen7_0_0_gras_cluster_gras_pipe_bv_registers[] = { 0x08000, 0x08008, 0x08010, 0x08092, 0x08094, 0x08099, 0x0809b, 0x0809d, 0x080a0, 0x080a7, 0x080af, 0x080f1, 0x080f4, 0x080f6, 0x080f8, 0x080fa, @@ -323,7 +323,7 @@ static const u32 gen7_0_0_gras_cluster_gras_pipe_bv_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_gras_cluster_gras_pipe_bv_registers), 8)); -/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BR */ +/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BR */ static const u32 gen7_0_0_pc_cluster_fe_pipe_br_registers[] = { 0x09800, 0x09804, 0x09806, 0x0980a, 0x09810, 0x09811, 0x09884, 0x09886, 0x09b00, 0x09b08, @@ -331,7 +331,7 @@ static const u32 gen7_0_0_pc_cluster_fe_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_pc_cluster_fe_pipe_br_registers), 8)); -/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BV */ +/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BV */ static const u32 gen7_0_0_pc_cluster_fe_pipe_bv_registers[] = { 0x09800, 0x09804, 0x09806, 0x0980a, 0x09810, 0x09811, 0x09884, 0x09886, 0x09b00, 0x09b08, @@ -339,7 +339,7 @@ static const u32 gen7_0_0_pc_cluster_fe_pipe_bv_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_pc_cluster_fe_pipe_bv_registers), 8)); -/* Block: RB_RAC Cluster: A7XX_CLUSTER_PS Pipeline: A7XX_PIPE_BR */ +/* Block: RB_RAC Cluster: A7XX_CLUSTER_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_rb_rac_cluster_ps_pipe_br_registers[] = { 0x08802, 0x08802, 0x08804, 0x08806, 0x08809, 0x0880a, 0x0880e, 0x08811, 0x08818, 0x0881e, 0x08821, 0x08821, 0x08823, 0x08826, 0x08829, 0x08829, @@ -355,7 +355,7 @@ static const u32 gen7_0_0_rb_rac_cluster_ps_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_rb_rac_cluster_ps_pipe_br_registers), 8)); -/* Block: RB_RBP Cluster: A7XX_CLUSTER_PS Pipeline: A7XX_PIPE_BR */ +/* Block: RB_RBP Cluster: A7XX_CLUSTER_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers[] = { 0x08800, 0x08801, 0x08803, 0x08803, 0x0880b, 0x0880d, 0x08812, 0x08812, 0x08820, 0x08820, 0x08822, 0x08822, 0x08827, 0x08828, 0x0882a, 0x0882a, @@ -370,7 +370,7 @@ static const u32 gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers[] = { 0x0a980, 0x0a980, 0x0a982, 0x0a984, 0x0a99e, 0x0a99e, 0x0a9a7, 0x0a9a7, 0x0a9aa, 0x0a9aa, 0x0a9ae, 0x0a9b0, 0x0a9b3, 0x0a9b5, 0x0a9ba, 0x0a9ba, @@ -381,7 +381,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers[] = { 0x0a9b0, 0x0a9b0, 0x0a9b3, 0x0a9b5, 0x0a9ba, 0x0a9ba, 0x0a9bc, 0x0a9bc, 0x0a9c4, 0x0a9c4, 0x0a9cd, 0x0a9cd, 0x0a9e2, 0x0a9e3, 0x0a9e6, 0x0a9fc, @@ -390,21 +390,21 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: HLSQ_DP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: HLSQ_DP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers[] = { 0x0a9b1, 0x0a9b1, 0x0a9c6, 0x0a9cb, 0x0a9d4, 0x0a9df, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: HLSQ_DP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: HLSQ_DP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers[] = { 0x0a9b1, 0x0a9b1, 0x0a9d4, 0x0a9df, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers[] = { 0x0a980, 0x0a980, 0x0a982, 0x0a984, 0x0a99e, 0x0a9a2, 0x0a9a7, 0x0a9a8, 0x0a9aa, 0x0a9aa, 0x0a9ae, 0x0a9ae, 0x0a9b0, 0x0a9b1, 0x0a9b3, 0x0a9b5, @@ -414,7 +414,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers[] = { 0x0a9b0, 0x0a9b1, 0x0a9b3, 0x0a9b5, 0x0a9ba, 0x0a9bc, 0x0a9e2, 0x0a9e3, 0x0a9e6, 0x0a9f9, 0x0aa00, 0x0aa00, 0x0ab00, 0x0ab00, @@ -422,7 +422,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers[] = { 0x0a980, 0x0a982, 0x0a985, 0x0a9a6, 0x0a9a8, 0x0a9a9, 0x0a9ab, 0x0a9ae, 0x0a9b0, 0x0a9b3, 0x0a9b6, 0x0a9b9, 0x0a9bb, 0x0a9bf, 0x0a9c2, 0x0a9c3, @@ -432,7 +432,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers[] = { 0x0a9b0, 0x0a9b3, 0x0a9b6, 0x0a9b9, 0x0a9bb, 0x0a9be, 0x0a9c2, 0x0a9c3, 0x0a9cd, 0x0a9cd, 0x0a9d0, 0x0a9d3, 0x0aa31, 0x0aa31, 0x0ab00, 0x0ab01, @@ -440,7 +440,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers[] = { 0x0a800, 0x0a800, 0x0a81b, 0x0a81d, 0x0a822, 0x0a822, 0x0a824, 0x0a824, 0x0a827, 0x0a82a, 0x0a830, 0x0a830, 0x0a833, 0x0a835, 0x0a83a, 0x0a83a, @@ -453,7 +453,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers[] = { 0x0a800, 0x0a800, 0x0a81b, 0x0a81d, 0x0a822, 0x0a822, 0x0a824, 0x0a824, 0x0a827, 0x0a82a, 0x0a830, 0x0a830, 0x0a833, 0x0a835, 0x0a83a, 0x0a83a, @@ -466,7 +466,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers[] = { 0x0a800, 0x0a800, 0x0a81c, 0x0a81d, 0x0a822, 0x0a824, 0x0a830, 0x0a831, 0x0a834, 0x0a835, 0x0a83a, 0x0a83c, 0x0a840, 0x0a840, 0x0a85c, 0x0a85d, @@ -477,7 +477,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers[] = { 0x0a800, 0x0a800, 0x0a81c, 0x0a81d, 0x0a822, 0x0a824, 0x0a830, 0x0a831, 0x0a834, 0x0a835, 0x0a83a, 0x0a83c, 0x0a840, 0x0a840, 0x0a85c, 0x0a85d, @@ -488,7 +488,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers[] = { 0x0a800, 0x0a81b, 0x0a81e, 0x0a821, 0x0a823, 0x0a827, 0x0a830, 0x0a833, 0x0a836, 0x0a839, 0x0a83b, 0x0a85b, 0x0a85e, 0x0a861, 0x0a863, 0x0a867, @@ -498,7 +498,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers[] = { 0x0a800, 0x0a81b, 0x0a81e, 0x0a821, 0x0a823, 0x0a827, 0x0a830, 0x0a833, 0x0a836, 0x0a839, 0x0a83b, 0x0a85b, 0x0a85e, 0x0a861, 0x0a863, 0x0a867, @@ -508,7 +508,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers[] = { 0x0b180, 0x0b183, 0x0b190, 0x0b195, 0x0b2c0, 0x0b2d5, 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, @@ -516,35 +516,35 @@ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_bv_hlsq_state_registers[] = { 0x0ab00, 0x0ab02, 0x0ab0a, 0x0ab1b, 0x0ab20, 0x0ab20, 0x0ab40, 0x0abbf, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_bv_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_bv_sp_top_registers[] = { 0x0ab00, 0x0ab00, 0x0ab02, 0x0ab02, 0x0ab0a, 0x0ab1b, 0x0ab20, 0x0ab20, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_bv_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_bv_usptp_registers[] = { 0x0ab00, 0x0ab02, 0x0ab21, 0x0ab22, 0x0ab40, 0x0abbf, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_bv_usptp_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV */ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_bv_registers[] = { 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_ps_pipe_bv_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC */ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers[] = { 0x0b180, 0x0b181, 0x0b300, 0x0b301, 0x0b307, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, @@ -552,84 +552,84 @@ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR */ static const u32 gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers[] = { 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV */ static const u32 gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers[] = { 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers), 8)); -/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BR */ +/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BR */ static const u32 gen7_0_0_vfd_cluster_fe_pipe_br_registers[] = { 0x0a000, 0x0a009, 0x0a00e, 0x0a0ef, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vfd_cluster_fe_pipe_br_registers), 8)); -/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BV */ +/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BV */ static const u32 gen7_0_0_vfd_cluster_fe_pipe_bv_registers[] = { 0x0a000, 0x0a009, 0x0a00e, 0x0a0ef, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vfd_cluster_fe_pipe_bv_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BR */ +/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BR */ static const u32 gen7_0_0_vpc_cluster_fe_pipe_br_registers[] = { 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_fe_pipe_br_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BV */ +/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BV */ static const u32 gen7_0_0_vpc_cluster_fe_pipe_bv_registers[] = { 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_fe_pipe_bv_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: A7XX_PIPE_BR */ +/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: PIPE_BR */ static const u32 gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers[] = { 0x09101, 0x0910c, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: A7XX_PIPE_BV */ +/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: PIPE_BV */ static const u32 gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers[] = { 0x09101, 0x0910c, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: A7XX_PIPE_BR */ +/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers[] = { 0x09200, 0x0920f, 0x09212, 0x09216, 0x09218, 0x09236, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: A7XX_PIPE_BV */ +/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: PIPE_BV */ static const u32 gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers[] = { 0x09200, 0x0920f, 0x09212, 0x09216, 0x09218, 0x09236, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_BR Location: HLSQ_STATE */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_BR Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers[] = { 0x0ae52, 0x0ae52, 0x0ae60, 0x0ae67, 0x0ae69, 0x0ae73, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_BR Location: SP_TOP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_BR Location: SP_TOP */ static const u32 gen7_0_0_sp_noncontext_pipe_br_sp_top_registers[] = { 0x0ae00, 0x0ae00, 0x0ae02, 0x0ae04, 0x0ae06, 0x0ae09, 0x0ae0c, 0x0ae0c, 0x0ae0f, 0x0ae0f, 0x0ae28, 0x0ae2b, 0x0ae35, 0x0ae35, 0x0ae3a, 0x0ae3f, @@ -638,7 +638,7 @@ static const u32 gen7_0_0_sp_noncontext_pipe_br_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_br_sp_top_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_BR Location: uSPTP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_BR Location: uSPTP */ static const u32 gen7_0_0_sp_noncontext_pipe_br_usptp_registers[] = { 0x0ae00, 0x0ae00, 0x0ae02, 0x0ae04, 0x0ae06, 0x0ae09, 0x0ae0c, 0x0ae0c, 0x0ae0f, 0x0ae0f, 0x0ae30, 0x0ae32, 0x0ae35, 0x0ae35, 0x0ae3a, 0x0ae3b, @@ -647,28 +647,28 @@ static const u32 gen7_0_0_sp_noncontext_pipe_br_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_br_usptp_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_LPAC Location: HLSQ_STATE */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_LPAC Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_hlsq_state_registers[] = { 0x0af88, 0x0af8a, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_hlsq_state_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_LPAC Location: SP_TOP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_LPAC Location: SP_TOP */ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers[] = { 0x0af80, 0x0af84, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_LPAC Location: uSPTP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_LPAC Location: uSPTP */ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = { 0x0af80, 0x0af84, 0x0af90, 0x0af92, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */ +/* Block: TPl1 Cluster: noncontext Pipeline: PIPE_NONE */ static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { 0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c, 0x0b60f, 0x0b621, 0x0b630, 0x0b633, @@ -676,14 +676,14 @@ static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ +/* Block: TPl1 Cluster: noncontext Pipeline: PIPE_BR */ static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { 0x0b600, 0x0b600, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */ +/* Block: TPl1 Cluster: noncontext Pipeline: PIPE_LPAC */ static const u32 gen7_0_0_tpl1_noncontext_pipe_lpac_registers[] = { 0x0b780, 0x0b780, UINT_MAX, UINT_MAX, @@ -691,184 +691,184 @@ static const u32 gen7_0_0_tpl1_noncontext_pipe_lpac_registers[] = { static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_lpac_registers), 8)); static const struct gen7_sel_reg gen7_0_0_rb_rac_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x0, }; static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x9, }; static const struct gen7_cluster_registers gen7_0_0_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_br_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BV, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_bv_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_LPAC, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_LPAC, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_lpac_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_rb_rac_pipe_br_registers, &gen7_0_0_rb_rac_sel, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_rb_rbp_pipe_br_registers, &gen7_0_0_rb_rbp_sel, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rbp_sel, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_br_sp_top_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_br_usptp_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_lpac_hlsq_state_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h index 772652eb61f3..7897622ea6f7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h @@ -96,87 +96,87 @@ static const u32 gen7_2_0_debugbus_blocks[] = { }; static const struct gen7_shader_block gen7_2_0_shader_blocks[] = { - {A7XX_TP0_TMO_DATA, 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_SMO_DATA, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_1, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_0_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_1_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_2_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_3_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_4_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_5_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_6_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_7_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_CB_RAM, 0x390, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_13_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_14_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_TAG, 0xc0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_2, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_TMO_TAG, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_SMO_TAG, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_STATE_DATA, 0x40, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_HWAVE_RAM, 0x100, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_L0_INST_BUF, 0x50, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_8_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_9_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_10_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_11_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_12_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x180, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x200, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_1, 0x1c0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x200, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x38, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_TP0_TMO_DATA, 0x200, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_SMO_DATA, 0x80, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_1, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_0_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_1_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_2_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_3_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_4_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_5_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_6_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_7_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_CB_RAM, 0x390, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_13_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_14_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_TAG, 0xc0, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_2, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_TMO_TAG, 0x80, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_SMO_TAG, 0x80, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_STATE_DATA, 0x40, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_HWAVE_RAM, 0x100, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_L0_INST_BUF, 0x50, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_8_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_9_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_10_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_11_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_12_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x180, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x200, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_1, 0x1c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x200, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x38, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, }; static const u32 gen7_2_0_gpu_registers[] = { @@ -478,182 +478,182 @@ static const u32 gen7_2_0_sp_noncontext_pipe_lpac_hlsq_state_registers[] = { static_assert(IS_ALIGNED(sizeof(gen7_2_0_sp_noncontext_pipe_lpac_hlsq_state_registers), 8)); static const struct gen7_sel_reg gen7_2_0_rb_rac_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x0, }; static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x9, }; static const struct gen7_cluster_registers gen7_2_0_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_br_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BV, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_bv_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_LPAC, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_LPAC, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_lpac_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_rb_rac_pipe_br_registers, &gen7_2_0_rb_rac_sel, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_rb_rbp_pipe_br_registers, &gen7_2_0_rb_rbp_sel, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_2_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_2_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_2_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_2_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_2_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_2_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rbp_sel, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_br_sp_top_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_br_usptp_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_noncontext_pipe_lpac_hlsq_state_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_NONE, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h index 0956dfca1f05..20125d1aa21d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h @@ -118,97 +118,97 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = { }; static const struct gen7_shader_block gen7_9_0_shader_blocks[] = { - { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_DATA_1, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_0_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_1_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_2_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_3_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_4_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_5_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_6_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_7_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_CB_RAM, 0x0390, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_13_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_14_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_TAG, 0x00C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_DATA_2, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_TMO_TAG, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_SMO_TAG, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_STATE_DATA, 0x0040, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_HWAVE_RAM, 0x0100, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_L0_INST_BUF, 0x0050, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_8_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_9_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_10_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_11_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_12_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_L2STC_TAG_RAM, 0x0200, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_L2STC_INFO_CMD, 0x0474, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0180, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM, 0x0640, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM, 0x00B0, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM_1, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM, 0x0200, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0050, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0008, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_TAG, 0x0014, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_TAG, 0x0010, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_TAG, 0x0004, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0020, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x03C0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0280, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0050, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0008, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_1, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_STPROC_META, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_2, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_DATAPATH_META, 0x0020, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INDIRECT_META, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA_1, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_0_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_1_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_2_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_3_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_4_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_5_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_6_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_7_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_CB_RAM, 0x0390, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_13_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_14_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_TAG, 0x00C0, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA_2, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_TMO_TAG, 0x0080, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_SMO_TAG, 0x0080, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_STATE_DATA, 0x0040, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_HWAVE_RAM, 0x0100, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_L0_INST_BUF, 0x0050, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_8_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_9_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_10_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_11_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_12_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_L2STC_TAG_RAM, 0x0200, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_L2STC_INFO_CMD, 0x0474, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0180, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM, 0x0640, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM, 0x00B0, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_1, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0200, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0050, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0008, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0014, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0010, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0004, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0020, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x03C0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0280, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0050, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0008, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_1, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_STPROC_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_2, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_DATAPATH_META, 0x0020, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INDIRECT_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, }; /* @@ -226,7 +226,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_pre_crashdumper_gpu_registers), 8)); * Block : ['BROADCAST', 'CP', 'GRAS', 'GXCLKCTL'] * Block : ['PC', 'RBBM', 'RDVM', 'UCHE'] * Block : ['VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 196 (Regs:1778) */ static const u32 gen7_9_0_gpu_registers[] = { @@ -290,7 +290,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gxclkctl_registers), 8)); /* * Block : ['GMUAO', 'GMUCX', 'GMUCX_RAM'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 134 (Regs:429) */ static const u32 gen7_9_0_gmu_registers[] = { @@ -334,7 +334,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gmu_registers), 8)); /* * Block : ['GMUGX'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 44 (Regs:454) */ static const u32 gen7_9_0_gmugx_registers[] = { @@ -355,7 +355,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gmugx_registers), 8)); /* * Block : ['CX_MISC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 7 (Regs:56) */ static const u32 gen7_9_0_cx_misc_registers[] = { @@ -367,7 +367,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_cx_misc_registers), 8)); /* * Block : ['DBGC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 19 (Regs:155) */ static const u32 gen7_9_0_dbgc_registers[] = { @@ -382,7 +382,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_dbgc_registers), 8)); /* * Block : ['CX_DBGC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 7 (Regs:75) */ static const u32 gen7_9_0_cx_dbgc_registers[] = { @@ -396,7 +396,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_cx_dbgc_registers), 8)); * Block : ['BROADCAST', 'CP', 'CX_DBGC', 'CX_MISC', 'DBGC', 'GBIF'] * Block : ['GMUAO', 'GMUCX', 'GMUGX', 'GRAS', 'GXCLKCTL', 'PC'] * Block : ['RBBM', 'RDVM', 'UCHE', 'VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * pairs : 29 (Regs:573) */ @@ -417,7 +417,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_pipe_br_registers), 8)); * Block : ['BROADCAST', 'CP', 'CX_DBGC', 'CX_MISC', 'DBGC', 'GBIF'] * Block : ['GMUAO', 'GMUCX', 'GMUGX', 'GRAS', 'GXCLKCTL', 'PC'] * Block : ['RBBM', 'RDVM', 'UCHE', 'VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_NONE * pairs : 29 (Regs:573) */ @@ -438,7 +438,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_pipe_bv_registers), 8)); * Block : ['BROADCAST', 'CP', 'CX_DBGC', 'CX_MISC', 'DBGC', 'GBIF'] * Block : ['GMUAO', 'GMUCX', 'GMUGX', 'GRAS', 'GXCLKCTL', 'PC'] * Block : ['RBBM', 'RDVM', 'UCHE', 'VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * pairs : 2 (Regs:7) */ @@ -450,7 +450,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_pipe_lpac_registers), 8)); /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * pairs : 5 (Regs:37) */ @@ -463,7 +463,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_rb_pipe_br_rac_registers), /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * pairs : 15 (Regs:66) */ @@ -478,7 +478,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_rb_pipe_br_rbp_registers), /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_HLSQ_STATE * pairs : 4 (Regs:28) @@ -491,7 +491,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_hlsq_state_regis /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_SP_TOP * pairs : 10 (Regs:61) @@ -506,7 +506,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_sp_top_registers /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 12 (Regs:62) @@ -521,7 +521,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_usptp_registers) /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_HLSQ_DP_STR * pairs : 2 (Regs:5) @@ -534,7 +534,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_hlsq_dp_str_regi /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_HLSQ_STATE * pairs : 1 (Regs:5) @@ -547,7 +547,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_lpac_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_SP_TOP * pairs : 1 (Regs:6) @@ -560,7 +560,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_lpac_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 2 (Regs:9) @@ -573,7 +573,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_lpac_usptp_register /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 5 (Regs:29) @@ -587,7 +587,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_tpl1_pipe_none_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 1 (Regs:1) @@ -600,7 +600,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_tpl1_pipe_br_usptp_register /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 1 (Regs:1) @@ -613,7 +613,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_tpl1_pipe_lpac_usptp_regist /* * Block : ['GRAS'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_GRAS * pairs : 14 (Regs:293) */ @@ -628,7 +628,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gras_pipe_br_cluster_gras_registers), 8 /* * Block : ['GRAS'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_GRAS * pairs : 14 (Regs:293) */ @@ -643,7 +643,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gras_pipe_bv_cluster_gras_registers), 8 /* * Block : ['PC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_FE * pairs : 6 (Regs:31) */ @@ -656,7 +656,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_pc_pipe_br_cluster_fe_registers), 8)); /* * Block : ['PC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_FE * pairs : 6 (Regs:31) */ @@ -669,7 +669,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_pc_pipe_bv_cluster_fe_registers), 8)); /* * Block : ['VFD'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:236) */ @@ -681,7 +681,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vfd_pipe_br_cluster_fe_registers), 8)); /* * Block : ['VFD'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:236) */ @@ -693,7 +693,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vfd_pipe_bv_cluster_fe_registers), 8)); /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:18) */ @@ -705,7 +705,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_br_cluster_fe_registers), 8)); /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_PC_VS * pairs : 3 (Regs:30) */ @@ -717,7 +717,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_br_cluster_pc_vs_registers), 8 /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_VPC_PS * pairs : 5 (Regs:76) */ @@ -730,7 +730,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_br_cluster_vpc_ps_registers), /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:18) */ @@ -742,7 +742,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_bv_cluster_fe_registers), 8)); /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_PC_VS * pairs : 3 (Regs:30) */ @@ -754,7 +754,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_bv_cluster_pc_vs_registers), 8 /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_VPC_PS * pairs : 5 (Regs:76) */ @@ -767,7 +767,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers), /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_PS * pairs : 39 (Regs:133) */ @@ -788,7 +788,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_rb_pipe_br_cluster_ps_rac_registers), 8 /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_PS * pairs : 34 (Regs:100) */ @@ -808,7 +808,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_rb_pipe_br_cluster_ps_rbp_registers), 8 /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_HLSQ_STATE * pairs : 29 (Regs:215) @@ -828,7 +828,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_vs_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_SP_TOP * pairs : 22 (Regs:73) @@ -846,7 +846,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_vs_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 16 (Regs:269) @@ -862,7 +862,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_vs_usptp_register /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_STATE * pairs : 21 (Regs:334) @@ -880,7 +880,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_DP * pairs : 3 (Regs:19) @@ -893,7 +893,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_regist /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_SP_TOP * pairs : 18 (Regs:77) @@ -910,7 +910,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 17 (Regs:333) @@ -927,7 +927,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_register /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_DP_STR * pairs : 1 (Regs:6) @@ -940,7 +940,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_re /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_HLSQ_STATE * pairs : 28 (Regs:213) @@ -959,7 +959,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_bv_cluster_sp_vs_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_SP_TOP * pairs : 21 (Regs:71) @@ -977,7 +977,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_bv_cluster_sp_vs_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 16 (Regs:266) @@ -993,7 +993,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_bv_cluster_sp_vs_usptp_register /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_STATE * pairs : 14 (Regs:299) @@ -1009,7 +1009,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_state_r /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_DP * pairs : 2 (Regs:13) @@ -1022,7 +1022,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_dp_regi /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_SP_TOP * pairs : 9 (Regs:34) @@ -1037,7 +1037,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_sp_top_regis /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 11 (Regs:279) @@ -1052,7 +1052,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 3 (Regs:10) @@ -1065,7 +1065,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_br_cluster_sp_vs_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 6 (Regs:42) @@ -1079,7 +1079,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 3 (Regs:10) @@ -1092,7 +1092,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_bv_cluster_sp_vs_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 5 (Regs:7) @@ -1105,192 +1105,192 @@ static const u32 gen7_9_0_tpl1_pipe_lpac_cluster_sp_ps_usptp_registers[] = { static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_lpac_cluster_sp_ps_usptp_registers), 8)); static const struct gen7_sel_reg gen7_9_0_rb_rac_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0, }; static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x9, }; static const struct gen7_cluster_registers gen7_9_0_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_br_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BV, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_bv_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_LPAC, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_LPAC, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_lpac_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_rb_pipe_br_rac_registers, &gen7_9_0_rb_rac_sel, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_rb_pipe_br_rbp_registers, &gen7_9_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_rb_pipe_br_cluster_ps_rac_registers, &gen7_9_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_rb_pipe_br_cluster_ps_rac_registers, &gen7_9_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_rb_pipe_br_cluster_ps_rbp_registers, &gen7_9_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_rb_pipe_br_cluster_ps_rbp_registers, &gen7_9_0_rb_rbp_sel, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_gras_pipe_br_cluster_gras_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_gras_pipe_br_cluster_gras_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_gras_pipe_bv_cluster_gras_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_gras_pipe_bv_cluster_gras_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_pc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_pc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_pc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_pc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vfd_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vfd_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vfd_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vfd_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_br_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_br_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_br_cluster_vpc_ps_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_br_cluster_vpc_ps_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_bv_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_bv_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, }; static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_9_0_non_context_sp_pipe_br_sp_top_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_non_context_sp_pipe_br_usptp_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_DP_STR, gen7_9_0_non_context_sp_pipe_br_hlsq_dp_str_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_lpac_hlsq_state_registers, 0xaf80}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_9_0_non_context_sp_pipe_lpac_sp_top_registers, 0xaf80}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_non_context_sp_pipe_lpac_usptp_registers, 0xaf80}, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_NONE, 0, A7XX_USPTP, gen7_9_0_non_context_tpl1_pipe_none_usptp_registers, 0xb600}, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_non_context_tpl1_pipe_br_usptp_registers, 0xb600}, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_non_context_tpl1_pipe_lpac_usptp_registers, 0xb780}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_bv_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_bv_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_SP_TOP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_bv_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_9_0_tpl1_pipe_bv_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_lpac_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index afaa3cfefd35..1c80909e63ca 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -284,6 +284,7 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, struct adreno_smmu_fault_info *info, const char *block, u32 scratch[4]) { + struct adreno_gpu *adreno_gpu = container_of(gpu, struct adreno_gpu, base); struct msm_drm_private *priv = gpu->dev->dev_private; struct msm_mmu *mmu = to_msm_vm(gpu->vm)->mmu; const char *type = "UNKNOWN"; @@ -336,6 +337,11 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, /* Turn off the hangcheck timer to keep it from bothering us */ timer_delete(&gpu->hangcheck_timer); + /* Let any concurrent GMU transactions know that the MMU may be + * blocked for a while and they should wait on us. + */ + reinit_completion(&adreno_gpu->fault_coredump_done); + fault_info.ttbr0 = info->ttbr0; fault_info.iova = iova; fault_info.flags = flags; @@ -343,18 +349,13 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, fault_info.block = block; msm_gpu_fault_crashstate_capture(gpu, &fault_info); + + complete_all(&adreno_gpu->fault_coredump_done); } return 0; } -static bool -adreno_smmu_has_prr(struct msm_gpu *gpu) -{ - struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev); - return adreno_smmu && adreno_smmu->set_prr_addr; -} - int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, uint32_t param, uint64_t *value, uint32_t *len) { @@ -1196,6 +1197,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, /* Only handle the core clock when GMU is not in use (or is absent). */ if (adreno_has_gmu_wrapper(adreno_gpu) || + adreno_has_rgmu(adreno_gpu) || adreno_gpu->info->family < ADRENO_6XX_GEN1) { /* * This can only be done before devm_pm_opp_of_add_table(), or @@ -1229,6 +1231,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, if (ret) return ret; + init_completion(&adreno_gpu->fault_coredump_done); + complete_all(&adreno_gpu->fault_coredump_done); + pm_runtime_set_autosuspend_delay(dev, adreno_gpu->info->inactive_period); pm_runtime_use_autosuspend(dev); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 390fa6720d9b..0f8d3de97636 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -27,6 +27,7 @@ enum { ADRENO_FW_PFP = 1, ADRENO_FW_GMU = 1, /* a6xx */ ADRENO_FW_GPMU = 2, + ADRENO_FW_AQE = 3, ADRENO_FW_MAX, }; @@ -50,6 +51,8 @@ enum adreno_family { ADRENO_7XX_GEN1, /* a730 family */ ADRENO_7XX_GEN2, /* a740 family */ ADRENO_7XX_GEN3, /* a750 family */ + ADRENO_8XX_GEN1, /* a830 family */ + ADRENO_8XX_GEN2, /* a840 family */ }; #define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0) @@ -71,9 +74,14 @@ enum adreno_family { (((_c) >> 8) & 0xff), \ ((_c) & 0xff) +struct adreno_gpu; + struct adreno_gpu_funcs { struct msm_gpu_funcs base; + struct msm_gpu *(*init)(struct drm_device *dev); int (*get_timestamp)(struct msm_gpu *gpu, uint64_t *value); + void (*bus_halt)(struct adreno_gpu *adreno_gpu, bool gx_off); + int (*mmu_fault_handler)(void *arg, unsigned long iova, int flags, void *data); }; struct adreno_reglist { @@ -81,6 +89,13 @@ struct adreno_reglist { u32 value; }; +/* Reglist with pipe information */ +struct adreno_reglist_pipe { + u32 offset; + u32 value; + u32 pipe; +}; + struct adreno_speedbin { uint16_t fuse; uint16_t speedbin; @@ -101,7 +116,7 @@ struct adreno_info { const char *fw[ADRENO_FW_MAX]; uint32_t gmem; u64 quirks; - struct msm_gpu *(*init)(struct drm_device *dev); + const struct adreno_gpu_funcs *funcs; const char *zapfw; u32 inactive_period; union { @@ -180,6 +195,8 @@ struct adreno_gpu { uint16_t speedbin; const struct adreno_gpu_funcs *funcs; + struct completion fault_coredump_done; + /* interesting register offsets to dump: */ const unsigned int *registers; @@ -392,6 +409,16 @@ static inline int adreno_is_a610(const struct adreno_gpu *gpu) return adreno_is_revn(gpu, 610); } +static inline int adreno_is_a612(const struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x06010200; +} + +static inline bool adreno_has_rgmu(const struct adreno_gpu *gpu) +{ + return adreno_is_a612(gpu); +} + static inline int adreno_is_a618(const struct adreno_gpu *gpu) { return adreno_is_revn(gpu, 618); @@ -466,9 +493,9 @@ static inline int adreno_is_a610_family(const struct adreno_gpu *gpu) { if (WARN_ON_ONCE(!gpu->info)) return false; - - /* TODO: A612 */ - return adreno_is_a610(gpu) || adreno_is_a702(gpu); + return adreno_is_a610(gpu) || + adreno_is_a612(gpu) || + adreno_is_a702(gpu); } /* TODO: 615/616 */ @@ -548,6 +575,21 @@ static inline int adreno_is_a7xx(struct adreno_gpu *gpu) adreno_is_a740_family(gpu); } +static inline int adreno_is_a8xx(struct adreno_gpu *gpu) +{ + return gpu->info->family >= ADRENO_8XX_GEN1; +} + +static inline int adreno_is_x285(struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x44070001; +} + +static inline int adreno_is_a840(struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x44050a01; +} + /* Put vm_start above 32b to catch issues with not setting xyz_BASE_HI */ #define ADRENO_VM_START 0x100000000ULL u64 adreno_private_vm_size(struct msm_gpu *gpu); @@ -673,12 +715,6 @@ OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt) OUT_RING(ring, PKT7(opcode, cnt)); } -struct msm_gpu *a2xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a3xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a4xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a5xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a6xx_gpu_init(struct drm_device *dev); - static inline uint32_t get_wptr(struct msm_ringbuffer *ring) { return (ring->cur - ring->start) % (MSM_GPU_RINGBUFFER_SZ >> 2); diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_12_2_glymur.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_12_2_glymur.h new file mode 100644 index 000000000000..13bb43ba67d3 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_12_2_glymur.h @@ -0,0 +1,541 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Linaro Limited + */ + +#ifndef _DPU_12_2_GLYMUR_H +#define _DPU_12_2_GLYMUR_H + +static const struct dpu_caps glymur_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0xb, + .has_src_split = true, + .has_dim_layer = true, + .has_idle_pc = true, + .has_3d_merge = true, + .max_linewidth = 8192, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, +}; + +static const struct dpu_mdp_cfg glymur_mdp = { + .name = "top_0", + .base = 0, .len = 0x494, + .clk_ctrls = { + [DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 }, + }, +}; + +static const struct dpu_ctl_cfg glymur_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x15000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, { + .name = "ctl_1", .id = CTL_1, + .base = 0x16000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), + }, { + .name = "ctl_2", .id = CTL_2, + .base = 0x17000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), + }, { + .name = "ctl_3", .id = CTL_3, + .base = 0x18000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12), + }, { + .name = "ctl_4", .id = CTL_4, + .base = 0x19000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13), + }, { + .name = "ctl_5", .id = CTL_5, + .base = 0x1a000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 23), + }, { + .name = "ctl_6", .id = CTL_6, + .base = 0x1b000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 14), + }, { + .name = "ctl_7", .id = CTL_7, + .base = 0x1c000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 15), + }, +}; + +static const struct dpu_sspp_cfg glymur_sspp[] = { + { + .name = "sspp_0", .id = SSPP_VIG0, + .base = 0x4000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_4, + .xin_id = 0, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_1", .id = SSPP_VIG1, + .base = 0x6000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_4, + .xin_id = 4, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_2", .id = SSPP_VIG2, + .base = 0x8000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_4, + .xin_id = 8, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_3", .id = SSPP_VIG3, + .base = 0xa000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_4, + .xin_id = 12, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_8", .id = SSPP_DMA0, + .base = 0x24000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 1, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_9", .id = SSPP_DMA1, + .base = 0x26000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 5, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_10", .id = SSPP_DMA2, + .base = 0x28000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 9, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_11", .id = SSPP_DMA3, + .base = 0x2a000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 13, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_12", .id = SSPP_DMA4, + .base = 0x2c000, .len = 0x344, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 14, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_13", .id = SSPP_DMA5, + .base = 0x2e000, .len = 0x344, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 15, + .type = SSPP_TYPE_DMA, + }, +}; + +static const struct dpu_lm_cfg glymur_lm[] = { + { + .name = "lm_0", .id = LM_0, + .base = 0x44000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_1, + .pingpong = PINGPONG_0, + .dspp = DSPP_0, + }, { + .name = "lm_1", .id = LM_1, + .base = 0x45000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_0, + .pingpong = PINGPONG_1, + .dspp = DSPP_1, + }, { + .name = "lm_2", .id = LM_2, + .base = 0x46000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_3, + .pingpong = PINGPONG_2, + .dspp = DSPP_2, + }, { + .name = "lm_3", .id = LM_3, + .base = 0x47000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_2, + .pingpong = PINGPONG_3, + .dspp = DSPP_3, + }, { + .name = "lm_4", .id = LM_4, + .base = 0x48000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_5, + .pingpong = PINGPONG_4, + }, { + .name = "lm_5", .id = LM_5, + .base = 0x49000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_4, + .pingpong = PINGPONG_5, + }, { + .name = "lm_6", .id = LM_6, + .base = 0x4a000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_7, + .pingpong = PINGPONG_6, + }, { + .name = "lm_7", .id = LM_7, + .base = 0x4b000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_6, + .pingpong = PINGPONG_7, + }, +}; + +static const struct dpu_dspp_cfg glymur_dspp[] = { + { + .name = "dspp_0", .id = DSPP_0, + .base = 0x54000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_1", .id = DSPP_1, + .base = 0x56000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_2", .id = DSPP_2, + .base = 0x58000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_3", .id = DSPP_3, + .base = 0x5a000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_4", .id = DSPP_4, + .base = 0x5c000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_5", .id = DSPP_5, + .base = 0x5e000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_6", .id = DSPP_6, + .base = 0x60000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_7", .id = DSPP_7, + .base = 0x62000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, +}; + +static const struct dpu_pingpong_cfg glymur_pp[] = { + { + .name = "pingpong_0", .id = PINGPONG_0, + .base = 0x69000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_0, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), + }, { + .name = "pingpong_1", .id = PINGPONG_1, + .base = 0x6a000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_0, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), + }, { + .name = "pingpong_2", .id = PINGPONG_2, + .base = 0x6b000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_1, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), + }, { + .name = "pingpong_3", .id = PINGPONG_3, + .base = 0x6c000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_1, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), + }, { + .name = "pingpong_4", .id = PINGPONG_4, + .base = 0x6d000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_2, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), + }, { + .name = "pingpong_5", .id = PINGPONG_5, + .base = 0x6e000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_2, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), + }, { + .name = "pingpong_6", .id = PINGPONG_6, + .base = 0x6f000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_3, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 20), + }, { + .name = "pingpong_7", .id = PINGPONG_7, + .base = 0x70000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_3, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 21), + }, { + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, + .base = 0x66000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_4, + }, { + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, + .base = 0x66400, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_4, + }, +}; + +static const struct dpu_merge_3d_cfg glymur_merge_3d[] = { + { + .name = "merge_3d_0", .id = MERGE_3D_0, + .base = 0x4e000, .len = 0x1c, + }, { + .name = "merge_3d_1", .id = MERGE_3D_1, + .base = 0x4f000, .len = 0x1c, + }, { + .name = "merge_3d_2", .id = MERGE_3D_2, + .base = 0x50000, .len = 0x1c, + }, { + .name = "merge_3d_3", .id = MERGE_3D_3, + .base = 0x51000, .len = 0x1c, + }, +}; + +/* + * NOTE: Each display compression engine (DCE) contains dual hard + * slice DSC encoders so both share same base address but with + * its own different sub block address. + */ +static const struct dpu_dsc_cfg glymur_dsc[] = { + { + .name = "dce_0_0", .id = DSC_0, + .base = 0x80000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_0_1", .id = DSC_1, + .base = 0x80000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, { + .name = "dce_1_0", .id = DSC_2, + .base = 0x81000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_1_1", .id = DSC_3, + .base = 0x81000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, { + .name = "dce_2_0", .id = DSC_4, + .base = 0x82000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_2_1", .id = DSC_5, + .base = 0x82000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, { + .name = "dce_3_0", .id = DSC_6, + .base = 0x83000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_3_1", .id = DSC_7, + .base = 0x83000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, + +}; + +static const struct dpu_wb_cfg glymur_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SDM845_MASK, + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 4096, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + +static const struct dpu_cwb_cfg glymur_cwb[] = { + { + .name = "cwb_0", .id = CWB_0, + .base = 0x66200, .len = 0x20, + }, + { + .name = "cwb_1", .id = CWB_1, + .base = 0x66600, .len = 0x20, + }, + { + .name = "cwb_2", .id = CWB_2, + .base = 0x7e200, .len = 0x20, + }, + { + .name = "cwb_3", .id = CWB_3, + .base = 0x7e600, .len = 0x20, + }, +}; + +static const struct dpu_intf_cfg glymur_intf[] = { + { + .name = "intf_0", .id = INTF_0, + .base = 0x34000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), + }, { + .name = "intf_1", .id = INTF_1, + .base = 0x35000, .len = 0x400, + .type = INTF_DSI, + .controller_id = MSM_DSI_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), + .intr_tear_rd_ptr = DPU_IRQ_IDX(MDP_INTF1_TEAR_INTR, 2), + }, { + .name = "intf_2", .id = INTF_2, + .base = 0x36000, .len = 0x400, + .type = INTF_DSI, + .controller_id = MSM_DSI_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), + .intr_tear_rd_ptr = DPU_IRQ_IDX(MDP_INTF2_TEAR_INTR, 2), + }, { + .name = "intf_3", .id = INTF_3, + .base = 0x37000, .len = 0x400, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_0, /* pair with intf_0 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), + }, { + .name = "intf_4", .id = INTF_4, + .base = 0x38000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21), + }, { + .name = "intf_5", .id = INTF_5, + .base = 0x39000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_3, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23), + }, { + .name = "intf_6", .id = INTF_6, + .base = 0x3A000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_2, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), + }, { + .name = "intf_7", .id = INTF_7, + .base = 0x3b000, .len = 0x400, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_2, /* pair with intf_6 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 18), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 19), + }, { + .name = "intf_8", .id = INTF_8, + .base = 0x3c000, .len = 0x400, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_1, /* pair with intf_4 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), + }, +}; + +static const struct dpu_perf_cfg glymur_perf_data = { + .max_bw_low = 18900000, + .max_bw_high = 28500000, + .min_core_ib = 2500000, + .min_llcc_ib = 0, + .min_dram_ib = 800000, + .min_prefill_lines = 35, + .danger_lut_tbl = {0x3ffff, 0x3ffff, 0x0}, + .safe_lut_tbl = {0xfe00, 0xfe00, 0xffff}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sc7180_qos_linear), + .entries = sc7180_qos_linear + }, + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + /* TODO: macrotile-qseed is different from macrotile */ + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + +static const struct dpu_mdss_version glymur_mdss_ver = { + .core_major_ver = 12, + .core_minor_ver = 2, +}; + +const struct dpu_mdss_cfg dpu_glymur_cfg = { + .mdss_ver = &glymur_mdss_ver, + .caps = &glymur_dpu_caps, + .mdp = &glymur_mdp, + .cdm = &dpu_cdm_5_x, + .ctl_count = ARRAY_SIZE(glymur_ctl), + .ctl = glymur_ctl, + .sspp_count = ARRAY_SIZE(glymur_sspp), + .sspp = glymur_sspp, + .mixer_count = ARRAY_SIZE(glymur_lm), + .mixer = glymur_lm, + .dspp_count = ARRAY_SIZE(glymur_dspp), + .dspp = glymur_dspp, + .pingpong_count = ARRAY_SIZE(glymur_pp), + .pingpong = glymur_pp, + .dsc_count = ARRAY_SIZE(glymur_dsc), + .dsc = glymur_dsc, + .merge_3d_count = ARRAY_SIZE(glymur_merge_3d), + .merge_3d = glymur_merge_3d, + .wb_count = ARRAY_SIZE(glymur_wb), + .wb = glymur_wb, + .cwb_count = ARRAY_SIZE(glymur_cwb), + .cwb = sm8650_cwb, + .intf_count = ARRAY_SIZE(glymur_intf), + .intf = glymur_intf, + .vbif_count = ARRAY_SIZE(sm8650_vbif), + .vbif = sm8650_vbif, + .perf = &glymur_perf_data, +}; + +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 4b970a59deaf..c39f1908ea65 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -200,7 +200,7 @@ static int dpu_crtc_get_lm_crc(struct drm_crtc *crtc, struct dpu_crtc_state *crtc_state) { struct dpu_crtc_mixer *m; - u32 crcs[CRTC_DUAL_MIXERS]; + u32 crcs[CRTC_QUAD_MIXERS]; int rc = 0; int i; @@ -400,7 +400,7 @@ static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) static void _dpu_crtc_blend_setup_pipe(struct drm_crtc *crtc, struct drm_plane *plane, struct dpu_crtc_mixer *mixer, - u32 num_mixers, + u32 lms_in_pair, enum dpu_stage stage, const struct msm_format *format, uint64_t modifier, @@ -419,7 +419,7 @@ static void _dpu_crtc_blend_setup_pipe(struct drm_crtc *crtc, trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane), state, to_dpu_plane_state(state), stage_idx, - format->pixel_format, + format->pixel_format, pipe, modifier); DRM_DEBUG_ATOMIC("crtc %d stage:%d - plane %d sspp %d fb %d multirect_idx %d\n", @@ -434,7 +434,7 @@ static void _dpu_crtc_blend_setup_pipe(struct drm_crtc *crtc, stage_cfg->multirect_index[stage][stage_idx] = pipe->multirect_index; /* blend config update */ - for (lm_idx = 0; lm_idx < num_mixers; lm_idx++) + for (lm_idx = 0; lm_idx < lms_in_pair; lm_idx++) mixer[lm_idx].lm_ctl->ops.update_pending_flush_sspp(mixer[lm_idx].lm_ctl, sspp_idx); } @@ -449,7 +449,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, struct dpu_plane_state *pstate = NULL; const struct msm_format *format; struct dpu_hw_ctl *ctl = mixer->lm_ctl; - u32 lm_idx; + u32 lm_idx, stage, i, pipe_idx, head_pipe_in_stage, lms_in_pair; bool bg_alpha_enable = false; DECLARE_BITMAP(active_fetch, SSPP_MAX); DECLARE_BITMAP(active_pipes, SSPP_MAX); @@ -472,22 +472,25 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable) bg_alpha_enable = true; - set_bit(pstate->pipe.sspp->idx, active_fetch); - set_bit(pstate->pipe.sspp->idx, active_pipes); - _dpu_crtc_blend_setup_pipe(crtc, plane, - mixer, cstate->num_mixers, - pstate->stage, - format, fb ? fb->modifier : 0, - &pstate->pipe, 0, stage_cfg); - - if (pstate->r_pipe.sspp) { - set_bit(pstate->r_pipe.sspp->idx, active_fetch); - set_bit(pstate->r_pipe.sspp->idx, active_pipes); - _dpu_crtc_blend_setup_pipe(crtc, plane, - mixer, cstate->num_mixers, - pstate->stage, - format, fb ? fb->modifier : 0, - &pstate->r_pipe, 1, stage_cfg); + /* loop pipe per mixer pair with config in stage structure */ + for (stage = 0; stage < STAGES_PER_PLANE; stage++) { + head_pipe_in_stage = stage * PIPES_PER_STAGE; + for (i = 0; i < PIPES_PER_STAGE; i++) { + pipe_idx = i + head_pipe_in_stage; + if (!pstate->pipe[pipe_idx].sspp) + continue; + lms_in_pair = min(cstate->num_mixers - (stage * PIPES_PER_STAGE), + PIPES_PER_STAGE); + set_bit(pstate->pipe[pipe_idx].sspp->idx, active_fetch); + set_bit(pstate->pipe[pipe_idx].sspp->idx, active_pipes); + _dpu_crtc_blend_setup_pipe(crtc, plane, + &mixer[head_pipe_in_stage], + lms_in_pair, + pstate->stage, + format, fb ? fb->modifier : 0, + &pstate->pipe[pipe_idx], i, + &stage_cfg[stage]); + } } /* blend config update */ @@ -523,7 +526,7 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) struct dpu_crtc_mixer *mixer = cstate->mixers; struct dpu_hw_ctl *ctl; struct dpu_hw_mixer *lm; - struct dpu_hw_stage_cfg stage_cfg; + struct dpu_hw_stage_cfg stage_cfg[STAGES_PER_PLANE]; DECLARE_BITMAP(active_lms, LM_MAX); int i; @@ -544,10 +547,10 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) } /* initialize stage cfg */ - memset(&stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg)); + memset(&stage_cfg, 0, sizeof(stage_cfg)); memset(active_lms, 0, sizeof(active_lms)); - _dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer, &stage_cfg); + _dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer, stage_cfg); for (i = 0; i < cstate->num_mixers; i++) { ctl = mixer[i].lm_ctl; @@ -568,13 +571,17 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) mixer[i].mixer_op_mode, ctl->idx - CTL_0); + /* + * call dpu_hw_ctl_setup_blendstage() to blend layers per stage cfg. + * stage data is shared between PIPES_PER_STAGE pipes. + */ if (ctl->ops.setup_blendstage) ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx, - &stage_cfg); + &stage_cfg[i / PIPES_PER_STAGE]); if (lm->ops.setup_blendstage) lm->ops.setup_blendstage(lm, mixer[i].hw_lm->idx, - &stage_cfg); + &stage_cfg[i / PIPES_PER_STAGE]); } } @@ -1310,7 +1317,7 @@ static int dpu_crtc_reassign_planes(struct drm_crtc *crtc, struct drm_crtc_state return ret; } -#define MAX_CHANNELS_PER_CRTC 2 +#define MAX_CHANNELS_PER_CRTC PIPES_PER_PLANE #define MAX_HDISPLAY_SPLIT 1080 static struct msm_display_topology dpu_crtc_get_topology( @@ -1321,6 +1328,7 @@ static struct msm_display_topology dpu_crtc_get_topology( struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct msm_display_topology topology = {0}; struct drm_encoder *drm_enc; + u32 num_rt_intf; drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) dpu_encoder_update_topology(drm_enc, &topology, crtc_state->state, @@ -1334,11 +1342,14 @@ static struct msm_display_topology dpu_crtc_get_topology( * Dual display * 2 LM, 2 INTF ( Split display using 2 interfaces) * + * If DSC is enabled, try to use 4:4:2 topology if there is enough + * resource. Otherwise, use 2:2:2 topology. + * * Single display * 1 LM, 1 INTF * 2 LM, 1 INTF (stream merge to support high resolution interfaces) * - * If DSC is enabled, use 2 LMs for 2:2:1 topology + * If DSC is enabled, use 2:2:1 topology * * Add dspps to the reservation requirements if ctm is requested * @@ -1350,14 +1361,23 @@ static struct msm_display_topology dpu_crtc_get_topology( * (mode->hdisplay > MAX_HDISPLAY_SPLIT) check. */ - if (topology.num_intf == 2 && !topology.cwb_enabled) + num_rt_intf = topology.num_intf; + if (topology.cwb_enabled) + num_rt_intf--; + + if (topology.num_dsc) { + if (dpu_kms->catalog->dsc_count >= num_rt_intf * 2) + topology.num_dsc = num_rt_intf * 2; + else + topology.num_dsc = num_rt_intf; + topology.num_lm = topology.num_dsc; + } else if (num_rt_intf == 2) { topology.num_lm = 2; - else if (topology.num_dsc == 2) - topology.num_lm = 2; - else if (dpu_kms->catalog->caps->has_3d_merge) + } else if (dpu_kms->catalog->caps->has_3d_merge) { topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; - else + } else { topology.num_lm = 1; + } if (crtc_state->ctm) topology.num_dspp = topology.num_lm; @@ -1545,6 +1565,9 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, adjusted_mode_clk = dpu_core_perf_adjusted_mode_clk(mode->clock, dpu_kms->perf.perf_cfg); + if (dpu_kms->catalog->caps->has_3d_merge) + adjusted_mode_clk /= 2; + /* * The given mode, adjusted for the perf clock factor, should not exceed * the max core clock rate @@ -1597,6 +1620,17 @@ int dpu_crtc_vblank(struct drm_crtc *crtc, bool en) return 0; } +/** + * dpu_crtc_get_num_lm - Get mixer number in this CRTC pipeline + * @state: Pointer to drm crtc state object + */ +unsigned int dpu_crtc_get_num_lm(const struct drm_crtc_state *state) +{ + struct dpu_crtc_state *cstate = to_dpu_crtc_state(state); + + return cstate->num_mixers; +} + #ifdef CONFIG_DEBUG_FS static int _dpu_debugfs_status_show(struct seq_file *s, void *data) { @@ -1679,15 +1713,15 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data) seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n", state->crtc_x, state->crtc_y, state->crtc_w, state->crtc_h); - seq_printf(s, "\tsspp[0]:%s\n", - pstate->pipe.sspp->cap->name); - seq_printf(s, "\tmultirect[0]: mode: %d index: %d\n", - pstate->pipe.multirect_mode, pstate->pipe.multirect_index); - if (pstate->r_pipe.sspp) { - seq_printf(s, "\tsspp[1]:%s\n", - pstate->r_pipe.sspp->cap->name); - seq_printf(s, "\tmultirect[1]: mode: %d index: %d\n", - pstate->r_pipe.multirect_mode, pstate->r_pipe.multirect_index); + + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!pstate->pipe[i].sspp) + continue; + seq_printf(s, "\tsspp[%d]:%s\n", + i, pstate->pipe[i].sspp->cap->name); + seq_printf(s, "\tmultirect[%d]: mode: %d index: %d\n", + i, pstate->pipe[i].multirect_mode, + pstate->pipe[i].multirect_index); } seq_puts(s, "\n"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index 94392b9b9245..455073c7025b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -210,7 +210,7 @@ struct dpu_crtc_state { bool bw_control; bool bw_split_vote; - struct drm_rect lm_bounds[CRTC_DUAL_MIXERS]; + struct drm_rect lm_bounds[CRTC_QUAD_MIXERS]; uint64_t input_fence_timeout_ns; @@ -218,10 +218,10 @@ struct dpu_crtc_state { /* HW Resources reserved for the crtc */ u32 num_mixers; - struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS]; + struct dpu_crtc_mixer mixers[CRTC_QUAD_MIXERS]; u32 num_ctls; - struct dpu_hw_ctl *hw_ctls[CRTC_DUAL_MIXERS]; + struct dpu_hw_ctl *hw_ctls[CRTC_QUAD_MIXERS]; enum dpu_crtc_crc_source crc_source; int crc_frame_skip_count; @@ -267,4 +267,6 @@ static inline enum dpu_crtc_client_type dpu_crtc_get_client_type( void dpu_crtc_frame_event_cb(struct drm_crtc *crtc, u32 event); +unsigned int dpu_crtc_get_num_lm(const struct drm_crtc_state *state); + #endif /* _DPU_CRTC_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 258edaa18fc0..d1cfe81a3373 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -55,7 +55,8 @@ #define MAX_PHYS_ENCODERS_PER_VIRTUAL \ (MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES) -#define MAX_CHANNELS_PER_ENC 2 +#define MAX_CHANNELS_PER_ENC 4 +#define MAX_CWB_PER_ENC 2 #define IDLE_SHORT_TIMEOUT 1 @@ -182,7 +183,7 @@ struct dpu_encoder_virt { struct dpu_encoder_phys *cur_master; struct dpu_encoder_phys *cur_slave; struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_cwb *hw_cwb[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_cwb *hw_cwb[MAX_CWB_PER_ENC]; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; unsigned int dsc_mask; @@ -660,7 +661,6 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc, struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); struct msm_drm_private *priv = dpu_enc->base.dev->dev_private; struct msm_display_info *disp_info = &dpu_enc->disp_info; - struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); struct drm_connector *connector; struct drm_connector_state *conn_state; struct drm_framebuffer *fb; @@ -674,22 +674,12 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc, dsc = dpu_encoder_get_dsc_config(drm_enc); - /* We only support 2 DSC mode (with 2 LM and 1 INTF) */ - if (dsc) { - /* - * Use 2 DSC encoders, 2 layer mixers and 1 or 2 interfaces - * when Display Stream Compression (DSC) is enabled, - * and when enough DSC blocks are available. - * This is power-optimal and can drive up to (including) 4k - * screens. - */ - WARN(topology->num_intf > 2, - "DSC topology cannot support more than 2 interfaces\n"); - if (topology->num_intf >= 2 || dpu_kms->catalog->dsc_count >= 2) - topology->num_dsc = 2; - else - topology->num_dsc = 1; - } + /* + * Set DSC number as 1 to mark the enabled status, will be adjusted + * in dpu_crtc_get_topology() + */ + if (dsc) + topology->num_dsc = 1; connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); if (!connector) @@ -1160,7 +1150,7 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_cwb[MAX_CHANNELS_PER_ENC]; - int num_ctl, num_pp, num_dsc; + int num_ctl, num_pp, num_dsc, num_pp_per_intf; int num_cwb = 0; bool is_cwb_encoder; unsigned int dsc_mask = 0; @@ -1239,10 +1229,16 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL; } + /* + * There may be 4 PP and 2 INTF for quad pipe case, so INTF is not + * mapped to PP 1:1. Let's calculate the stride with pipe/INTF + */ + num_pp_per_intf = num_pp / dpu_enc->num_phys_encs; + for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - phys->hw_pp = dpu_enc->hw_pp[i]; + phys->hw_pp = dpu_enc->hw_pp[num_pp_per_intf * i]; if (!phys->hw_pp) { DPU_ERROR_ENC(dpu_enc, "no pp block assigned at idx: %d\n", i); @@ -2171,15 +2167,12 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) { - struct dpu_hw_mixer_cfg mixer; int i, num_lm; struct dpu_global_state *global_state; - struct dpu_hw_blk *hw_lm[2]; - struct dpu_hw_mixer *hw_mixer[2]; + struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_mixer *hw_mixer[MAX_CHANNELS_PER_ENC]; struct dpu_hw_ctl *ctl = phys_enc->hw_ctl; - memset(&mixer, 0, sizeof(mixer)); - /* reset all mixers for this encoder */ if (ctl->ops.clear_all_blendstages) ctl->ops.clear_all_blendstages(ctl); @@ -2383,7 +2376,7 @@ void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, */ cwb_cfg.input = INPUT_MODE_LM_OUT; - for (int i = 0; i < MAX_CHANNELS_PER_ENC; i++) { + for (int i = 0; i < MAX_CWB_PER_ENC; i++) { hw_cwb = dpu_enc->hw_cwb[i]; if (!hw_cwb) continue; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h index 61b22d949454..09395d7910ac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -302,7 +302,7 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode( /* Use merge_3d unless DSC MERGE topology is used */ if (phys_enc->split_role == ENC_ROLE_SOLO && - dpu_cstate->num_mixers == CRTC_DUAL_MIXERS && + (dpu_cstate->num_mixers != 1) && !dpu_encoder_use_dsc_merge(phys_enc->parent)) return BLEND_3D_H_ROW_INT; 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 6641455c4ec6..23bb39b471b7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -267,8 +267,8 @@ static const u32 wb2_formats_rgb_yuv[] = { .base = 0x200, .len = 0xa0,}, \ .csc_blk = {.name = "csc", \ .base = 0x320, .len = 0x100,}, \ - .format_list = plane_formats_yuv, \ - .num_formats = ARRAY_SIZE(plane_formats_yuv), \ + .format_list = plane_formats, \ + .num_formats = ARRAY_SIZE(plane_formats), \ .rotation_cfg = NULL, \ } @@ -726,3 +726,4 @@ static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = { #include "catalog/dpu_10_0_sm8650.h" #include "catalog/dpu_12_0_sm8750.h" +#include "catalog/dpu_12_2_glymur.h" 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 f0768f54e9b3..336757103b5a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -24,7 +24,7 @@ #define DPU_MAX_IMG_WIDTH 0x3fff #define DPU_MAX_IMG_HEIGHT 0x3fff -#define CRTC_DUAL_MIXERS 2 +#define CRTC_QUAD_MIXERS 4 #define MAX_XIN_COUNT 16 @@ -749,6 +749,7 @@ struct dpu_mdss_cfg { const struct dpu_format_extended *vig_formats; }; +extern const struct dpu_mdss_cfg dpu_glymur_cfg; extern const struct dpu_mdss_cfg dpu_msm8917_cfg; extern const struct dpu_mdss_cfg dpu_msm8937_cfg; extern const struct dpu_mdss_cfg dpu_msm8953_cfg; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h index b7013c9822d2..cc7cc6f6f7cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h @@ -71,12 +71,6 @@ struct dpu_hw_dsc *dpu_hw_dsc_init_1_2(struct drm_device *dev, const struct dpu_dsc_cfg *cfg, void __iomem *addr); -/** - * dpu_hw_dsc_destroy - destroys dsc driver context - * @dsc: Pointer to dsc driver context returned by dpu_hw_dsc_init - */ -void dpu_hw_dsc_destroy(struct dpu_hw_dsc *dsc); - static inline struct dpu_hw_dsc *to_dpu_hw_dsc(struct dpu_hw_blk *hw) { return container_of(hw, struct dpu_hw_dsc, base); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h index 175639c8bfbb..31451241f083 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -34,7 +34,9 @@ #define DPU_MAX_PLANES 4 #endif +#define STAGES_PER_PLANE 2 #define PIPES_PER_STAGE 2 +#define PIPES_PER_PLANE (PIPES_PER_STAGE * STAGES_PER_PLANE) #ifndef DPU_MAX_DE_CURVES #define DPU_MAX_DE_CURVES 3 #endif @@ -149,6 +151,10 @@ enum dpu_dspp { DSPP_1, DSPP_2, DSPP_3, + DSPP_4, + DSPP_5, + DSPP_6, + DSPP_7, DSPP_MAX }; @@ -159,6 +165,8 @@ enum dpu_ctl { CTL_3, CTL_4, CTL_5, + CTL_6, + CTL_7, CTL_MAX }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 4e5a8ecd31f7..f4c9767c418d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1505,6 +1505,7 @@ static const struct dev_pm_ops dpu_pm_ops = { }; static const struct of_device_id dpu_dt_match[] = { + { .compatible = "qcom,glymur-dpu", .data = &dpu_glymur_cfg, }, { .compatible = "qcom,msm8917-mdp5", .data = &dpu_msm8917_cfg, }, { .compatible = "qcom,msm8937-mdp5", .data = &dpu_msm8937_cfg, }, { .compatible = "qcom,msm8953-mdp5", .data = &dpu_msm8953_cfg, }, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index f54cf0faa1c7..d07a6ab6e7ee 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -500,13 +500,15 @@ static void _dpu_plane_setup_pixel_ext(struct dpu_hw_scaler3_cfg *scale_cfg, int i; for (i = 0; i < DPU_MAX_PLANES; i++) { + uint32_t w = src_w, h = src_h; + if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) { - src_w /= chroma_subsmpl_h; - src_h /= chroma_subsmpl_v; + w /= chroma_subsmpl_h; + h /= chroma_subsmpl_v; } - pixel_ext->num_ext_pxls_top[i] = src_h; - pixel_ext->num_ext_pxls_left[i] = src_w; + pixel_ext->num_ext_pxls_top[i] = h; + pixel_ext->num_ext_pxls_left[i] = w; } } @@ -620,6 +622,7 @@ static void _dpu_plane_color_fill(struct dpu_plane *pdpu, struct msm_drm_private *priv = plane->dev->dev_private; struct dpu_plane_state *pstate = to_dpu_plane_state(plane->state); u32 fill_color = (color & 0xFFFFFF) | ((alpha & 0xFF) << 24); + int i; DPU_DEBUG_PLANE(pdpu, "\n"); @@ -633,12 +636,13 @@ static void _dpu_plane_color_fill(struct dpu_plane *pdpu, return; /* update sspp */ - _dpu_plane_color_fill_pipe(pstate, &pstate->pipe, &pstate->pipe_cfg.dst_rect, - fill_color, fmt); - - if (pstate->r_pipe.sspp) - _dpu_plane_color_fill_pipe(pstate, &pstate->r_pipe, &pstate->r_pipe_cfg.dst_rect, + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!pstate->pipe[i].sspp) + continue; + _dpu_plane_color_fill_pipe(pstate, &pstate->pipe[i], + &pstate->pipe_cfg[i].dst_rect, fill_color, fmt); + } } static int dpu_plane_prepare_fb(struct drm_plane *plane, @@ -740,7 +744,7 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, * We already have verified scaling against platform limitations. * Now check if the SSPP supports scaling at all. */ - if (!sblk->scaler_blk.len && + if (!(sblk->scaler_blk.len && pipe->sspp->ops.setup_scaler) && ((drm_rect_width(&new_plane_state->src) >> 16 != drm_rect_width(&new_plane_state->dst)) || (drm_rect_height(&new_plane_state->src) >> 16 != @@ -820,10 +824,14 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base); u64 max_mdp_clk_rate = kms->perf.max_core_clk_rate; struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + struct dpu_sw_pipe_cfg *pipe_cfg; + struct dpu_sw_pipe_cfg *r_pipe_cfg; + struct dpu_sw_pipe_cfg init_pipe_cfg; struct drm_rect fb_rect = { 0 }; + const struct drm_display_mode *mode = &crtc_state->adjusted_mode; uint32_t max_linewidth; + u32 num_lm; + int stage_id, num_stages; min_scale = FRAC_16_16(1, MAX_UPSCALE_RATIO); max_scale = MAX_DOWNSCALE_RATIO << 16; @@ -846,10 +854,10 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, return -EINVAL; } - /* state->src is 16.16, src_rect is not */ - drm_rect_fp_to_int(&pipe_cfg->src_rect, &new_plane_state->src); + num_lm = dpu_crtc_get_num_lm(crtc_state); - pipe_cfg->dst_rect = new_plane_state->dst; + /* state->src is 16.16, src_rect is not */ + drm_rect_fp_to_int(&init_pipe_cfg.src_rect, &new_plane_state->src); fb_rect.x2 = new_plane_state->fb->width; fb_rect.y2 = new_plane_state->fb->height; @@ -874,35 +882,94 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, max_linewidth = pdpu->catalog->caps->max_linewidth; - drm_rect_rotate(&pipe_cfg->src_rect, + drm_rect_rotate(&init_pipe_cfg.src_rect, new_plane_state->fb->width, new_plane_state->fb->height, new_plane_state->rotation); - if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || - _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) { - if (drm_rect_width(&pipe_cfg->src_rect) > 2 * max_linewidth) { - DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n", - DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); - return -E2BIG; + /* + * We have 1 mixer pair cfg for 1:1:1 and 2:2:1 topology, 2 mixer pair + * configs for left and right half screen in case of 4:4:2 topology. + * But we may have 2 rect to split wide plane that exceeds limit with 1 + * config for 2:2:1. So need to handle both wide plane splitting, and + * two halves of screen splitting for quad-pipe case. Check dest + * rectangle left/right clipping first, then check wide rectangle + * splitting in every half next. + */ + num_stages = (num_lm + 1) / 2; + /* iterate mixer configs for this plane, to separate left/right with the id */ + for (stage_id = 0; stage_id < num_stages; stage_id++) { + struct drm_rect mixer_rect = { + .x1 = stage_id * mode->hdisplay / num_stages, + .y1 = 0, + .x2 = (stage_id + 1) * mode->hdisplay / num_stages, + .y2 = mode->vdisplay + }; + int cfg_idx = stage_id * PIPES_PER_STAGE; + + pipe_cfg = &pstate->pipe_cfg[cfg_idx]; + r_pipe_cfg = &pstate->pipe_cfg[cfg_idx + 1]; + + drm_rect_fp_to_int(&pipe_cfg->src_rect, &new_plane_state->src); + pipe_cfg->dst_rect = new_plane_state->dst; + + DPU_DEBUG_PLANE(pdpu, "checking src " DRM_RECT_FMT + " vs clip window " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), + DRM_RECT_ARG(&mixer_rect)); + + /* + * If this plane does not fall into mixer rect, check next + * mixer rect. + */ + if (!drm_rect_clip_scaled(&pipe_cfg->src_rect, + &pipe_cfg->dst_rect, + &mixer_rect)) { + memset(pipe_cfg, 0, 2 * sizeof(struct dpu_sw_pipe_cfg)); + + continue; } - *r_pipe_cfg = *pipe_cfg; - pipe_cfg->src_rect.x2 = (pipe_cfg->src_rect.x1 + pipe_cfg->src_rect.x2) >> 1; - pipe_cfg->dst_rect.x2 = (pipe_cfg->dst_rect.x1 + pipe_cfg->dst_rect.x2) >> 1; - r_pipe_cfg->src_rect.x1 = pipe_cfg->src_rect.x2; - r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; - } else { - memset(r_pipe_cfg, 0, sizeof(*r_pipe_cfg)); - } + pipe_cfg->dst_rect.x1 -= mixer_rect.x1; + pipe_cfg->dst_rect.x2 -= mixer_rect.x1; - drm_rect_rotate_inv(&pipe_cfg->src_rect, - new_plane_state->fb->width, new_plane_state->fb->height, - new_plane_state->rotation); - if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) - drm_rect_rotate_inv(&r_pipe_cfg->src_rect, - new_plane_state->fb->width, new_plane_state->fb->height, + DPU_DEBUG_PLANE(pdpu, "Got clip src:" DRM_RECT_FMT " dst: " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), DRM_RECT_ARG(&pipe_cfg->dst_rect)); + + /* Split wide rect into 2 rect */ + if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || + _dpu_plane_calc_clk(mode, pipe_cfg) > max_mdp_clk_rate) { + + if (drm_rect_width(&pipe_cfg->src_rect) > 2 * max_linewidth) { + DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); + return -E2BIG; + } + + memcpy(r_pipe_cfg, pipe_cfg, sizeof(struct dpu_sw_pipe_cfg)); + pipe_cfg->src_rect.x2 = (pipe_cfg->src_rect.x1 + pipe_cfg->src_rect.x2) >> 1; + pipe_cfg->dst_rect.x2 = (pipe_cfg->dst_rect.x1 + pipe_cfg->dst_rect.x2) >> 1; + r_pipe_cfg->src_rect.x1 = pipe_cfg->src_rect.x2; + r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; + DPU_DEBUG_PLANE(pdpu, "Split wide plane into:" + DRM_RECT_FMT " and " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), + DRM_RECT_ARG(&r_pipe_cfg->src_rect)); + } else { + memset(r_pipe_cfg, 0, sizeof(struct dpu_sw_pipe_cfg)); + } + + drm_rect_rotate_inv(&pipe_cfg->src_rect, + new_plane_state->fb->width, + new_plane_state->fb->height, new_plane_state->rotation); + if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) + drm_rect_rotate_inv(&r_pipe_cfg->src_rect, + new_plane_state->fb->width, + new_plane_state->fb->height, + new_plane_state->rotation); + } + pstate->needs_qos_remap = drm_atomic_crtc_needs_modeset(crtc_state); return 0; @@ -952,6 +1019,23 @@ static int dpu_plane_is_multirect_parallel_capable(struct dpu_hw_sspp *sspp, dpu_plane_is_parallel_capable(pipe_cfg, fmt, max_linewidth); } +static bool dpu_plane_get_single_pipe_in_stage(struct dpu_plane_state *pstate, + struct dpu_sw_pipe **single_pipe, + struct dpu_sw_pipe_cfg **single_pipe_cfg, + int stage_index) +{ + int pipe_idx; + + pipe_idx = stage_index * PIPES_PER_STAGE; + if (drm_rect_width(&pstate->pipe_cfg[pipe_idx].src_rect) != 0 && + drm_rect_width(&pstate->pipe_cfg[pipe_idx + 1].src_rect) == 0) { + *single_pipe = &pstate->pipe[pipe_idx]; + *single_pipe_cfg = &pstate->pipe_cfg[pipe_idx]; + return true; + } + + return false; +} static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, struct drm_atomic_state *state, @@ -961,20 +1045,17 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, drm_atomic_get_new_plane_state(state, plane); struct dpu_plane *pdpu = to_dpu_plane(plane); struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); - struct dpu_sw_pipe *pipe = &pstate->pipe; - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; - int ret = 0; + struct dpu_sw_pipe *pipe; + struct dpu_sw_pipe_cfg *pipe_cfg; + int ret = 0, i; - ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, - &crtc_state->adjusted_mode, - new_plane_state); - if (ret) - return ret; - - if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { - ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, + for (i = 0; i < PIPES_PER_PLANE; i++) { + pipe = &pstate->pipe[i]; + pipe_cfg = &pstate->pipe_cfg[i]; + if (!drm_rect_width(&pipe_cfg->src_rect)) + continue; + DPU_DEBUG_PLANE(pdpu, "pipe %d is in use, validate it\n", i); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, &crtc_state->adjusted_mode, new_plane_state); if (ret) @@ -1017,17 +1098,20 @@ static bool dpu_plane_try_multirect_parallel(struct dpu_sw_pipe *pipe, struct dp static int dpu_plane_try_multirect_shared(struct dpu_plane_state *pstate, struct dpu_plane_state *prev_adjacent_pstate, const struct msm_format *fmt, - uint32_t max_linewidth) + uint32_t max_linewidth, int stage_index) { - struct dpu_sw_pipe *pipe = &pstate->pipe; - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe *prev_pipe = &prev_adjacent_pstate->pipe; - struct dpu_sw_pipe_cfg *prev_pipe_cfg = &prev_adjacent_pstate->pipe_cfg; + struct dpu_sw_pipe *pipe, *prev_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg, *prev_pipe_cfg; const struct msm_format *prev_fmt = msm_framebuffer_format(prev_adjacent_pstate->base.fb); u16 max_tile_height = 1; - if (prev_adjacent_pstate->r_pipe.sspp != NULL || + if (!dpu_plane_get_single_pipe_in_stage(pstate, &pipe, + &pipe_cfg, stage_index)) + return false; + + if (!dpu_plane_get_single_pipe_in_stage(prev_adjacent_pstate, + &prev_pipe, &prev_pipe_cfg, + stage_index) || prev_pipe->multirect_mode != DPU_SSPP_MULTIRECT_NONE) return false; @@ -1042,11 +1126,6 @@ static int dpu_plane_try_multirect_shared(struct dpu_plane_state *pstate, if (MSM_FORMAT_IS_UBWC(prev_fmt)) max_tile_height = max(max_tile_height, prev_fmt->tile_height); - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - - r_pipe->sspp = NULL; - if (dpu_plane_is_parallel_capable(pipe_cfg, fmt, max_linewidth) && dpu_plane_is_parallel_capable(prev_pipe_cfg, prev_fmt, max_linewidth) && (pipe_cfg->dst_rect.x1 >= prev_pipe_cfg->dst_rect.x2 || @@ -1087,10 +1166,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, struct dpu_plane *pdpu = to_dpu_plane(plane); struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); - struct dpu_sw_pipe *pipe = &pstate->pipe; - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + struct dpu_sw_pipe *pipe = &pstate->pipe[0]; + struct dpu_sw_pipe *r_pipe = &pstate->pipe[1]; + struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg[0]; + struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->pipe_cfg[1]; const struct drm_crtc_state *crtc_state = NULL; uint32_t max_linewidth = dpu_kms->catalog->caps->max_linewidth; @@ -1134,7 +1213,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, drm_atomic_get_old_plane_state(state, plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); struct drm_crtc_state *crtc_state = NULL; - int ret; + int ret, i; if (IS_ERR(plane_state)) return PTR_ERR(plane_state); @@ -1152,8 +1231,8 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, * resources are freed by dpu_crtc_assign_plane_resources(), * but clean them here. */ - pstate->pipe.sspp = NULL; - pstate->r_pipe.sspp = NULL; + for (i = 0; i < PIPES_PER_PLANE; i++) + pstate->pipe[i].sspp = NULL; return 0; } @@ -1175,37 +1254,72 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, return 0; } +static int dpu_plane_assign_resource_in_stage(struct dpu_sw_pipe *pipe, + struct dpu_sw_pipe_cfg *pipe_cfg, + struct drm_plane_state *plane_state, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs) +{ + struct drm_plane *plane = plane_state->plane; + struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + struct dpu_sw_pipe *r_pipe = pipe + 1; + struct dpu_sw_pipe_cfg *r_pipe_cfg = pipe_cfg + 1; + + if (drm_rect_width(&pipe_cfg->src_rect) == 0) + return 0; + + pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, reqs); + if (!pipe->sspp) + return -ENODEV; + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + if (drm_rect_width(&r_pipe_cfg->src_rect) == 0) + return 0; + + if (dpu_plane_try_multirect_parallel(pipe, pipe_cfg, r_pipe, r_pipe_cfg, + pipe->sspp, + msm_framebuffer_format(plane_state->fb), + dpu_kms->catalog->caps->max_linewidth)) + return 0; + + r_pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, reqs); + if (!r_pipe->sspp) + return -ENODEV; + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + return 0; +} + static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc, struct dpu_global_state *global_state, struct drm_atomic_state *state, struct drm_plane_state *plane_state, - struct drm_plane_state *prev_adjacent_plane_state) + struct drm_plane_state **prev_adjacent_plane_state) { const struct drm_crtc_state *crtc_state = NULL; struct drm_plane *plane = plane_state->plane; struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); struct dpu_rm_sspp_requirements reqs; - struct dpu_plane_state *pstate, *prev_adjacent_pstate; + struct dpu_plane_state *pstate, *prev_adjacent_pstate[STAGES_PER_PLANE]; struct dpu_sw_pipe *pipe; - struct dpu_sw_pipe *r_pipe; struct dpu_sw_pipe_cfg *pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg; const struct msm_format *fmt; + int i, ret; if (plane_state->crtc) crtc_state = drm_atomic_get_new_crtc_state(state, plane_state->crtc); pstate = to_dpu_plane_state(plane_state); - prev_adjacent_pstate = prev_adjacent_plane_state ? - to_dpu_plane_state(prev_adjacent_plane_state) : NULL; - pipe = &pstate->pipe; - r_pipe = &pstate->r_pipe; - pipe_cfg = &pstate->pipe_cfg; - r_pipe_cfg = &pstate->r_pipe_cfg; + for (i = 0; i < STAGES_PER_PLANE; i++) + prev_adjacent_pstate[i] = prev_adjacent_plane_state[i] ? + to_dpu_plane_state(prev_adjacent_plane_state[i]) : NULL; - pipe->sspp = NULL; - r_pipe->sspp = NULL; + for (i = 0; i < PIPES_PER_PLANE; i++) + pstate->pipe[i].sspp = NULL; if (!plane_state->fb) return -EINVAL; @@ -1217,42 +1331,24 @@ static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc, reqs.rot90 = drm_rotation_90_or_270(plane_state->rotation); - if (drm_rect_width(&r_pipe_cfg->src_rect) == 0) { - if (!prev_adjacent_pstate || - !dpu_plane_try_multirect_shared(pstate, prev_adjacent_pstate, fmt, - dpu_kms->catalog->caps->max_linewidth)) { - pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); - if (!pipe->sspp) - return -ENODEV; + for (i = 0; i < STAGES_PER_PLANE; i++) { + if (prev_adjacent_pstate[i] && + dpu_plane_try_multirect_shared(pstate, prev_adjacent_pstate[i], fmt, + dpu_kms->catalog->caps->max_linewidth, + i)) + continue; - r_pipe->sspp = NULL; + if (dpu_plane_get_single_pipe_in_stage(pstate, &pipe, &pipe_cfg, i)) + prev_adjacent_plane_state[i] = plane_state; - pipe->multirect_index = DPU_SSPP_RECT_SOLO; - pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - } - } else { - pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); - if (!pipe->sspp) - return -ENODEV; - - if (!dpu_plane_try_multirect_parallel(pipe, pipe_cfg, r_pipe, r_pipe_cfg, - pipe->sspp, - msm_framebuffer_format(plane_state->fb), - dpu_kms->catalog->caps->max_linewidth)) { - /* multirect is not possible, use two SSPP blocks */ - r_pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); - if (!r_pipe->sspp) - return -ENODEV; - - pipe->multirect_index = DPU_SSPP_RECT_SOLO; - pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - } + pipe = &pstate->pipe[i * PIPES_PER_STAGE]; + pipe_cfg = &pstate->pipe_cfg[i * PIPES_PER_STAGE]; + ret = dpu_plane_assign_resource_in_stage(pipe, pipe_cfg, + plane_state, + global_state, + crtc, &reqs); + if (ret) + return ret; } return dpu_plane_atomic_check_sspp(plane, state, crtc_state); @@ -1265,7 +1361,7 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state, unsigned int num_planes) { unsigned int i; - struct drm_plane_state *prev_adjacent_plane_state = NULL; + struct drm_plane_state *prev_adjacent_plane_state[STAGES_PER_PLANE] = { NULL }; for (i = 0; i < num_planes; i++) { struct drm_plane_state *plane_state = states[i]; @@ -1278,9 +1374,7 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state, state, plane_state, prev_adjacent_plane_state); if (ret) - break; - - prev_adjacent_plane_state = plane_state; + return ret; } return 0; @@ -1316,6 +1410,7 @@ void dpu_plane_flush(struct drm_plane *plane) { struct dpu_plane *pdpu; struct dpu_plane_state *pstate; + int i; if (!plane || !plane->state) { DPU_ERROR("invalid plane\n"); @@ -1336,8 +1431,8 @@ void dpu_plane_flush(struct drm_plane *plane) /* force 100% alpha */ _dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF); else { - dpu_plane_flush_csc(pdpu, &pstate->pipe); - dpu_plane_flush_csc(pdpu, &pstate->r_pipe); + for (i = 0; i < PIPES_PER_PLANE; i++) + dpu_plane_flush_csc(pdpu, &pstate->pipe[i]); } /* flag h/w flush complete */ @@ -1438,15 +1533,12 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane, struct dpu_plane *pdpu = to_dpu_plane(plane); struct drm_plane_state *state = plane->state; struct dpu_plane_state *pstate = to_dpu_plane_state(state); - struct dpu_sw_pipe *pipe = &pstate->pipe; - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; struct drm_crtc *crtc = state->crtc; struct drm_framebuffer *fb = state->fb; bool is_rt_pipe; const struct msm_format *fmt = msm_framebuffer_format(fb); - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + int i; pstate->pending = true; @@ -1461,12 +1553,11 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane, crtc->base.id, DRM_RECT_ARG(&state->dst), &fmt->pixel_format, MSM_FORMAT_IS_UBWC(fmt)); - dpu_plane_sspp_update_pipe(plane, pipe, pipe_cfg, fmt, - drm_mode_vrefresh(&crtc->mode), - &pstate->layout); - - if (r_pipe->sspp) { - dpu_plane_sspp_update_pipe(plane, r_pipe, r_pipe_cfg, fmt, + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!drm_rect_width(&pstate->pipe_cfg[i].src_rect)) + continue; + dpu_plane_sspp_update_pipe(plane, &pstate->pipe[i], + &pstate->pipe_cfg[i], fmt, drm_mode_vrefresh(&crtc->mode), &pstate->layout); } @@ -1474,15 +1565,17 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane, if (pstate->needs_qos_remap) pstate->needs_qos_remap = false; - pstate->plane_fetch_bw = _dpu_plane_calc_bw(pdpu->catalog, fmt, - &crtc->mode, pipe_cfg); + pstate->plane_fetch_bw = 0; + pstate->plane_clk = 0; + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!drm_rect_width(&pstate->pipe_cfg[i].src_rect)) + continue; + pstate->plane_fetch_bw += _dpu_plane_calc_bw(pdpu->catalog, fmt, + &crtc->mode, &pstate->pipe_cfg[i]); - pstate->plane_clk = _dpu_plane_calc_clk(&crtc->mode, pipe_cfg); - - if (r_pipe->sspp) { - pstate->plane_fetch_bw += _dpu_plane_calc_bw(pdpu->catalog, fmt, &crtc->mode, r_pipe_cfg); - - pstate->plane_clk = max(pstate->plane_clk, _dpu_plane_calc_clk(&crtc->mode, r_pipe_cfg)); + pstate->plane_clk = max(pstate->plane_clk, + _dpu_plane_calc_clk(&crtc->mode, + &pstate->pipe_cfg[i])); } } @@ -1490,17 +1583,28 @@ static void _dpu_plane_atomic_disable(struct drm_plane *plane) { struct drm_plane_state *state = plane->state; struct dpu_plane_state *pstate = to_dpu_plane_state(state); - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; + struct dpu_sw_pipe *pipe; + int i; - trace_dpu_plane_disable(DRMID(plane), false, - pstate->pipe.multirect_mode); + for (i = 0; i < PIPES_PER_PLANE; i += 1) { + pipe = &pstate->pipe[i]; + if (!pipe->sspp) + continue; - if (r_pipe->sspp) { - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + trace_dpu_plane_disable(DRMID(plane), false, + pstate->pipe[i].multirect_mode); - if (r_pipe->sspp->ops.setup_multirect) - r_pipe->sspp->ops.setup_multirect(r_pipe); + if (i % PIPES_PER_STAGE == 0) + continue; + + /* + * clear multirect for the right pipe so that the SSPP + * can be further reused in the solo mode + */ + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + if (pipe->sspp->ops.setup_multirect) + pipe->sspp->ops.setup_multirect(pipe); } pstate->pending = true; @@ -1595,31 +1699,26 @@ static void dpu_plane_atomic_print_state(struct drm_printer *p, const struct drm_plane_state *state) { const struct dpu_plane_state *pstate = to_dpu_plane_state(state); - const struct dpu_sw_pipe *pipe = &pstate->pipe; - const struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - const struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - const struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + const struct dpu_sw_pipe *pipe; + const struct dpu_sw_pipe_cfg *pipe_cfg; + int i; drm_printf(p, "\tstage=%d\n", pstate->stage); - if (pipe->sspp) { - drm_printf(p, "\tsspp[0]=%s\n", pipe->sspp->cap->name); - drm_printf(p, "\tmultirect_mode[0]=%s\n", + for (i = 0; i < PIPES_PER_PLANE; i++) { + pipe = &pstate->pipe[i]; + if (!pipe->sspp) + continue; + pipe_cfg = &pstate->pipe_cfg[i]; + drm_printf(p, "\tsspp[%d]=%s\n", i, pipe->sspp->cap->name); + drm_printf(p, "\tmultirect_mode[%d]=%s\n", i, dpu_get_multirect_mode(pipe->multirect_mode)); - drm_printf(p, "\tmultirect_index[0]=%s\n", + drm_printf(p, "\tmultirect_index[%d]=%s\n", i, dpu_get_multirect_index(pipe->multirect_index)); - drm_printf(p, "\tsrc[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->src_rect)); - drm_printf(p, "\tdst[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->dst_rect)); - } - - if (r_pipe->sspp) { - drm_printf(p, "\tsspp[1]=%s\n", r_pipe->sspp->cap->name); - drm_printf(p, "\tmultirect_mode[1]=%s\n", - dpu_get_multirect_mode(r_pipe->multirect_mode)); - drm_printf(p, "\tmultirect_index[1]=%s\n", - dpu_get_multirect_index(r_pipe->multirect_index)); - drm_printf(p, "\tsrc[1]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&r_pipe_cfg->src_rect)); - drm_printf(p, "\tdst[1]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&r_pipe_cfg->dst_rect)); + drm_printf(p, "\tsrc[%d]=" DRM_RECT_FMT "\n", i, + DRM_RECT_ARG(&pipe_cfg->src_rect)); + drm_printf(p, "\tdst[%d]=" DRM_RECT_FMT "\n", i, + DRM_RECT_ARG(&pipe_cfg->dst_rect)); } } @@ -1657,14 +1756,17 @@ void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable) struct dpu_plane *pdpu = to_dpu_plane(plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane->state); struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + int i; if (!pdpu->is_rt_pipe) return; pm_runtime_get_sync(&dpu_kms->pdev->dev); - _dpu_plane_set_qos_ctrl(plane, &pstate->pipe, enable); - if (pstate->r_pipe.sspp) - _dpu_plane_set_qos_ctrl(plane, &pstate->r_pipe, enable); + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!pstate->pipe[i].sspp) + continue; + _dpu_plane_set_qos_ctrl(plane, &pstate->pipe[i], enable); + } pm_runtime_put_sync(&dpu_kms->pdev->dev); } #endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index a3a6e9028333..1ef5a041b8ac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -17,10 +17,8 @@ /** * struct dpu_plane_state: Define dpu extension of drm plane state object * @base: base drm plane state object - * @pipe: software pipe description - * @r_pipe: software pipe description of the second pipe - * @pipe_cfg: software pipe configuration - * @r_pipe_cfg: software pipe configuration for the second pipe + * @pipe: software pipe description array + * @pipe_cfg: software pipe configuration array * @stage: assigned by crtc blender * @needs_qos_remap: qos remap settings need to be updated * @multirect_index: index of the rectangle of SSPP @@ -33,10 +31,8 @@ */ struct dpu_plane_state { struct drm_plane_state base; - struct dpu_sw_pipe pipe; - struct dpu_sw_pipe r_pipe; - struct dpu_sw_pipe_cfg pipe_cfg; - struct dpu_sw_pipe_cfg r_pipe_cfg; + struct dpu_sw_pipe pipe[PIPES_PER_PLANE]; + struct dpu_sw_pipe_cfg pipe_cfg[PIPES_PER_PLANE]; enum dpu_stage stage; bool needs_qos_remap; bool pending; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 2c77c74fac0f..f6568ed8375f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -374,7 +374,11 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, if (!rm->mixer_blks[i]) continue; - lm_count = 0; + /* + * Reset lm_count to an even index. This will drop the previous + * primary mixer if failed to find its peer. + */ + lm_count &= ~1; lm_idx[lm_count] = i; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, @@ -842,7 +846,7 @@ struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, if (!reqs->scale && !reqs->yuv) hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_DMA); - if (!hw_sspp && reqs->scale) + if (!hw_sspp && !reqs->yuv) hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_RGB); if (!hw_sspp) hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_VIG); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h index 5307cbc2007c..cb24ad2a6d8d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h @@ -651,9 +651,9 @@ TRACE_EVENT(dpu_crtc_setup_mixer, TP_PROTO(uint32_t crtc_id, uint32_t plane_id, struct drm_plane_state *state, struct dpu_plane_state *pstate, uint32_t stage_idx, uint32_t pixel_format, - uint64_t modifier), + struct dpu_sw_pipe *pipe, uint64_t modifier), TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, - pixel_format, modifier), + pixel_format, pipe, modifier), TP_STRUCT__entry( __field( uint32_t, crtc_id ) __field( uint32_t, plane_id ) @@ -676,9 +676,9 @@ TRACE_EVENT(dpu_crtc_setup_mixer, __entry->dst_rect = drm_plane_state_dest(state); __entry->stage_idx = stage_idx; __entry->stage = pstate->stage; - __entry->sspp = pstate->pipe.sspp->idx; - __entry->multirect_idx = pstate->pipe.multirect_index; - __entry->multirect_mode = pstate->pipe.multirect_mode; + __entry->sspp = pipe->sspp->idx; + __entry->multirect_idx = pipe->multirect_index; + __entry->multirect_mode = pipe->multirect_mode; __entry->pixel_format = pixel_format; __entry->modifier = modifier; ), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index cd73468e369a..7545c0293efb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -72,6 +72,9 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector, DPU_ERROR("invalid fb w=%d, maxlinewidth=%u\n", fb->width, dpu_wb_conn->maxlinewidth); return -EINVAL; + } else if (fb->modifier != DRM_FORMAT_MOD_LINEAR) { + DPU_ERROR("unsupported fb modifier:%#llx\n", fb->modifier); + return -EINVAL; } return drm_atomic_helper_check_wb_connector_state(conn_state->connector, conn_state->state); diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h index b5f452bd7ada..53bd1dcde15f 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h @@ -38,6 +38,7 @@ * struct msm_disp_state - structure to store current dpu state * @dev: device pointer * @drm_dev: drm device pointer + * @blocks: list head for hardware state blocks * @atomic_state: atomic state duplicated at the time of the error * @time: timestamp at which the coredump was captured */ @@ -55,7 +56,7 @@ struct msm_disp_state { /** * struct msm_disp_state_block - structure to store each hardware block state * @name: name of the block - * @drm_dev: handle to the linked list head + * @node: handle to the linked list head * @size: size of the register space of this hardware block * @state: array holding the register dump of this hardware block * @base_addr: starting address of this hardware block's register space @@ -88,8 +89,9 @@ void msm_disp_snapshot_destroy(struct drm_device *drm_dev); * msm_disp_snapshot_state_sync - synchronously snapshot display state * @kms: the kms object * - * Returns state or error + * Returns: state or error * + * Context: * Must be called with &kms->dump_mutex held */ struct msm_disp_state *msm_disp_snapshot_state_sync(struct msm_kms *kms); @@ -97,7 +99,7 @@ struct msm_disp_state *msm_disp_snapshot_state_sync(struct msm_kms *kms); /** * msm_disp_snapshot_state - trigger to dump the display snapshot * @drm_dev: handle to drm device - + * * Returns: none */ void msm_disp_snapshot_state(struct drm_device *drm_dev); @@ -114,7 +116,7 @@ void msm_disp_state_print(struct msm_disp_state *disp_state, struct drm_printer /** * msm_disp_snapshot_capture_state - utility to capture atomic state and hw registers * @disp_state: handle to msm_disp_state struct - + * * Returns: none */ void msm_disp_snapshot_capture_state(struct msm_disp_state *disp_state); @@ -122,7 +124,7 @@ void msm_disp_snapshot_capture_state(struct msm_disp_state *disp_state); /** * msm_disp_state_free - free the memory after the coredump has been read * @data: handle to struct msm_disp_state - + * * Returns: none */ void msm_disp_state_free(void *data); @@ -130,7 +132,6 @@ void msm_disp_state_free(void *data); /** * msm_disp_snapshot_add_block - add a hardware block with its register dump * @disp_state: handle to struct msm_disp_state - * @name: name of the hardware block * @len: size of the register space of the hardware block * @base_addr: starting address of the register space of the hardware block * @fmt: format in which the block names need to be printed diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index c42fd2c17a32..cbcc7c2f0ffc 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -423,13 +423,13 @@ static void msm_dp_ctrl_config_ctrl(struct msm_dp_ctrl_private *ctrl) static void msm_dp_ctrl_lane_mapping(struct msm_dp_ctrl_private *ctrl) { - u32 ln_0 = 0, ln_1 = 1, ln_2 = 2, ln_3 = 3; /* One-to-One mapping */ + u32 *lane_map = ctrl->link->lane_map; u32 ln_mapping; - ln_mapping = ln_0 << LANE0_MAPPING_SHIFT; - ln_mapping |= ln_1 << LANE1_MAPPING_SHIFT; - ln_mapping |= ln_2 << LANE2_MAPPING_SHIFT; - ln_mapping |= ln_3 << LANE3_MAPPING_SHIFT; + ln_mapping = lane_map[0] << LANE0_MAPPING_SHIFT; + ln_mapping |= lane_map[1] << LANE1_MAPPING_SHIFT; + ln_mapping |= lane_map[2] << LANE2_MAPPING_SHIFT; + ln_mapping |= lane_map[3] << LANE3_MAPPING_SHIFT; msm_dp_write_link(ctrl, REG_DP_LOGICAL2PHYSICAL_LANE_MAPPING, ln_mapping); diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index d87d47cc7ec3..9bd9cd5c1e03 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -130,6 +130,14 @@ struct msm_dp_desc { bool wide_bus_supported; }; +static const struct msm_dp_desc msm_dp_desc_glymur[] = { + { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, + { .io_start = 0x0af5c000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true }, + { .io_start = 0x0af64000, .id = MSM_DP_CONTROLLER_2, .wide_bus_supported = true }, + { .io_start = 0x0af6c000, .id = MSM_DP_CONTROLLER_3, .wide_bus_supported = true }, + {} +}; + static const struct msm_dp_desc msm_dp_desc_sa8775p[] = { { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, { .io_start = 0x0af5c000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true }, @@ -187,6 +195,7 @@ static const struct msm_dp_desc msm_dp_desc_x1e80100[] = { }; static const struct of_device_id msm_dp_dt_match[] = { + { .compatible = "qcom,glymur-dp", .data = &msm_dp_desc_glymur }, { .compatible = "qcom,sa8775p-dp", .data = &msm_dp_desc_sa8775p }, { .compatible = "qcom,sc7180-dp", .data = &msm_dp_desc_sc7180 }, { .compatible = "qcom,sc7280-dp", .data = &msm_dp_desc_sc7280 }, diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 66e1bbd80db3..34a91e194a12 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -6,12 +6,14 @@ #define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ #include +#include #include #include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" +#define DP_LINK_RATE_HBR2 540000 /* kbytes */ #define DP_TEST_REQUEST_MASK 0x7F enum audio_sample_rate { @@ -1210,10 +1212,121 @@ u32 msm_dp_link_get_test_bits_depth(struct msm_dp_link *msm_dp_link, u32 bpp) return tbd; } +static u32 msm_dp_link_link_frequencies(struct device_node *of_node) +{ + struct device_node *endpoint; + u64 frequency = 0; + int cnt; + + endpoint = of_graph_get_endpoint_by_regs(of_node, 1, 0); /* port@1 */ + if (!endpoint) + return 0; + + cnt = of_property_count_u64_elems(endpoint, "link-frequencies"); + + if (cnt > 0) + of_property_read_u64_index(endpoint, "link-frequencies", + cnt - 1, &frequency); + of_node_put(endpoint); + + do_div(frequency, + 10 * /* from symbol rate to link rate */ + 1000); /* kbytes */ + + return frequency; +} + +/* + * Always populate msm_dp_link->lane_map with 4 lanes. + * - Use DTS "data-lanes" if present; otherwise fall back to default mapping. + * - For partial definitions, fill remaining entries with unused lanes in + * ascending order. + */ +static int msm_dp_link_lane_map(struct device *dev, struct msm_dp_link *msm_dp_link) +{ + struct device_node *of_node = dev->of_node; + struct device_node *endpoint; + int cnt = msm_dp_link->max_dp_lanes; + u32 tmp[DP_MAX_NUM_DP_LANES]; + u32 map[DP_MAX_NUM_DP_LANES] = {0, 1, 2, 3}; /* default 1:1 mapping */ + bool used[DP_MAX_NUM_DP_LANES] = {false}; + int i, j = 0, ret = -EINVAL; + + endpoint = of_graph_get_endpoint_by_regs(of_node, 1, -1); + if (endpoint) { + ret = of_property_read_u32_array(endpoint, "data-lanes", tmp, cnt); + if (ret) + dev_dbg(dev, "endpoint data-lanes read failed (ret=%d)\n", ret); + } + + if (ret) { + ret = of_property_read_u32_array(of_node, "data-lanes", tmp, cnt); + if (ret) { + dev_info(dev, "data-lanes not defined, set to default\n"); + goto out; + } + } + + for (i = 0; i < cnt; i++) { + if (tmp[i] >= DP_MAX_NUM_DP_LANES) { + dev_err(dev, "data-lanes[%d]=%u out of range\n", i, tmp[i]); + return -EINVAL; + } + used[tmp[i]] = true; + map[i] = tmp[i]; + } + + /* Fill the remaining entries with unused physical lanes (ascending) */ + for (i = cnt; i < DP_MAX_NUM_DP_LANES && j < DP_MAX_NUM_DP_LANES; j++) { + if (!used[j]) + map[i++] = j; + } + +out: + if (endpoint) + of_node_put(endpoint); + + dev_dbg(dev, "data-lanes count %d <%d %d %d %d>\n", cnt, map[0], map[1], map[2], map[3]); + memcpy(msm_dp_link->lane_map, map, sizeof(map)); + return 0; +} + +static int msm_dp_link_parse_dt(struct device *dev, struct msm_dp_link *msm_dp_link) +{ + struct device_node *of_node = dev->of_node; + int cnt; + + /* + * data-lanes is the property of msm_dp_out endpoint + */ + cnt = drm_of_get_data_lanes_count_ep(of_node, 1, 0, 1, DP_MAX_NUM_DP_LANES); + if (cnt < 0) { + /* legacy code, data-lanes is the property of mdss_dp node */ + cnt = drm_of_get_data_lanes_count(of_node, 1, DP_MAX_NUM_DP_LANES); + } + + if (cnt > 0) + msm_dp_link->max_dp_lanes = cnt; + else + msm_dp_link->max_dp_lanes = DP_MAX_NUM_DP_LANES; /* 4 lanes */ + + if (msm_dp_link_lane_map(dev, msm_dp_link)) { + dev_err(dev, "failed to parse data-lanes\n"); + return -EINVAL; + } + + msm_dp_link->max_dp_link_rate = msm_dp_link_link_frequencies(of_node); + if (!msm_dp_link->max_dp_link_rate) + msm_dp_link->max_dp_link_rate = DP_LINK_RATE_HBR2; + + return 0; +} + struct msm_dp_link *msm_dp_link_get(struct device *dev, struct drm_dp_aux *aux) { struct msm_dp_link_private *link; struct msm_dp_link *msm_dp_link; + int ret; if (!dev || !aux) { DRM_ERROR("invalid input\n"); @@ -1229,5 +1342,9 @@ struct msm_dp_link *msm_dp_link_get(struct device *dev, struct drm_dp_aux *aux) mutex_init(&link->psm_mutex); msm_dp_link = &link->msm_dp_link; + ret = msm_dp_link_parse_dt(dev, msm_dp_link); + if (ret) + return ERR_PTR(ret); + return msm_dp_link; } diff --git a/drivers/gpu/drm/msm/dp/dp_link.h b/drivers/gpu/drm/msm/dp/dp_link.h index ba47c6d19fbf..b1eb2de6d2a7 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.h +++ b/drivers/gpu/drm/msm/dp/dp_link.h @@ -12,6 +12,7 @@ #define DS_PORT_STATUS_CHANGED 0x200 #define DP_TEST_BIT_DEPTH_UNKNOWN 0xFFFFFFFF #define DP_LINK_CAP_ENHANCED_FRAMING (1 << 0) +#define DP_MAX_NUM_DP_LANES 4 struct msm_dp_link_info { unsigned char revision; @@ -72,6 +73,10 @@ struct msm_dp_link { struct msm_dp_link_test_audio test_audio; struct msm_dp_link_phy_params phy_params; struct msm_dp_link_info link_params; + + u32 lane_map[DP_MAX_NUM_DP_LANES]; + u32 max_dp_lanes; + u32 max_dp_link_rate; }; /** diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 15b7f6c7146e..ad5d55bf009d 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -16,9 +16,6 @@ #define DP_INTF_CONFIG_DATABUS_WIDEN BIT(4) -#define DP_MAX_NUM_DP_LANES 4 -#define DP_LINK_RATE_HBR2 540000 /* kbytes */ - struct msm_dp_panel_private { struct device *dev; struct drm_device *drm_dev; @@ -91,6 +88,7 @@ static int msm_dp_panel_read_dpcd(struct msm_dp_panel *msm_dp_panel) int rc, max_lttpr_lanes, max_lttpr_rate; struct msm_dp_panel_private *panel; struct msm_dp_link_info *link_info; + struct msm_dp_link *link; u8 *dpcd, major, minor; panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); @@ -105,16 +103,20 @@ static int msm_dp_panel_read_dpcd(struct msm_dp_panel *msm_dp_panel) major = (link_info->revision >> 4) & 0x0f; minor = link_info->revision & 0x0f; + link = panel->link; + drm_dbg_dp(panel->drm_dev, "max_lanes=%d max_link_rate=%d\n", + link->max_dp_lanes, link->max_dp_link_rate); + link_info->rate = drm_dp_max_link_rate(dpcd); link_info->num_lanes = drm_dp_max_lane_count(dpcd); /* Limit data lanes from data-lanes of endpoint property of dtsi */ - if (link_info->num_lanes > msm_dp_panel->max_dp_lanes) - link_info->num_lanes = msm_dp_panel->max_dp_lanes; + if (link_info->num_lanes > link->max_dp_lanes) + link_info->num_lanes = link->max_dp_lanes; /* Limit link rate from link-frequencies of endpoint property of dtsi */ - if (link_info->rate > msm_dp_panel->max_dp_link_rate) - link_info->rate = msm_dp_panel->max_dp_link_rate; + if (link_info->rate > link->max_dp_link_rate) + link_info->rate = link->max_dp_link_rate; /* Limit data lanes from LTTPR capabilities, if any */ max_lttpr_lanes = drm_dp_lttpr_max_lane_count(panel->link->lttpr_common_caps); @@ -173,9 +175,6 @@ int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); - drm_dbg_dp(panel->drm_dev, "max_lanes=%d max_link_rate=%d\n", - msm_dp_panel->max_dp_lanes, msm_dp_panel->max_dp_link_rate); - rc = msm_dp_panel_read_dpcd(msm_dp_panel); if (rc) { DRM_ERROR("read dpcd failed %d\n", rc); @@ -648,60 +647,6 @@ int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel) return 0; } -static u32 msm_dp_panel_link_frequencies(struct device_node *of_node) -{ - struct device_node *endpoint; - u64 frequency = 0; - int cnt; - - endpoint = of_graph_get_endpoint_by_regs(of_node, 1, 0); /* port@1 */ - if (!endpoint) - return 0; - - cnt = of_property_count_u64_elems(endpoint, "link-frequencies"); - - if (cnt > 0) - of_property_read_u64_index(endpoint, "link-frequencies", - cnt - 1, &frequency); - of_node_put(endpoint); - - do_div(frequency, - 10 * /* from symbol rate to link rate */ - 1000); /* kbytes */ - - return frequency; -} - -static int msm_dp_panel_parse_dt(struct msm_dp_panel *msm_dp_panel) -{ - struct msm_dp_panel_private *panel; - struct device_node *of_node; - int cnt; - - panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); - of_node = panel->dev->of_node; - - /* - * data-lanes is the property of msm_dp_out endpoint - */ - cnt = drm_of_get_data_lanes_count_ep(of_node, 1, 0, 1, DP_MAX_NUM_DP_LANES); - if (cnt < 0) { - /* legacy code, data-lanes is the property of mdss_dp node */ - cnt = drm_of_get_data_lanes_count(of_node, 1, DP_MAX_NUM_DP_LANES); - } - - if (cnt > 0) - msm_dp_panel->max_dp_lanes = cnt; - else - msm_dp_panel->max_dp_lanes = DP_MAX_NUM_DP_LANES; /* 4 lanes */ - - msm_dp_panel->max_dp_link_rate = msm_dp_panel_link_frequencies(of_node); - if (!msm_dp_panel->max_dp_link_rate) - msm_dp_panel->max_dp_link_rate = DP_LINK_RATE_HBR2; - - return 0; -} - struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux, struct msm_dp_link *link, void __iomem *link_base, @@ -709,7 +654,6 @@ struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux { struct msm_dp_panel_private *panel; struct msm_dp_panel *msm_dp_panel; - int ret; if (!dev || !aux || !link) { DRM_ERROR("invalid input\n"); @@ -729,10 +673,6 @@ struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux msm_dp_panel = &panel->msm_dp_panel; msm_dp_panel->max_bw_code = DP_LINK_BW_8_1; - ret = msm_dp_panel_parse_dt(msm_dp_panel); - if (ret) - return ERR_PTR(ret); - return msm_dp_panel; } diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index d2cf401506dc..921a296852d4 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -41,9 +41,6 @@ struct msm_dp_panel { bool vsc_sdp_supported; u32 hw_revision; - u32 max_dp_lanes; - u32 max_dp_link_rate; - u32 max_bw_code; }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index e391505fdaf0..3cbf08231492 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -109,7 +109,6 @@ struct msm_dsi_phy { struct msm_dsi_dphy_timing timing; const struct msm_dsi_phy_cfg *cfg; void *tuning_cfg; - void *pll_data; enum msm_dsi_phy_usecase usecase; bool regulator_ldo_mode; 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 32f06edd21a9..c5e1d2016bcc 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -426,11 +426,8 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) u32 data; spin_lock_irqsave(&pll->pll_enable_lock, flags); - if (pll->pll_enable_cnt++) { - spin_unlock_irqrestore(&pll->pll_enable_lock, flags); - WARN_ON(pll->pll_enable_cnt == INT_MAX); - return; - } + pll->pll_enable_cnt++; + WARN_ON(pll->pll_enable_cnt == INT_MAX); data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; @@ -876,7 +873,6 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) spin_lock_init(&pll_7nm->pll_enable_lock); pll_7nm->phy = phy; - phy->pll_data = pll_7nm; ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws); if (ret) { @@ -965,10 +961,8 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, u32 const delay_us = 5; u32 const timeout_us = 1000; struct msm_dsi_dphy_timing *timing = &phy->timing; - struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; bool less_than_1500_mhz; - unsigned long flags; u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0; u32 glbl_pemph_ctrl_0; u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0; @@ -1090,13 +1084,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, glbl_rescode_bot_ctrl = 0x3c; } - spin_lock_irqsave(&pll->pll_enable_lock, flags); - pll->pll_enable_cnt = 1; /* de-assert digital and pll power down */ data = DSI_7nm_PHY_CMN_CTRL_0_DIGTOP_PWRDN_B | DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); - spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* Assert PLL core reset */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL); @@ -1209,9 +1200,7 @@ static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable) static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) { - struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; - unsigned long flags; u32 data; DBG(""); @@ -1238,11 +1227,8 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); writel(0, base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0); - spin_lock_irqsave(&pll->pll_enable_lock, flags); - pll->pll_enable_cnt = 0; /* Turn off all PHY blocks */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_CTRL_0); - spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* make sure phy is turned off */ wmb(); diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index aad6fb77f0de..fd19995b12b5 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -91,9 +91,9 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, { struct drm_device *dev = helper->dev; struct msm_drm_private *priv = dev->dev_private; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = NULL; struct drm_gem_object *bo; - struct fb_info *fbi = NULL; uint64_t paddr; uint32_t format; int ret, pitch; @@ -126,13 +126,6 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - DRM_DEV_ERROR(dev->dev, "failed to allocate fb info\n"); - ret = PTR_ERR(fbi); - goto fail; - } - DBG("fbi=%p, dev=%p", fbi, dev); helper->funcs = &msm_fbdev_helper_funcs; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 688705a871cf..017411a0bf45 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -701,7 +701,6 @@ int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev, struct drm_mode_create_dumb *args) { u32 fourcc; - const struct drm_format_info *info; u64 pitch_align; int ret; @@ -711,12 +710,16 @@ int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev, * Use the result as pitch alignment. */ fourcc = drm_driver_color_mode_format(dev, args->bpp); - if (fourcc == DRM_FORMAT_INVALID) - return -EINVAL; - info = drm_format_info(fourcc); - if (!info) - return -EINVAL; - pitch_align = drm_format_info_min_pitch(info, 0, SZ_32); + if (fourcc != DRM_FORMAT_INVALID) { + const struct drm_format_info *info; + + info = drm_format_info(fourcc); + if (!info) + return -EINVAL; + pitch_align = drm_format_info_min_pitch(info, 0, 32); + } else { + pitch_align = round_up(args->width, 32) * DIV_ROUND_UP(args->bpp, SZ_8); + } if (!pitch_align || pitch_align > U32_MAX) return -EINVAL; ret = drm_mode_size_dumb(dev, args, pitch_align, 0); @@ -1143,12 +1146,16 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } - if (obj->resv != &obj->_resv) { + /* + * In error paths, we could end up here before msm_gem_new_handle() + * has changed obj->resv to point to the shared resv. In this case, + * we don't want to drop a ref to the shared r_obj that we haven't + * taken yet. + */ + if ((msm_obj->flags & MSM_BO_NO_SHARE) && (obj->resv != &obj->_resv)) { struct drm_gem_object *r_obj = container_of(obj->resv, struct drm_gem_object, _resv); - WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE)); - /* Drop reference we hold to shared resv obj: */ drm_gem_object_put(r_obj); } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3ab3b27134f9..75d9f3574370 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -414,6 +414,11 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) submit->user_fence, DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_BOOKKEEP); + + last_fence = vm->last_fence; + vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence); + dma_fence_put(last_fence); + return; } @@ -427,10 +432,6 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) dma_resv_add_fence(obj->resv, submit->user_fence, DMA_RESV_USAGE_READ); } - - last_fence = vm->last_fence; - vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence); - dma_fence_put(last_fence); } static int submit_bo(struct msm_gem_submit *submit, uint32_t idx, diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 8316af1723c2..71d5238437eb 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -462,15 +462,20 @@ struct op_arg { bool kept; }; -static void +static int vm_op_enqueue(struct op_arg *arg, struct msm_vm_op _op) { struct msm_vm_op *op = kmalloc(sizeof(*op), GFP_KERNEL); + if (!op) + return -ENOMEM; + *op = _op; list_add_tail(&op->node, &arg->job->vm_ops); if (op->obj) drm_gem_object_get(op->obj); + + return 0; } static struct drm_gpuva * @@ -489,6 +494,7 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) struct drm_gpuva *vma; struct sg_table *sgt; unsigned prot; + int ret; if (arg->kept) return 0; @@ -500,8 +506,6 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); - vma->flags = ((struct op_arg *)arg)->flags; - if (obj) { sgt = to_msm_bo(obj)->sgt; prot = msm_gem_prot(obj); @@ -510,7 +514,7 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) prot = IOMMU_READ | IOMMU_WRITE; } - vm_op_enqueue(arg, (struct msm_vm_op){ + ret = vm_op_enqueue(arg, (struct msm_vm_op){ .op = MSM_VM_OP_MAP, .map = { .sgt = sgt, @@ -523,6 +527,10 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) .obj = vma->gem.obj, }); + if (ret) + return ret; + + vma->flags = ((struct op_arg *)arg)->flags; to_msm_vma(vma)->mapped = true; return 0; @@ -538,6 +546,7 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) struct drm_gpuvm_bo *vm_bo = orig_vma->vm_bo; bool mapped = to_msm_vma(orig_vma)->mapped; unsigned flags; + int ret; vm_dbg("orig_vma: %p:%p:%p: %016llx %016llx", vm, orig_vma, orig_vma->gem.obj, orig_vma->va.addr, orig_vma->va.range); @@ -547,7 +556,7 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) drm_gpuva_op_remap_to_unmap_range(&op->remap, &unmap_start, &unmap_range); - vm_op_enqueue(arg, (struct msm_vm_op){ + ret = vm_op_enqueue(arg, (struct msm_vm_op){ .op = MSM_VM_OP_UNMAP, .unmap = { .iova = unmap_start, @@ -557,6 +566,9 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) .obj = orig_vma->gem.obj, }); + if (ret) + return ret; + /* * Part of this GEM obj is still mapped, but we're going to kill the * existing VMA and replace it with one or two new ones (ie. two if @@ -618,6 +630,7 @@ msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) struct msm_vm_bind_job *job = arg->job; struct drm_gpuva *vma = op->unmap.va; struct msm_gem_vma *msm_vma = to_msm_vma(vma); + int ret; vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); @@ -650,7 +663,7 @@ msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) if (!msm_vma->mapped) goto out_close; - vm_op_enqueue(arg, (struct msm_vm_op){ + ret = vm_op_enqueue(arg, (struct msm_vm_op){ .op = MSM_VM_OP_UNMAP, .unmap = { .iova = vma->va.addr, @@ -660,6 +673,9 @@ msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) .obj = vma->gem.obj, }); + if (ret) + return ret; + msm_vma->mapped = false; out_close: @@ -971,6 +987,7 @@ static int lookup_op(struct msm_vm_bind_job *job, const struct drm_msm_vm_bind_op *op) { struct drm_device *dev = job->vm->drm; + struct msm_drm_private *priv = dev->dev_private; int i = job->nr_ops++; int ret = 0; @@ -1017,6 +1034,11 @@ lookup_op(struct msm_vm_bind_job *job, const struct drm_msm_vm_bind_op *op) break; } + if ((op->op == MSM_VM_BIND_OP_MAP_NULL) && + !adreno_smmu_has_prr(priv->gpu)) { + ret = UERR(EINVAL, dev, "PRR not supported\n"); + } + return ret; } @@ -1421,7 +1443,7 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) * Maybe we could allow just UNMAP ops? OTOH userspace should just * immediately close the device file and all will be torn down. */ - if (to_msm_vm(ctx->vm)->unusable) + if (to_msm_vm(msm_context_vm(dev, ctx))->unusable) return UERR(EPIPE, dev, "context is unusable"); /* diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 17759abc46d7..dd0605fe1243 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -287,16 +287,17 @@ static void crashstate_get_bos(struct msm_gpu_state *state, struct msm_gem_submi state->bos = kcalloc(cnt, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); - drm_gpuvm_for_each_va (vma, submit->vm) { - bool dump = rd_full || (vma->flags & MSM_VMA_DUMP); + if (state->bos) + drm_gpuvm_for_each_va(vma, submit->vm) { + bool dump = rd_full || (vma->flags & MSM_VMA_DUMP); - /* Skip MAP_NULL/PRR VMAs: */ - if (!vma->gem.obj) - continue; + /* Skip MAP_NULL/PRR VMAs: */ + if (!vma->gem.obj) + continue; - msm_gpu_crashstate_get_bo(state, vma->gem.obj, vma->va.addr, - dump, vma->gem.offset, vma->va.range); - } + msm_gpu_crashstate_get_bo(state, vma->gem.obj, vma->va.addr, + dump, vma->gem.offset, vma->va.range); + } drm_exec_fini(&exec); } else { @@ -348,6 +349,10 @@ static void crashstate_get_vm_logs(struct msm_gpu_state *state, struct msm_gem_v state->vm_logs = kmalloc_array( state->nr_vm_logs, sizeof(vm->log[0]), GFP_KERNEL); + if (!state->vm_logs) { + state->nr_vm_logs = 0; + } + for (int i = 0; i < state->nr_vm_logs; i++) { int idx = (i + first) & vm_log_mask; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index a597f2bee30b..2894fc118485 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -299,6 +299,17 @@ static inline struct msm_gpu *dev_to_gpu(struct device *dev) return container_of(adreno_smmu, struct msm_gpu, adreno_smmu); } +static inline bool +adreno_smmu_has_prr(struct msm_gpu *gpu) +{ + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev); + + if (!adreno_smmu) + return false; + + return adreno_smmu && adreno_smmu->set_prr_addr; +} + /* It turns out that all targets use the same ringbuffer size */ #define MSM_GPU_RINGBUFFER_SZ SZ_32K #define MSM_GPU_RINGBUFFER_BLKSIZE 32 diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 0e18619f96cb..a188617653e8 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -338,6 +338,8 @@ msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_preall ret = kmem_cache_alloc_bulk(pt_cache, GFP_KERNEL, p->count, p->pages); if (ret != p->count) { + kfree(p->pages); + p->pages = NULL; p->count = ret; return -ENOMEM; } @@ -351,6 +353,9 @@ msm_iommu_pagetable_prealloc_cleanup(struct msm_mmu *mmu, struct msm_mmu_preallo struct kmem_cache *pt_cache = get_pt_cache(mmu); uint32_t remaining_pt_count = p->count - p->ptr; + if (!p->pages) + return; + if (p->count > 0) trace_msm_mmu_prealloc_cleanup(p->count, remaining_pt_count); diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 2d0e3e784c04..bf9a33e925ac 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -553,8 +553,10 @@ static const struct msm_mdss_data data_153k6 = { static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,mdss", .data = &data_153k6 }, + { .compatible = "qcom,glymur-mdss", .data = &data_57k }, { .compatible = "qcom,msm8998-mdss", .data = &data_76k8 }, { .compatible = "qcom,qcm2290-mdss", .data = &data_76k8 }, + { .compatible = "qcom,qcs8300-mdss", .data = &data_74k }, { .compatible = "qcom,sa8775p-mdss", .data = &data_74k }, { .compatible = "qcom,sar2130p-mdss", .data = &data_74k }, { .compatible = "qcom,sdm670-mdss", .data = &data_76k8 }, diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index 9459b6038217..3941e7510754 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -7,9 +7,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + + - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - + + @@ -115,11 +222,16 @@ by a particular renderpass/blit. - + + + + + - + + - + b0..7 identifies where MRB data starts (and RB data ends) b8.15 identifies where VSD data starts (and MRB data ends) @@ -131,7 +243,7 @@ by a particular renderpass/blit. - + low bits identify where CP_SET_DRAW_STATE stateobj processing starts (and IB2 data ends). I'm guessing @@ -147,176 +259,293 @@ by a particular renderpass/blit. - - - - - + + + + + + + + - + - + + + + + + + + + + + - + + + + + + + - + - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - + + - - + + - + + + + + + + + + + + + + + + + + + + + - - - - - - + + + + + + - - - - - + + + + + + + - + + + + + + + number of remaining dwords incl current dword being consumed? - - - number of remaining dwords incl current dword being consumed? - - - - number of remaining dwords incl current dword being consumed? - - - - number of remaining dwords incl current dword being consumed? - - - - number of dwords that have already been read but haven't been consumed by $addr - - - - number of remaining dwords incl current dword being consumed? - - + + + + + + + + + + + + + + + + - + - - + + + + + + - + - + - - - - - - - - - - - - - + + - - - - + + + + + + + - - - - - - - + + + - - - - - - - + + + + + + + + + + + + + + + - - - + + number of remaining dwords incl current dword being consumed? + + + + number of remaining dwords incl current dword being consumed? + + + + number of remaining dwords incl current dword being consumed? + + - - - - - - - - - - - - + + + - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -342,22 +571,59 @@ by a particular renderpass/blit. - - - + + + - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - + + + + + + + + + + + + + @@ -376,49 +642,96 @@ by a particular renderpass/blit. - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - - - - - - - + + + + + + + + + + + + + + + + + + @@ -610,6 +964,8 @@ by a particular renderpass/blit. + + @@ -638,72 +994,276 @@ by a particular renderpass/blit. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - Set to true when binning, isn't changed afterwards - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - - + + + + + + + + + - + - - - + + + + + - - + + + + + + + + + + + + - - - - - - + + + + + + - - + + - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + @@ -712,30 +1272,66 @@ by a particular renderpass/blit. + + - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - + + + + + + + + + + + @@ -803,10 +1399,14 @@ by a particular renderpass/blit. - - + + + + - + + + @@ -829,6 +1429,7 @@ by a particular renderpass/blit. + @@ -839,6 +1440,18 @@ by a particular renderpass/blit. + + + + + + + + + + + + @@ -853,6 +1466,7 @@ by a particular renderpass/blit. + @@ -860,9 +1474,7 @@ by a particular renderpass/blit. - - - + @@ -887,6 +1499,7 @@ by a particular renderpass/blit. + @@ -921,10 +1534,23 @@ by a particular renderpass/blit. + + + + + + + + + + + + + @@ -951,6 +1577,13 @@ by a particular renderpass/blit. + + + + + + + @@ -958,25 +1591,31 @@ by a particular renderpass/blit. + + + + + + @@ -984,16 +1623,25 @@ by a particular renderpass/blit. + + + + + + + + - + + @@ -1008,6 +1656,7 @@ by a particular renderpass/blit. + @@ -1022,10 +1671,16 @@ by a particular renderpass/blit. + + + + + + @@ -1073,7 +1728,6 @@ by a particular renderpass/blit. - @@ -1084,7 +1738,10 @@ by a particular renderpass/blit. - + + + + @@ -1123,6 +1780,28 @@ by a particular renderpass/blit. + + + + + + + Allows draws that don't have GRAS_LRZ_CNTL.LRZ_WRITE but have + GRAS_LRZ_CNTL.ENABLE to contribute to LRZ during RENDERING pass. + In sysmem mode GRAS_LRZ_CNTL.LRZ_WRITE is not considered. + + + Disable LRZ feedback writes + + + + + + + + + + @@ -1130,6 +1809,7 @@ by a particular renderpass/blit. + @@ -1137,6 +1817,7 @@ by a particular renderpass/blit. + @@ -1158,13 +1839,21 @@ by a particular renderpass/blit. + + + + + + + + @@ -1176,14 +1865,26 @@ by a particular renderpass/blit. + + + + + + + + + + + + @@ -1203,6 +1904,7 @@ by a particular renderpass/blit. + @@ -1210,6 +1912,7 @@ by a particular renderpass/blit. + @@ -1217,8 +1920,10 @@ by a particular renderpass/blit. + + @@ -1226,6 +1931,7 @@ by a particular renderpass/blit. + @@ -1244,7 +1950,6 @@ by a particular renderpass/blit. - 0.0 if GREATER - 1.0 if LESS - @@ -1258,11 +1963,27 @@ by a particular renderpass/blit. Disable LRZ based on previous direction and the current one. If DIR_WRITE is not enabled - there is no write to direction buffer. - - + + + + + + + + + + The total size of the LRZ image array (not including + fast clear buffer), used as a stride for double + buffering used with concurrent binning. + + + + + + @@ -1275,14 +1996,17 @@ by a particular renderpass/blit. + + + @@ -1290,6 +2014,9 @@ by a particular renderpass/blit. + + + + + + + - - - - - - + + LUT used to convert quality buffer values to HW shading rate values. An array of 4-bit values. - + + - + + + + + + + + + + @@ -1372,7 +2109,7 @@ by a particular renderpass/blit. - + @@ -1391,7 +2128,7 @@ by a particular renderpass/blit. - + - + - - - - - + + + + + + + + + + + + + + + @@ -1462,7 +2219,8 @@ by a particular renderpass/blit. - + + @@ -1534,8 +2292,32 @@ by a particular renderpass/blit. - - + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -1546,11 +2328,17 @@ by a particular renderpass/blit. - + + + + + + + - - + + @@ -1613,7 +2401,9 @@ by a particular renderpass/blit. - + + + @@ -1627,14 +2417,15 @@ by a particular renderpass/blit. + + - - - + + @@ -1702,12 +2493,22 @@ by a particular renderpass/blit. - + + + + + + + + + + + @@ -1720,6 +2521,11 @@ by a particular renderpass/blit. + + + + + @@ -1798,8 +2604,10 @@ by a particular renderpass/blit. + + - + @@ -1814,12 +2622,30 @@ by a particular renderpass/blit. --> - + + + + + + + + + + + + + - + - - + + @@ -1849,9 +2675,19 @@ by a particular renderpass/blit. the address is specified through CP_EVENT_WRITE7::WRITE_SAMPLE_COUNT. - - + + + + + + + + + + + + - + - + @@ -1963,7 +2799,7 @@ by a particular renderpass/blit. - + @@ -1972,26 +2808,40 @@ by a particular renderpass/blit. - + + + + + - + + + + + + + - - - - + + + + + + + - - + + + @@ -2014,6 +2864,10 @@ by a particular renderpass/blit. + + + + @@ -2028,6 +2882,9 @@ by a particular renderpass/blit. + + + @@ -2042,6 +2899,7 @@ by a particular renderpass/blit. + @@ -2051,6 +2909,7 @@ by a particular renderpass/blit. + @@ -2091,9 +2950,13 @@ by a particular renderpass/blit. + + + + @@ -2119,6 +2982,15 @@ by a particular renderpass/blit. + + Packed array of a6xx_varying_interp_mode + + + + Packed array of a6xx_varying_ps_repl_mode + + + @@ -2128,6 +3000,11 @@ by a particular renderpass/blit. + + + + + + + @@ -2181,13 +3061,23 @@ by a particular renderpass/blit. + + + + + + + + + + @@ -2211,6 +3101,10 @@ by a particular renderpass/blit. + + + + @@ -2231,6 +3125,7 @@ by a particular renderpass/blit. + - - - - + + + + + + + + + + - - - - + + + + + + + + + + @@ -2285,6 +3213,7 @@ by a particular renderpass/blit. + @@ -2292,10 +3221,13 @@ by a particular renderpass/blit. + + + @@ -2304,6 +3236,7 @@ by a particular renderpass/blit. + @@ -2311,12 +3244,19 @@ by a particular renderpass/blit. + + + + + + + @@ -2326,6 +3266,9 @@ by a particular renderpass/blit. + + + @@ -2333,6 +3276,7 @@ by a particular renderpass/blit. + + + + @@ -2381,7 +3329,13 @@ by a particular renderpass/blit. + + + + + + @@ -2391,24 +3345,37 @@ by a particular renderpass/blit. + + - - - - + + + + + + + + + + + + + + + @@ -2419,6 +3386,10 @@ by a particular renderpass/blit. + + + + @@ -2430,20 +3401,30 @@ by a particular renderpass/blit. + + + + + Written by CP_SET_VISIBILITY_OVERRIDE handler + - + - + + + - + + + @@ -2530,11 +3511,15 @@ by a particular renderpass/blit. - + - + + + + + - - @@ -2720,6 +3703,15 @@ by a particular renderpass/blit. + + Same on a6xx/a7xx, UMD should not need to write this + + + + UMD needs to write in some cases + + + @@ -2729,6 +3721,8 @@ by a particular renderpass/blit. + + @@ -2754,6 +3748,8 @@ by a particular renderpass/blit. + + @@ -2791,6 +3787,8 @@ by a particular renderpass/blit. + + @@ -2814,7 +3812,10 @@ by a particular renderpass/blit. - + + + + @@ -2843,6 +3844,8 @@ by a particular renderpass/blit. + + @@ -2886,13 +3889,19 @@ by a particular renderpass/blit. - + - + + + + + + + @@ -2993,13 +4002,11 @@ by a particular renderpass/blit. - + + - - - @@ -3036,6 +4043,7 @@ by a particular renderpass/blit. must be at least the actual CONSTLEN. + @@ -3047,7 +4055,8 @@ by a particular renderpass/blit. - + + @@ -3158,6 +4167,18 @@ by a particular renderpass/blit. + + + + + + + + + + + + - + - + + + + + @@ -3210,9 +4235,12 @@ by a particular renderpass/blit. --> + + + @@ -3234,22 +4262,27 @@ by a particular renderpass/blit. - - + + + - - + + - - - - + + + + + + + + - + @@ -3260,24 +4293,47 @@ by a particular renderpass/blit. - + - - - + + + + + - + - + + + - + + + + + + + + + + + + + + + + + + + + - - + + + + + @@ -3303,10 +4362,12 @@ by a particular renderpass/blit. - - + + + + @@ -3315,13 +4376,17 @@ by a particular renderpass/blit. + + + + @@ -3387,11 +4452,12 @@ by a particular renderpass/blit. + - - - + + + @@ -3404,7 +4470,7 @@ by a particular renderpass/blit. - + @@ -3414,8 +4480,13 @@ by a particular renderpass/blit. + + + + + @@ -3458,10 +4529,8 @@ by a particular renderpass/blit. - - - - + + @@ -3512,9 +4581,12 @@ by a particular renderpass/blit. - + + + + - + @@ -3718,7 +4790,7 @@ by a particular renderpass/blit. - + This register clears pending loads queued up by CP_LOAD_STATE6. Each bit resets a particular kind(s) of @@ -3741,10 +4813,30 @@ by a particular renderpass/blit. + + + This register clears pending loads queued up by + CP_LOAD_STATE6. Each bit resets a particular kind(s) of + CP_LOAD_STATE6. + + + + + + + + + + + + + + + @@ -3781,15 +4873,15 @@ by a particular renderpass/blit. - - - - + + + + - + @@ -3918,6 +5010,7 @@ by a particular renderpass/blit. + diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml index 4e42f055b85f..81538831dc19 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml @@ -303,7 +303,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> @@ -233,12 +256,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> - - - - - - + + + + + + diff --git a/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml index 661b0dd0f675..8d195ee5d284 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml @@ -93,13 +93,6 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> - - - - - - - diff --git a/drivers/gpu/drm/msm/registers/adreno/a8xx_descriptors.xml b/drivers/gpu/drm/msm/registers/adreno/a8xx_descriptors.xml new file mode 100644 index 000000000000..edcbdb3b6921 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a8xx_descriptors.xml @@ -0,0 +1,121 @@ + + + + + + + + + + Texture sampler dwords + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Texture memobj dwords + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/drivers/gpu/drm/msm/registers/adreno/a8xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a8xx_enums.xml new file mode 100644 index 000000000000..c842db8c78d6 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a8xx_enums.xml @@ -0,0 +1,299 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml index 218ec8bb966e..79d204f1e400 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml @@ -11,6 +11,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + @@ -397,4 +398,15 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + + + + + + + + + + + diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml index 0e10e1c6d263..51e9c94f5e37 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -6,103 +6,102 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> - - - - + + + + Flushes dirty data from UCHE, and also writes a GPU timestamp to the address if one is provided. - - - - - - - - - - + + + + + + + + + + - - - - - + + + + + If A6XX_RB_SAMPLE_COUNTER_CNTL.copy is true, writes OQ Z passed sample counts to RB_SAMPLE_COUNTER_BASE. This writes to main memory, skipping UCHE. - - + + Writes the GPU timestamp to the address that follows, once RB access and flushes are complete. - + - - - - + + + + - - - - - - - - - + + + + + + + + + Invalidates depth attachment data from the CCU. We assume this happens in the last stage. - + Invalidates color attachment data from the CCU. We assume this happens in the last stage. - + Flushes the small cache used by CP_EVENT_WRITE::BLIT (which, along with its registers, would be better named RESOLVE). - + Flushes depth attachment data from the CCU. We assume this happens in the last stage. - + Flushes color attachment data from the CCU. We assume this happens in the last stage. - + - 2D blit to resolve GMEM to system memory (skipping CCU) at the - end of a render pass. Compare to CP_BLIT's BLIT_OP_SCALE for - more general blitting. + Triggers a resolve (GMEM to sysmem) or unresolve (sysmem to + GMEM) or clear blit, depending on CCU programming. - + Flip between the primary and secondary LRZ buffers. This is used for concurrent binning, so that BV can write to one buffer while BR reads from the other. - + Clears based on GRAS_LRZ_CNTL configuration, could clear @@ -115,44 +114,46 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> CUR_DIR_UNSET = 0x3 Clear of direction means setting the direction to CUR_DIR_UNSET. - + - - - - - - - - - + + + + + + + + + + Invalidates UCHE. - + - + Doesn't seem to do anything - - - - - - - - - - - - + + + + + + + + + + + - - + + + + @@ -310,11 +311,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> generate a VS|PS_done event - + generate a cache flush done event - + generate a z_pass done event - + not sure the real name, but this seems to be what is used for opencl, instead of CP_DRAW_INDX.. @@ -335,9 +336,9 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> load constant into chip and to memory load sequencer instruction memory (pointer-based) - + load sequencer instruction memory (code embedded in packet) - + load constants from a location in memory selective invalidation of state pointers @@ -662,6 +663,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> + + + + + + @@ -1800,49 +1807,73 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) - + - - + + + + + + + + + + - - - + + + + - - - - + + + - - - - - + + + + + + + + + + + + + + + + + + + @@ -2066,6 +2097,14 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) payload *and* skipsaverestore is set. This is expected to restore static register values not saved when skipsaverestore is set. + + On BV, a skipsaverestore preemption is triggered + and this preamble type is executed whenever a + CP_THREAD_CONTROL that synchronizes threads + happens. This can be explicitly via + SYNC_THREADS, or implicitly when the value of + CONCURRENT_BIN_DISABLE changes from the previous + thread control. @@ -2308,5 +2347,99 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) + + + A7xx introduces the "resource table" which is managed by + CP_RESOURCE_LIST. It is used to synchronize BR and BV access + to resources such as LRZ buffers. + + The resource table consists of resources that are in-use by BR. + Each "resource" has a base address, which is + usually a pointer but is treated by the HW as an opaque handle, + a read/write bit, and a timestamp when it was last used. + Resources are removed from the table upon event completion when + a special CP_EVENT_WRITE::CLEAR_RENDER_RESOURCE bit is set, which + will remove all resources with a timestamp up to the current + timestamp. + + CP_RESOURCE_LIST first specifies a list of BV resources. For + each BV resource, the HW will check if there is a corresponding + BR resource in the table, and if at least one of the BV and BR + resources is marked WRITE then it will stall until the BR + resource is removed. + + It then specifies a list of BR resources. These will be added to + the resource table, unless there is an overflow in which case + the designated overflow register will have bit 0 set. Overflow + should cause the next binning pass to stall until BR is done, + effectively disabling concurrent binning. + + CP_RESOURCE_LIST must be executed by BV. BR resources are added + by BV and removed by BR. + + There is a separate table for "LRZ resources." These behave a + bit differently: specifying an LRZ resource via BV_RES_LRZ + stalls on any matching resource existing and then adds it to the + table, making it both a BV and BR resource in one. There is a + separate CLEAR_LRZ_RESOURCE bit for removing resources from the + LRZ table, and it only removes one resource given by a base + address passed to CP_EVENT_WRITE. Therefore timestamps are + unnecessary. + + + + What follows is a list of CP_BV_RESOURCE and then CP_RESOURCE_LIST_BR. + + + + + + BV resources don't go in the table. Instead CP waits until any + corresponding BR resources with the same base pointer are + finished before the packet completes. + + + + + INDIRECT resources are encoded as a 32b offset + 3b + bindless base selector. The offset is added to the given + BINDLESS_BASE pseudoregister and then the 64b value + fetched there is used as the pointer. + + + + + + + + + + + + + + + + + + + + What follows is a list of CP_BR_RESOURCE. + + + + + + + + + + + + + + + + diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py index 1d603dadfabd..2acad951f1e2 100644 --- a/drivers/gpu/drm/msm/registers/gen_header.py +++ b/drivers/gpu/drm/msm/registers/gen_header.py @@ -189,12 +189,13 @@ class Bitset(object): print(" return (struct fd_reg_pair) {") print(" .reg = (uint32_t)%s," % reg.reg_offset()) print(" .value =") + cast = "(uint64_t)" if reg.bit_size == 64 else "" for f in self.fields: if f.type in [ "address", "waddress" ]: continue else: type, val = f.ctype("fields.%s" % field_name(reg, f)) - print(" (%-40s << %2d) |" % (val, f.low)) + print(" (%s%-40s << %2d) |" % (cast, val, f.low)) value_name = "dword" if reg.bit_size == 64: value_name = "qword" @@ -264,10 +265,11 @@ class Bitset(object): (prefix, prefix, prefix, skip)) - def dump(self, is_deprecated, prefix=None): + def dump(self, is_deprecated, prefix=None, reg=None): if prefix is None: prefix = self.name - if self.reg and self.reg.bit_size == 64: + reg64 = reg and self.reg and self.reg.bit_size == 64 + if reg64: print("static inline uint32_t %s_LO(uint32_t val)\n{" % prefix) print("\treturn val;\n}") print("static inline uint32_t %s_HI(uint32_t val)\n{" % prefix) @@ -283,14 +285,17 @@ class Bitset(object): elif f.type == "boolean" or (f.type is None and f.low == f.high): tab_to("#define %s" % name, "0x%08x" % (1 << f.low)) else: - tab_to("#define %s__MASK" % name, "0x%08x" % mask(f.low, f.high)) + typespec = "ull" if reg64 else "u" + tab_to("#define %s__MASK" % name, "0x%08x%s" % (mask(f.low, f.high), typespec)) tab_to("#define %s__SHIFT" % name, "%d" % f.low) type, val = f.ctype("val") + ret_type = "uint64_t" if reg64 else "uint32_t" + cast = "(uint64_t)" if reg64 else "" - print("static inline uint32_t %s(%s val)\n{" % (name, type)) + print("static inline %s %s(%s val)\n{" % (ret_type, name, type)) if f.shr > 0: print("\tassert(!(val & 0x%x));" % mask(0, f.shr - 1)) - print("\treturn ((%s) << %s__SHIFT) & %s__MASK;\n}" % (val, name, name)) + print("\treturn (%s(%s) << %s__SHIFT) & %s__MASK;\n}" % (cast, val, name, name)) print() class Array(object): @@ -437,7 +442,7 @@ class Reg(object): print("static inline%s uint32_t REG_%s(%s) { return 0x%08x + %s; }" % (depcrstr, self.full_name, proto, offset, strides)) if self.bitset.inline: - self.bitset.dump(is_deprecated, self.full_name) + self.bitset.dump(is_deprecated, self.full_name, self) print("") def dump_pack_struct(self, is_deprecated): diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index e97e39abf3a2..12b1dba8e05d 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2867,7 +2867,9 @@ nv50_display_create(struct drm_device *dev) } /* Assign the correct format modifiers */ - if (disp->disp->object.oclass >= TU102_DISP) + if (disp->disp->object.oclass >= GB202_DISP) + nouveau_display(dev)->format_modifiers = wndwca7e_modifiers; + else if (disp->disp->object.oclass >= TU102_DISP) nouveau_display(dev)->format_modifiers = wndwc57e_modifiers; else if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h index 15f9242b72ac..5d998f0319dc 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.h +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h @@ -104,4 +104,5 @@ struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder); extern const u64 disp50xx_modifiers[]; extern const u64 disp90xx_modifiers[]; extern const u64 wndwc57e_modifiers[]; +extern const u64 wndwca7e_modifiers[]; #endif diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index e2c55f4b9c5a..ef9e410babbf 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -786,13 +786,14 @@ nv50_wndw_destroy(struct drm_plane *plane) } /* This function assumes the format has already been validated against the plane - * and the modifier was validated against the device-wides modifier list at FB + * and the modifier was validated against the device-wide modifier list at FB * creation time. */ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, u32 format, u64 modifier) { struct nouveau_drm *drm = nouveau_drm(plane->dev); + const struct drm_format_info *info = drm_format_info(format); uint8_t i; /* All chipsets can display all formats in linear layout */ @@ -800,13 +801,32 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, return true; if (drm->client.device.info.chipset < 0xc0) { - const struct drm_format_info *info = drm_format_info(format); const uint8_t kind = (modifier >> 12) & 0xff; if (!format) return false; for (i = 0; i < info->num_planes; i++) if ((info->cpp[i] != 4) && kind != 0x70) return false; + } else if (drm->client.device.info.chipset >= 0x1b2) { + const uint8_t slayout = ((modifier >> 22) & 0x1) | + ((modifier >> 25) & 0x6); + + if (!format) + return false; + + /* + * Note in practice this implies only formats where cpp is equal + * for each plane, or >= 4 for all planes, are supported. + */ + for (i = 0; i < info->num_planes; i++) { + if (((info->cpp[i] == 2) && slayout != 3) || + ((info->cpp[i] == 1) && slayout != 2) || + ((info->cpp[i] >= 4) && slayout != 1)) + return false; + + /* 24-bit not supported. It has yet another layout */ + WARN_ON(info->cpp[i] == 3); + } } return true; diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c index 0d8e9a9d1a57..2cec8cfbd546 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c @@ -179,6 +179,39 @@ wndwca7e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw) return 0; } +/**************************************************************** + * Log2(block height) ----------------------------+ * + * Page Kind ----------------------------------+ | * + * Gob Height/Page Kind Generation ------+ | | * + * Sector layout -------+ | | | * + * Compression ------+ | | | | */ +const u64 wndwca7e_modifiers[] = { /* | | | | | */ + /* 4cpp+ modifiers */ + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 0), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 1), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 2), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 3), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 4), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 5), + /* 1cpp/8bpp modifiers */ + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 0), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 1), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 2), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 3), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 4), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 5), + /* 2cpp/16bpp modifiers */ + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 0), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 1), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 2), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 3), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 4), + DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 5), + /* All formats support linear */ + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + static const struct nv50_wndw_func wndwca7e = { .acquire = wndwc37e_acquire, diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index e60f7892f5ce..a7bf539e5d86 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -482,6 +482,17 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, return 0; } +static bool +nouveau_sched_job_list_empty(struct nouveau_sched *sched) +{ + bool empty; + + spin_lock(&sched->job.list.lock); + empty = list_empty(&sched->job.list.head); + spin_unlock(&sched->job.list.lock); + + return empty; +} static void nouveau_sched_fini(struct nouveau_sched *sched) @@ -489,8 +500,7 @@ nouveau_sched_fini(struct nouveau_sched *sched) struct drm_gpu_scheduler *drm_sched = &sched->base; struct drm_sched_entity *entity = &sched->entity; - rmb(); /* for list_empty to work without lock */ - wait_event(sched->job.wq, list_empty(&sched->job.list.head)); + wait_event(sched->job.wq, nouveau_sched_job_list_empty(sched)); drm_sched_entity_fini(entity); drm_sched_fini(drm_sched); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c index 8a286a9349ac..7ce1b65e2c1c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c @@ -279,7 +279,7 @@ nvkm_fb_ctor(const struct nvkm_fb_func *func, struct nvkm_device *device, mutex_init(&fb->tags.mutex); if (func->sysmem.flush_page_init) { - fb->sysmem.flush_page = alloc_page(GFP_KERNEL | __GFP_ZERO); + fb->sysmem.flush_page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO); if (!fb->sysmem.flush_page) return -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb100.c index 1c78c8853617..170776cc82fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb100.c @@ -15,6 +15,9 @@ gb100_fb_sysmem_flush_page_init(struct nvkm_fb *fb) const u32 hshub = DRF_LO(NV_PFB_HSHUB0); struct nvkm_device *device = fb->subdev.device; + // Ensure that the address is within hardware limits + WARN_ON(fb->sysmem.flush_page_addr > DMA_BIT_MASK(52)); + nvkm_wr32(device, hshub + NV_PFB_HSHUB_PCIE_FLUSH_SYSMEM_ADDR_HI, addr_hi); nvkm_wr32(device, hshub + NV_PFB_HSHUB_PCIE_FLUSH_SYSMEM_ADDR_LO, addr_lo); nvkm_wr32(device, hshub + NV_PFB_HSHUB_EG_PCIE_FLUSH_SYSMEM_ADDR_HI, addr_hi); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb202.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb202.c index 848505026d02..a21bf19e1041 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb202.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gb202.c @@ -13,6 +13,9 @@ gb202_fb_sysmem_flush_page_init(struct nvkm_fb *fb) struct nvkm_device *device = fb->subdev.device; const u64 addr = fb->sysmem.flush_page_addr; + // Ensure that the address is within hardware limits + WARN_ON(fb->sysmem.flush_page_addr > DMA_BIT_MASK(52)); + nvkm_wr32(device, NV_PFB_FBHUB0_PCIE_FLUSH_SYSMEM_ADDR_HI, upper_32_bits(addr)); nvkm_wr32(device, NV_PFB_FBHUB0_PCIE_FLUSH_SYSMEM_ADDR_LO, lower_32_bits(addr)); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c index 07db9b397ac1..64281a09fb39 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c @@ -80,6 +80,9 @@ gf100_fb_init_page(struct nvkm_fb *fb) void gf100_fb_sysmem_flush_page_init(struct nvkm_fb *fb) { + // Ensure that the address can actually fit in the register + WARN_ON(fb->sysmem.flush_page_addr > DMA_BIT_MASK(40)); + nvkm_wr32(fb->subdev.device, 0x100c10, fb->sysmem.flush_page_addr >> 8); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gh100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gh100.c index 2d8c51f882d5..8c9394048f25 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gh100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gh100.c @@ -13,6 +13,9 @@ gh100_fb_sysmem_flush_page_init(struct nvkm_fb *fb) const u64 addr = fb->sysmem.flush_page_addr >> NV_PFB_NISO_FLUSH_SYSMEM_ADDR_SHIFT; struct nvkm_device *device = fb->subdev.device; + // Ensure that the address is within hardware limits + WARN_ON(fb->sysmem.flush_page_addr > DMA_BIT_MASK(52)); + nvkm_wr32(device, NV_PFB_FBHUB_PCIE_FLUSH_SYSMEM_ADDR_HI, upper_32_bits(addr)); nvkm_wr32(device, NV_PFB_FBHUB_PCIE_FLUSH_SYSMEM_ADDR_LO, lower_32_bits(addr)); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c index a6efbd913c13..076d968b7297 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c @@ -214,6 +214,9 @@ nv50_fb_tags(struct nvkm_fb *base) static void nv50_fb_sysmem_flush_page_init(struct nvkm_fb *fb) { + // Ensure that the address can actually fit in the register + WARN_ON(fb->sysmem.flush_page_addr > DMA_BIT_MASK(40)); + nvkm_wr32(fb->subdev.device, 0x100c08, fb->sysmem.flush_page_addr >> 8); } diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index d89761f13cd7..ca3fb186bf19 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -154,9 +154,9 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, struct drm_device *dev = helper->dev; struct omap_drm_private *priv = dev->dev_private; struct omap_fbdev *fbdev = priv->fbdev; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = NULL; union omap_gem_size gsize; - struct fb_info *fbi = NULL; struct drm_mode_fb_cmd2 mode_cmd = {0}; struct drm_gem_object *bo; dma_addr_t dma_addr; @@ -225,13 +225,6 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - dev_err(dev->dev, "failed to allocate fb info\n"); - ret = PTR_ERR(fbi); - goto fail; - } - DBG("fbi=%p, dev=%p", fbi, dev); helper->funcs = &omap_fbdev_helper_funcs; diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index ad54537d914a..76f6af819037 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -408,6 +408,19 @@ config DRM_PANEL_LG_LB035Q02 (found on the Gumstix Overo Palo35 board). To compile this driver as a module, choose M here. +config DRM_PANEL_LG_LD070WX3 + tristate "LG LD070WX3 MIPI DSI panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + select VIDEOMODE_HELPERS + help + Say Y here if you want to enable support for the LD070WX3 MIPI DSI + panel found in the NVIDIA Tegra Note 7 tablet. + + To compile this driver as a module, choose M here: the module will + be called panel-lg-ld070wx3. + config DRM_PANEL_LG_LG4573 tristate "LG4573 RGB/SPI panel" depends on OF && SPI @@ -881,16 +894,17 @@ config DRM_PANEL_SAMSUNG_S6E8AA5X01_AMS561RA01 DSI protocol with 4 lanes. config DRM_PANEL_SAMSUNG_SOFEF00 - tristate "Samsung sofef00/s6e3fc2x01 OnePlus 6/6T DSI cmd mode panels" + tristate "Samsung SOFEF00 DSI panel controller" depends on OF depends on DRM_MIPI_DSI depends on BACKLIGHT_CLASS_DEVICE select VIDEOMODE_HELPERS help Say Y or M here if you want to enable support for the Samsung AMOLED - command mode panels found in the OnePlus 6/6T smartphones. + panel SOFEF00 DDIC and connected panel. + Currently supported panels: - The panels are 2280x1080@60Hz and 2340x1080@60Hz respectively + Samsung AMS628NW01 (found in OnePlus 6, 1080x2280@60Hz) config DRM_PANEL_SEIKO_43WVF1G tristate "Seiko 43WVF1G panel" diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index 4c4b6b4aefd0..b9562a6fdcb3 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK050H3146W) += panel-leadtek-ltk050h3146w.o obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK500HD1829) += panel-leadtek-ltk500hd1829.o obj-$(CONFIG_DRM_PANEL_LINCOLNTECH_LCD197) += panel-lincolntech-lcd197.o obj-$(CONFIG_DRM_PANEL_LG_LB035Q02) += panel-lg-lb035q02.o +obj-$(CONFIG_DRM_PANEL_LG_LD070WX3) += panel-lg-ld070wx3.o obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o obj-$(CONFIG_DRM_PANEL_LG_SW43408) += panel-lg-sw43408.o obj-$(CONFIG_DRM_PANEL_MAGNACHIP_D53E6EA8966) += panel-magnachip-d53e6ea8966.o diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 944c7c70de55..415b894890ad 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1965,6 +1965,7 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a3e, &delay_200_500_e80_d50, "NV116WHM-N49"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a5d, &delay_200_500_e50, "NV116WHM-N45"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a6a, &delay_200_500_e80, "NV140WUM-N44"), + EDP_PANEL_ENTRY('B', 'O', 'E', 0x0a84, &delay_200_500_e50, "NV133WUM-T01"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0ac5, &delay_200_500_e50, "NV116WHM-N4C"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0ae8, &delay_200_500_e50_p2e80, "NV140WUM-N41"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0b09, &delay_200_500_e50_po2e200, "NV140FHM-NZ"), diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c index 7ecb81225981..947b47841b01 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c @@ -820,6 +820,204 @@ static const struct ili9881c_instr tl050hdv35_init[] = { ILI9881C_COMMAND_INSTR(0xd3, 0x39), }; +static const struct ili9881c_instr w552946aaa_init[] = { + ILI9881C_SWITCH_PAGE_INSTR(3), + ILI9881C_COMMAND_INSTR(0x01, 0x00), + ILI9881C_COMMAND_INSTR(0x02, 0x00), + ILI9881C_COMMAND_INSTR(0x03, 0x53), + ILI9881C_COMMAND_INSTR(0x04, 0x53), + ILI9881C_COMMAND_INSTR(0x05, 0x13), + ILI9881C_COMMAND_INSTR(0x06, 0x04), + ILI9881C_COMMAND_INSTR(0x07, 0x02), + ILI9881C_COMMAND_INSTR(0x08, 0x02), + ILI9881C_COMMAND_INSTR(0x09, 0x00), + ILI9881C_COMMAND_INSTR(0x0a, 0x00), + ILI9881C_COMMAND_INSTR(0x0b, 0x00), + ILI9881C_COMMAND_INSTR(0x0c, 0x00), + ILI9881C_COMMAND_INSTR(0x0d, 0x00), + ILI9881C_COMMAND_INSTR(0x0e, 0x00), + ILI9881C_COMMAND_INSTR(0x0f, 0x00), + ILI9881C_COMMAND_INSTR(0x10, 0x00), + ILI9881C_COMMAND_INSTR(0x11, 0x00), + ILI9881C_COMMAND_INSTR(0x12, 0x00), + ILI9881C_COMMAND_INSTR(0x13, 0x00), + ILI9881C_COMMAND_INSTR(0x14, 0x00), + ILI9881C_COMMAND_INSTR(0x15, 0x08), + ILI9881C_COMMAND_INSTR(0x16, 0x10), + ILI9881C_COMMAND_INSTR(0x17, 0x00), + ILI9881C_COMMAND_INSTR(0x18, 0x08), + ILI9881C_COMMAND_INSTR(0x19, 0x00), + ILI9881C_COMMAND_INSTR(0x1a, 0x00), + ILI9881C_COMMAND_INSTR(0x1b, 0x00), + ILI9881C_COMMAND_INSTR(0x1c, 0x00), + ILI9881C_COMMAND_INSTR(0x1d, 0x00), + ILI9881C_COMMAND_INSTR(0x1e, 0xc0), + ILI9881C_COMMAND_INSTR(0x1f, 0x80), + ILI9881C_COMMAND_INSTR(0x20, 0x02), + ILI9881C_COMMAND_INSTR(0x21, 0x09), + ILI9881C_COMMAND_INSTR(0x22, 0x00), + ILI9881C_COMMAND_INSTR(0x23, 0x00), + ILI9881C_COMMAND_INSTR(0x24, 0x00), + ILI9881C_COMMAND_INSTR(0x25, 0x00), + ILI9881C_COMMAND_INSTR(0x26, 0x00), + ILI9881C_COMMAND_INSTR(0x27, 0x00), + ILI9881C_COMMAND_INSTR(0x28, 0x55), + ILI9881C_COMMAND_INSTR(0x29, 0x03), + ILI9881C_COMMAND_INSTR(0x2a, 0x00), + ILI9881C_COMMAND_INSTR(0x2b, 0x00), + ILI9881C_COMMAND_INSTR(0x2c, 0x00), + ILI9881C_COMMAND_INSTR(0x2d, 0x00), + ILI9881C_COMMAND_INSTR(0x2e, 0x00), + ILI9881C_COMMAND_INSTR(0x2f, 0x00), + ILI9881C_COMMAND_INSTR(0x30, 0x00), + ILI9881C_COMMAND_INSTR(0x31, 0x00), + ILI9881C_COMMAND_INSTR(0x32, 0x00), + ILI9881C_COMMAND_INSTR(0x33, 0x00), + ILI9881C_COMMAND_INSTR(0x34, 0x04), + ILI9881C_COMMAND_INSTR(0x35, 0x05), + ILI9881C_COMMAND_INSTR(0x36, 0x05), + ILI9881C_COMMAND_INSTR(0x37, 0x00), + ILI9881C_COMMAND_INSTR(0x38, 0x3c), + ILI9881C_COMMAND_INSTR(0x39, 0x35), + ILI9881C_COMMAND_INSTR(0x3a, 0x00), + ILI9881C_COMMAND_INSTR(0x3b, 0x40), + ILI9881C_COMMAND_INSTR(0x3c, 0x00), + ILI9881C_COMMAND_INSTR(0x3d, 0x00), + ILI9881C_COMMAND_INSTR(0x3e, 0x00), + ILI9881C_COMMAND_INSTR(0x3f, 0x00), + ILI9881C_COMMAND_INSTR(0x40, 0x00), + ILI9881C_COMMAND_INSTR(0x41, 0x88), + ILI9881C_COMMAND_INSTR(0x42, 0x00), + ILI9881C_COMMAND_INSTR(0x43, 0x00), + ILI9881C_COMMAND_INSTR(0x44, 0x1f), + ILI9881C_COMMAND_INSTR(0x50, 0x01), + ILI9881C_COMMAND_INSTR(0x51, 0x23), + ILI9881C_COMMAND_INSTR(0x52, 0x45), + ILI9881C_COMMAND_INSTR(0x53, 0x67), + ILI9881C_COMMAND_INSTR(0x54, 0x89), + ILI9881C_COMMAND_INSTR(0x55, 0xab), + ILI9881C_COMMAND_INSTR(0x56, 0x01), + ILI9881C_COMMAND_INSTR(0x57, 0x23), + ILI9881C_COMMAND_INSTR(0x58, 0x45), + ILI9881C_COMMAND_INSTR(0x59, 0x67), + ILI9881C_COMMAND_INSTR(0x5a, 0x89), + ILI9881C_COMMAND_INSTR(0x5b, 0xab), + ILI9881C_COMMAND_INSTR(0x5c, 0xcd), + ILI9881C_COMMAND_INSTR(0x5d, 0xef), + ILI9881C_COMMAND_INSTR(0x5e, 0x03), + ILI9881C_COMMAND_INSTR(0x5f, 0x14), + ILI9881C_COMMAND_INSTR(0x60, 0x15), + ILI9881C_COMMAND_INSTR(0x61, 0x0c), + ILI9881C_COMMAND_INSTR(0x62, 0x0d), + ILI9881C_COMMAND_INSTR(0x63, 0x0e), + ILI9881C_COMMAND_INSTR(0x64, 0x0f), + ILI9881C_COMMAND_INSTR(0x65, 0x10), + ILI9881C_COMMAND_INSTR(0x66, 0x11), + ILI9881C_COMMAND_INSTR(0x67, 0x08), + ILI9881C_COMMAND_INSTR(0x68, 0x02), + ILI9881C_COMMAND_INSTR(0x69, 0x0a), + ILI9881C_COMMAND_INSTR(0x6a, 0x02), + ILI9881C_COMMAND_INSTR(0x6b, 0x02), + ILI9881C_COMMAND_INSTR(0x6c, 0x02), + ILI9881C_COMMAND_INSTR(0x6d, 0x02), + ILI9881C_COMMAND_INSTR(0x6e, 0x02), + ILI9881C_COMMAND_INSTR(0x6f, 0x02), + ILI9881C_COMMAND_INSTR(0x70, 0x02), + ILI9881C_COMMAND_INSTR(0x71, 0x02), + ILI9881C_COMMAND_INSTR(0x72, 0x06), + ILI9881C_COMMAND_INSTR(0x73, 0x02), + ILI9881C_COMMAND_INSTR(0x74, 0x02), + ILI9881C_COMMAND_INSTR(0x75, 0x14), + ILI9881C_COMMAND_INSTR(0x76, 0x15), + ILI9881C_COMMAND_INSTR(0x77, 0x0f), + ILI9881C_COMMAND_INSTR(0x78, 0x0e), + ILI9881C_COMMAND_INSTR(0x79, 0x0d), + ILI9881C_COMMAND_INSTR(0x7a, 0x0c), + ILI9881C_COMMAND_INSTR(0x7b, 0x11), + ILI9881C_COMMAND_INSTR(0x7c, 0x10), + ILI9881C_COMMAND_INSTR(0x7d, 0x06), + ILI9881C_COMMAND_INSTR(0x7e, 0x02), + ILI9881C_COMMAND_INSTR(0x7f, 0x0a), + ILI9881C_COMMAND_INSTR(0x80, 0x02), + ILI9881C_COMMAND_INSTR(0x81, 0x02), + ILI9881C_COMMAND_INSTR(0x82, 0x02), + ILI9881C_COMMAND_INSTR(0x83, 0x02), + ILI9881C_COMMAND_INSTR(0x84, 0x02), + ILI9881C_COMMAND_INSTR(0x85, 0x02), + ILI9881C_COMMAND_INSTR(0x86, 0x02), + ILI9881C_COMMAND_INSTR(0x87, 0x02), + ILI9881C_COMMAND_INSTR(0x88, 0x08), + ILI9881C_COMMAND_INSTR(0x89, 0x02), + ILI9881C_COMMAND_INSTR(0x8a, 0x02), + ILI9881C_SWITCH_PAGE_INSTR(4), + ILI9881C_COMMAND_INSTR(0x00, 0x80), + ILI9881C_COMMAND_INSTR(0x70, 0x00), + ILI9881C_COMMAND_INSTR(0x71, 0x00), + ILI9881C_COMMAND_INSTR(0x66, 0xfe), + ILI9881C_COMMAND_INSTR(0x82, 0x15), + ILI9881C_COMMAND_INSTR(0x84, 0x15), + ILI9881C_COMMAND_INSTR(0x85, 0x15), + ILI9881C_COMMAND_INSTR(0x3a, 0x24), + ILI9881C_COMMAND_INSTR(0x32, 0xac), + ILI9881C_COMMAND_INSTR(0x8c, 0x80), + ILI9881C_COMMAND_INSTR(0x3c, 0xf5), + ILI9881C_COMMAND_INSTR(0x88, 0x33), + ILI9881C_SWITCH_PAGE_INSTR(1), + ILI9881C_COMMAND_INSTR(0x22, 0x0a), + ILI9881C_COMMAND_INSTR(0x31, 0x00), + ILI9881C_COMMAND_INSTR(0x53, 0x78), + ILI9881C_COMMAND_INSTR(0x55, 0x7b), + ILI9881C_COMMAND_INSTR(0x60, 0x20), + ILI9881C_COMMAND_INSTR(0x61, 0x00), + ILI9881C_COMMAND_INSTR(0x62, 0x0d), + ILI9881C_COMMAND_INSTR(0x63, 0x00), + ILI9881C_COMMAND_INSTR(0xa0, 0x00), + ILI9881C_COMMAND_INSTR(0xa1, 0x10), + ILI9881C_COMMAND_INSTR(0xa2, 0x1c), + ILI9881C_COMMAND_INSTR(0xa3, 0x13), + ILI9881C_COMMAND_INSTR(0xa4, 0x15), + ILI9881C_COMMAND_INSTR(0xa5, 0x26), + ILI9881C_COMMAND_INSTR(0xa6, 0x1a), + ILI9881C_COMMAND_INSTR(0xa7, 0x1d), + ILI9881C_COMMAND_INSTR(0xa8, 0x67), + ILI9881C_COMMAND_INSTR(0xa9, 0x1c), + ILI9881C_COMMAND_INSTR(0xaa, 0x29), + ILI9881C_COMMAND_INSTR(0xab, 0x5b), + ILI9881C_COMMAND_INSTR(0xac, 0x26), + ILI9881C_COMMAND_INSTR(0xad, 0x28), + ILI9881C_COMMAND_INSTR(0xae, 0x5c), + ILI9881C_COMMAND_INSTR(0xaf, 0x30), + ILI9881C_COMMAND_INSTR(0xb0, 0x31), + ILI9881C_COMMAND_INSTR(0xb1, 0x32), + ILI9881C_COMMAND_INSTR(0xb2, 0x00), + ILI9881C_COMMAND_INSTR(0xb1, 0x2e), + ILI9881C_COMMAND_INSTR(0xb2, 0x32), + ILI9881C_COMMAND_INSTR(0xb3, 0x00), + ILI9881C_COMMAND_INSTR(0xb6, 0x02), + ILI9881C_COMMAND_INSTR(0xb7, 0x03), + ILI9881C_COMMAND_INSTR(0xc0, 0x00), + ILI9881C_COMMAND_INSTR(0xc1, 0x10), + ILI9881C_COMMAND_INSTR(0xc2, 0x1c), + ILI9881C_COMMAND_INSTR(0xc3, 0x13), + ILI9881C_COMMAND_INSTR(0xc4, 0x15), + ILI9881C_COMMAND_INSTR(0xc5, 0x26), + ILI9881C_COMMAND_INSTR(0xc6, 0x1a), + ILI9881C_COMMAND_INSTR(0xc7, 0x1d), + ILI9881C_COMMAND_INSTR(0xc8, 0x67), + ILI9881C_COMMAND_INSTR(0xc9, 0x1c), + ILI9881C_COMMAND_INSTR(0xca, 0x29), + ILI9881C_COMMAND_INSTR(0xcb, 0x5b), + ILI9881C_COMMAND_INSTR(0xcc, 0x26), + ILI9881C_COMMAND_INSTR(0xcd, 0x28), + ILI9881C_COMMAND_INSTR(0xce, 0x5c), + ILI9881C_COMMAND_INSTR(0xcf, 0x30), + ILI9881C_COMMAND_INSTR(0xd0, 0x31), + ILI9881C_COMMAND_INSTR(0xd1, 0x2e), + ILI9881C_COMMAND_INSTR(0xd2, 0x32), + ILI9881C_COMMAND_INSTR(0xd3, 0x00), + ILI9881C_SWITCH_PAGE_INSTR(0), +}; + static const struct ili9881c_instr w552946ab_init[] = { ILI9881C_SWITCH_PAGE_INSTR(3), ILI9881C_COMMAND_INSTR(0x01, 0x00), @@ -1960,6 +2158,23 @@ static const struct drm_display_mode tl050hdv35_default_mode = { .height_mm = 110, }; +static const struct drm_display_mode w552946aaa_default_mode = { + .clock = 65000, + + .hdisplay = 720, + .hsync_start = 720 + 52, + .hsync_end = 720 + 52 + 8, + .htotal = 720 + 52 + 8 + 48, + + .vdisplay = 1280, + .vsync_start = 1280 + 16, + .vsync_end = 1280 + 16 + 6, + .vtotal = 1280 + 16 + 6 + 15, + + .width_mm = 68, + .height_mm = 121, +}; + static const struct drm_display_mode w552946aba_default_mode = { .clock = 64000, @@ -2188,6 +2403,15 @@ static const struct ili9881c_desc tl050hdv35_desc = { .default_address_mode = 0x03, }; +static const struct ili9881c_desc w552946aaa_desc = { + .init = w552946aaa_init, + .init_length = ARRAY_SIZE(w552946aaa_init), + .mode = &w552946aaa_default_mode, + .mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET, + .lanes = 2, +}; + static const struct ili9881c_desc w552946aba_desc = { .init = w552946ab_init, .init_length = ARRAY_SIZE(w552946ab_init), @@ -2236,6 +2460,7 @@ static const struct of_device_id ili9881c_of_match[] = { { .compatible = "feixin,k101-im2byl02", .data = &k101_im2byl02_desc }, { .compatible = "startek,kd050hdfia020", .data = &kd050hdfia020_desc }, { .compatible = "tdo,tl050hdv35", .data = &tl050hdv35_desc }, + { .compatible = "wanchanglong,w552946aaa", .data = &w552946aaa_desc }, { .compatible = "wanchanglong,w552946aba", .data = &w552946aba_desc }, { .compatible = "ampire,am8001280g", .data = &am8001280g_desc }, { .compatible = "raspberrypi,dsi-5inch", &rpi_5inch_desc }, diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c index 5c2530598ddb..aa05316dc57b 100644 --- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c +++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c @@ -1132,22 +1132,19 @@ static int jadard_dsi_probe(struct mipi_dsi_device *dsi) dsi->lanes = desc->lanes; jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(jadard->reset)) { - DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n"); - return PTR_ERR(jadard->reset); - } + if (IS_ERR(jadard->reset)) + return dev_err_probe(&dsi->dev, PTR_ERR(jadard->reset), + "failed to get our reset GPIO\n"); jadard->vdd = devm_regulator_get(dev, "vdd"); - if (IS_ERR(jadard->vdd)) { - DRM_DEV_ERROR(&dsi->dev, "failed to get vdd regulator\n"); - return PTR_ERR(jadard->vdd); - } + if (IS_ERR(jadard->vdd)) + return dev_err_probe(&dsi->dev, PTR_ERR(jadard->vdd), + "failed to get vdd regulator\n"); jadard->vccio = devm_regulator_get(dev, "vccio"); - if (IS_ERR(jadard->vccio)) { - DRM_DEV_ERROR(&dsi->dev, "failed to get vccio regulator\n"); - return PTR_ERR(jadard->vccio); - } + if (IS_ERR(jadard->vccio)) + return dev_err_probe(&dsi->dev, PTR_ERR(jadard->vccio), + "failed to get vccio regulator\n"); ret = of_drm_get_panel_orientation(dev->of_node, &jadard->orientation); if (ret < 0) diff --git a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c index 2fc7b0779b37..893af9b16756 100644 --- a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c +++ b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c @@ -359,7 +359,7 @@ static int kingdisplay_panel_probe(struct mipi_dsi_device *dsi) dsi->lanes = 4; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | - MIPI_DSI_MODE_LPM; + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET; kingdisplay = devm_drm_panel_alloc(&dsi->dev, __typeof(*kingdisplay), base, &kingdisplay_panel_funcs, diff --git a/drivers/gpu/drm/panel/panel-lg-ld070wx3.c b/drivers/gpu/drm/panel/panel-lg-ld070wx3.c new file mode 100644 index 000000000000..00cbfc5518a5 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-lg-ld070wx3.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include +#include +#include + +#include