diff options
520 files changed, 18159 insertions, 8614 deletions
@@ -200,10 +200,11 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> Dikshita Agarwal <quic_dikshita@quicinc.com> <dikshita@codeaurora.org> -Dmitry Baryshkov <dbaryshkov@gmail.com> -Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]> -Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com> -Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com> +Dmitry Baryshkov <lumag@kernel.org> <dbaryshkov@gmail.com> +Dmitry Baryshkov <lumag@kernel.org> <[dbaryshkov@gmail.com]> +Dmitry Baryshkov <lumag@kernel.org> <dmitry_baryshkov@mentor.com> +Dmitry Baryshkov <lumag@kernel.org> <dmitry_eremin@mentor.com> +Dmitry Baryshkov <lumag@kernel.org> <dmitry.baryshkov@linaro.org> Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com> Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> @@ -323,7 +324,8 @@ Jeff Johnson <jeff.johnson@oss.qualcomm.com> <quic_jjohnson@quicinc.com> Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net> Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> -Jeffrey Hugo <quic_jhugo@quicinc.com> <jhugo@codeaurora.org> +Jeff Hugo <jeff.hugo@oss.qualcomm.com> <jhugo@codeaurora.org> +Jeff Hugo <jeff.hugo@oss.qualcomm.com> <quic_jhugo@quicinc.com> Jens Axboe <axboe@kernel.dk> <axboe@suse.de> Jens Axboe <axboe@kernel.dk> <jens.axboe@oracle.com> Jens Axboe <axboe@kernel.dk> <axboe@fb.com> @@ -613,6 +615,8 @@ Richard Leitner <richard.leitner@linux.dev> <me@g0hl1n.net> Richard Leitner <richard.leitner@linux.dev> <richard.leitner@skidata.com> Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org> Rocky Liao <quic_rjliao@quicinc.com> <rjliao@codeaurora.org> +Rodrigo Siqueira <siqueira@igalia.com> <rodrigosiqueiramelo@gmail.com> +Rodrigo Siqueira <siqueira@igalia.com> <Rodrigo.Siqueira@amd.com> Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com> Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com> Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru> diff --git a/Documentation/devicetree/bindings/display/apple,h7-display-pipe-mipi.yaml b/Documentation/devicetree/bindings/display/apple,h7-display-pipe-mipi.yaml new file mode 100644 index 000000000000..5e6da66499a5 --- /dev/null +++ b/Documentation/devicetree/bindings/display/apple,h7-display-pipe-mipi.yaml @@ -0,0 +1,83 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/apple,h7-display-pipe-mipi.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple pre-DCP display controller MIPI interface + +maintainers: + - Sasha Finkelstein <fnkl.kernel@gmail.com> + +description: + The MIPI controller part of the pre-DCP Apple display controller + +allOf: + - $ref: dsi-controller.yaml# + +properties: + compatible: + items: + - enum: + - apple,t8112-display-pipe-mipi + - apple,t8103-display-pipe-mipi + - const: apple,h7-display-pipe-mipi + + reg: + maxItems: 1 + + power-domains: + maxItems: 1 + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: Input port. Always connected to the primary controller + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Output MIPI DSI port to the panel + + required: + - port@0 + - port@1 + +required: + - compatible + - reg + - ports + +unevaluatedProperties: false + +examples: + - | + dsi@28200000 { + compatible = "apple,t8103-display-pipe-mipi", "apple,h7-display-pipe-mipi"; + reg = <0x28200000 0xc000>; + power-domains = <&ps_dispdfr_mipi>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + dfr_adp_out_mipi: endpoint { + remote-endpoint = <&dfr_adp_out_mipi>; + }; + }; + + port@1 { + reg = <1>; + + dfr_panel_in: endpoint { + remote-endpoint = <&dfr_mipi_out_panel>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/apple,h7-display-pipe.yaml b/Documentation/devicetree/bindings/display/apple,h7-display-pipe.yaml new file mode 100644 index 000000000000..102fb1804c0c --- /dev/null +++ b/Documentation/devicetree/bindings/display/apple,h7-display-pipe.yaml @@ -0,0 +1,88 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/apple,h7-display-pipe.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple pre-DCP display controller + +maintainers: + - Sasha Finkelstein <fnkl.kernel@gmail.com> + +description: + A secondary display controller used to drive the "touchbar" on + certain Apple laptops. + +properties: + compatible: + items: + - enum: + - apple,t8112-display-pipe + - apple,t8103-display-pipe + - const: apple,h7-display-pipe + + reg: + items: + - description: Primary register block, controls planes and blending + - description: + Contains other configuration registers like interrupt + and FIFO control + + reg-names: + items: + - const: be + - const: fe + + power-domains: + description: + Phandles to pmgr entries that are needed for this controller to turn on. + Aside from that, their specific functions are unknown + maxItems: 2 + + interrupts: + items: + - description: Unknown function + - description: Primary interrupt. Vsync events are reported via it + + interrupt-names: + items: + - const: be + - const: fe + + iommus: + maxItems: 1 + + port: + $ref: /schemas/graph.yaml#/properties/port + description: Output port. Always connected to apple,h7-display-pipe-mipi + +required: + - compatible + - reg + - interrupts + - port + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/apple-aic.h> + display-pipe@28200000 { + compatible = "apple,t8103-display-pipe", "apple,h7-display-pipe"; + reg = <0x28200000 0xc000>, + <0x28400000 0x4000>; + reg-names = "be", "fe"; + power-domains = <&ps_dispdfr_fe>, <&ps_dispdfr_be>; + interrupt-parent = <&aic>; + interrupts = <AIC_IRQ 502 IRQ_TYPE_LEVEL_HIGH>, + <AIC_IRQ 506 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "be", "fe"; + iommus = <&displaydfr_dart 0>; + + port { + dfr_adp_out_mipi: endpoint { + remote-endpoint = <&dfr_mipi_in_adp>; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index ffbd1dc9470e..2aab33cd0017 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -231,6 +231,7 @@ allOf: then: properties: clocks: + minItems: 7 maxItems: 7 clock-names: items: @@ -248,29 +249,12 @@ allOf: contains: enum: - qcom,msm8916-dsi-ctrl - then: - properties: - clocks: - maxItems: 6 - clock-names: - items: - - const: mdp_core - - const: iface - - const: bus - - const: byte - - const: pixel - - const: core - - - if: - properties: - compatible: - contains: - enum: - qcom,msm8953-dsi-ctrl - qcom,msm8976-dsi-ctrl then: properties: clocks: + minItems: 6 maxItems: 6 clock-names: items: @@ -291,6 +275,7 @@ allOf: then: properties: clocks: + minItems: 7 maxItems: 7 clock-names: items: @@ -311,6 +296,7 @@ allOf: then: properties: clocks: + minItems: 7 maxItems: 7 clock-names: items: @@ -328,28 +314,13 @@ allOf: contains: enum: - qcom,msm8998-dsi-ctrl - - qcom,sm6125-dsi-ctrl - - qcom,sm6350-dsi-ctrl - then: - properties: - clocks: - maxItems: 6 - clock-names: - items: - - const: byte - - const: byte_intf - - const: pixel - - const: core - - const: iface - - const: bus - - - if: - properties: - compatible: - contains: - enum: - qcom,sc7180-dsi-ctrl - qcom,sc7280-dsi-ctrl + - qcom,sdm845-dsi-ctrl + - qcom,sm6115-dsi-ctrl + - qcom,sm6125-dsi-ctrl + - qcom,sm6350-dsi-ctrl + - qcom,sm6375-dsi-ctrl - qcom,sm6150-dsi-ctrl - qcom,sm7150-dsi-ctrl - qcom,sm8150-dsi-ctrl @@ -361,6 +332,7 @@ allOf: then: properties: clocks: + minItems: 6 maxItems: 6 clock-names: items: @@ -380,6 +352,7 @@ allOf: then: properties: clocks: + minItems: 9 maxItems: 9 clock-names: items: @@ -393,27 +366,6 @@ allOf: - const: pixel - const: core - - if: - properties: - compatible: - contains: - enum: - - qcom,sdm845-dsi-ctrl - - qcom,sm6115-dsi-ctrl - - qcom,sm6375-dsi-ctrl - then: - properties: - clocks: - maxItems: 6 - clock-names: - items: - - const: byte - - const: byte_intf - - const: pixel - - const: core - - const: iface - - const: bus - unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml index 6b57ce41c95f..d0ce85a08b6d 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-common.yaml @@ -15,6 +15,8 @@ description: properties: "#clock-cells": const: 1 + description: + See include/dt-bindings/clock/qcom,dsi-phy-28nm.h for clock IDs. "#phy-cells": const: 0 diff --git a/Documentation/devicetree/bindings/display/msm/gmu.yaml b/Documentation/devicetree/bindings/display/msm/gmu.yaml index ab884e236429..4392aa7a4ffe 100644 --- a/Documentation/devicetree/bindings/display/msm/gmu.yaml +++ b/Documentation/devicetree/bindings/display/msm/gmu.yaml @@ -123,6 +123,7 @@ allOf: compatible: contains: enum: + - qcom,adreno-gmu-623.0 - qcom,adreno-gmu-635.0 - qcom,adreno-gmu-660.1 - qcom,adreno-gmu-663.0 diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml index a90a8b3f1a9e..5fac3e266703 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sa8775p-mdss.yaml @@ -52,6 +52,13 @@ patternProperties: items: - const: qcom,sa8775p-dp + "^phy@[0-9a-f]+$": + type: object + additionalProperties: true + properties: + compatible: + const: qcom,sa8775p-edp-phy + required: - compatible @@ -61,6 +68,7 @@ examples: - | #include <dt-bindings/interconnect/qcom,icc.h> #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/clock/qcom,sa8775p-dispcc.h> #include <dt-bindings/clock/qcom,sa8775p-gcc.h> #include <dt-bindings/interconnect/qcom,sa8775p-rpmh.h> #include <dt-bindings/power/qcom,rpmhpd.h> @@ -158,6 +166,26 @@ examples: }; }; + mdss0_dp0_phy: phy@aec2a00 { + compatible = "qcom,sa8775p-edp-phy"; + + reg = <0x0aec2a00 0x200>, + <0x0aec2200 0xd0>, + <0x0aec2600 0xd0>, + <0x0aec2000 0x1c8>; + + clocks = <&dispcc0 MDSS_DISP_CC_MDSS_DPTX0_AUX_CLK>, + <&dispcc0 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,sa8775p-dp"; @@ -186,9 +214,9 @@ examples: assigned-clocks = <&dispcc_mdss_dptx0_link_clk_src>, <&dispcc_mdss_dptx0_pixel0_clk_src>; - assigned-clock-parents = <&mdss0_edp_phy 0>, <&mdss0_edp_phy 1>; + assigned-clock-parents = <&mdss0_dp0_phy 0>, <&mdss0_dp0_phy 1>; - phys = <&mdss0_edp_phy>; + phys = <&mdss0_dp0_phy>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8550-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8550-mdss.yaml index 1ea50a2c7c8e..59192c59ddb9 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8550-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8550-mdss.yaml @@ -30,10 +30,14 @@ properties: maxItems: 1 interconnects: - maxItems: 2 + items: + - description: Interconnect path from mdp0 port to the data bus + - description: Interconnect path from CPU to the reg bus interconnect-names: - maxItems: 2 + items: + - const: mdp0-mem + - const: cpu-cfg patternProperties: "^display-controller@[0-9a-f]+$": @@ -91,9 +95,9 @@ examples: reg = <0x0ae00000 0x1000>; reg-names = "mdss"; - interconnects = <&mmss_noc MASTER_MDP 0 &gem_noc SLAVE_LLCC 0>, - <&mc_virt MASTER_LLCC 0 &mc_virt SLAVE_EBI1 0>; - interconnect-names = "mdp0-mem", "mdp1-mem"; + interconnects = <&mmss_noc MASTER_MDP 0 &mc_virt SLAVE_EBI1 0>, + <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_DISPLAY_CFG 0>; + interconnect-names = "mdp0-mem", "cpu-cfg"; resets = <&dispcc DISP_CC_MDSS_CORE_BCR>; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8650-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8650-mdss.yaml index 24cece1e888b..a1c53e191033 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8650-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8650-mdss.yaml @@ -29,10 +29,14 @@ properties: maxItems: 1 interconnects: - maxItems: 2 + items: + - description: Interconnect path from mdp0 port to the data bus + - description: Interconnect path from CPU to the reg bus interconnect-names: - maxItems: 2 + items: + - const: mdp0-mem + - const: cpu-cfg patternProperties: "^display-controller@[0-9a-f]+$": @@ -75,12 +79,17 @@ examples: #include <dt-bindings/clock/qcom,rpmh.h> #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/power/qcom,rpmhpd.h> + #include <dt-bindings/interconnect/qcom,sm8650-rpmh.h> display-subsystem@ae00000 { compatible = "qcom,sm8650-mdss"; reg = <0x0ae00000 0x1000>; reg-names = "mdss"; + interconnects = <&mmss_noc MASTER_MDP 0 &mc_virt SLAVE_EBI1 0>, + <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_DISPLAY_CFG 0>; + interconnect-names = "mdp0-mem", "cpu-cfg"; + resets = <&dispcc_core_bcr>; power-domains = <&dispcc_gdsc>; diff --git a/Documentation/devicetree/bindings/display/panel/apple,summit.yaml b/Documentation/devicetree/bindings/display/panel/apple,summit.yaml new file mode 100644 index 000000000000..f081755325e9 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/apple,summit.yaml @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/apple,summit.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple "Summit" display panel + +maintainers: + - Sasha Finkelstein <fnkl.kernel@gmail.com> + +description: + An OLED panel used as a touchbar on certain Apple laptops. + Contains a backlight device, which controls brightness of the panel itself. + The backlight common properties are included for this reason + +allOf: + - $ref: panel-common.yaml# + - $ref: /schemas/leds/backlight/common.yaml# + +properties: + compatible: + items: + - enum: + - apple,j293-summit + - apple,j493-summit + - const: apple,summit + + reg: + maxItems: 1 + +required: + - compatible + - reg + - max-brightness + - port + +unevaluatedProperties: false + +examples: + - | + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "apple,j293-summit", "apple,summit"; + reg = <0>; + max-brightness = <255>; + + port { + endpoint { + remote-endpoint = <&dfr_bridge_out>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple-lvds-dual-ports.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple-lvds-dual-ports.yaml index e80fc7006984..548f5ac14500 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple-lvds-dual-ports.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple-lvds-dual-ports.yaml @@ -40,6 +40,8 @@ properties: - auo,g185han01 # AU Optronics Corporation 19.0" (1280x1024) TFT LCD panel - auo,g190ean01 + # BOE AV123Z7M-N17 12.3" (1920x720) LVDS TFT LCD panel + - boe,av123z7m-n17 # Kaohsiung Opto-Electronics Inc. 10.1" WUXGA (1920 x 1200) LVDS TFT LCD panel - koe,tx26d202vm0bwa # Lincoln Technology Solutions, LCD185-101CT 10.1" TFT 1920x1200 diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index e3ee3a332bb7..b0de4fd6f3d4 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -63,6 +63,8 @@ properties: - auo,t215hvn01 # Shanghai AVIC Optoelectronics 7" 1024x600 color TFT-LCD panel - avic,tm070ddh03 + # BOE AV101HDT-a10 10.1" 1280x720 LVDS panel + - boe,av101hdt-a10 # BOE BP082WX1-100 8.2" WXGA (1280x800) LVDS panel - boe,bp082wx1-100 # BOE BP101WX1-100 10.1" WXGA (1280x800) LVDS panel diff --git a/Documentation/devicetree/bindings/display/panel/raydium,rm67200.yaml b/Documentation/devicetree/bindings/display/panel/raydium,rm67200.yaml new file mode 100644 index 000000000000..54c9c0ef45ec --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/raydium,rm67200.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/raydium,rm67200.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Raydium RM67200 based MIPI-DSI panels + +maintainers: + - Sebastian Reichel <sebastian.reichel@collabora.com> + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + items: + - enum: + - wanchanglong,w552793baa + - const: raydium,rm67200 + + reg: + maxItems: 1 + + vdd-supply: + description: 2.8V Logic voltage + + iovcc-supply: + description: 1.8V IO voltage + + vsp-supply: + description: positive 5.5V voltage + + vsn-supply: + description: negative 5.5V voltage + + backlight: true + port: true + reset-gpios: true + +required: + - compatible + - port + - reg + - reset-gpios + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + dsi { + #address-cells = <1>; + #size-cells = <0>; + panel@0 { + compatible = "wanchanglong,w552793baa", "raydium,rm67200"; + reg = <0>; + + vdd-supply = <®ulator1>; + iovcc-supply = <®ulator2>; + vsp-supply = <®ulator3>; + vsn-supply = <®ulator4>; + reset-gpios = <&gpiobank 42 GPIO_ACTIVE_LOW>; + + port { + panel0_in: endpoint { + remote-endpoint = <&dsi0_out>; + }; + }; + }; + }; +... diff --git a/Documentation/devicetree/bindings/display/panel/visionox,rm692e5.yaml b/Documentation/devicetree/bindings/display/panel/visionox,rm692e5.yaml new file mode 100644 index 000000000000..d4b4672815fe --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/visionox,rm692e5.yaml @@ -0,0 +1,77 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/visionox,rm692e5.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Visionox RM692E5 6.55" 2400x1080 120Hz MIPI-DSI Panel + +maintainers: + - Danila Tikhonov <danila@jiaxyga.com> + +description: + The Visionox RM692E5 is a generic DSI Panel IC used to control + AMOLED panels. + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + oneOf: + - enum: + - visionox,rm692e5 + - items: + - enum: + - nothing,rm692e5-spacewar + - const: visionox,rm692e5 + + reg: + maxItems: 1 + + vdd-supply: + description: 3.3V source voltage rail + + vddio-supply: + description: 1.8V I/O source voltage rail + + reset-gpios: true + port: true + +required: + - compatible + - reg + - reset-gpios + - vdd-supply + - vddio-supply + - port + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + dsi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "nothing,rm692e5-spacewar", + "visionox,rm692e5"; + reg = <0>; + + reset-gpios = <&tlmm 44 GPIO_ACTIVE_LOW>; + + vdd-supply = <&vdd_oled>; + vddio-supply = <&vdd_io_oled>; + + port { + panel_in: endpoint { + remote-endpoint = <&mdss_dsi0_out>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-vop2.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip-vop2.yaml index 46d956e63338..f546d481b7e5 100644 --- a/Documentation/devicetree/bindings/display/rockchip/rockchip-vop2.yaml +++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-vop2.yaml @@ -14,12 +14,14 @@ description: maintainers: - Sandy Huang <hjc@rock-chips.com> - Heiko Stuebner <heiko@sntech.de> + - Andy Yan <andyshrk@163.com> properties: compatible: enum: - rockchip,rk3566-vop - rockchip,rk3568-vop + - rockchip,rk3576-vop - rockchip,rk3588-vop reg: @@ -37,10 +39,21 @@ properties: - const: gamma-lut interrupts: - maxItems: 1 + minItems: 1 + maxItems: 4 description: - The VOP interrupt is shared by several interrupt sources, such as - frame start (VSYNC), line flag and other status interrupts. + For VOP version under rk3576, the interrupt is shared by several interrupt + sources, such as frame start (VSYNC), line flag and other interrupt status. + For VOP version from rk3576 there is a system interrupt for bus error, and + every video port has it's independent interrupts for vsync and other video + port related error interrupts. + + interrupt-names: + items: + - const: sys + - const: vp0 + - const: vp1 + - const: vp2 # See compatible-specific constraints below. clocks: @@ -124,43 +137,100 @@ allOf: properties: compatible: contains: - const: rockchip,rk3588-vop + enum: + - rockchip,rk3566-vop + - rockchip,rk3568-vop then: properties: clocks: - minItems: 7 + maxItems: 5 + clock-names: - minItems: 7 + maxItems: 5 + + interrupts: + maxItems: 1 + + interrupt-names: false ports: required: - port@0 - port@1 - port@2 - - port@3 + + rockchip,vo1-grf: false + rockchip,vop-grf: false + rockchip,pmu: false required: - rockchip,grf - - rockchip,vo1-grf - - rockchip,vop-grf - - rockchip,pmu - else: + - if: + properties: + compatible: + contains: + enum: + - rockchip,rk3576-vop + then: properties: + clocks: + maxItems: 5 + + clock-names: + maxItems: 5 + + interrupts: + minItems: 4 + + interrupt-names: + minItems: 4 + + ports: + required: + - port@0 + - port@1 + - port@2 + rockchip,vo1-grf: false rockchip,vop-grf: false - rockchip,pmu: false + required: + - rockchip,grf + - rockchip,pmu + + - if: + properties: + compatible: + contains: + const: rockchip,rk3588-vop + then: + properties: clocks: - maxItems: 5 + minItems: 7 + maxItems: 9 + clock-names: - maxItems: 5 + minItems: 7 + maxItems: 9 + + interrupts: + maxItems: 1 + + interrupt-names: false ports: required: - port@0 - port@1 - port@2 + - port@3 + + required: + - rockchip,grf + - rockchip,vo1-grf + - rockchip,vop-grf + - rockchip,pmu additionalProperties: false @@ -188,6 +258,7 @@ examples: "dclk_vp1", "dclk_vp2"; power-domains = <&power RK3568_PD_VO>; + rockchip,grf = <&grf>; iommus = <&vop_mmu>; vop_out: ports { #address-cells = <1>; diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml index 735c7f06c24e..fc8e82cb28a9 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml @@ -25,6 +25,7 @@ properties: - renesas,r9a07g044-mali - renesas,r9a07g054-mali - rockchip,px30-mali + - rockchip,rk3562-mali - rockchip,rk3568-mali - rockchip,rk3576-mali - const: arm,mali-bifrost # Mali Bifrost GPU model/revision is fully discoverable diff --git a/Documentation/gpu/amdgpu/amdgpu-glossary.rst b/Documentation/gpu/amdgpu/amdgpu-glossary.rst index 00a47ebb0b0f..1e9283e076ba 100644 --- a/Documentation/gpu/amdgpu/amdgpu-glossary.rst +++ b/Documentation/gpu/amdgpu/amdgpu-glossary.rst @@ -12,6 +12,9 @@ we have a dedicated glossary for Display Core at The number of CUs that are active on the system. The number of active CUs may be less than SE * SH * CU depending on the board configuration. + CE + Constant Engine + CP Command Processor @@ -68,6 +71,9 @@ we have a dedicated glossary for Display Core at IB Indirect Buffer + IMU + Integrated Management Unit (Power Management support) + IP Intellectual Property blocks @@ -80,6 +86,12 @@ we have a dedicated glossary for Display Core at KIQ Kernel Interface Queue + MC + Memory Controller + + ME + MicroEngine (Graphics) + MEC MicroEngine Compute @@ -92,6 +104,9 @@ we have a dedicated glossary for Display Core at MQD Memory Queue Descriptor + PFP + Pre-Fetch Parser (Graphics) + PPLib PowerPlay Library - PowerPlay is the power management component. @@ -99,7 +114,10 @@ we have a dedicated glossary for Display Core at Platform Security Processor RLC - RunList Controller + RunList Controller. This name is a remnant of past ages and doesn't have + much meaning today. It's a group of general-purpose helper engines for + the GFX block. It's involved in GFX power management and SR-IOV, among + other things. SDMA System DMA @@ -110,14 +128,35 @@ we have a dedicated glossary for Display Core at SH SHader array - SMU - System Management Unit + SMU/SMC + System Management Unit / System Management Controller + + SRLC + Save/Restore List Control + + SRLG + Save/Restore List GPM_MEM + + SRLS + Save/Restore List SRM_MEM SS Spread Spectrum + TA + Trusted Application + + TOC + Table of Contents + + UVD + Unified Video Decoder + VCE Video Compression Engine VCN Video Codec Next + + VPE + Video Processing Engine diff --git a/Documentation/gpu/amdgpu/display/dc-glossary.rst b/Documentation/gpu/amdgpu/display/dc-glossary.rst index 0b0ffd428dd2..7dc034e9e586 100644 --- a/Documentation/gpu/amdgpu/display/dc-glossary.rst +++ b/Documentation/gpu/amdgpu/display/dc-glossary.rst @@ -167,9 +167,6 @@ consider asking in the amdgfx and update this page. MALL Memory Access at Last Level - MC - Memory Controller - MPC/MPCC Multiple pipes and plane combine @@ -232,6 +229,3 @@ consider asking in the amdgfx and update this page. VRR Variable Refresh Rate - - UVD - Unified Video Decoder diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst index cb9ae282771c..94f93fd3b8a0 100644 --- a/Documentation/gpu/drm-internals.rst +++ b/Documentation/gpu/drm-internals.rst @@ -208,6 +208,13 @@ follows: ``CONFIG_VIRTIO_UML`` and ``CONFIG_UML_PCI_OVER_VIRTIO`` are not included in it because they are only required for User Mode Linux. +KUnit Coverage Rules +~~~~~~~~~~~~~~~~~~~~ + +KUnit support is gradually added to the DRM framework and helpers. There's no +general requirement for the framework and helpers to have KUnit tests at the +moment. However, patches that are affecting a function or helper already +covered by KUnit tests must provide tests if the change calls for one. Legacy Support Code =================== diff --git a/MAINTAINERS b/MAINTAINERS index cddcb097f7f3..0fa53d0bb346 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1046,14 +1046,14 @@ F: drivers/crypto/ccp/hsti.* AMD DISPLAY CORE M: Harry Wentland <harry.wentland@amd.com> M: Leo Li <sunpeng.li@amd.com> -M: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com> +R: Rodrigo Siqueira <siqueira@igalia.com> L: amd-gfx@lists.freedesktop.org S: Supported T: git https://gitlab.freedesktop.org/agd5f/linux.git F: drivers/gpu/drm/amd/display/ AMD DISPLAY CORE - DML -M: Chaitanya Dhere <chaitanya.dhere@amd.com> +M: Austin Zheng <austin.zheng@amd.com> M: Jun Lei <jun.lei@amd.com> S: Supported F: drivers/gpu/drm/amd/display/dc/dml/ @@ -7149,6 +7149,14 @@ S: Supported T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/sun4i/sun8i* +DRM DRIVER FOR APPLE TOUCH BARS +M: Aun-Ali Zaidi <admin@kodeit.net> +M: Aditya Garg <gargaditya08@live.com> +L: dri-devel@lists.freedesktop.org +S: Maintained +T: git https://gitlab.freedesktop.org/drm/misc/kernel.git +F: drivers/gpu/drm/tiny/appletbdrm.c + DRM DRIVER FOR ARM PL111 CLCD M: Linus Walleij <linus.walleij@linaro.org> S: Maintained @@ -7347,7 +7355,8 @@ T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/mgag200/ DRM DRIVER FOR MI0283QT -S: Orphan +M: Alex Lanzano <lanzano.alex@gmail.com> +S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: Documentation/devicetree/bindings/display/multi-inno,mi0283qt.txt F: drivers/gpu/drm/tiny/mi0283qt.c @@ -7380,7 +7389,7 @@ F: include/uapi/drm/msm_drm.h DRM DRIVER for Qualcomm display hardware M: Rob Clark <robdclark@gmail.com> M: Abhinav Kumar <quic_abhinavk@quicinc.com> -M: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> +M: Dmitry Baryshkov <lumag@kernel.org> R: Sean Paul <sean@poorly.run> R: Marijn Suijten <marijn.suijten@somainline.org> L: linux-arm-msm@vger.kernel.org @@ -7392,6 +7401,7 @@ T: git https://gitlab.freedesktop.org/drm/msm.git F: Documentation/devicetree/bindings/display/msm/ F: drivers/gpu/drm/ci/xfails/msm* F: drivers/gpu/drm/msm/ +F: include/dt-bindings/clock/qcom,dsi-phy-28nm.h F: include/uapi/drm/msm_drm.h DRM DRIVER FOR NOVATEK NT35510 PANELS @@ -7449,7 +7459,8 @@ F: Documentation/devicetree/bindings/display/bridge/ps8640.yaml F: drivers/gpu/drm/bridge/parade-ps8640.c DRM DRIVER FOR PERVASIVE DISPLAYS REPAPER PANELS -S: Orphan +M: Alex Lanzano <lanzano.alex@gmail.com> +S: Maintained T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: Documentation/devicetree/bindings/display/repaper.txt F: drivers/gpu/drm/tiny/repaper.c @@ -7826,6 +7837,22 @@ F: drivers/gpu/host1x/ F: include/linux/host1x.h F: include/uapi/drm/tegra_drm.h +DRM DRIVERS FOR PRE-DCP APPLE DISPLAY OUTPUT +M: Sasha Finkelstein <fnkl.kernel@gmail.com> +R: Janne Grunau <j@jannau.net> +L: dri-devel@lists.freedesktop.org +L: asahi@lists.linux.dev +S: Maintained +W: https://asahilinux.org +B: https://github.com/AsahiLinux/linux/issues +C: irc://irc.oftc.net/asahi-dev +T: git https://gitlab.freedesktop.org/drm/misc/kernel.git +F: Documentation/devicetree/bindings/display/apple,h7-display-pipe-mipi.yaml +F: Documentation/devicetree/bindings/display/apple,h7-display-pipe.yaml +F: Documentation/devicetree/bindings/display/panel/apple,summit.yaml +F: drivers/gpu/drm/adp/ +F: drivers/gpu/drm/panel/panel-summit.c + DRM DRIVERS FOR RENESAS R-CAR M: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com> M: Tomi Valkeinen <tomi.valkeinen+renesas@ideasonboard.com> @@ -19425,7 +19452,7 @@ F: drivers/clk/qcom/ F: include/dt-bindings/clock/qcom,* QUALCOMM CLOUD AI (QAIC) DRIVER -M: Jeffrey Hugo <quic_jhugo@quicinc.com> +M: Jeff Hugo <jeff.hugo@oss.qualcomm.com> R: Carl Vanderlip <quic_carlv@quicinc.com> L: linux-arm-msm@vger.kernel.org L: dri-devel@lists.freedesktop.org @@ -19655,7 +19682,6 @@ F: drivers/net/wireless/quantenna RADEON and AMDGPU DRM DRIVERS M: Alex Deucher <alexander.deucher@amd.com> M: Christian König <christian.koenig@amd.com> -M: Xinhui Pan <Xinhui.Pan@amd.com> L: amd-gfx@lists.freedesktop.org S: Supported B: https://gitlab.freedesktop.org/drm/amd/-/issues diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index aa07e67400ef..da1ac89bb78f 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -349,8 +349,6 @@ static irqreturn_t mailbox_irq_handler(int irq, void *p) trace_mbox_irq_handle(MAILBOX_NAME, irq); /* Schedule a rx_work to call the callback functions */ queue_work(mb_chann->work_q, &mb_chann->rx_work); - /* Clear IOHUB register */ - mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0); return IRQ_HANDLED; } @@ -367,6 +365,9 @@ static void mailbox_rx_worker(struct work_struct *rx_work) return; } +again: + mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0); + while (1) { /* * If return is 0, keep consuming next message, until there is @@ -380,10 +381,18 @@ static void mailbox_rx_worker(struct work_struct *rx_work) if (unlikely(ret)) { MB_ERR(mb_chann, "Unexpected ret %d, disable irq", ret); WRITE_ONCE(mb_chann->bad_state, true); - disable_irq(mb_chann->msix_irq); - break; + return; } } + + /* + * The hardware will not generate interrupt if firmware creates a new + * response right after driver clears interrupt register. Check + * the interrupt register to make sure there is not any new response + * before exiting. + */ + if (mailbox_reg_read(mb_chann, mb_chann->iohub_int_addr)) + goto again; } int xdna_mailbox_send_msg(struct mailbox_channel *mb_chann, diff --git a/drivers/base/component.c b/drivers/base/component.c index 5d10600bbc25..a482708566bc 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -569,6 +569,20 @@ void component_master_del(struct device *parent, } EXPORT_SYMBOL_GPL(component_master_del); +bool component_master_is_bound(struct device *parent, + const struct component_master_ops *ops) +{ + struct aggregate_device *adev; + + guard(mutex)(&component_mutex); + adev = __aggregate_find(parent, ops); + if (!adev) + return 0; + + return adev->bound; +} +EXPORT_SYMBOL_GPL(component_master_is_bound); + static void component_unbind(struct component *component, struct aggregate_device *adev, void *data) { diff --git a/drivers/bus/mhi/host/boot.c b/drivers/bus/mhi/host/boot.c index c8e48f621a8c..efa3b6dddf4d 100644 --- a/drivers/bus/mhi/host/boot.c +++ b/drivers/bus/mhi/host/boot.c @@ -608,7 +608,7 @@ fw_load_ready_state: return; error_ready_state: - if (fw_load_type == MHI_FW_LOAD_FBC) { + if (mhi_cntrl->fbc_image) { mhi_free_bhie_table(mhi_cntrl, mhi_cntrl->fbc_image); mhi_cntrl->fbc_image = NULL; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 693f338e5b28..1be14d8634f4 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -448,6 +448,8 @@ source "drivers/gpu/drm/mcde/Kconfig" source "drivers/gpu/drm/tidss/Kconfig" +source "drivers/gpu/drm/adp/Kconfig" + source "drivers/gpu/drm/xlnx/Kconfig" source "drivers/gpu/drm/gud/Kconfig" diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 186b611a88b5..ed54a546bbe2 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -207,6 +207,7 @@ obj-y += mxsfb/ obj-y += tiny/ obj-$(CONFIG_DRM_PL111) += pl111/ obj-$(CONFIG_DRM_TVE200) += tve200/ +obj-$(CONFIG_DRM_ADP) += adp/ obj-$(CONFIG_DRM_XEN) += xen/ obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/ obj-$(CONFIG_DRM_LIMA) += lima/ diff --git a/drivers/gpu/drm/adp/Kconfig b/drivers/gpu/drm/adp/Kconfig new file mode 100644 index 000000000000..9fcc27eb200d --- /dev/null +++ b/drivers/gpu/drm/adp/Kconfig @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT +config DRM_ADP + tristate "DRM Support for pre-DCP Apple display controllers" + depends on DRM && OF && ARM64 + depends on ARCH_APPLE || COMPILE_TEST + select DRM_KMS_HELPER + select DRM_BRIDGE_CONNECTOR + select DRM_DISPLAY_HELPER + select DRM_KMS_DMA_HELPER + select DRM_GEM_DMA_HELPER + select DRM_PANEL_BRIDGE + select VIDEOMODE_HELPERS + select DRM_MIPI_DSI + help + Chose this option if you have an Apple Arm laptop with a touchbar. + + If M is selected, this module will be called adpdrm. diff --git a/drivers/gpu/drm/adp/Makefile b/drivers/gpu/drm/adp/Makefile new file mode 100644 index 000000000000..8e7b618edd35 --- /dev/null +++ b/drivers/gpu/drm/adp/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only OR MIT + +adpdrm-y := adp_drv.o +adpdrm-mipi-y := adp-mipi.o +obj-$(CONFIG_DRM_ADP) += adpdrm.o adpdrm-mipi.o diff --git a/drivers/gpu/drm/adp/adp-mipi.c b/drivers/gpu/drm/adp/adp-mipi.c new file mode 100644 index 000000000000..ad80542b60ed --- /dev/null +++ b/drivers/gpu/drm/adp/adp-mipi.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/component.h> +#include <linux/iopoll.h> +#include <linux/of.h> +#include <linux/platform_device.h> + +#include <drm/drm_bridge.h> +#include <drm/drm_mipi_dsi.h> + +#define DSI_GEN_HDR 0x6c +#define DSI_GEN_PLD_DATA 0x70 + +#define DSI_CMD_PKT_STATUS 0x74 + +#define GEN_PLD_R_EMPTY BIT(4) +#define GEN_PLD_W_FULL BIT(3) +#define GEN_PLD_W_EMPTY BIT(2) +#define GEN_CMD_FULL BIT(1) +#define GEN_CMD_EMPTY BIT(0) +#define GEN_RD_CMD_BUSY BIT(6) +#define CMD_PKT_STATUS_TIMEOUT_US 20000 + +struct adp_mipi_drv_private { + struct mipi_dsi_host dsi; + struct drm_bridge bridge; + struct drm_bridge *next_bridge; + void __iomem *mipi; +}; + +#define mipi_to_adp(x) container_of(x, struct adp_mipi_drv_private, dsi) + +static int adp_dsi_gen_pkt_hdr_write(struct adp_mipi_drv_private *adp, u32 hdr_val) +{ + int ret; + u32 val, mask; + + ret = readl_poll_timeout(adp->mipi + DSI_CMD_PKT_STATUS, + val, !(val & GEN_CMD_FULL), 1000, + CMD_PKT_STATUS_TIMEOUT_US); + if (ret) { + dev_err(adp->dsi.dev, "failed to get available command FIFO\n"); + return ret; + } + + writel(hdr_val, adp->mipi + DSI_GEN_HDR); + + mask = GEN_CMD_EMPTY | GEN_PLD_W_EMPTY; + ret = readl_poll_timeout(adp->mipi + DSI_CMD_PKT_STATUS, + val, (val & mask) == mask, + 1000, CMD_PKT_STATUS_TIMEOUT_US); + if (ret) { + dev_err(adp->dsi.dev, "failed to write command FIFO\n"); + return ret; + } + + return 0; +} + +static int adp_dsi_write(struct adp_mipi_drv_private *adp, + const struct mipi_dsi_packet *packet) +{ + const u8 *tx_buf = packet->payload; + int len = packet->payload_length, pld_data_bytes = sizeof(u32), ret; + __le32 word; + u32 val; + + while (len) { + if (len < pld_data_bytes) { + word = 0; + memcpy(&word, tx_buf, len); + writel(le32_to_cpu(word), adp->mipi + DSI_GEN_PLD_DATA); + len = 0; + } else { + memcpy(&word, tx_buf, pld_data_bytes); + writel(le32_to_cpu(word), adp->mipi + DSI_GEN_PLD_DATA); + tx_buf += pld_data_bytes; + len -= pld_data_bytes; + } + + ret = readl_poll_timeout(adp->mipi + DSI_CMD_PKT_STATUS, + val, !(val & GEN_PLD_W_FULL), 1000, + CMD_PKT_STATUS_TIMEOUT_US); + if (ret) { + dev_err(adp->dsi.dev, + "failed to get available write payload FIFO\n"); + return ret; + } + } + + word = 0; + memcpy(&word, packet->header, sizeof(packet->header)); + return adp_dsi_gen_pkt_hdr_write(adp, le32_to_cpu(word)); +} + +static int adp_dsi_read(struct adp_mipi_drv_private *adp, + const struct mipi_dsi_msg *msg) +{ + int i, j, ret, len = msg->rx_len; + u8 *buf = msg->rx_buf; + u32 val; + + /* Wait end of the read operation */ + ret = readl_poll_timeout(adp->mipi + DSI_CMD_PKT_STATUS, + val, !(val & GEN_RD_CMD_BUSY), + 1000, CMD_PKT_STATUS_TIMEOUT_US); + if (ret) { + dev_err(adp->dsi.dev, "Timeout during read operation\n"); + return ret; + } + + for (i = 0; i < len; i += 4) { + /* Read fifo must not be empty before all bytes are read */ + ret = readl_poll_timeout(adp->mipi + DSI_CMD_PKT_STATUS, + val, !(val & GEN_PLD_R_EMPTY), + 1000, CMD_PKT_STATUS_TIMEOUT_US); + if (ret) { + dev_err(adp->dsi.dev, "Read payload FIFO is empty\n"); + return ret; + } + + val = readl(adp->mipi + DSI_GEN_PLD_DATA); + for (j = 0; j < 4 && j + i < len; j++) + buf[i + j] = val >> (8 * j); + } + + return ret; +} + +static ssize_t adp_dsi_host_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg) +{ + struct adp_mipi_drv_private *adp = mipi_to_adp(host); + struct mipi_dsi_packet packet; + int ret, nb_bytes; + + ret = mipi_dsi_create_packet(&packet, msg); + if (ret) { + dev_err(adp->dsi.dev, "failed to create packet: %d\n", ret); + return ret; + } + + ret = adp_dsi_write(adp, &packet); + if (ret) + return ret; + + if (msg->rx_buf && msg->rx_len) { + ret = adp_dsi_read(adp, msg); + if (ret) + return ret; + nb_bytes = msg->rx_len; + } else { + nb_bytes = packet.size; + } + + return nb_bytes; +} + +static int adp_dsi_bind(struct device *dev, struct device *master, void *data) +{ + return 0; +} + +static void adp_dsi_unbind(struct device *dev, struct device *master, void *data) +{ +} + +static const struct component_ops adp_dsi_component_ops = { + .bind = adp_dsi_bind, + .unbind = adp_dsi_unbind, +}; + +static int adp_dsi_host_attach(struct mipi_dsi_host *host, + struct mipi_dsi_device *dev) +{ + struct adp_mipi_drv_private *adp = mipi_to_adp(host); + struct drm_bridge *next; + int ret; + + next = devm_drm_of_get_bridge(adp->dsi.dev, adp->dsi.dev->of_node, 1, 0); + if (IS_ERR(next)) + return PTR_ERR(next); + + adp->next_bridge = next; + + drm_bridge_add(&adp->bridge); + + ret = component_add(host->dev, &adp_dsi_component_ops); + if (ret) { + pr_err("failed to add dsi_host component: %d\n", ret); + drm_bridge_remove(&adp->bridge); + return ret; + } + + return 0; +} + +static int adp_dsi_host_detach(struct mipi_dsi_host *host, + struct mipi_dsi_device *dev) +{ + struct adp_mipi_drv_private *adp = mipi_to_adp(host); + + component_del(host->dev, &adp_dsi_component_ops); + drm_bridge_remove(&adp->bridge); + return 0; +} + +static const struct mipi_dsi_host_ops adp_dsi_host_ops = { + .transfer = adp_dsi_host_transfer, + .attach = adp_dsi_host_attach, + .detach = adp_dsi_host_detach, +}; + +static int adp_dsi_bridge_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct adp_mipi_drv_private *adp = + container_of(bridge, struct adp_mipi_drv_private, bridge); + + return drm_bridge_attach(bridge->encoder, adp->next_bridge, bridge, flags); +} + +static const struct drm_bridge_funcs adp_dsi_bridge_funcs = { + .attach = adp_dsi_bridge_attach, +}; + +static int adp_mipi_probe(struct platform_device *pdev) +{ + struct adp_mipi_drv_private *adp; + + adp = devm_kzalloc(&pdev->dev, sizeof(*adp), GFP_KERNEL); + if (!adp) + return -ENOMEM; + + adp->mipi = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(adp->mipi)) { + dev_err(&pdev->dev, "failed to map mipi mmio"); + return PTR_ERR(adp->mipi); + } + + adp->dsi.dev = &pdev->dev; + adp->dsi.ops = &adp_dsi_host_ops; + adp->bridge.funcs = &adp_dsi_bridge_funcs; + adp->bridge.of_node = pdev->dev.of_node; + adp->bridge.type = DRM_MODE_CONNECTOR_DSI; + dev_set_drvdata(&pdev->dev, adp); + return mipi_dsi_host_register(&adp->dsi); +} + +static void adp_mipi_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct adp_mipi_drv_private *adp = dev_get_drvdata(dev); + + mipi_dsi_host_unregister(&adp->dsi); +} + +static const struct of_device_id adp_mipi_of_match[] = { + { .compatible = "apple,h7-display-pipe-mipi", }, + { }, +}; +MODULE_DEVICE_TABLE(of, adp_mipi_of_match); + +static struct platform_driver adp_mipi_platform_driver = { + .driver = { + .name = "adp-mipi", + .of_match_table = adp_mipi_of_match, + }, + .probe = adp_mipi_probe, + .remove = adp_mipi_remove, +}; + +module_platform_driver(adp_mipi_platform_driver); + +MODULE_DESCRIPTION("Apple Display Pipe MIPI driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/adp/adp_drv.c b/drivers/gpu/drm/adp/adp_drv.c new file mode 100644 index 000000000000..0eeb9e5fab26 --- /dev/null +++ b/drivers/gpu/drm/adp/adp_drv.c @@ -0,0 +1,612 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/component.h> +#include <linux/iopoll.h> +#include <linux/of.h> +#include <linux/platform_device.h> + +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_bridge_connector.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_dma_helper.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_dma_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_of.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_vblank.h> + +#define ADP_INT_STATUS 0x34 +#define ADP_INT_STATUS_INT_MASK 0x7 +#define ADP_INT_STATUS_VBLANK 0x1 +#define ADP_CTRL 0x100 +#define ADP_CTRL_VBLANK_ON 0x12 +#define ADP_CTRL_FIFO_ON 0x601 +#define ADP_SCREEN_SIZE 0x0c +#define ADP_SCREEN_HSIZE GENMASK(15, 0) +#define ADP_SCREEN_VSIZE GENMASK(31, 16) + +#define ADBE_FIFO 0x10c0 +#define ADBE_FIFO_SYNC 0xc0000000 + +#define ADBE_BLEND_BYPASS 0x2020 +#define ADBE_BLEND_EN1 0x2028 +#define ADBE_BLEND_EN2 0x2074 +#define ADBE_BLEND_EN3 0x202c +#define ADBE_BLEND_EN4 0x2034 +#define ADBE_MASK_BUF 0x2200 + +#define ADBE_SRC_START 0x4040 +#define ADBE_SRC_SIZE 0x4048 +#define ADBE_DST_START 0x4050 +#define ADBE_DST_SIZE 0x4054 +#define ADBE_STRIDE 0x4038 +#define ADBE_FB_BASE 0x4030 + +#define ADBE_LAYER_EN1 0x4020 +#define ADBE_LAYER_EN2 0x4068 +#define ADBE_LAYER_EN3 0x40b4 +#define ADBE_LAYER_EN4 0x40f4 +#define ADBE_SCALE_CTL 0x40ac +#define ADBE_SCALE_CTL_BYPASS 0x100000 + +#define ADBE_LAYER_CTL 0x1038 +#define ADBE_LAYER_CTL_ENABLE 0x10000 + +#define ADBE_PIX_FMT 0x402c +#define ADBE_PIX_FMT_XRGB32 0x53e4001 + +static int adp_open(struct inode *inode, struct file *filp) +{ + /* + * The modesetting driver does not check the non-desktop connector + * property and keeps the device open and locked. If the touchbar daemon + * opens the device first, modesetting breaks the whole X session. + * Simply refuse to open the device for X11 server processes as + * workaround. + */ + if (current->comm[0] == 'X') + return -EBUSY; + + return drm_open(inode, filp); +} + +static const struct file_operations adp_fops = { + .owner = THIS_MODULE, + .open = adp_open, + .release = drm_release, + .unlocked_ioctl = drm_ioctl, + .compat_ioctl = drm_compat_ioctl, + .poll = drm_poll, + .read = drm_read, + .llseek = noop_llseek, + .mmap = drm_gem_mmap, + .fop_flags = FOP_UNSIGNED_OFFSET, + DRM_GEM_DMA_UNMAPPED_AREA_FOPS +}; + +static int adp_drm_gem_dumb_create(struct drm_file *file_priv, + struct drm_device *drm, + struct drm_mode_create_dumb *args) +{ + args->height = ALIGN(args->height, 64); + args->size = args->pitch * args->height; + + return drm_gem_dma_dumb_create_internal(file_priv, drm, args); +} + +static const struct drm_driver adp_driver = { + .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, + .fops = &adp_fops, + DRM_GEM_DMA_DRIVER_OPS_VMAP_WITH_DUMB_CREATE(adp_drm_gem_dumb_create), + .name = "adp", + .desc = "Apple Display Pipe DRM Driver", + .major = 0, + .minor = 1, +}; + +struct adp_drv_private { + struct drm_device drm; + struct drm_crtc crtc; + struct drm_encoder *encoder; + struct drm_connector *connector; + struct drm_bridge *next_bridge; + void __iomem *be; + void __iomem *fe; + u32 *mask_buf; + u64 mask_buf_size; + dma_addr_t mask_iova; + int be_irq; + int fe_irq; + spinlock_t irq_lock; + struct drm_pending_vblank_event *event; +}; + +#define to_adp(x) container_of(x, struct adp_drv_private, drm) +#define crtc_to_adp(x) container_of(x, struct adp_drv_private, crtc) + +static int adp_plane_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *new_plane_state; + struct drm_crtc_state *crtc_state; + + new_plane_state = drm_atomic_get_new_plane_state(state, plane); + + if (!new_plane_state->crtc) + return 0; + + crtc_state = drm_atomic_get_crtc_state(state, new_plane_state->crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); + + return drm_atomic_helper_check_plane_state(new_plane_state, + crtc_state, + DRM_PLANE_NO_SCALING, + DRM_PLANE_NO_SCALING, + true, true); +} + +static void adp_plane_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct adp_drv_private *adp; + struct drm_rect src_rect; + struct drm_gem_dma_object *obj; + struct drm_framebuffer *fb; + struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); + u32 src_pos, src_size, dst_pos, dst_size; + + if (!plane || !new_state) + return; + + fb = new_state->fb; + if (!fb) + return; + adp = to_adp(plane->dev); + + drm_rect_fp_to_int(&src_rect, &new_state->src); + src_pos = src_rect.x1 << 16 | src_rect.y1; + dst_pos = new_state->dst.x1 << 16 | new_state->dst.y1; + src_size = drm_rect_width(&src_rect) << 16 | drm_rect_height(&src_rect); + dst_size = drm_rect_width(&new_state->dst) << 16 | + drm_rect_height(&new_state->dst); + writel(src_pos, adp->be + ADBE_SRC_START); + writel(src_size, adp->be + ADBE_SRC_SIZE); + writel(dst_pos, adp->be + ADBE_DST_START); + writel(dst_size, adp->be + ADBE_DST_SIZE); + writel(fb->pitches[0], adp->be + ADBE_STRIDE); + obj = drm_fb_dma_get_gem_obj(fb, 0); + if (obj) + writel(obj->dma_addr + fb->offsets[0], adp->be + ADBE_FB_BASE); + + writel(BIT(0), adp->be + ADBE_LAYER_EN1); + writel(BIT(0), adp->be + ADBE_LAYER_EN2); + writel(BIT(0), adp->be + ADBE_LAYER_EN3); + writel(BIT(0), adp->be + ADBE_LAYER_EN4); + writel(ADBE_SCALE_CTL_BYPASS, adp->be + ADBE_SCALE_CTL); + writel(ADBE_LAYER_CTL_ENABLE | BIT(0), adp->be + ADBE_LAYER_CTL); + writel(ADBE_PIX_FMT_XRGB32, adp->be + ADBE_PIX_FMT); +} + +static void adp_plane_atomic_disable(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct adp_drv_private *adp = to_adp(plane->dev); + + writel(0x0, adp->be + ADBE_LAYER_EN1); + writel(0x0, adp->be + ADBE_LAYER_EN2); + writel(0x0, adp->be + ADBE_LAYER_EN3); + writel(0x0, adp->be + ADBE_LAYER_EN4); + writel(ADBE_LAYER_CTL_ENABLE, adp->be + ADBE_LAYER_CTL); +} + +static const struct drm_plane_helper_funcs adp_plane_helper_funcs = { + .atomic_check = adp_plane_atomic_check, + .atomic_update = adp_plane_atomic_update, + .atomic_disable = adp_plane_atomic_disable, + DRM_GEM_SHADOW_PLANE_HELPER_FUNCS +}; + +static const struct drm_plane_funcs adp_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + DRM_GEM_SHADOW_PLANE_FUNCS +}; + +static const u32 plane_formats[] = { + DRM_FORMAT_XRGB8888, +}; + +#define ALL_CRTCS 1 + +static struct drm_plane *adp_plane_new(struct adp_drv_private *adp) +{ + struct drm_device *drm = &adp->drm; + struct drm_plane *plane; + + plane = __drmm_universal_plane_alloc(drm, sizeof(struct drm_plane), 0, + ALL_CRTCS, &adp_plane_funcs, + plane_formats, ARRAY_SIZE(plane_formats), + NULL, DRM_PLANE_TYPE_PRIMARY, "plane"); + if (!plane) { + drm_err(drm, "failed to allocate plane"); + return ERR_PTR(-ENOMEM); + } + + drm_plane_helper_add(plane, &adp_plane_helper_funcs); + return plane; +} + +static void adp_enable_vblank(struct adp_drv_private *adp) +{ + u32 cur_ctrl; + + writel(ADP_INT_STATUS_INT_MASK, adp->fe + ADP_INT_STATUS); + + cur_ctrl = readl(adp->fe + ADP_CTRL); + writel(cur_ctrl | ADP_CTRL_VBLANK_ON, adp->fe + ADP_CTRL); +} + +static int adp_crtc_enable_vblank(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct adp_drv_private *adp = to_adp(dev); + + adp_enable_vblank(adp); + + return 0; +} + +static void adp_disable_vblank(struct adp_drv_private *adp) +{ + u32 cur_ctrl; + + cur_ctrl = readl(adp->fe + ADP_CTRL); + writel(cur_ctrl & ~ADP_CTRL_VBLANK_ON, adp->fe + ADP_CTRL); + writel(ADP_INT_STATUS_INT_MASK, adp->fe + ADP_INT_STATUS); +} + +static void adp_crtc_disable_vblank(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct adp_drv_private *adp = to_adp(dev); + + adp_disable_vblank(adp); +} + +static void adp_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct adp_drv_private *adp = crtc_to_adp(crtc); + + writel(BIT(0), adp->be + ADBE_BLEND_EN2); + writel(BIT(4), adp->be + ADBE_BLEND_EN1); + writel(BIT(0), adp->be + ADBE_BLEND_EN3); + writel(BIT(0), adp->be + ADBE_BLEND_BYPASS); + writel(BIT(0), adp->be + ADBE_BLEND_EN4); +} + +static void adp_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + struct adp_drv_private *adp = crtc_to_adp(crtc); + struct drm_crtc_state *old_state = drm_atomic_get_old_crtc_state(state, crtc); + + drm_atomic_helper_disable_planes_on_crtc(old_state, false); + + writel(0x0, adp->be + ADBE_BLEND_EN2); + writel(0x0, adp->be + ADBE_BLEND_EN1); + writel(0x0, adp->be + ADBE_BLEND_EN3); + writel(0x0, adp->be + ADBE_BLEND_BYPASS); + writel(0x0, adp->be + ADBE_BLEND_EN4); + drm_crtc_vblank_off(crtc); +} + +static void adp_crtc_atomic_flush(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + u32 frame_num = 1; + struct adp_drv_private *adp = crtc_to_adp(crtc); + struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc); + u64 new_size = ALIGN(new_state->mode.hdisplay * + new_state->mode.vdisplay * 4, PAGE_SIZE); + + if (new_size != adp->mask_buf_size) { + if (adp->mask_buf) + dma_free_coherent(crtc->dev->dev, adp->mask_buf_size, + adp->mask_buf, adp->mask_iova); + adp->mask_buf = NULL; + if (new_size != 0) { + adp->mask_buf = dma_alloc_coherent(crtc->dev->dev, new_size, + &adp->mask_iova, GFP_KERNEL); + memset(adp->mask_buf, 0xFF, new_size); + writel(adp->mask_iova, adp->be + ADBE_MASK_BUF); + } + adp->mask_buf_size = new_size; + } + writel(ADBE_FIFO_SYNC | frame_num, adp->be + ADBE_FIFO); + //FIXME: use adbe flush interrupt + spin_lock_irq(&crtc->dev->event_lock); + if (crtc->state->event) { + drm_crtc_vblank_get(crtc); + adp->event = crtc->state->event; + } + crtc->state->event = NULL; + spin_unlock_irq(&crtc->dev->event_lock); +} + +static const struct drm_crtc_funcs adp_crtc_funcs = { + .destroy = drm_crtc_cleanup, + .set_config = drm_atomic_helper_set_config, + .page_flip = drm_atomic_helper_page_flip, + .reset = drm_atomic_helper_crtc_reset, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, + .enable_vblank = adp_crtc_enable_vblank, + .disable_vblank = adp_crtc_disable_vblank, +}; + + +static const struct drm_crtc_helper_funcs adp_crtc_helper_funcs = { + .atomic_enable = adp_crtc_atomic_enable, + .atomic_disable = adp_crtc_atomic_disable, + .atomic_flush = adp_crtc_atomic_flush, +}; + +static int adp_setup_crtc(struct adp_drv_private *adp) +{ + struct drm_device *drm = &adp->drm; + struct drm_plane *primary; + int ret; + + primary = adp_plane_new(adp); + if (IS_ERR(primary)) + return PTR_ERR(primary); + + ret = drm_crtc_init_with_planes(drm, &adp->crtc, primary, + NULL, &adp_crtc_funcs, NULL); + if (ret) + return ret; + + drm_crtc_helper_add(&adp->crtc, &adp_crtc_helper_funcs); + return 0; +} + +static const struct drm_mode_config_funcs adp_mode_config_funcs = { + .fb_create = drm_gem_fb_create_with_dirty, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static int adp_setup_mode_config(struct adp_drv_private *adp) +{ + struct drm_device *drm = &adp->drm; + int ret; + u32 size; + + ret = drmm_mode_config_init(drm); + if (ret) + return ret; + + /* + * Query screen size restrict the frame buffer size to the screen size + * aligned to the next multiple of 64. This is not necessary but can be + * used as simple check for non-desktop devices. + * Xorg's modesetting driver does not care about the connector + * "non-desktop" property. The max frame buffer width or height can be + * easily checked and a device can be reject if the max width/height is + * smaller than 120 for example. + * Any touchbar daemon is not limited by this small framebuffer size. + */ + size = readl(adp->fe + ADP_SCREEN_SIZE); + + drm->mode_config.min_width = 32; + drm->mode_config.min_height = 32; + drm->mode_config.max_width = ALIGN(FIELD_GET(ADP_SCREEN_HSIZE, size), 64); + drm->mode_config.max_height = ALIGN(FIELD_GET(ADP_SCREEN_VSIZE, size), 64); + drm->mode_config.preferred_depth = 24; + drm->mode_config.prefer_shadow = 0; + drm->mode_config.funcs = &adp_mode_config_funcs; + + ret = adp_setup_crtc(adp); + if (ret) { + drm_err(drm, "failed to create crtc"); + return ret; + } + + adp->encoder = drmm_plain_encoder_alloc(drm, NULL, DRM_MODE_ENCODER_DSI, NULL); + if (IS_ERR(adp->encoder)) { + drm_err(drm, "failed to init encoder"); + return PTR_ERR(adp->encoder); + } + adp->encoder->possible_crtcs = ALL_CRTCS; + + ret = drm_bridge_attach(adp->encoder, adp->next_bridge, NULL, + DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (ret) { + drm_err(drm, "failed to init bridge chain"); + return ret; + } + + adp->connector = drm_bridge_connector_init(drm, adp->encoder); + if (IS_ERR(adp->connector)) + return PTR_ERR(adp->connector); + + drm_connector_attach_encoder(adp->connector, adp->encoder); + + ret = drm_vblank_init(drm, drm->mode_config.num_crtc); + if (ret < 0) { + drm_err(drm, "failed to initialize vblank"); + return ret; + } + + drm_mode_config_reset(drm); + + return 0; +} + +static int adp_parse_of(struct platform_device *pdev, struct adp_drv_private *adp) +{ + struct device *dev = &pdev->dev; + + adp->be = devm_platform_ioremap_resource_byname(pdev, "be"); + if (IS_ERR(adp->be)) { + dev_err(dev, "failed to map display backend mmio"); + return PTR_ERR(adp->be); + } + + adp->fe = devm_platform_ioremap_resource_byname(pdev, "fe"); + if (IS_ERR(adp->fe)) { + dev_err(dev, "failed to map display pipe mmio"); + return PTR_ERR(adp->fe); + } + + adp->be_irq = platform_get_irq_byname(pdev, "be"); + if (adp->be_irq < 0) + return adp->be_irq; + + adp->fe_irq = platform_get_irq_byname(pdev, "fe"); + if (adp->fe_irq < 0) + return adp->fe_irq; + + return 0; +} + +static irqreturn_t adp_fe_irq(int irq, void *arg) +{ + struct adp_drv_private *adp = (struct adp_drv_private *)arg; + u32 int_status; + u32 int_ctl; + + spin_lock(&adp->irq_lock); + + int_status = readl(adp->fe + ADP_INT_STATUS); + if (int_status & ADP_INT_STATUS_VBLANK) { + drm_crtc_handle_vblank(&adp->crtc); + spin_lock(&adp->crtc.dev->event_lock); + if (adp->event) { + int_ctl = readl(adp->fe + ADP_CTRL); + if ((int_ctl & 0xF00) == 0x600) { + drm_crtc_send_vblank_event(&adp->crtc, adp->event); + adp->event = NULL; + drm_crtc_vblank_put(&adp->crtc); + } + } + spin_unlock(&adp->crtc.dev->event_lock); + } + + writel(int_status, adp->fe + ADP_INT_STATUS); + + spin_unlock(&adp->irq_lock); + + return IRQ_HANDLED; +} + +static int adp_drm_bind(struct device *dev) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct adp_drv_private *adp = to_adp(drm); + int err; + + adp_disable_vblank(adp); + writel(ADP_CTRL_FIFO_ON | ADP_CTRL_VBLANK_ON, adp->fe + ADP_CTRL); + + adp->next_bridge = drmm_of_get_bridge(&adp->drm, dev->of_node, 0, 0); + if (IS_ERR(adp->next_bridge)) { + dev_err(dev, "failed to find next bridge"); + return PTR_ERR(adp->next_bridge); + } + + err = adp_setup_mode_config(adp); + if (err < 0) + return err; + + err = request_irq(adp->fe_irq, adp_fe_irq, 0, "adp-fe", adp); + if (err) + return err; + + err = drm_dev_register(&adp->drm, 0); + if (err) + return err; + + return 0; +} + +static void adp_drm_unbind(struct device *dev) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct adp_drv_private *adp = to_adp(drm); + + drm_dev_unregister(drm); + drm_atomic_helper_shutdown(drm); + free_irq(adp->fe_irq, adp); +} + +static const struct component_master_ops adp_master_ops = { + .bind = adp_drm_bind, + .unbind = adp_drm_unbind, +}; + +static int compare_dev(struct device *dev, void *data) +{ + return dev->of_node == data; +} + +static int adp_probe(struct platform_device *pdev) +{ + struct device_node *port; + struct component_match *match = NULL; + struct adp_drv_private *adp; + int err; + + adp = devm_drm_dev_alloc(&pdev->dev, &adp_driver, struct adp_drv_private, drm); + if (IS_ERR(adp)) + return PTR_ERR(adp); + + spin_lock_init(&adp->irq_lock); + + dev_set_drvdata(&pdev->dev, &adp->drm); + + err = adp_parse_of(pdev, adp); + if (err < 0) + return err; + + port = of_graph_get_remote_node(pdev->dev.of_node, 0, 0); + if (!port) + return -ENODEV; + + drm_of_component_match_add(&pdev->dev, &match, compare_dev, port); + of_node_put(port); + + return component_master_add_with_match(&pdev->dev, &adp_master_ops, match); +} + +static void adp_remove(struct platform_device *pdev) +{ + component_master_del(&pdev->dev, &adp_master_ops); + dev_set_drvdata(&pdev->dev, NULL); +} + +static const struct of_device_id adp_of_match[] = { + { .compatible = "apple,h7-display-pipe", }, + { }, +}; +MODULE_DEVICE_TABLE(of, adp_of_match); + +static struct platform_driver adp_platform_driver = { + .driver = { + .name = "adp", + .of_match_table = adp_of_match, + }, + .probe = adp_probe, + .remove = adp_remove, +}; + +module_platform_driver(adp_platform_driver); + +MODULE_DESCRIPTION("Apple Display Pipe DRM driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2b1990ea9639..2a9a41f4e748 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1192,6 +1192,7 @@ struct amdgpu_device { bool debug_use_vram_fw_buf; bool debug_enable_ras_aca; bool debug_exp_resets; + bool debug_disable_gpu_ring_reset; bool enforce_isolation[MAX_XCP]; /* Added this mutex for cleaner shader isolation between GFX and compute processes */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c index d11593cd1922..ffd4c64e123c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c @@ -392,6 +392,9 @@ static void aca_banks_generate_cper(struct amdgpu_device *adev, struct aca_bank_node *node; struct aca_bank *bank; + if (!adev->cper.enabled) + return; + if (!banks || !count) { dev_warn(adev->dev, "fail to generate cper records\n"); return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h index b84a3489b116..6f62e5d80ed6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h @@ -76,6 +76,12 @@ struct ras_query_context; #define mmSMNAID_XCD1_MCA_SMU 0x38430400 /* SMN AID XCD1 */ #define mmSMNXCD_XCD0_MCA_SMU 0x40430400 /* SMN XCD XCD0 */ +#define ACA_BANK_ERR_CE_DE_DECODE(bank) \ + ((ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) || \ + ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS])) ? \ + ACA_ERROR_TYPE_DEFERRED : \ + ACA_ERROR_TYPE_CE) + enum aca_reg_idx { ACA_REG_IDX_CTL = 0, ACA_REG_IDX_STATUS = 1, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index deb0785350e8..4926996f94da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -579,7 +579,7 @@ static int acp_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool acp_is_idle(void *handle) +static bool acp_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index b8d4e07d2043..b7f8f2ff143d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -394,6 +394,10 @@ static int amdgpu_atif_query_backlight_caps(struct amdgpu_atif *atif) characteristics.max_input_signal; atif->backlight_caps.ac_level = characteristics.ac_level; atif->backlight_caps.dc_level = characteristics.dc_level; + atif->backlight_caps.data_points = characteristics.number_of_points; + memcpy(atif->backlight_caps.luminance_data, + characteristics.data_points, + sizeof(atif->backlight_caps.luminance_data)); out: kfree(info); return err; @@ -1277,11 +1281,7 @@ void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps) { struct amdgpu_atif *atif = &amdgpu_acpi_priv.atif; - caps->caps_valid = atif->backlight_caps.caps_valid; - caps->min_input_signal = atif->backlight_caps.min_input_signal; - caps->max_input_signal = atif->backlight_caps.max_input_signal; - caps->ac_level = atif->backlight_caps.ac_level; - caps->dc_level = atif->backlight_caps.dc_level; + memcpy(caps, &atif->backlight_caps, sizeof(*caps)); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 0312231b703e..4cec3a873995 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -555,48 +555,6 @@ out_put: return r; } -uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst, - struct amdgpu_device *src) -{ - struct amdgpu_device *peer_adev = src; - struct amdgpu_device *adev = dst; - int ret = amdgpu_xgmi_get_hops_count(adev, peer_adev); - - if (ret < 0) { - DRM_ERROR("amdgpu: failed to get xgmi hops count between node %d and %d. ret = %d\n", - adev->gmc.xgmi.physical_node_id, - peer_adev->gmc.xgmi.physical_node_id, ret); - ret = 0; - } - return (uint8_t)ret; -} - -int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst, - struct amdgpu_device *src, - bool is_min) -{ - struct amdgpu_device *adev = dst, *peer_adev; - int num_links; - - if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2)) - return 0; - - if (src) - peer_adev = src; - - /* num links returns 0 for indirect peers since indirect route is unknown. */ - num_links = is_min ? 1 : amdgpu_xgmi_get_num_links(adev, peer_adev); - if (num_links < 0) { - DRM_ERROR("amdgpu: failed to get xgmi num links between node %d and %d. ret = %d\n", - adev->gmc.xgmi.physical_node_id, - peer_adev->gmc.xgmi.physical_node_id, num_links); - num_links = 0; - } - - /* Aldebaran xGMI DPM is defeatured so assume x16 x 25Gbps for bandwidth. */ - return (num_links * 16 * 25000)/BITS_PER_BYTE; -} - int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min) { int num_lanes_shift = (is_min ? ffs(adev->pm.pcie_mlw_mask) : diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 236b73e283e8..b6ca41859b53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -193,7 +193,7 @@ int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data); #if IS_ENABLED(CONFIG_HSA_AMD) bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm); struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f); -int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo); +void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo); int amdgpu_amdkfd_evict_userptr(struct mmu_interval_notifier *mni, unsigned long cur_seq, struct kgd_mem *mem); int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo, @@ -213,9 +213,8 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) } static inline -int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo) +void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo) { - return 0; } static inline @@ -255,11 +254,6 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd, uint64_t *bo_size, void *metadata_buffer, size_t buffer_size, uint32_t *metadata_size, uint32_t *flags, int8_t *xcp_id); -uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct amdgpu_device *dst, - struct amdgpu_device *src); -int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst, - struct amdgpu_device *src, - bool is_min); int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min); int amdgpu_amdkfd_send_close_event_drain_irq(struct amdgpu_device *adev, uint32_t *payload); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c index 8dfdb18197c4..6e861d08d044 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c @@ -193,4 +193,5 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = { .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c index 9abf29b58ac7..c820418e8ccd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c @@ -419,5 +419,6 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = { .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v9_hqd_reset + .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c index e2ae714a700f..0c0998477598 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c @@ -509,6 +509,17 @@ static uint32_t kgd_gfx_v9_4_3_clear_address_watch(struct amdgpu_device *adev, return 0; } +static uint32_t kgd_gfx_v9_4_3_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + uint32_t reg_offset = get_sdma_rlc_reg_offset(adev, engine, queue); + uint32_t status = RREG32(regSDMA_RLC0_CONTEXT_STATUS + reg_offset); + uint32_t doorbell_off = RREG32(regSDMA_RLC0_DOORBELL_OFFSET + reg_offset); + bool is_active = !!REG_GET_FIELD(status, SDMA_RLC0_CONTEXT_STATUS, SELECTED); + + return is_active ? doorbell_off >> 2 : 0; +} + const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = { .program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_gfx_v9_4_3_set_pasid_vmid_mapping, @@ -543,5 +554,6 @@ const struct kfd2kgd_calls gc_9_4_3_kfd2kgd = { .set_address_watch = kgd_gfx_v9_4_3_set_address_watch, .clear_address_watch = kgd_gfx_v9_4_3_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v9_hqd_reset + .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_4_3_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c index 62176d607bef..2887b6f3eaa2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c @@ -1084,6 +1084,12 @@ uint64_t kgd_gfx_v10_hqd_reset(struct amdgpu_device *adev, return 0; } +uint32_t kgd_gfx_v10_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + return 0; +} + const struct kfd2kgd_calls gfx_v10_kfd2kgd = { .program_sh_mem_settings = kgd_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping, @@ -1112,5 +1118,6 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = { .build_grace_period_packet_info = kgd_gfx_v10_build_grace_period_packet_info, .program_trap_handler_settings = program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v10_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v10_hqd_reset + .hqd_reset = kgd_gfx_v10_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v10_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h index 9efd2dd4fdd7..db577c2a847a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.h @@ -65,3 +65,5 @@ uint64_t kgd_gfx_v10_hqd_reset(struct amdgpu_device *adev, uint32_t queue_id, uint32_t inst, unsigned int utimeout); +uint32_t kgd_gfx_v10_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index c718bedda0ca..ac9ad505f9d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -682,5 +682,6 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = { .set_address_watch = kgd_gfx_v10_set_address_watch, .clear_address_watch = kgd_gfx_v10_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v10_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v10_hqd_reset + .hqd_reset = kgd_gfx_v10_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v10_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c index a4ba49cb22db..e0e6a6a49d90 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c @@ -800,6 +800,12 @@ static uint64_t kgd_gfx_v11_hqd_reset(struct amdgpu_device *adev, return 0; } +static uint32_t kgd_gfx_v11_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + return 0; +} + const struct kfd2kgd_calls gfx_v11_kfd2kgd = { .program_sh_mem_settings = program_sh_mem_settings_v11, .set_pasid_vmid_mapping = set_pasid_vmid_mapping_v11, @@ -824,5 +830,6 @@ const struct kfd2kgd_calls gfx_v11_kfd2kgd = { .set_address_watch = kgd_gfx_v11_set_address_watch, .clear_address_watch = kgd_gfx_v11_clear_address_watch, .hqd_get_pq_addr = kgd_gfx_v11_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v11_hqd_reset + .hqd_reset = kgd_gfx_v11_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v11_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c index 0dfe7093bd8a..6f0dc23c901b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c @@ -361,6 +361,12 @@ static uint32_t kgd_gfx_v12_clear_address_watch(struct amdgpu_device *adev, return 0; } +static uint32_t kgd_gfx_v12_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) +{ + return 0; +} + const struct kfd2kgd_calls gfx_v12_kfd2kgd = { .init_interrupts = init_interrupts_v12, .hqd_dump = hqd_dump_v12, @@ -374,4 +380,5 @@ const struct kfd2kgd_calls gfx_v12_kfd2kgd = { .set_wave_launch_mode = kgd_gfx_v12_set_wave_launch_mode, .set_address_watch = kgd_gfx_v12_set_address_watch, .clear_address_watch = kgd_gfx_v12_clear_address_watch, + .hqd_sdma_get_doorbell = kgd_gfx_v12_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index 441568163e20..84135eb90660 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -1131,9 +1131,6 @@ uint64_t kgd_gfx_v9_hqd_get_pq_addr(struct amdgpu_device *adev, uint32_t low, high; uint64_t queue_addr = 0; - if (!amdgpu_gpu_recovery) - return 0; - kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst); amdgpu_gfx_rlc_enter_safe_mode(adev, inst); @@ -1182,9 +1179,6 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev, uint32_t low, high, pipe_reset_data = 0; uint64_t queue_addr = 0; - if (!amdgpu_gpu_recovery) - return 0; - kgd_gfx_v9_acquire_queue(adev, pipe_id, queue_id, inst); amdgpu_gfx_rlc_enter_safe_mode(adev, inst); @@ -1229,6 +1223,13 @@ unlock_out: return queue_addr; } +uint32_t kgd_gfx_v9_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue) + +{ + return 0; +} + const struct kfd2kgd_calls gfx_v9_kfd2kgd = { .program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings, .set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping, @@ -1258,5 +1259,6 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = { .get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy, .program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings, .hqd_get_pq_addr = kgd_gfx_v9_hqd_get_pq_addr, - .hqd_reset = kgd_gfx_v9_hqd_reset + .hqd_reset = kgd_gfx_v9_hqd_reset, + .hqd_sdma_get_doorbell = kgd_gfx_v9_hqd_sdma_get_doorbell }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h index b6a91a552aa4..90c8fa13d519 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h @@ -111,3 +111,5 @@ uint64_t kgd_gfx_v9_hqd_reset(struct amdgpu_device *adev, uint32_t queue_id, uint32_t inst, unsigned int utimeout); +uint32_t kgd_gfx_v9_hqd_sdma_get_doorbell(struct amdgpu_device *adev, + int engine, int queue); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index ea3f7ee18923..2ac6d4fa0601 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -370,40 +370,32 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, return 0; } -int amdgpu_amdkfd_remove_fence_on_pt_pd_bos(struct amdgpu_bo *bo) +/** + * amdgpu_amdkfd_remove_all_eviction_fences - Remove all eviction fences + * @bo: the BO where to remove the evictions fences from. + * + * This functions should only be used on release when all references to the BO + * are already dropped. We remove the eviction fence from the private copy of + * the dma_resv object here since that is what is used during release to + * determine of the BO is idle or not. + */ +void amdgpu_amdkfd_remove_all_eviction_fences(struct amdgpu_bo *bo) { - struct amdgpu_bo *root = bo; - struct amdgpu_vm_bo_base *vm_bo; - struct amdgpu_vm *vm; - struct amdkfd_process_info *info; - struct amdgpu_amdkfd_fence *ef; - int ret; - - /* we can always get vm_bo from root PD bo.*/ - while (root->parent) - root = root->parent; + struct dma_resv *resv = &bo->tbo.base._resv; + struct dma_fence *fence, *stub; + struct dma_resv_iter cursor; - vm_bo = root->vm_bo; - if (!vm_bo) - return 0; - - vm = vm_bo->vm; - if (!vm) - return 0; - - info = vm->process_info; - if (!info || !info->eviction_fence) - return 0; + dma_resv_assert_held(resv); - ef = container_of(dma_fence_get(&info->eviction_fence->base), - struct amdgpu_amdkfd_fence, base); - - BUG_ON(!dma_resv_trylock(bo->tbo.base.resv)); - ret = amdgpu_amdkfd_remove_eviction_fence(bo, ef); - dma_resv_unlock(bo->tbo.base.resv); + stub = dma_fence_get_stub(); + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) { + if (!to_amdgpu_amdkfd_fence(fence)) + continue; - dma_fence_put(&ef->base); - return ret; + dma_resv_replace_fences(resv, fence->context, stub, + DMA_RESV_USAGE_BOOKKEEP); + } + dma_fence_put(stub); } static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain, @@ -603,12 +595,6 @@ kfd_mem_dmamap_dmabuf(struct kfd_mem_attachment *attachment) { struct ttm_operation_ctx ctx = {.interruptible = true}; struct amdgpu_bo *bo = attachment->bo_va->base.bo; - int ret; - - amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU); - ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (ret) - return ret; amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT); return ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c index 20c474a32852..3f291b30b79f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c @@ -57,6 +57,8 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev, enum amdgpu_cper_type type, enum cper_error_severity sev) { + char record_id[16]; + hdr->signature[0] = 'C'; hdr->signature[1] = 'P'; hdr->signature[2] = 'E'; @@ -71,7 +73,13 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev, amdgpu_cper_get_timestamp(&hdr->timestamp); - snprintf(hdr->record_id, 8, "%d", atomic_inc_return(&adev->cper.unique_id)); + snprintf(record_id, 9, "%d:%X", + (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ? + adev->smuio.funcs->get_socket_id(adev) : + 0, + atomic_inc_return(&adev->cper.unique_id)); + memcpy(hdr->record_id, record_id, 8); + snprintf(hdr->platform_id, 16, "0x%04X:0x%04X", adev->pdev->vendor, adev->pdev->device); /* pmfw version should be part of creator_id according to CPER spec */ @@ -112,18 +120,15 @@ static int amdgpu_cper_entry_fill_section_desc(struct amdgpu_device *adev, section_desc->revision_major = CPER_SEC_MAJOR_REV_22; section_desc->sec_offset = section_offset; section_desc->sec_length = section_length; - section_desc->valid_bits.fru_id = 1; section_desc->valid_bits.fru_text = 1; section_desc->flag_bits.primary = 1; section_desc->severity = sev; section_desc->sec_type = sec_type; - if (adev->smuio.funcs && - adev->smuio.funcs->get_socket_id) - snprintf(section_desc->fru_text, 20, "OAM%d", - adev->smuio.funcs->get_socket_id(adev)); - /* TODO: fru_id is 16 bytes in CPER spec, but driver defines it as 20 bytes */ - snprintf(section_desc->fru_id, 16, "%llx", adev->unique_id); + snprintf(section_desc->fru_text, 20, "OAM%d", + (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ? + adev->smuio.funcs->get_socket_id(adev) : + 0); if (bp_threshold) section_desc->flag_bits.exceed_err_threshold = 1; @@ -304,6 +309,7 @@ int amdgpu_cper_generate_ue_record(struct amdgpu_device *adev, return ret; amdgpu_cper_ring_write(ring, fatal, fatal->record_length); + kfree(fatal); return 0; } @@ -326,6 +332,7 @@ int amdgpu_cper_generate_bp_threshold_record(struct amdgpu_device *adev) return ret; amdgpu_cper_ring_write(ring, bp_threshold, bp_threshold->record_length); + kfree(bp_threshold); return 0; } @@ -376,7 +383,7 @@ int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev, amdgpu_cper_entry_fill_hdr(adev, corrected, AMDGPU_CPER_TYPE_RUNTIME, sev); - /* Combine CE and UE in cper record */ + /* Combine CE and DE in cper record */ list_for_each_entry(node, &banks->list, node) { bank = &node->bank; reg_data[CPER_ACA_REG_CTL_LO] = lower_32_bits(bank->regs[ACA_REG_IDX_CTL]); @@ -402,6 +409,7 @@ int amdgpu_cper_generate_ce_records(struct amdgpu_device *adev, } amdgpu_cper_ring_write(ring, corrected, corrected->record_length); + kfree(corrected); return 0; } @@ -538,15 +546,23 @@ static int amdgpu_cper_ring_init(struct amdgpu_device *adev) int amdgpu_cper_init(struct amdgpu_device *adev) { + int r; + if (!amdgpu_aca_is_enabled(adev)) return 0; + r = amdgpu_cper_ring_init(adev); + if (r) { + dev_err(adev->dev, "failed to initialize cper ring, r = %d\n", r); + return r; + } + mutex_init(&adev->cper.cper_lock); adev->cper.enabled = true; adev->cper.max_count = CPER_MAX_ALLOWED_COUNT; - return amdgpu_cper_ring_init(adev); + return 0; } int amdgpu_cper_fini(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 824f9da5b6ce..7b50741dc097 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -364,5 +364,9 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check, dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT, amdgpu_devcoredump_read, amdgpu_devcoredump_free); + + drm_info(dev, "AMDGPU device coredump file has been created\n"); + drm_info(dev, "Check your /sys/class/drm/card%d/device/devcoredump/data\n", + dev->primary->index); } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 17e5967bfa60..9e9fec5b52de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1662,6 +1662,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev) if (amdgpu_sriov_vf(adev)) return 0; + /* resizing on Dell G5 SE platforms causes problems with runtime pm */ + if ((amdgpu_runtime_pm != 0) && + adev->pdev->vendor == PCI_VENDOR_ID_ATI && + adev->pdev->device == 0x731f && + adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL) + return 0; + /* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */ if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR)) DRM_WARN("System can't access extended configuration space, please check!!\n"); @@ -3098,7 +3105,8 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) amdgpu_fru_get_product_info(adev); - r = amdgpu_cper_init(adev); + if (!amdgpu_sriov_vf(adev) || amdgpu_sriov_ras_cper_en(adev)) + r = amdgpu_cper_init(adev); init_failed: @@ -4332,10 +4340,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, * for throttling interrupt) = 60 seconds. */ ratelimit_state_init(&adev->throttling_logging_rs, (60 - 1) * HZ, 1); - ratelimit_state_init(&adev->virt.ras_telemetry_rs, 5 * HZ, 1); ratelimit_set_flags(&adev->throttling_logging_rs, RATELIMIT_MSG_ON_RELEASE); - ratelimit_set_flags(&adev->virt.ras_telemetry_rs, RATELIMIT_MSG_ON_RELEASE); /* Registers mapping */ /* TODO: block userspace mapping of io register */ @@ -4367,7 +4373,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, return -ENOMEM; /* detect hw virtualization here */ - amdgpu_detect_virtualization(adev); + amdgpu_virt_init(adev); amdgpu_device_get_pcie_info(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 1819166cb4cf..ce08c428ba4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -137,6 +137,7 @@ enum AMDGPU_DEBUG_MASK { AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3), AMDGPU_DEBUG_ENABLE_RAS_ACA = BIT(4), AMDGPU_DEBUG_ENABLE_EXP_RESETS = BIT(5), + AMDGPU_DEBUG_DISABLE_GPU_RING_RESET = BIT(6), }; unsigned int amdgpu_vram_limit = UINT_MAX; @@ -2223,6 +2224,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev) pr_info("debug: enable experimental reset features\n"); adev->debug_exp_resets = true; } + + if (amdgpu_debug_mask & AMDGPU_DEBUG_DISABLE_GPU_RING_RESET) { + pr_info("debug: ring reset disabled\n"); + adev->debug_disable_gpu_ring_reset = true; + } } static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags) @@ -2557,7 +2563,6 @@ static int amdgpu_pmops_freeze(struct device *dev) int r; r = amdgpu_device_suspend(drm_dev, true); - adev->in_s4 = false; if (r) return r; @@ -2569,8 +2574,13 @@ static int amdgpu_pmops_freeze(struct device *dev) static int amdgpu_pmops_thaw(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_resume(drm_dev, true); + r = amdgpu_device_resume(drm_dev, true); + adev->in_s4 = false; + + return r; } static int amdgpu_pmops_poweroff(struct device *dev) @@ -2583,6 +2593,9 @@ static int amdgpu_pmops_poweroff(struct device *dev) static int amdgpu_pmops_restore(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + adev->in_s4 = false; return amdgpu_device_resume(drm_dev, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c index 89109eb2ce16..1ae88c459da5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c @@ -31,6 +31,7 @@ #define FRU_EEPROM_MADDR_6 0x60000 #define FRU_EEPROM_MADDR_8 0x80000 +#define FRU_EEPROM_MADDR_INV 0xFFFFF static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr) { @@ -104,6 +105,10 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev, u32 *fru_addr) if (fru_addr) *fru_addr = FRU_EEPROM_MADDR_8; return true; + case IP_VERSION(13, 0, 12): + if (fru_addr) + *fru_addr = FRU_EEPROM_MADDR_INV; + return true; default: return false; } @@ -120,6 +125,10 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev) if (!is_fru_eeprom_supported(adev, &fru_addr)) return 0; + /* FRU data avaialble, but no direct EEPROM access */ + if (fru_addr == FRU_EEPROM_MADDR_INV) + return 0; + if (!adev->fru_info) { adev->fru_info = kzalloc(sizeof(*adev->fru_info), GFP_KERNEL); if (!adev->fru_info) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index b9bd6654f317..a194bf3347cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -1665,24 +1665,19 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev, } mutex_lock(&adev->enforce_isolation_mutex); - for (i = 0; i < num_partitions; i++) { - if (adev->enforce_isolation[i] && !partition_values[i]) { + if (adev->enforce_isolation[i] && !partition_values[i]) /* Going from enabled to disabled */ amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i)); - if (adev->enable_mes && adev->gfx.enable_cleaner_shader) - amdgpu_mes_set_enforce_isolation(adev, i, false); - } else if (!adev->enforce_isolation[i] && partition_values[i]) { + else if (!adev->enforce_isolation[i] && partition_values[i]) /* Going from disabled to enabled */ amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i)); - if (adev->enable_mes && adev->gfx.enable_cleaner_shader) - amdgpu_mes_set_enforce_isolation(adev, i, true); - } adev->enforce_isolation[i] = partition_values[i]; } - mutex_unlock(&adev->enforce_isolation_mutex); + amdgpu_mes_update_enforce_isolation(adev); + return count; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index c6e5c50a3322..4eefa17fa39b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -269,7 +269,7 @@ void amdgpu_gmc_sysvm_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc * @mc: memory controller structure holding memory information * @gart_placement: GART placement policy with respect to VRAM * - * Function will place try to place GART before or after VRAM. + * Function will try to place GART before or after VRAM. * If GART size is bigger than space left then we ajust GART size. * Thus function will never fails. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index 459a30fe239f..bd7fc123b8f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -29,6 +29,7 @@ #include <linux/types.h> #include "amdgpu_irq.h" +#include "amdgpu_xgmi.h" #include "amdgpu_ras.h" /* VA hole for 48bit addresses on Vega10 */ @@ -174,28 +175,6 @@ struct amdgpu_gmc_funcs { bool (*need_reset_on_init)(struct amdgpu_device *adev); }; -struct amdgpu_xgmi_ras { - struct amdgpu_ras_block_object ras_block; -}; - -struct amdgpu_xgmi { - /* from psp */ - u64 node_id; - u64 hive_id; - /* fixed per family */ - u64 node_segment_size; - /* physical node (0-3) */ - unsigned physical_node_id; - /* number of nodes (0-4) */ - unsigned num_physical_nodes; - /* gpu list in the same hive */ - struct list_head head; - bool supported; - struct ras_common_if *ras_if; - bool connected_to_cpu; - struct amdgpu_xgmi_ras *ras; -}; - struct amdgpu_mem_partition_info { union { struct { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h index 7d4395a5d8ac..b0a88f92cd82 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h @@ -78,6 +78,9 @@ struct amdgpu_ih_ring { #define amdgpu_ih_ts_after(t1, t2) \ (((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL) +#define amdgpu_ih_ts_after_or_equal(t1, t2) \ + (((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) >= 0LL) + /* provided by the ih block */ struct amdgpu_ih_funcs { /* ring read/write ptr handling, called from interrupt context */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c index 732744488b03..43fc941dfa57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c @@ -124,7 +124,7 @@ static int isp_early_init(struct amdgpu_ip_block *ip_block) return 0; } -static bool isp_is_idle(void *handle) +static bool isp_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h index b03664c66dd6..4f3b7b5d9c1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.h @@ -50,6 +50,7 @@ struct amdgpu_isp { struct mfd_cell *isp_cell; struct resource *isp_res; struct resource *isp_i2c_res; + struct resource *isp_gpio_res; struct isp_platform_data *isp_pdata; unsigned int harvest_config; const struct firmware *fw; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 100f04475943..1d26be3c6d9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -130,29 +130,47 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) amdgpu_vm_put_task_info(ti); } - dma_fence_set_error(&s_job->s_fence->finished, -ETIME); - /* attempt a per ring reset */ - if (amdgpu_gpu_recovery && - ring->funcs->reset) { + if (unlikely(adev->debug_disable_gpu_ring_reset)) { + dev_err(adev->dev, "Ring reset disabled by debug mask\n"); + } else if (amdgpu_gpu_recovery && ring->funcs->reset) { + bool is_guilty; + dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name); /* stop the scheduler, but don't mess with the * bad job yet because if ring reset fails * we'll fall back to full GPU reset. */ drm_sched_wqueue_stop(&ring->sched); + + /* for engine resets, we need to reset the engine, + * but individual queues may be unaffected. + * check here to make sure the accounting is correct. + */ + if (ring->funcs->is_guilty) + is_guilty = ring->funcs->is_guilty(ring); + else + is_guilty = true; + + if (is_guilty) + dma_fence_set_error(&s_job->s_fence->finished, -ETIME); + r = amdgpu_ring_reset(ring, job->vmid); if (!r) { if (amdgpu_ring_sched_ready(ring)) drm_sched_stop(&ring->sched, s_job); - atomic_inc(&ring->adev->gpu_reset_counter); - amdgpu_fence_driver_force_completion(ring); + if (is_guilty) { + atomic_inc(&ring->adev->gpu_reset_counter); + amdgpu_fence_driver_force_completion(ring); + } if (amdgpu_ring_sched_ready(ring)) drm_sched_start(&ring->sched, 0); + dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name); goto exit; } dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name); } + dma_fence_set_error(&s_job->s_fence->finished, -ETIME); if (amdgpu_device_should_recover_gpu(ring->adev)) { struct amdgpu_reset_context reset_context; @@ -411,8 +429,24 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) return fence; } -#define to_drm_sched_job(sched_job) \ - container_of((sched_job), struct drm_sched_job, queue_node) +/* + * This is a duplicate function from DRM scheduler sched_internal.h. + * Plan is to remove it when amdgpu_job_stop_all_jobs_on_sched is removed, due + * latter being incorrect and racy. + * + * See https://lore.kernel.org/amd-gfx/44edde63-7181-44fb-a4f7-94e50514f539@amd.com/ + */ +static struct drm_sched_job * +drm_sched_entity_queue_pop(struct drm_sched_entity *entity) +{ + struct spsc_node *node; + + node = spsc_queue_pop(&entity->job_queue); + if (!node) + return NULL; + + return container_of(node, struct drm_sched_job, queue_node); +} void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) { @@ -425,7 +459,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) struct drm_sched_rq *rq = sched->sched_rq[i]; spin_lock(&rq->lock); list_for_each_entry(s_entity, &rq->entities, list) { - while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) { + while ((s_job = drm_sched_entity_queue_pop(s_entity))) { struct drm_sched_fence *s_fence = s_job->s_fence; dma_fence_signal(&s_fence->scheduled); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 05c73bf7541c..27bfe9c8af06 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -459,7 +459,7 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev, if (adev->vcn.harvest_config & (1 << i)) continue; - for (j = 0; j < adev->vcn.num_enc_rings; j++) + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; j++) if (adev->vcn.inst[i].ring_enc[j].sched.ready) ++num_rings; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 32b27a1658e7..709c11cbeabd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1681,7 +1681,8 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev) } /* Fix me -- node_id is used to identify the correct MES instances in the future */ -int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable) +static int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, + uint32_t node_id, bool enable) { struct mes_misc_op_input op_input = {0}; int r; @@ -1703,6 +1704,23 @@ error: return r; } +int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev) +{ + int i, r = 0; + + if (adev->enable_mes && adev->gfx.enable_cleaner_shader) { + mutex_lock(&adev->enforce_isolation_mutex); + for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) { + if (adev->enforce_isolation[i]) + r |= amdgpu_mes_set_enforce_isolation(adev, i, true); + else + r |= amdgpu_mes_set_enforce_isolation(adev, i, false); + } + mutex_unlock(&adev->enforce_isolation_mutex); + } + return r; +} + #if defined(CONFIG_DEBUG_FS) static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 2df2444ee892..68d640aaa2e1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -56,7 +56,7 @@ enum amdgpu_mes_priority_level { struct amdgpu_mes_funcs; -enum admgpu_mes_pipe { +enum amdgpu_mes_pipe { AMDGPU_MES_SCHED_PIPE = 0, AMDGPU_MES_KIQ_PIPE, AMDGPU_MAX_MES_PIPES = 2, @@ -534,6 +534,6 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes) bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev); -int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable); +int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev); #endif /* __AMDGPU_MES_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 96f4b8904e9a..80cd6f5273db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1295,28 +1295,36 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (abo->kfd_bo) amdgpu_amdkfd_release_notify(abo); - /* We only remove the fence if the resv has individualized. */ - WARN_ON_ONCE(bo->type == ttm_bo_type_kernel - && bo->base.resv != &bo->base._resv); - if (bo->base.resv == &bo->base._resv) - amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); + /* + * We lock the private dma_resv object here and since the BO is about to + * be released nobody else should have a pointer to it. + * So when this locking here fails something is wrong with the reference + * counting. + */ + if (WARN_ON_ONCE(!dma_resv_trylock(&bo->base._resv))) + return; + + amdgpu_amdkfd_remove_all_eviction_fences(abo); if (!bo->resource || bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || adev->in_suspend || drm_dev_is_unplugged(adev_to_drm(adev))) - return; + goto out; - if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) - return; + r = dma_resv_reserve_fences(&bo->base._resv, 1); + if (r) + goto out; - r = amdgpu_fill_buffer(abo, 0, bo->base.resv, &fence, true); - if (!WARN_ON(r)) { - amdgpu_vram_mgr_set_cleared(bo->resource); - amdgpu_bo_fence(abo, fence, false); - dma_fence_put(fence); - } + r = amdgpu_fill_buffer(abo, 0, &bo->base._resv, &fence, true); + if (WARN_ON(r)) + goto out; + + amdgpu_vram_mgr_set_cleared(bo->resource); + dma_resv_add_fence(&bo->base._resv, fence, DMA_RESV_USAGE_KERNEL); + dma_fence_put(fence); - dma_resv_unlock(bo->base.resv); +out: + dma_resv_unlock(&bo->base._resv); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3c3312bbfee8..285e3aa2bb2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2799,20 +2799,100 @@ static int amdgpu_ras_mca2pa(struct amdgpu_device *adev, return -EINVAL; } +static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev, + struct eeprom_table_record *bps, int count) +{ + int j; + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); + struct ras_err_handler_data *data = con->eh_data; + + for (j = 0; j < count; j++) { + if (amdgpu_ras_check_bad_page_unlock(con, + bps[j].retired_page << AMDGPU_GPU_PAGE_SHIFT)) + continue; + + if (!data->space_left && + amdgpu_ras_realloc_eh_data_space(adev, data, 256)) { + return -ENOMEM; + } + + amdgpu_ras_reserve_page(adev, bps[j].retired_page); + + memcpy(&data->bps[data->count], &(bps[j]), + sizeof(struct eeprom_table_record)); + data->count++; + data->space_left--; + } + + return 0; +} + +static int __amdgpu_ras_convert_rec_array_from_rom(struct amdgpu_device *adev, + struct eeprom_table_record *bps, struct ras_err_data *err_data, + enum amdgpu_memory_partition nps) +{ + int i = 0; + enum amdgpu_memory_partition save_nps; + + save_nps = (bps[0].retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK; + + for (i = 0; i < adev->umc.retire_unit; i++) + bps[i].retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT); + + if (save_nps) { + if (save_nps == nps) { + if (amdgpu_umc_pages_in_a_row(adev, err_data, + bps[0].retired_page << AMDGPU_GPU_PAGE_SHIFT)) + return -EINVAL; + } else { + if (amdgpu_ras_mca2pa_by_idx(adev, &bps[0], err_data)) + return -EINVAL; + } + } else { + if (amdgpu_ras_mca2pa(adev, &bps[0], err_data)) { + if (nps == AMDGPU_NPS1_PARTITION_MODE) + memcpy(err_data->err_addr, bps, + sizeof(struct eeprom_table_record) * adev->umc.retire_unit); + else + return -EOPNOTSUPP; + } + } + + return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr, adev->umc.retire_unit); +} + +static int __amdgpu_ras_convert_rec_from_rom(struct amdgpu_device *adev, + struct eeprom_table_record *bps, struct ras_err_data *err_data, + enum amdgpu_memory_partition nps) +{ + enum amdgpu_memory_partition save_nps; + + save_nps = (bps->retired_page >> UMC_NPS_SHIFT) & UMC_NPS_MASK; + bps->retired_page &= ~(UMC_NPS_MASK << UMC_NPS_SHIFT); + + if (save_nps == nps) { + if (amdgpu_umc_pages_in_a_row(adev, err_data, + bps->retired_page << AMDGPU_GPU_PAGE_SHIFT)) + return -EINVAL; + } else { + if (amdgpu_ras_mca2pa_by_idx(adev, bps, err_data)) + return -EINVAL; + } + return __amdgpu_ras_restore_bad_pages(adev, err_data->err_addr, + adev->umc.retire_unit); +} + /* it deal with vram only. */ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, struct eeprom_table_record *bps, int pages, bool from_rom) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - struct ras_err_handler_data *data; struct ras_err_data err_data; - struct eeprom_table_record *err_rec; struct amdgpu_ras_eeprom_control *control = &adev->psp.ras_context.ras->eeprom_control; enum amdgpu_memory_partition nps = AMDGPU_NPS1_PARTITION_MODE; int ret = 0; - uint32_t i, j, loop_cnt = 1; - bool find_pages_per_pa = false; + uint32_t i; if (!con || !con->eh_data || !bps || pages <= 0) return 0; @@ -2823,114 +2903,46 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, sizeof(struct eeprom_table_record), GFP_KERNEL); if (!err_data.err_addr) { dev_warn(adev->dev, "Failed to alloc UMC error address record in mca2pa conversion!\n"); - ret = -ENOMEM; - goto out; + return -ENOMEM; } - err_rec = err_data.err_addr; - loop_cnt = adev->umc.retire_unit; if (adev->gmc.gmc_funcs->query_mem_partition_mode) nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev); } mutex_lock(&con->recovery_lock); - data = con->eh_data; - if (!data) { - /* Returning 0 as the absence of eh_data is acceptable */ - goto free; - } - - for (i = 0; i < pages; i++) { - if (from_rom && - control->rec_type == AMDGPU_RAS_EEPROM_REC_MCA) { - if (!find_pages_per_pa) { - if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) { - if (!i && nps == AMDGPU_NPS1_PARTITION_MODE) { - /* may use old RAS TA, use PA to find pages in - * one row - */ - if (amdgpu_umc_pages_in_a_row(adev, &err_data, - bps[i].retired_page << - AMDGPU_GPU_PAGE_SHIFT)) { - ret = -EINVAL; - goto free; - } else { - find_pages_per_pa = true; - } - } else { - /* unsupported cases */ - ret = -EOPNOTSUPP; - goto free; - } - } - } else { - if (amdgpu_umc_pages_in_a_row(adev, &err_data, - bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) { - ret = -EINVAL; - goto free; - } - } - } else { - if (from_rom && !find_pages_per_pa) { - if (bps[i].retired_page & UMC_CHANNEL_IDX_V2) { - /* bad page in any NPS mode in eeprom */ - if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) { - ret = -EINVAL; + + if (from_rom) { + for (i = 0; i < pages; i++) { + if (control->ras_num_recs - i >= adev->umc.retire_unit) { + if ((bps[i].address == bps[i + 1].address) && + (bps[i].mem_channel == bps[i + 1].mem_channel)) { + //deal with retire_unit records a time + ret = __amdgpu_ras_convert_rec_array_from_rom(adev, + &bps[i], &err_data, nps); + if (ret) goto free; - } + i += (adev->umc.retire_unit - 1); } else { - /* legacy bad page in eeprom, generated only in - * NPS1 mode - */ - if (amdgpu_ras_mca2pa(adev, &bps[i], &err_data)) { - /* old RAS TA or ASICs which don't support to - * convert addrss via mca address - */ - if (!i && nps == AMDGPU_NPS1_PARTITION_MODE) { - find_pages_per_pa = true; - err_rec = &bps[i]; - loop_cnt = 1; - } else { - /* non-nps1 mode, old RAS TA - * can't support it - */ - ret = -EOPNOTSUPP; - goto free; - } - } + break; } - - if (!find_pages_per_pa) - i += (adev->umc.retire_unit - 1); } else { - err_rec = &bps[i]; + break; } } - - for (j = 0; j < loop_cnt; j++) { - if (amdgpu_ras_check_bad_page_unlock(con, - err_rec[j].retired_page << AMDGPU_GPU_PAGE_SHIFT)) - continue; - - if (!data->space_left && - amdgpu_ras_realloc_eh_data_space(adev, data, 256)) { - ret = -ENOMEM; + for (; i < pages; i++) { + ret = __amdgpu_ras_convert_rec_from_rom(adev, + &bps[i], &err_data, nps); + if (ret) goto free; - } - - amdgpu_ras_reserve_page(adev, err_rec[j].retired_page); - - memcpy(&data->bps[data->count], &(err_rec[j]), - sizeof(struct eeprom_table_record)); - data->count++; - data->space_left--; } + } else { + ret = __amdgpu_ras_restore_bad_pages(adev, bps, pages); } free: if (from_rom) kfree(err_data.err_addr); -out: mutex_unlock(&con->recovery_lock); return ret; @@ -2969,24 +2981,14 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev, /* only new entries are saved */ if (save_count > 0) { - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) { + for (i = 0; i < unit_num; i++) { if (amdgpu_ras_eeprom_append(control, - &data->bps[control->ras_num_recs], - save_count)) { + &data->bps[bad_page_num + i * adev->umc.retire_unit], + 1)) { dev_err(adev->dev, "Failed to save EEPROM table data!"); return -EIO; } - } else { - for (i = 0; i < unit_num; i++) { - if (amdgpu_ras_eeprom_append(control, - &data->bps[bad_page_num + i * adev->umc.retire_unit], - 1)) { - dev_err(adev->dev, "Failed to save EEPROM table data!"); - return -EIO; - } - } } - dev_info(adev->dev, "Saved %d pages to EEPROM table.\n", save_count); } @@ -3002,7 +3004,7 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev) struct amdgpu_ras_eeprom_control *control = &adev->psp.ras_context.ras->eeprom_control; struct eeprom_table_record *bps; - int ret; + int ret, i = 0; /* no bad page record, skip eeprom access */ if (control->ras_num_recs == 0 || amdgpu_bad_page_threshold == 0) @@ -3016,13 +3018,23 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev) if (ret) { dev_err(adev->dev, "Failed to load EEPROM table records!"); } else { - if (control->ras_num_recs > 1 && - adev->umc.ras && adev->umc.ras->convert_ras_err_addr) { - if ((bps[0].address == bps[1].address) && - (bps[0].mem_channel == bps[1].mem_channel)) - control->rec_type = AMDGPU_RAS_EEPROM_REC_PA; - else - control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA; + if (adev->umc.ras && adev->umc.ras->convert_ras_err_addr) { + for (i = 0; i < control->ras_num_recs; i++) { + if ((control->ras_num_recs - i) >= adev->umc.retire_unit) { + if ((bps[i].address == bps[i + 1].address) && + (bps[i].mem_channel == bps[i + 1].mem_channel)) { + control->ras_num_pa_recs += adev->umc.retire_unit; + i += (adev->umc.retire_unit - 1); + } else { + control->ras_num_mca_recs += + (control->ras_num_recs - i); + break; + } + } else { + control->ras_num_mca_recs += (control->ras_num_recs - i); + break; + } + } } ret = amdgpu_ras_eeprom_check(control); @@ -3428,12 +3440,7 @@ int amdgpu_ras_init_badpage_info(struct amdgpu_device *adev) return ret; if (!adev->umc.ras || !adev->umc.ras->convert_ras_err_addr) - control->rec_type = AMDGPU_RAS_EEPROM_REC_PA; - - /* default status is MCA storage */ - if (control->ras_num_recs <= 1 && - adev->umc.ras && adev->umc.ras->convert_ras_err_addr) - control->rec_type = AMDGPU_RAS_EEPROM_REC_MCA; + control->ras_num_pa_recs = control->ras_num_recs; if (control->ras_num_recs) { ret = amdgpu_ras_load_bad_pages(adev); @@ -5131,9 +5138,9 @@ static void amdgpu_ras_boot_time_error_reporting(struct amdgpu_device *adev, "socket: %d, aid: %d, fw_status: 0x%x, data abort exception\n", socket_id, aid_id, fw_status); - if (AMDGPU_RAS_GPU_ERR_UNKNOWN(boot_error)) + if (AMDGPU_RAS_GPU_ERR_GENERIC(boot_error)) dev_info(adev->dev, - "socket: %d, aid: %d, fw_status: 0x%x, unknown boot time errors\n", + "socket: %d, aid: %d, fw_status: 0x%x, Boot Controller Generic Error\n", socket_id, aid_id, fw_status); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index cc4586581dba..764e9fa0a914 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -47,7 +47,7 @@ struct amdgpu_iv_entry; #define AMDGPU_RAS_GPU_ERR_AID_ID(x) AMDGPU_GET_REG_FIELD(x, 12, 11) #define AMDGPU_RAS_GPU_ERR_HBM_ID(x) AMDGPU_GET_REG_FIELD(x, 14, 13) #define AMDGPU_RAS_GPU_ERR_DATA_ABORT(x) AMDGPU_GET_REG_FIELD(x, 29, 29) -#define AMDGPU_RAS_GPU_ERR_UNKNOWN(x) AMDGPU_GET_REG_FIELD(x, 30, 30) +#define AMDGPU_RAS_GPU_ERR_GENERIC(x) AMDGPU_GET_REG_FIELD(x, 30, 30) #define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT 100 #define AMDGPU_RAS_BOOT_STEADY_STATUS 0xBA diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 83b54efcaa87..09a6f8bc1a5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -727,11 +727,9 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control, - control->ras_fri) % control->ras_max_record_count; - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) - control->ras_num_bad_pages = control->ras_num_recs; - else - control->ras_num_bad_pages = - control->ras_num_recs * adev->umc.retire_unit; + control->ras_num_mca_recs += num; + control->ras_num_bad_pages += num * adev->umc.retire_unit; + Out: kfree(buf); return res; @@ -749,7 +747,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) /* Modify the header if it exceeds. */ if (amdgpu_bad_page_threshold != 0 && - control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) { + control->ras_num_bad_pages > ras->bad_page_cnt_threshold) { dev_warn(adev->dev, "Saved bad pages %d reaches threshold value %d\n", control->ras_num_bad_pages, ras->bad_page_cnt_threshold); @@ -808,7 +806,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) */ if (amdgpu_bad_page_threshold != 0 && control->tbl_hdr.version == RAS_TABLE_VER_V2_1 && - control->ras_num_bad_pages < ras->bad_page_cnt_threshold) + control->ras_num_bad_pages <= ras->bad_page_cnt_threshold) control->tbl_rai.health_percent = ((ras->bad_page_cnt_threshold - control->ras_num_bad_pages) * 100) / ras->bad_page_cnt_threshold; @@ -852,6 +850,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, { struct amdgpu_device *adev = to_amdgpu_device(control); int res, i; + uint64_t nps = AMDGPU_NPS1_PARTITION_MODE; if (!__is_ras_eeprom_supported(adev)) return 0; @@ -865,9 +864,12 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, return -EINVAL; } + if (adev->gmc.gmc_funcs->query_mem_partition_mode) + nps = adev->gmc.gmc_funcs->query_mem_partition_mode(adev); + /* set the new channel index flag */ for (i = 0; i < num; i++) - record[i].retired_page |= UMC_CHANNEL_IDX_V2; + record[i].retired_page |= (nps << UMC_NPS_SHIFT); mutex_lock(&control->ras_tbl_mutex); @@ -881,7 +883,7 @@ int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, /* clear channel index flag, the flag is only saved on eeprom */ for (i = 0; i < num; i++) - record[i].retired_page &= ~UMC_CHANNEL_IDX_V2; + record[i].retired_page &= ~(nps << UMC_NPS_SHIFT); return res; } @@ -1392,6 +1394,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control) } control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset); + control->ras_num_mca_recs = 0; + control->ras_num_pa_recs = 0; return 0; } @@ -1412,11 +1416,8 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control) if (!__get_eeprom_i2c_addr(adev, control)) return -EINVAL; - if (control->rec_type == AMDGPU_RAS_EEPROM_REC_PA) - control->ras_num_bad_pages = control->ras_num_recs; - else - control->ras_num_bad_pages = - control->ras_num_recs * adev->umc.retire_unit; + control->ras_num_bad_pages = control->ras_num_pa_recs + + control->ras_num_mca_recs * adev->umc.retire_unit; if (hdr->header == RAS_TABLE_HDR_VAL) { DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records", @@ -1455,7 +1456,7 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control) res); return -EINVAL; } - if (ras->bad_page_cnt_threshold > control->ras_num_bad_pages) { + if (ras->bad_page_cnt_threshold >= control->ras_num_bad_pages) { /* This means that, the threshold was increased since * the last time the system was booted, and now, * ras->bad_page_cnt_threshold - control->num_recs > 0, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h index 81d55cb7b397..13f7eda9a696 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h @@ -43,19 +43,6 @@ enum amdgpu_ras_eeprom_err_type { AMDGPU_RAS_EEPROM_ERR_COUNT, }; -/* - * one UMC MCA address could map to multiply physical address (PA), - * such as 1:16, we use eeprom_table_record.address to store MCA - * address and use eeprom_table_record.retired_page to save PA. - * - * AMDGPU_RAS_EEPROM_REC_PA: one record store one PA - * AMDGPU_RAS_EEPROM_REC_MCA: one record store one MCA address - */ -enum amdgpu_ras_eeprom_rec_type { - AMDGPU_RAS_EEPROM_REC_PA, - AMDGPU_RAS_EEPROM_REC_MCA, -}; - struct amdgpu_ras_eeprom_table_header { uint32_t header; uint32_t version; @@ -100,6 +87,12 @@ struct amdgpu_ras_eeprom_control { */ u32 ras_num_bad_pages; + /* Number of records store mca address */ + u32 ras_num_mca_recs; + + /* Number of records store physical address */ + u32 ras_num_pa_recs; + /* First record index to read, 0-based. * Range is [0, num_recs-1]. This is * an absolute index, starting right after @@ -120,7 +113,6 @@ struct amdgpu_ras_eeprom_control { /* Record channel info which occurred bad pages */ u32 bad_channel_bitmap; - enum amdgpu_ras_eeprom_rec_type rec_type; }; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index f53887e2f528..d55c8b7fdb59 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -349,6 +349,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->buf_mask = (ring->ring_size / 4) - 1; ring->ptr_mask = ring->funcs->support_64bit_ptrs ? 0xffffffffffffffff : ring->buf_mask; + /* Initialize cached_rptr to 0 */ + ring->cached_rptr = 0; /* Allocate ring buffer */ if (ring->is_mes_queue) { @@ -576,12 +578,32 @@ out: return result; } +static ssize_t amdgpu_debugfs_virt_ring_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_ring *ring = file_inode(f)->i_private; + + if (*pos & 3 || size & 3) + return -EINVAL; + + if (ring->funcs->type == AMDGPU_RING_TYPE_CPER) + amdgpu_virt_req_ras_cper_dump(ring->adev, false); + + return amdgpu_debugfs_ring_read(f, buf, size, pos); +} + static const struct file_operations amdgpu_debugfs_ring_fops = { .owner = THIS_MODULE, .read = amdgpu_debugfs_ring_read, .llseek = default_llseek }; +static const struct file_operations amdgpu_debugfs_virt_ring_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_virt_ring_read, + .llseek = default_llseek +}; + static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { @@ -669,9 +691,14 @@ void amdgpu_debugfs_ring_init(struct amdgpu_device *adev, char name[32]; sprintf(name, "amdgpu_ring_%s", ring->name); - debugfs_create_file_size(name, S_IFREG | 0444, root, ring, - &amdgpu_debugfs_ring_fops, - ring->ring_size + 12); + if (amdgpu_sriov_vf(adev)) + debugfs_create_file_size(name, S_IFREG | 0444, root, ring, + &amdgpu_debugfs_virt_ring_fops, + ring->ring_size + 12); + else + debugfs_create_file_size(name, S_IFREG | 0444, root, ring, + &amdgpu_debugfs_ring_fops, + ring->ring_size + 12); if (ring->mqd_obj) { sprintf(name, "amdgpu_mqd_%s", ring->name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 7372e4aed6b0..b4fd1e17205e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -37,7 +37,7 @@ struct amdgpu_job; struct amdgpu_vm; /* max number of rings */ -#define AMDGPU_MAX_RINGS 132 +#define AMDGPU_MAX_RINGS 133 #define AMDGPU_MAX_HWIP_RINGS 64 #define AMDGPU_MAX_GFX_RINGS 2 #define AMDGPU_MAX_SW_GFX_RINGS 2 @@ -238,6 +238,7 @@ struct amdgpu_ring_funcs { void (*patch_de)(struct amdgpu_ring *ring, unsigned offset); int (*reset)(struct amdgpu_ring *ring, unsigned int vmid); void (*emit_cleaner_shader)(struct amdgpu_ring *ring); + bool (*is_guilty)(struct amdgpu_ring *ring); }; struct amdgpu_ring { @@ -307,6 +308,8 @@ struct amdgpu_ring { bool is_sw_ring; unsigned int entry_index; + /* store the cached rptr to restore after reset */ + uint64_t cached_rptr; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 174badca27e7..3a4cef896018 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -25,6 +25,7 @@ #include "amdgpu.h" #include "amdgpu_sdma.h" #include "amdgpu_ras.h" +#include "amdgpu_reset.h" #define AMDGPU_CSA_SDMA_SIZE 64 /* SDMA CSA reside in the 3rd page of CSA */ @@ -355,23 +356,44 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev) static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val) { struct amdgpu_device *adev = (struct amdgpu_device *)data; - u32 i; + u64 i, num_ring; u64 mask = 0; - struct amdgpu_ring *ring; + struct amdgpu_ring *ring, *page = NULL; if (!adev) return -ENODEV; - mask = BIT_ULL(adev->sdma.num_instances) - 1; + /* Determine the number of rings per SDMA instance + * (1 for sdma gfx ring, 2 if page queue exists) + */ + if (adev->sdma.has_page_queue) + num_ring = 2; + else + num_ring = 1; + + /* Calculate the maximum possible mask value + * based on the number of SDMA instances and rings + */ + mask = BIT_ULL(adev->sdma.num_instances * num_ring) - 1; + if ((val & mask) == 0) return -EINVAL; for (i = 0; i < adev->sdma.num_instances; ++i) { ring = &adev->sdma.instance[i].ring; - if (val & BIT_ULL(i)) + if (adev->sdma.has_page_queue) + page = &adev->sdma.instance[i].page; + if (val & BIT_ULL(i * num_ring)) ring->sched.ready = true; else ring->sched.ready = false; + + if (page) { + if (val & BIT_ULL(i * num_ring + 1)) + page->sched.ready = true; + else + page->sched.ready = false; + } } /* publish sched.ready flag update effective immediately across smp */ smp_rmb(); @@ -381,16 +403,37 @@ static int amdgpu_debugfs_sdma_sched_mask_set(void *data, u64 val) static int amdgpu_debugfs_sdma_sched_mask_get(void *data, u64 *val) { struct amdgpu_device *adev = (struct amdgpu_device *)data; - u32 i; + u64 i, num_ring; u64 mask = 0; - struct amdgpu_ring *ring; + struct amdgpu_ring *ring, *page = NULL; if (!adev) return -ENODEV; + + /* Determine the number of rings per SDMA instance + * (1 for sdma gfx ring, 2 if page queue exists) + */ + if (adev->sdma.has_page_queue) + num_ring = 2; + else + num_ring = 1; + for (i = 0; i < adev->sdma.num_instances; ++i) { ring = &adev->sdma.instance[i].ring; + if (adev->sdma.has_page_queue) + page = &adev->sdma.instance[i].page; + if (ring->sched.ready) - mask |= 1 << i; + mask |= BIT_ULL(i * num_ring); + else + mask &= ~BIT_ULL(i * num_ring); + + if (page) { + if (page->sched.ready) + mask |= BIT_ULL(i * num_ring + 1); + else + mask &= ~BIT_ULL(i * num_ring + 1); + } } *val = mask; @@ -460,3 +503,123 @@ void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev) device_remove_file(adev->dev, &dev_attr_sdma_reset_mask); } } + +/** + * amdgpu_sdma_register_on_reset_callbacks - Register SDMA reset callbacks + * @funcs: Pointer to the callback structure containing pre_reset and post_reset functions + * + * This function allows KFD and AMDGPU to register their own callbacks for handling + * pre-reset and post-reset operations for engine reset. These are needed because engine + * reset will stop all queues on that engine. + */ +void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs) +{ + if (!funcs) + return; + + /* Ensure the reset_callback_list is initialized */ + if (!adev->sdma.reset_callback_list.next) { + INIT_LIST_HEAD(&adev->sdma.reset_callback_list); + } + /* Initialize the list node in the callback structure */ + INIT_LIST_HEAD(&funcs->list); + + /* Add the callback structure to the global list */ + list_add_tail(&funcs->list, &adev->sdma.reset_callback_list); +} + +/** + * amdgpu_sdma_reset_engine - Reset a specific SDMA engine + * @adev: Pointer to the AMDGPU device + * @instance_id: ID of the SDMA engine instance to reset + * @suspend_user_queues: check if suspend user queue. + * + * This function performs the following steps: + * 1. Calls all registered pre_reset callbacks to allow KFD and AMDGPU to save their state. + * 2. Resets the specified SDMA engine instance. + * 3. Calls all registered post_reset callbacks to allow KFD and AMDGPU to restore their state. + * + * Returns: 0 on success, or a negative error code on failure. + */ +int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id, bool suspend_user_queues) +{ + struct sdma_on_reset_funcs *funcs; + int ret = 0; + struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];; + struct amdgpu_ring *gfx_ring = &sdma_instance->ring; + struct amdgpu_ring *page_ring = &sdma_instance->page; + bool gfx_sched_stopped = false, page_sched_stopped = false; + + /* Suspend KFD if suspend_user_queues is true. + * prevent the destruction of in-flight healthy user queue packets and + * avoid race conditions between KFD and KGD during the reset process. + */ + if (suspend_user_queues) + amdgpu_amdkfd_suspend(adev, false); + + /* Stop the scheduler's work queue for the GFX and page rings if they are running. + * This ensures that no new tasks are submitted to the queues while + * the reset is in progress. + */ + if (!amdgpu_ring_sched_ready(gfx_ring)) { + drm_sched_wqueue_stop(&gfx_ring->sched); + gfx_sched_stopped = true; + } + + if (adev->sdma.has_page_queue && !amdgpu_ring_sched_ready(page_ring)) { + drm_sched_wqueue_stop(&page_ring->sched); + page_sched_stopped = true; + } + + /* Invoke all registered pre_reset callbacks */ + list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) { + if (funcs->pre_reset) { + ret = funcs->pre_reset(adev, instance_id); + if (ret) { + dev_err(adev->dev, + "beforeReset callback failed for instance %u: %d\n", + instance_id, ret); + goto exit; + } + } + } + + /* Perform the SDMA reset for the specified instance */ + ret = amdgpu_dpm_reset_sdma(adev, 1 << instance_id); + if (ret) { + dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id); + goto exit; + } + + /* Invoke all registered post_reset callbacks */ + list_for_each_entry(funcs, &adev->sdma.reset_callback_list, list) { + if (funcs->post_reset) { + ret = funcs->post_reset(adev, instance_id); + if (ret) { + dev_err(adev->dev, + "afterReset callback failed for instance %u: %d\n", + instance_id, ret); + goto exit; + } + } + } + +exit: + /* Restart the scheduler's work queue for the GFX and page rings + * if they were stopped by this function. This allows new tasks + * to be submitted to the queues after the reset is complete. + */ + if (ret) { + if (gfx_sched_stopped && amdgpu_ring_sched_ready(gfx_ring)) { + drm_sched_wqueue_start(&gfx_ring->sched); + } + if (page_sched_stopped && amdgpu_ring_sched_ready(page_ring)) { + drm_sched_wqueue_start(&page_ring->sched); + } + } + + if (suspend_user_queues) + amdgpu_amdkfd_resume(adev, false); + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index 5f60736051d1..965169320065 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -98,6 +98,13 @@ struct amdgpu_sdma_ras { struct amdgpu_ras_block_object ras_block; }; +struct sdma_on_reset_funcs { + int (*pre_reset)(struct amdgpu_device *adev, uint32_t instance_id); + int (*post_reset)(struct amdgpu_device *adev, uint32_t instance_id); + /* Linked list node to store this structure in a list; */ + struct list_head list; +}; + struct amdgpu_sdma { struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES]; struct amdgpu_irq_src trap_irq; @@ -118,6 +125,10 @@ struct amdgpu_sdma { struct amdgpu_sdma_ras *ras; uint32_t *ip_dump; uint32_t supported_reset; + struct list_head reset_callback_list; + /* track guilty state of GFX and PAGE queues */ + bool gfx_guilty; + bool page_guilty; }; /* @@ -157,6 +168,9 @@ struct amdgpu_buffer_funcs { uint32_t byte_count); }; +void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct sdma_on_reset_funcs *funcs); +int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id, bool suspend_user_queues); + #define amdgpu_emit_copy_buffer(adev, ib, s, d, b, t) (adev)->mman.buffer_funcs->emit_copy_buffer((ib), (s), (d), (b), (t)) #define amdgpu_emit_fill_buffer(adev, ib, s, d, b) (adev)->mman.buffer_funcs->emit_fill_buffer((ib), (s), (d), (b)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index bcb4bcc4ab75..53b71e9d8076 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -2295,7 +2295,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo, struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; struct amdgpu_res_cursor cursor; u64 addr; - int r; + int r = 0; if (!adev->mman.buffer_funcs_enabled) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index a4a7e61817aa..857693bcd8d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -71,6 +71,13 @@ */ #define UMC_CHANNEL_IDX_V2 BIT_ULL(47) +/* + * save nps value to eeprom_table_record.retired_page[47:40], + * the channel index flag above will be retired. + */ +#define UMC_NPS_SHIFT 40 +#define UMC_NPS_MASK 0xffULL + typedef int (*umc_func)(struct amdgpu_device *adev, uint32_t node_inst, uint32_t umc_inst, uint32_t ch_inst, void *data); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 83faf6e6788a..8d8b39e6d197 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -93,47 +93,53 @@ MODULE_FIRMWARE(FIRMWARE_VCN5_0_1); static void amdgpu_vcn_idle_work_handler(struct work_struct *work); -int amdgpu_vcn_early_init(struct amdgpu_device *adev) +int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i) { char ucode_prefix[25]; - int r, i; + int r; + adev->vcn.inst[i].adev = adev; + adev->vcn.inst[i].inst = i; amdgpu_ucode_ip_version_decode(adev, UVD_HWIP, ucode_prefix, sizeof(ucode_prefix)); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (i == 1 && amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 6)) - r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw, - AMDGPU_UCODE_REQUIRED, - "amdgpu/%s_%d.bin", ucode_prefix, i); - else - r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw, + + if (i != 0 && adev->vcn.per_inst_fw) { + r = amdgpu_ucode_request(adev, &adev->vcn.inst[i].fw, + AMDGPU_UCODE_REQUIRED, + "amdgpu/%s_%d.bin", ucode_prefix, i); + if (r) + amdgpu_ucode_release(&adev->vcn.inst[i].fw); + } else { + if (!adev->vcn.inst[0].fw) { + r = amdgpu_ucode_request(adev, &adev->vcn.inst[0].fw, AMDGPU_UCODE_REQUIRED, "amdgpu/%s.bin", ucode_prefix); - if (r) { - amdgpu_ucode_release(&adev->vcn.inst[i].fw); - return r; + if (r) + amdgpu_ucode_release(&adev->vcn.inst[0].fw); + } else { + r = 0; } + adev->vcn.inst[i].fw = adev->vcn.inst[0].fw; } + return r; } -int amdgpu_vcn_sw_init(struct amdgpu_device *adev) +int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i) { unsigned long bo_size; const struct common_firmware_header *hdr; unsigned char fw_check; unsigned int fw_shared_size, log_offset; - int i, r; - - INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler); - mutex_init(&adev->vcn.vcn_pg_lock); - mutex_init(&adev->vcn.vcn1_jpeg1_workaround); - atomic_set(&adev->vcn.total_submission_cnt, 0); - for (i = 0; i < adev->vcn.num_vcn_inst; i++) - atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); + int r; + mutex_init(&adev->vcn.inst[i].vcn1_jpeg1_workaround); + mutex_init(&adev->vcn.inst[i].vcn_pg_lock); + atomic_set(&adev->vcn.inst[i].total_submission_cnt, 0); + INIT_DELAYED_WORK(&adev->vcn.inst[i].idle_work, amdgpu_vcn_idle_work_handler); + atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) - adev->vcn.indirect_sram = true; + adev->vcn.inst[i].indirect_sram = true; /* * Some Steam Deck's BIOS versions are incompatible with the @@ -146,18 +152,19 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) const char *bios_ver = dmi_get_system_info(DMI_BIOS_VERSION); if (bios_ver && (!strncmp("F7A0113", bios_ver, 7) || - !strncmp("F7A0114", bios_ver, 7))) { - adev->vcn.indirect_sram = false; + !strncmp("F7A0114", bios_ver, 7))) { + adev->vcn.inst[i].indirect_sram = false; dev_info(adev->dev, - "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver); + "Steam Deck quirk: indirect SRAM disabled on BIOS %s\n", bios_ver); } } /* from vcn4 and above, only unified queue is used */ - adev->vcn.using_unified_queue = + adev->vcn.inst[i].using_unified_queue = amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0); - hdr = (const struct common_firmware_header *)adev->vcn.inst[0].fw->data; + hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; + adev->vcn.inst[i].fw_version = le32_to_cpu(hdr->ucode_version); adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version); /* Bit 20-23, it is encode major and non-zero for new naming convention. @@ -175,16 +182,17 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) enc_major = fw_check; dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf; vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf; - DRM_INFO("Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n", - enc_major, enc_minor, dec_ver, vep, fw_rev); + dev_info(adev->dev, + "Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n", + enc_major, enc_minor, dec_ver, vep, fw_rev); } else { unsigned int version_major, version_minor, family_id; family_id = le32_to_cpu(hdr->ucode_version) & 0xff; version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff; version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff; - DRM_INFO("Found VCN firmware Version: %u.%u Family ID: %u\n", - version_major, version_minor, family_id); + dev_info(adev->dev, "Found VCN firmware Version: %u.%u Family ID: %u\n", + version_major, version_minor, family_id); } bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_CONTEXT_SIZE; @@ -207,80 +215,77 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) if (amdgpu_vcnfw_log) bo_size += AMDGPU_VCNFW_LOG_SIZE; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM | + AMDGPU_GEM_DOMAIN_GTT, + &adev->vcn.inst[i].vcpu_bo, + &adev->vcn.inst[i].gpu_addr, + &adev->vcn.inst[i].cpu_addr); + if (r) { + dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r); + return r; + } + + adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr + + bo_size - fw_shared_size; + adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr + + bo_size - fw_shared_size; + + adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size; + + if (amdgpu_vcnfw_log) { + adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE; + adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE; + adev->vcn.inst[i].fw_shared.log_offset = log_offset; + } - r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, + if (adev->vcn.inst[i].indirect_sram) { + r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT, - &adev->vcn.inst[i].vcpu_bo, - &adev->vcn.inst[i].gpu_addr, - &adev->vcn.inst[i].cpu_addr); + &adev->vcn.inst[i].dpg_sram_bo, + &adev->vcn.inst[i].dpg_sram_gpu_addr, + &adev->vcn.inst[i].dpg_sram_cpu_addr); if (r) { - dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r); + dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r); return r; } - - adev->vcn.inst[i].fw_shared.cpu_addr = adev->vcn.inst[i].cpu_addr + - bo_size - fw_shared_size; - adev->vcn.inst[i].fw_shared.gpu_addr = adev->vcn.inst[i].gpu_addr + - bo_size - fw_shared_size; - - adev->vcn.inst[i].fw_shared.mem_size = fw_shared_size; - - if (amdgpu_vcnfw_log) { - adev->vcn.inst[i].fw_shared.cpu_addr -= AMDGPU_VCNFW_LOG_SIZE; - adev->vcn.inst[i].fw_shared.gpu_addr -= AMDGPU_VCNFW_LOG_SIZE; - adev->vcn.inst[i].fw_shared.log_offset = log_offset; - } - - if (adev->vcn.indirect_sram) { - r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM | - AMDGPU_GEM_DOMAIN_GTT, - &adev->vcn.inst[i].dpg_sram_bo, - &adev->vcn.inst[i].dpg_sram_gpu_addr, - &adev->vcn.inst[i].dpg_sram_cpu_addr); - if (r) { - dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r); - return r; - } - } } return 0; } -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) +int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i) { - int i, j; + int j; - for (j = 0; j < adev->vcn.num_vcn_inst; ++j) { - if (adev->vcn.harvest_config & (1 << j)) - continue; + if (adev->vcn.harvest_config & (1 << i)) + return 0; - amdgpu_bo_free_kernel( - &adev->vcn.inst[j].dpg_sram_bo, - &adev->vcn.inst[j].dpg_sram_gpu_addr, - (void **)&adev->vcn.inst[j].dpg_sram_cpu_addr); + amdgpu_bo_free_kernel( + &adev->vcn.inst[i].dpg_sram_bo, + &adev->vcn.inst[i].dpg_sram_gpu_addr, + (void **)&adev->vcn.inst[i].dpg_sram_cpu_addr); - kvfree(adev->vcn.inst[j].saved_bo); + kvfree(adev->vcn.inst[i].saved_bo); - amdgpu_bo_free_kernel(&adev->vcn.inst[j].vcpu_bo, - &adev->vcn.inst[j].gpu_addr, - (void **)&adev->vcn.inst[j].cpu_addr); + amdgpu_bo_free_kernel(&adev->vcn.inst[i].vcpu_bo, + &adev->vcn.inst[i].gpu_addr, + (void **)&adev->vcn.inst[i].cpu_addr); - amdgpu_ring_fini(&adev->vcn.inst[j].ring_dec); + amdgpu_ring_fini(&adev->vcn.inst[i].ring_dec); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) - amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]); + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) + amdgpu_ring_fini(&adev->vcn.inst[i].ring_enc[j]); - amdgpu_ucode_release(&adev->vcn.inst[j].fw); + if (adev->vcn.per_inst_fw) { + amdgpu_ucode_release(&adev->vcn.inst[i].fw); + } else { + amdgpu_ucode_release(&adev->vcn.inst[0].fw); + adev->vcn.inst[i].fw = NULL; } - - mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround); - mutex_destroy(&adev->vcn.vcn_pg_lock); + mutex_destroy(&adev->vcn.inst[i].vcn_pg_lock); + mutex_destroy(&adev->vcn.inst[i].vcn1_jpeg1_workaround); return 0; } @@ -300,179 +305,190 @@ bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type t return ret; } -int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev) +static int amdgpu_vcn_save_vcpu_bo_inst(struct amdgpu_device *adev, int i) { unsigned int size; void *ptr; - int i, idx; + int idx; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - if (adev->vcn.inst[i].vcpu_bo == NULL) - return 0; + if (adev->vcn.harvest_config & (1 << i)) + return 0; + if (adev->vcn.inst[i].vcpu_bo == NULL) + return 0; - size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); - ptr = adev->vcn.inst[i].cpu_addr; + size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); + ptr = adev->vcn.inst[i].cpu_addr; - adev->vcn.inst[i].saved_bo = kvmalloc(size, GFP_KERNEL); - if (!adev->vcn.inst[i].saved_bo) - return -ENOMEM; + adev->vcn.inst[i].saved_bo = kvmalloc(size, GFP_KERNEL); + if (!adev->vcn.inst[i].saved_bo) + return -ENOMEM; - if (drm_dev_enter(adev_to_drm(adev), &idx)) { - memcpy_fromio(adev->vcn.inst[i].saved_bo, ptr, size); - drm_dev_exit(idx); - } + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + memcpy_fromio(adev->vcn.inst[i].saved_bo, ptr, size); + drm_dev_exit(idx); } return 0; } -int amdgpu_vcn_suspend(struct amdgpu_device *adev) +int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev) +{ + int ret, i; + + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + ret = amdgpu_vcn_save_vcpu_bo_inst(adev, i); + if (ret) + return ret; + } + + return 0; +} + +int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i) { bool in_ras_intr = amdgpu_ras_intr_triggered(); - cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->vcn.harvest_config & (1 << i)) + return 0; + + cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work); /* err_event_athub will corrupt VCPU buffer, so we need to * restore fw data and clear buffer in amdgpu_vcn_resume() */ if (in_ras_intr) return 0; - return amdgpu_vcn_save_vcpu_bo(adev); + return amdgpu_vcn_save_vcpu_bo_inst(adev, i); } -int amdgpu_vcn_resume(struct amdgpu_device *adev) +int amdgpu_vcn_resume(struct amdgpu_device *adev, int i) { unsigned int size; void *ptr; - int i, idx; + int idx; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - if (adev->vcn.inst[i].vcpu_bo == NULL) - return -EINVAL; + if (adev->vcn.harvest_config & (1 << i)) + return 0; + if (adev->vcn.inst[i].vcpu_bo == NULL) + return -EINVAL; - size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); - ptr = adev->vcn.inst[i].cpu_addr; + size = amdgpu_bo_size(adev->vcn.inst[i].vcpu_bo); + ptr = adev->vcn.inst[i].cpu_addr; + + if (adev->vcn.inst[i].saved_bo != NULL) { + if (drm_dev_enter(adev_to_drm(adev), &idx)) { + memcpy_toio(ptr, adev->vcn.inst[i].saved_bo, size); + drm_dev_exit(idx); + } + kvfree(adev->vcn.inst[i].saved_bo); + adev->vcn.inst[i].saved_bo = NULL; + } else { + const struct common_firmware_header *hdr; + unsigned int offset; - if (adev->vcn.inst[i].saved_bo != NULL) { + hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; + if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) { + offset = le32_to_cpu(hdr->ucode_array_offset_bytes); if (drm_dev_enter(adev_to_drm(adev), &idx)) { - memcpy_toio(ptr, adev->vcn.inst[i].saved_bo, size); + memcpy_toio(adev->vcn.inst[i].cpu_addr, + adev->vcn.inst[i].fw->data + offset, + le32_to_cpu(hdr->ucode_size_bytes)); drm_dev_exit(idx); } - kvfree(adev->vcn.inst[i].saved_bo); - adev->vcn.inst[i].saved_bo = NULL; - } else { - const struct common_firmware_header *hdr; - unsigned int offset; - - hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; - if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) { - offset = le32_to_cpu(hdr->ucode_array_offset_bytes); - if (drm_dev_enter(adev_to_drm(adev), &idx)) { - memcpy_toio(adev->vcn.inst[i].cpu_addr, - adev->vcn.inst[i].fw->data + offset, - le32_to_cpu(hdr->ucode_size_bytes)); - drm_dev_exit(idx); - } - size -= le32_to_cpu(hdr->ucode_size_bytes); - ptr += le32_to_cpu(hdr->ucode_size_bytes); - } - memset_io(ptr, 0, size); + size -= le32_to_cpu(hdr->ucode_size_bytes); + ptr += le32_to_cpu(hdr->ucode_size_bytes); } + memset_io(ptr, 0, size); } + return 0; } static void amdgpu_vcn_idle_work_handler(struct work_struct *work) { - struct amdgpu_device *adev = - container_of(work, struct amdgpu_device, vcn.idle_work.work); + struct amdgpu_vcn_inst *vcn_inst = + container_of(work, struct amdgpu_vcn_inst, idle_work.work); + struct amdgpu_device *adev = vcn_inst->adev; unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0}; - unsigned int i, j; + unsigned int i = vcn_inst->inst, j; int r = 0; - for (j = 0; j < adev->vcn.num_vcn_inst; ++j) { - if (adev->vcn.harvest_config & (1 << j)) - continue; - - for (i = 0; i < adev->vcn.num_enc_rings; ++i) - fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]); + if (adev->vcn.harvest_config & (1 << i)) + return; - /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - !adev->vcn.using_unified_queue) { - struct dpg_pause_state new_state; + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) + fence[i] += amdgpu_fence_count_emitted(&vcn_inst->ring_enc[j]); - if (fence[j] || - unlikely(atomic_read(&adev->vcn.inst[j].dpg_enc_submission_cnt))) - new_state.fw_based = VCN_DPG_STATE__PAUSE; - else - new_state.fw_based = VCN_DPG_STATE__UNPAUSE; + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.inst[i].using_unified_queue) { + struct dpg_pause_state new_state; - adev->vcn.pause_dpg_mode(adev, j, &new_state); - } + if (fence[i] || + unlikely(atomic_read(&vcn_inst->dpg_enc_submission_cnt))) + new_state.fw_based = VCN_DPG_STATE__PAUSE; + else + new_state.fw_based = VCN_DPG_STATE__UNPAUSE; - fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_dec); - fences += fence[j]; + adev->vcn.inst[i].pause_dpg_mode(vcn_inst, &new_state); } - if (!fences && !atomic_read(&adev->vcn.total_submission_cnt)) { - amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, - AMD_PG_STATE_GATE); + fence[i] += amdgpu_fence_count_emitted(&vcn_inst->ring_dec); + fences += fence[i]; + + if (!fences && !atomic_read(&vcn_inst->total_submission_cnt)) { + vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_GATE); r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO, - false); + false); if (r) dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r); } else { - schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + schedule_delayed_work(&vcn_inst->idle_work, VCN_IDLE_TIMEOUT); } } void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; + struct amdgpu_vcn_inst *vcn_inst = &adev->vcn.inst[ring->me]; int r = 0; - atomic_inc(&adev->vcn.total_submission_cnt); + atomic_inc(&vcn_inst->total_submission_cnt); - if (!cancel_delayed_work_sync(&adev->vcn.idle_work)) { + if (!cancel_delayed_work_sync(&vcn_inst->idle_work)) { r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO, true); if (r) dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r); } - mutex_lock(&adev->vcn.vcn_pg_lock); - amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, - AMD_PG_STATE_UNGATE); + mutex_lock(&vcn_inst->vcn_pg_lock); + vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_UNGATE); /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - !adev->vcn.using_unified_queue) { + !vcn_inst->using_unified_queue) { struct dpg_pause_state new_state; if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) { - atomic_inc(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt); + atomic_inc(&vcn_inst->dpg_enc_submission_cnt); new_state.fw_based = VCN_DPG_STATE__PAUSE; } else { unsigned int fences = 0; unsigned int i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) - fences += amdgpu_fence_count_emitted(&adev->vcn.inst[ring->me].ring_enc[i]); + for (i = 0; i < vcn_inst->num_enc_rings; ++i) + fences += amdgpu_fence_count_emitted(&vcn_inst->ring_enc[i]); - if (fences || atomic_read(&adev->vcn.inst[ring->me].dpg_enc_submission_cnt)) + if (fences || atomic_read(&vcn_inst->dpg_enc_submission_cnt)) new_state.fw_based = VCN_DPG_STATE__PAUSE; else new_state.fw_based = VCN_DPG_STATE__UNPAUSE; } - adev->vcn.pause_dpg_mode(adev, ring->me, &new_state); + vcn_inst->pause_dpg_mode(vcn_inst, &new_state); } - mutex_unlock(&adev->vcn.vcn_pg_lock); + mutex_unlock(&vcn_inst->vcn_pg_lock); } void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) @@ -482,12 +498,13 @@ void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC && - !adev->vcn.using_unified_queue) + !adev->vcn.inst[ring->me].using_unified_queue) atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt); - atomic_dec(&ring->adev->vcn.total_submission_cnt); + atomic_dec(&ring->adev->vcn.inst[ring->me].total_submission_cnt); - schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + schedule_delayed_work(&ring->adev->vcn.inst[ring->me].idle_work, + VCN_IDLE_TIMEOUT); } int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring) @@ -505,7 +522,7 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring) r = amdgpu_ring_alloc(ring, 3); if (r) return r; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.scratch9, 0)); amdgpu_ring_write(ring, 0xDEADBEEF); amdgpu_ring_commit(ring); for (i = 0; i < adev->usec_timeout; i++) { @@ -570,14 +587,14 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring, goto err; ib = &job->ibs[0]; - ib->ptr[0] = PACKET0(adev->vcn.internal.data0, 0); + ib->ptr[0] = PACKET0(adev->vcn.inst[ring->me].internal.data0, 0); ib->ptr[1] = addr; - ib->ptr[2] = PACKET0(adev->vcn.internal.data1, 0); + ib->ptr[2] = PACKET0(adev->vcn.inst[ring->me].internal.data1, 0); ib->ptr[3] = addr >> 32; - ib->ptr[4] = PACKET0(adev->vcn.internal.cmd, 0); + ib->ptr[4] = PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0); ib->ptr[5] = 0; for (i = 6; i < 16; i += 2) { - ib->ptr[i] = PACKET0(adev->vcn.internal.nop, 0); + ib->ptr[i] = PACKET0(adev->vcn.inst[ring->me].internal.nop, 0); ib->ptr[i+1] = 0; } ib->length_dw = 16; @@ -740,7 +757,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, uint32_t ib_pack_in_dw; int i, r; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -753,7 +770,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, ib->length_dw = 0; /* single queue headers */ - if (adev->vcn.using_unified_queue) { + if (adev->vcn.inst[ring->me].using_unified_queue) { ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t) + 4 + 2; /* engine info + decoding ib in dw */ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false); @@ -772,7 +789,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw); r = amdgpu_job_submit_direct(job, ring, &f); @@ -870,7 +887,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand uint64_t addr; int i, r; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -884,7 +901,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand ib->length_dw = 0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -906,7 +923,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); @@ -937,7 +954,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han uint64_t addr; int i, r; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -951,7 +968,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han ib->length_dw = 0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -973,7 +990,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (adev->vcn.using_unified_queue) + if (adev->vcn.inst[ring->me].using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); @@ -1058,36 +1075,32 @@ enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring) } } -void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev) +void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev, int i) { - int i; unsigned int idx; if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { const struct common_firmware_header *hdr; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - - hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; - /* currently only support 2 FW instances */ - if (i >= 2) { - dev_info(adev->dev, "More then 2 VCN FW instances!\n"); - break; - } - idx = AMDGPU_UCODE_ID_VCN + i; - adev->firmware.ucode[idx].ucode_id = idx; - adev->firmware.ucode[idx].fw = adev->vcn.inst[i].fw; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - - if (amdgpu_ip_version(adev, UVD_HWIP, 0) == - IP_VERSION(4, 0, 3) || - amdgpu_ip_version(adev, UVD_HWIP, 0) == - IP_VERSION(5, 0, 1)) - break; + if (adev->vcn.harvest_config & (1 << i)) + return; + + if ((amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 3) || + amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(5, 0, 1)) + && (i > 0)) + return; + + hdr = (const struct common_firmware_header *)adev->vcn.inst[i].fw->data; + /* currently only support 2 FW instances */ + if (i >= 2) { + dev_info(adev->dev, "More then 2 VCN FW instances!\n"); + return; } + idx = AMDGPU_UCODE_ID_VCN + i; + adev->firmware.ucode[idx].ucode_id = idx; + adev->firmware.ucode[idx].fw = adev->vcn.inst[i].fw; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); } } @@ -1390,10 +1403,33 @@ void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev) struct dentry *root = minor->debugfs_root; char name[32]; - if (adev->vcn.num_vcn_inst <= 1 || !adev->vcn.using_unified_queue) + if (adev->vcn.num_vcn_inst <= 1 || !adev->vcn.inst[0].using_unified_queue) return; sprintf(name, "amdgpu_vcn_sched_mask"); debugfs_create_file(name, 0600, root, adev, &amdgpu_debugfs_vcn_sched_mask_fops); #endif } + +/** + * vcn_set_powergating_state - set VCN block powergating state + * + * @ip_block: amdgpu_ip_block pointer + * @state: power gating state + * + * Set VCN block powergating state + */ +int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block, + enum amd_powergating_state state) +{ + struct amdgpu_device *adev = ip_block->adev; + int ret = 0, i; + + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + + ret |= vinst->set_pg_state(vinst, state); + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index c92f683ee595..26c9c2d90f45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -295,6 +295,8 @@ struct amdgpu_vcn_fw_shared { }; struct amdgpu_vcn_inst { + struct amdgpu_device *adev; + int inst; struct amdgpu_bo *vcpu_bo; void *cpu_addr; uint64_t gpu_addr; @@ -316,6 +318,20 @@ struct amdgpu_vcn_inst { const struct firmware *fw; /* VCN firmware */ uint8_t vcn_config; uint32_t vcn_codec_disable_mask; + atomic_t total_submission_cnt; + struct mutex vcn_pg_lock; + enum amd_powergating_state cur_state; + struct delayed_work idle_work; + unsigned fw_version; + unsigned num_enc_rings; + bool indirect_sram; + struct amdgpu_vcn_reg internal; + struct mutex vcn1_jpeg1_workaround; + int (*pause_dpg_mode)(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); + int (*set_pg_state)(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); + bool using_unified_queue; }; struct amdgpu_vcn_ras { @@ -323,35 +339,25 @@ struct amdgpu_vcn_ras { }; struct amdgpu_vcn { - unsigned fw_version; - struct delayed_work idle_work; - unsigned num_enc_rings; - enum amd_powergating_state cur_state; - bool indirect_sram; - uint8_t num_vcn_inst; struct amdgpu_vcn_inst inst[AMDGPU_MAX_VCN_INSTANCES]; - struct amdgpu_vcn_reg internal; - struct mutex vcn_pg_lock; - struct mutex vcn1_jpeg1_workaround; - atomic_t total_submission_cnt; unsigned harvest_config; - int (*pause_dpg_mode)(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); struct ras_common_if *ras_if; struct amdgpu_vcn_ras *ras; uint16_t inst_mask; uint8_t num_inst_per_aid; - bool using_unified_queue; /* IP reg dump */ uint32_t *ip_dump; uint32_t supported_reset; uint32_t caps; + + bool per_inst_fw; + unsigned fw_version; }; struct amdgpu_fw_shared_rb_ptrs_struct { @@ -500,11 +506,11 @@ enum vcn_ring_type { VCN_UNIFIED_RING, }; -int amdgpu_vcn_early_init(struct amdgpu_device *adev); -int amdgpu_vcn_sw_init(struct amdgpu_device *adev); -int amdgpu_vcn_sw_fini(struct amdgpu_device *adev); -int amdgpu_vcn_suspend(struct amdgpu_device *adev); -int amdgpu_vcn_resume(struct amdgpu_device *adev); +int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i); +int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i); +int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i); +int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i); +int amdgpu_vcn_resume(struct amdgpu_device *adev, int i); void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring); void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring); @@ -522,7 +528,7 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout); enum amdgpu_ring_priority_level amdgpu_vcn_get_enc_ring_prio(int ring); -void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev); +void amdgpu_vcn_setup_ucode(struct amdgpu_device *adev, int i); void amdgpu_vcn_fwlog_init(struct amdgpu_vcn_inst *vcn); void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, @@ -542,4 +548,7 @@ int amdgpu_vcn_sysfs_reset_mask_init(struct amdgpu_device *adev); void amdgpu_vcn_sysfs_reset_mask_fini(struct amdgpu_device *adev); void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev); +int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block, + enum amd_powergating_state state); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index e6f0152e5b08..ab7e73d0e7b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -739,7 +739,7 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev) } } -void amdgpu_detect_virtualization(struct amdgpu_device *adev) +static u32 amdgpu_virt_init_detect_asic(struct amdgpu_device *adev) { uint32_t reg; @@ -775,8 +775,17 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; } + return reg; +} + +static bool amdgpu_virt_init_req_data(struct amdgpu_device *adev, u32 reg) +{ + bool is_sriov = false; + /* we have the ability to check now */ if (amdgpu_sriov_vf(adev)) { + is_sriov = true; + switch (adev->asic_type) { case CHIP_TONGA: case CHIP_FIJI: @@ -805,10 +814,39 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) amdgpu_virt_request_init_data(adev); break; default: /* other chip doesn't support SRIOV */ + is_sriov = false; DRM_ERROR("Unknown asic type: %d!\n", adev->asic_type); break; } } + + return is_sriov; +} + +static void amdgpu_virt_init_ras(struct amdgpu_device *adev) +{ + ratelimit_state_init(&adev->virt.ras.ras_error_cnt_rs, 5 * HZ, 1); + ratelimit_state_init(&adev->virt.ras.ras_cper_dump_rs, 5 * HZ, 1); + + ratelimit_set_flags(&adev->virt.ras.ras_error_cnt_rs, + RATELIMIT_MSG_ON_RELEASE); + ratelimit_set_flags(&adev->virt.ras.ras_cper_dump_rs, + RATELIMIT_MSG_ON_RELEASE); + + mutex_init(&adev->virt.ras.ras_telemetry_mutex); + + adev->virt.ras.cper_rptr = 0; +} + +void amdgpu_virt_init(struct amdgpu_device *adev) +{ + bool is_sriov = false; + uint32_t reg = amdgpu_virt_init_detect_asic(adev); + + is_sriov = amdgpu_virt_init_req_data(adev, reg); + + if (is_sriov) + amdgpu_virt_init_ras(adev); } static bool amdgpu_virt_access_debugfs_is_mmio(struct amdgpu_device *adev) @@ -1288,10 +1326,12 @@ static int amdgpu_virt_req_ras_err_count_internal(struct amdgpu_device *adev, bo * will ignore incoming guest messages. Ratelimit the guest messages to * prevent guest self DOS. */ - if (__ratelimit(&adev->virt.ras_telemetry_rs) || force_update) { + if (__ratelimit(&virt->ras.ras_error_cnt_rs) || force_update) { + mutex_lock(&virt->ras.ras_telemetry_mutex); if (!virt->ops->req_ras_err_count(adev)) amdgpu_virt_cache_host_error_counts(adev, - adev->virt.fw_reserve.ras_telemetry); + virt->fw_reserve.ras_telemetry); + mutex_unlock(&virt->ras.ras_telemetry_mutex); } return 0; @@ -1322,6 +1362,98 @@ int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_bl return 0; } +static int +amdgpu_virt_write_cpers_to_ring(struct amdgpu_device *adev, + struct amdsriov_ras_telemetry *host_telemetry, + u32 *more) +{ + struct amd_sriov_ras_cper_dump *cper_dump = NULL; + struct cper_hdr *entry = NULL; + struct amdgpu_ring *ring = &adev->cper.ring_buf; + uint32_t checksum, used_size, i; + int ret = 0; + + checksum = host_telemetry->header.checksum; + used_size = host_telemetry->header.used_size; + + if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10)) + return 0; + + cper_dump = kmemdup(&host_telemetry->body.cper_dump, used_size, GFP_KERNEL); + if (!cper_dump) + return -ENOMEM; + + if (checksum != amd_sriov_msg_checksum(cper_dump, used_size, 0, 0)) + goto out; + + *more = cper_dump->more; + + if (cper_dump->wptr < adev->virt.ras.cper_rptr) { + dev_warn( + adev->dev, + "guest specified rptr that was too high! guest rptr: 0x%llx, host rptr: 0x%llx\n", + adev->virt.ras.cper_rptr, cper_dump->wptr); + + adev->virt.ras.cper_rptr = cper_dump->wptr; + goto out; + } + + entry = (struct cper_hdr *)&cper_dump->buf[0]; + + for (i = 0; i < cper_dump->count; i++) { + amdgpu_cper_ring_write(ring, entry, entry->record_length); + entry = (struct cper_hdr *)((char *)entry + + entry->record_length); + } + + if (cper_dump->overflow_count) + dev_warn(adev->dev, + "host reported CPER overflow of 0x%llx entries!\n", + cper_dump->overflow_count); + + adev->virt.ras.cper_rptr = cper_dump->wptr; +out: + kfree(cper_dump); + + return ret; +} + +static int amdgpu_virt_req_ras_cper_dump_internal(struct amdgpu_device *adev) +{ + struct amdgpu_virt *virt = &adev->virt; + int ret = 0; + uint32_t more = 0; + + if (!amdgpu_sriov_ras_cper_en(adev)) + return -EOPNOTSUPP; + + do { + if (!virt->ops->req_ras_cper_dump(adev, virt->ras.cper_rptr)) + ret = amdgpu_virt_write_cpers_to_ring( + adev, virt->fw_reserve.ras_telemetry, &more); + else + ret = 0; + } while (more); + + return ret; +} + +int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update) +{ + struct amdgpu_virt *virt = &adev->virt; + int ret = 0; + + if ((__ratelimit(&virt->ras.ras_cper_dump_rs) || force_update) && + down_read_trylock(&adev->reset_domain->sem)) { + mutex_lock(&virt->ras.ras_telemetry_mutex); + ret = amdgpu_virt_req_ras_cper_dump_internal(adev); + mutex_unlock(&virt->ras.ras_telemetry_mutex); + up_read(&adev->reset_domain->sem); + } + + return ret; +} + int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev) { unsigned long ue_count, ce_count; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 0f3ccae5c1ab..9f65487e60f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -96,6 +96,7 @@ struct amdgpu_virt_ops { enum amdgpu_ras_block block); bool (*rcvd_ras_intr)(struct amdgpu_device *adev); int (*req_ras_err_count)(struct amdgpu_device *adev); + int (*req_ras_cper_dump)(struct amdgpu_device *adev, u64 vf_rptr); }; /* @@ -140,6 +141,7 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_MES_INFO_ENABLE = (1 << 8), AMDGIM_FEATURE_RAS_CAPS = (1 << 9), AMDGIM_FEATURE_RAS_TELEMETRY = (1 << 10), + AMDGIM_FEATURE_RAS_CPER = (1 << 11), }; enum AMDGIM_REG_ACCESS_FLAG { @@ -242,6 +244,13 @@ struct amdgpu_virt_ras_err_handler_data { int last_reserved; }; +struct amdgpu_virt_ras { + struct ratelimit_state ras_error_cnt_rs; + struct ratelimit_state ras_cper_dump_rs; + struct mutex ras_telemetry_mutex; + uint64_t cper_rptr; +}; + /* GPU virtualization */ struct amdgpu_virt { uint32_t caps; @@ -284,8 +293,7 @@ struct amdgpu_virt { union amd_sriov_ras_caps ras_en_caps; union amd_sriov_ras_caps ras_telemetry_en_caps; - - struct ratelimit_state ras_telemetry_rs; + struct amdgpu_virt_ras ras; struct amd_sriov_ras_telemetry_error_count count_cache; }; @@ -340,6 +348,9 @@ struct amdgpu_video_codec_info; #define amdgpu_sriov_ras_telemetry_block_en(adev, sriov_blk) \ (amdgpu_sriov_ras_telemetry_en((adev)) && (adev)->virt.ras_telemetry_en_caps.all & BIT(sriov_blk)) +#define amdgpu_sriov_ras_cper_en(adev) \ +((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_CPER) + static inline bool is_virtual_machine(void) { #if defined(CONFIG_X86) @@ -378,7 +389,7 @@ void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev); void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev); void amdgpu_virt_exchange_data(struct amdgpu_device *adev); void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev); -void amdgpu_detect_virtualization(struct amdgpu_device *adev); +void amdgpu_virt_init(struct amdgpu_device *adev); bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev); int amdgpu_virt_enable_access_debugfs(struct amdgpu_device *adev); @@ -406,6 +417,7 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev); int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block, struct ras_err_data *err_data); +int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update); int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev); bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev, enum amdgpu_ras_block block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 03308261f894..fc6d02d0f047 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -627,7 +627,7 @@ static int amdgpu_vkms_resume(struct amdgpu_ip_block *ip_block) return drm_mode_config_helper_resume(adev_to_drm(ip_block->adev)); } -static bool amdgpu_vkms_is_idle(void *handle) +static bool amdgpu_vkms_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index c98b6b35cfdf..7fdf30f1161c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -315,6 +315,7 @@ int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num) switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): xgmi_state_reg_val = xgmi_v6_4_get_link_status(adev, global_link_num); break; default: @@ -818,28 +819,69 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev * num_hops[2:0] = number of hops */ int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev) + struct amdgpu_device *peer_adev) { struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info; uint8_t num_hops_mask = 0x7; int i; + if (!adev->gmc.xgmi.supported) + return 0; + for (i = 0 ; i < top->num_nodes; ++i) if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id) return top->nodes[i].num_hops & num_hops_mask; - return -EINVAL; + + dev_err(adev->dev, "Failed to get xgmi hops count for peer %d.\n", + peer_adev->gmc.xgmi.physical_node_id); + + return 0; } -int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev) +int amdgpu_xgmi_get_bandwidth(struct amdgpu_device *adev, struct amdgpu_device *peer_adev, + enum amdgpu_xgmi_bw_mode bw_mode, enum amdgpu_xgmi_bw_unit bw_unit, + uint32_t *min_bw, uint32_t *max_bw) { - struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info; - int i; + bool peer_mode = bw_mode == AMDGPU_XGMI_BW_MODE_PER_PEER; + int unit_scale = bw_unit == AMDGPU_XGMI_BW_UNIT_MBYTES ? 1000 : 1; + int speed = 25, num_lanes = 16, num_links = !peer_mode ? 1 : -1; - for (i = 0 ; i < top->num_nodes; ++i) - if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id) - return top->nodes[i].num_links; - return -EINVAL; + if (!(min_bw && max_bw)) + return -EINVAL; + + *min_bw = 0; + *max_bw = 0; + + if (!adev->gmc.xgmi.supported) + return -ENODATA; + + if (peer_mode && !peer_adev) + return -EINVAL; + + if (peer_mode) { + struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info; + int i; + + for (i = 0 ; i < top->num_nodes; ++i) { + if (top->nodes[i].node_id != peer_adev->gmc.xgmi.node_id) + continue; + + num_links = top->nodes[i].num_links; + break; + } + } + + if (num_links == -1) { + dev_err(adev->dev, "Failed to get number of xgmi links for peer %d.\n", + peer_adev->gmc.xgmi.physical_node_id); + } else if (num_links) { + int per_link_bw = (speed * num_lanes * unit_scale)/BITS_PER_BYTE; + + *min_bw = per_link_bw; + *max_bw = num_links * per_link_bw; + } + + return 0; } bool amdgpu_xgmi_get_is_sharing_enabled(struct amdgpu_device *adev, @@ -1128,8 +1170,8 @@ static int xgmi_v6_4_0_aca_bank_parser(struct aca_handle *handle, struct aca_ban break; case ACA_SMU_TYPE_CE: count = ext_error_code == 6 ? count : 0ULL; - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, count); + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, count); break; default: return -EINVAL; @@ -1164,6 +1206,7 @@ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_comm switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL, &xgmi_v6_4_0_aca_info, NULL); if (r) @@ -1223,6 +1266,7 @@ static void amdgpu_xgmi_legacy_reset_ras_error_count(struct amdgpu_device *adev) switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++) pcs_clear_status(adev, xgmi3x16_pcs_err_status_reg_v6_4[i]); @@ -1257,6 +1301,7 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) { switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): xgmi_v6_4_0_reset_ras_error_count(adev); break; default: @@ -1282,7 +1327,9 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev, if (amdgpu_ip_version(adev, XGMI_HWIP, 0) == IP_VERSION(6, 1, 0) || amdgpu_ip_version(adev, XGMI_HWIP, 0) == - IP_VERSION(6, 4, 0)) { + IP_VERSION(6, 4, 0) || + amdgpu_ip_version(adev, XGMI_HWIP, 0) == + IP_VERSION(6, 4, 1)) { pcs_ras_fields = &xgmi3x16_pcs_ras_fields[0]; field_array_size = ARRAY_SIZE(xgmi3x16_pcs_ras_fields); } else { @@ -1390,6 +1437,7 @@ static void amdgpu_xgmi_legacy_query_ras_error_count(struct amdgpu_device *adev, switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): /* check xgmi3x16 pcs error */ for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++) { data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_v6_4[i]); @@ -1486,6 +1534,7 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, { switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) { case IP_VERSION(6, 4, 0): + case IP_VERSION(6, 4, 1): xgmi_v6_4_0_query_ras_error_count(adev, ras_error_status); break; default: @@ -1673,3 +1722,34 @@ int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev, return r; } + +bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, + struct amdgpu_device *bo_adev) +{ + return (amdgpu_use_xgmi_p2p && adev != bo_adev && + adev->gmc.xgmi.hive_id && + adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id); +} + +void amdgpu_xgmi_early_init(struct amdgpu_device *adev) +{ + if (!adev->gmc.xgmi.supported) + return; + + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 4, 0): + case IP_VERSION(9, 4, 1): + case IP_VERSION(9, 4, 2): + adev->gmc.xgmi.max_speed = XGMI_SPEED_25GT; + adev->gmc.xgmi.max_width = 16; + break; + case IP_VERSION(9, 4, 3): + case IP_VERSION(9, 4, 4): + case IP_VERSION(9, 5, 0): + adev->gmc.xgmi.max_speed = XGMI_SPEED_32GT; + adev->gmc.xgmi.max_width = 16; + break; + default: + break; + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h index d1282b4c6348..32dabba4062f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h @@ -23,9 +23,14 @@ #define __AMDGPU_XGMI_H__ #include <drm/task_barrier.h> -#include "amdgpu_psp.h" #include "amdgpu_ras.h" +enum amdgpu_xgmi_link_speed { + XGMI_SPEED_16GT = 16, + XGMI_SPEED_25GT = 25, + XGMI_SPEED_32GT = 32 +}; + struct amdgpu_hive_info { struct kobject kobj; uint64_t hive_id; @@ -55,29 +60,63 @@ struct amdgpu_pcs_ras_field { uint32_t pcs_err_shift; }; -extern struct amdgpu_xgmi_ras xgmi_ras; +/** + * Bandwidth range reporting comes in two modes. + * + * PER_LINK - range for any xgmi link + * PER_PEER - range of max of single xgmi link to max of multiple links based on source peer + */ +enum amdgpu_xgmi_bw_mode { + AMDGPU_XGMI_BW_MODE_PER_LINK = 0, + AMDGPU_XGMI_BW_MODE_PER_PEER +}; + +enum amdgpu_xgmi_bw_unit { + AMDGPU_XGMI_BW_UNIT_GBYTES = 0, + AMDGPU_XGMI_BW_UNIT_MBYTES +}; + +struct amdgpu_xgmi_ras { + struct amdgpu_ras_block_object ras_block; +}; +extern struct amdgpu_xgmi_ras xgmi_ras; + +struct amdgpu_xgmi { + /* from psp */ + u64 node_id; + u64 hive_id; + /* fixed per family */ + u64 node_segment_size; + /* physical node (0-3) */ + unsigned physical_node_id; + /* number of nodes (0-4) */ + unsigned num_physical_nodes; + /* gpu list in the same hive */ + struct list_head head; + bool supported; + struct ras_common_if *ras_if; + bool connected_to_cpu; + struct amdgpu_xgmi_ras *ras; + enum amdgpu_xgmi_link_speed max_speed; + uint8_t max_width; +}; + struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev); void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive); int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev); int amdgpu_xgmi_add_device(struct amdgpu_device *adev); int amdgpu_xgmi_remove_device(struct amdgpu_device *adev); int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate); -int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev); -int amdgpu_xgmi_get_num_links(struct amdgpu_device *adev, - struct amdgpu_device *peer_adev); +int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, struct amdgpu_device *peer_adev); +int amdgpu_xgmi_get_bandwidth(struct amdgpu_device *adev, struct amdgpu_device *peer_adev, + enum amdgpu_xgmi_bw_mode bw_mode, enum amdgpu_xgmi_bw_unit bw_unit, + uint32_t *min_bw, uint32_t *max_bw); bool amdgpu_xgmi_get_is_sharing_enabled(struct amdgpu_device *adev, struct amdgpu_device *peer_adev); uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev, uint64_t addr); -static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, - struct amdgpu_device *bo_adev) -{ - return (amdgpu_use_xgmi_p2p && - adev != bo_adev && - adev->gmc.xgmi.hive_id && - adev->gmc.xgmi.hive_id == bo_adev->gmc.xgmi.hive_id); -} +bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, + struct amdgpu_device *bo_adev); int amdgpu_xgmi_ras_sw_init(struct amdgpu_device *adev); int amdgpu_xgmi_reset_on_init(struct amdgpu_device *adev); @@ -87,4 +126,7 @@ int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev, int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num); +void amdgpu_xgmi_early_init(struct amdgpu_device *adev); +uint32_t amdgpu_xgmi_get_max_bandwidth(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index b4f9c2f4e92c..d6ac2652f0ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -97,11 +97,12 @@ union amd_sriov_msg_feature_flags { uint32_t pp_one_vf_mode : 1; uint32_t reg_indirect_acc : 1; uint32_t av1_support : 1; - uint32_t vcn_rb_decouple : 1; + uint32_t vcn_rb_decouple : 1; uint32_t mes_info_dump_enable : 1; uint32_t ras_caps : 1; uint32_t ras_telemetry : 1; - uint32_t reserved : 21; + uint32_t ras_cper : 1; + uint32_t reserved : 20; } flags; uint32_t all; }; @@ -328,21 +329,25 @@ enum amd_sriov_mailbox_request_message { MB_REQ_MSG_READY_TO_RESET = 201, MB_REQ_MSG_RAS_POISON = 202, MB_REQ_RAS_ERROR_COUNT = 203, + MB_REQ_RAS_CPER_DUMP = 204, }; /* mailbox message send from host to guest */ enum amd_sriov_mailbox_response_message { - MB_RES_MSG_CLR_MSG_BUF = 0, - MB_RES_MSG_READY_TO_ACCESS_GPU = 1, - MB_RES_MSG_FLR_NOTIFICATION, - MB_RES_MSG_FLR_NOTIFICATION_COMPLETION, - MB_RES_MSG_SUCCESS, - MB_RES_MSG_FAIL, - MB_RES_MSG_QUERY_ALIVE, - MB_RES_MSG_GPU_INIT_DATA_READY, - MB_RES_MSG_RAS_ERROR_COUNT_READY = 11, - - MB_RES_MSG_TEXT_MESSAGE = 255 + MB_RES_MSG_CLR_MSG_BUF = 0, + MB_RES_MSG_READY_TO_ACCESS_GPU = 1, + MB_RES_MSG_FLR_NOTIFICATION = 2, + MB_RES_MSG_FLR_NOTIFICATION_COMPLETION = 3, + MB_RES_MSG_SUCCESS = 4, + MB_RES_MSG_FAIL = 5, + MB_RES_MSG_QUERY_ALIVE = 6, + MB_RES_MSG_GPU_INIT_DATA_READY = 7, + MB_RES_MSG_RAS_POISON_READY = 8, + MB_RES_MSG_PF_SOFT_FLR_NOTIFICATION = 9, + MB_RES_MSG_GPU_RMA = 10, + MB_RES_MSG_RAS_ERROR_COUNT_READY = 11, + MB_REQ_RAS_CPER_DUMP_READY = 14, + MB_RES_MSG_TEXT_MESSAGE = 255 }; enum amd_sriov_ras_telemetry_gpu_block { @@ -386,11 +391,20 @@ struct amd_sriov_ras_telemetry_error_count { } block[RAS_TELEMETRY_GPU_BLOCK_COUNT]; }; +struct amd_sriov_ras_cper_dump { + uint32_t more; + uint64_t overflow_count; + uint64_t count; + uint64_t wptr; + uint32_t buf[]; +}; + struct amdsriov_ras_telemetry { struct amd_sriov_ras_telemetry_header header; union { struct amd_sriov_ras_telemetry_error_count error_count; + struct amd_sriov_ras_cper_dump cper_dump; } body; }; diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 08d6787893b3..9cd63b4177bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -2148,7 +2148,7 @@ static int cik_common_resume(struct amdgpu_ip_block *ip_block) return cik_common_hw_init(ip_block); } -static bool cik_common_is_idle(void *handle) +static bool cik_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c index 444563486769..41f4705bdbbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c @@ -345,9 +345,9 @@ static int cik_ih_resume(struct amdgpu_ip_block *ip_block) return cik_ih_hw_init(ip_block); } -static bool cik_ih_is_idle(void *handle) +static bool cik_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (tmp & SRBM_STATUS__IH_BUSY_MASK) diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index d9bd8f3f17e2..508cea965983 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -1025,9 +1025,9 @@ static int cik_sdma_resume(struct amdgpu_ip_block *ip_block) return cik_sdma_hw_init(ip_block); } -static bool cik_sdma_is_idle(void *handle) +static bool cik_sdma_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS2); if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/cikd.h b/drivers/gpu/drm/amd/amdgpu/cikd.h index 06088d52d81c..279288365940 100644 --- a/drivers/gpu/drm/amd/amdgpu/cikd.h +++ b/drivers/gpu/drm/amd/amdgpu/cikd.h @@ -51,6 +51,15 @@ #define HPD4_REGISTER_OFFSET (0x1813 - 0x1807) #define HPD5_REGISTER_OFFSET (0x1816 - 0x1807) +/* audio endpt instance offsets */ +#define AUD0_REGISTER_OFFSET (0x1780 - 0x1780) +#define AUD1_REGISTER_OFFSET (0x1786 - 0x1780) +#define AUD2_REGISTER_OFFSET (0x178c - 0x1780) +#define AUD3_REGISTER_OFFSET (0x1792 - 0x1780) +#define AUD4_REGISTER_OFFSET (0x1798 - 0x1780) +#define AUD5_REGISTER_OFFSET (0x179d - 0x1780) +#define AUD6_REGISTER_OFFSET (0x17a4 - 0x1780) + #define BONAIRE_GB_ADDR_CONFIG_GOLDEN 0x12010001 #define HAWAII_GB_ADDR_CONFIG_GOLDEN 0x12011003 diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index 82586b76aeda..2f891fb846d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -341,9 +341,9 @@ static int cz_ih_resume(struct amdgpu_ip_block *ip_block) return cz_ih_hw_init(ip_block); } -static bool cz_ih_is_idle(void *handle) +static bool cz_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY)) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index c5e3d2251b18..df401aded662 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2970,7 +2970,7 @@ static int dce_v10_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v10_0_is_idle(void *handle) +static bool dce_v10_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index ea42a4472bf6..80f01c3989cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3108,7 +3108,7 @@ static int dce_v11_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v11_0_is_idle(void *handle) +static bool dce_v11_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 915804a6a1d7..ac51b7a6e8d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -206,9 +206,9 @@ static void dce_v6_0_page_flip(struct amdgpu_device *adev, /* update the scanout addresses */ WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, upper_32_bits(crtc_base)); + /* writing to the low address triggers the update */ WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset, (u32)crtc_base); - /* post the write */ RREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + amdgpu_crtc->crtc_offset); } @@ -218,11 +218,11 @@ static int dce_v6_0_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, { if ((crtc < 0) || (crtc >= adev->mode_info.num_crtc)) return -EINVAL; + *vbl = RREG32(mmCRTC_V_BLANK_START_END + crtc_offsets[crtc]); *position = RREG32(mmCRTC_STATUS_POSITION + crtc_offsets[crtc]); return 0; - } /** @@ -242,7 +242,8 @@ static bool dce_v6_0_hpd_sense(struct amdgpu_device *adev, if (hpd >= adev->mode_info.num_hpd) return connected; - if (RREG32(mmDC_HPD1_INT_STATUS + hpd_offsets[hpd]) & DC_HPD1_INT_STATUS__DC_HPD1_SENSE_MASK) + if (RREG32(mmDC_HPD1_INT_STATUS + hpd_offsets[hpd]) & + DC_HPD1_INT_STATUS__DC_HPD1_SENSE_MASK) connected = true; return connected; @@ -370,13 +371,41 @@ static u32 dce_v6_0_hpd_get_gpio_reg(struct amdgpu_device *adev) return mmDC_GPIO_HPD_A; } +static bool dce_v6_0_is_display_hung(struct amdgpu_device *adev) +{ + u32 crtc_hung = 0; + u32 crtc_status[6]; + u32 i, j, tmp; + + for (i = 0; i < adev->mode_info.num_crtc; i++) { + if (RREG32(mmCRTC_CONTROL + crtc_offsets[i]) & CRTC_CONTROL__CRTC_MASTER_EN_MASK) { + crtc_status[i] = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]); + crtc_hung |= (1 << i); + } + } + + for (j = 0; j < 10; j++) { + for (i = 0; i < adev->mode_info.num_crtc; i++) { + if (crtc_hung & (1 << i)) { + tmp = RREG32(mmCRTC_STATUS_HV_COUNT + crtc_offsets[i]); + if (tmp != crtc_status[i]) + crtc_hung &= ~(1 << i); + } + } + if (crtc_hung == 0) + return false; + udelay(100); + } + + return true; +} + static void dce_v6_0_set_vga_render_state(struct amdgpu_device *adev, bool render) { if (!render) WREG32(mmVGA_RENDER_CONTROL, RREG32(mmVGA_RENDER_CONTROL) & VGA_VSTATUS_CNTL); - } static int dce_v6_0_get_num_crtc(struct amdgpu_device *adev) @@ -419,7 +448,6 @@ void dce_v6_0_disable_dce(struct amdgpu_device *adev) static void dce_v6_0_program_fmt(struct drm_encoder *encoder) { - struct drm_device *dev = encoder->dev; struct amdgpu_device *adev = drm_to_adev(dev); struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); @@ -895,8 +923,8 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev, wm_high.dram_channels = dram_channels; wm_high.num_heads = num_heads; - if (adev->pm.dpm_enabled) { /* watermark for low clocks */ + if (adev->pm.dpm_enabled) { wm_low.yclk = amdgpu_dpm_get_mclk(adev, true) * 10; wm_low.sclk = @@ -1006,6 +1034,20 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev, } /* watermark setup */ +/** + * dce_v6_0_line_buffer_adjust - Set up the line buffer + * + * @adev: amdgpu_device pointer + * @amdgpu_crtc: the selected display controller + * @mode: the current display mode on the selected display + * controller + * @other_mode: the display mode of another display controller + * that may be sharing the line buffer + * + * Setup up the line buffer allocation for + * the selected display controller (CIK). + * Returns the line buffer size in pixels. + */ static u32 dce_v6_0_line_buffer_adjust(struct amdgpu_device *adev, struct amdgpu_crtc *amdgpu_crtc, struct drm_display_mode *mode, @@ -1386,6 +1428,8 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev) adev->mode_info.audio.pin[i].connected = false; adev->mode_info.audio.pin[i].offset = pin_offsets[i]; adev->mode_info.audio.pin[i].id = i; + /* disable audio. it will be set up later */ + /* XXX remove once we switch to ip funcs */ dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); } @@ -2865,14 +2909,35 @@ static int dce_v6_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v6_0_is_idle(void *handle) +static bool dce_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } static int dce_v6_0_soft_reset(struct amdgpu_ip_block *ip_block) { - DRM_INFO("xxxx: dce_v6_0_soft_reset --- no impl!!\n"); + u32 srbm_soft_reset = 0, tmp; + struct amdgpu_device *adev = ip_block->adev; + + if (dce_v6_0_is_display_hung(adev)) + srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_DC_MASK; + + if (srbm_soft_reset) { + tmp = RREG32(mmSRBM_SOFT_RESET); + tmp |= srbm_soft_reset; + dev_info(adev->dev, "SRBM_SOFT_RESET=0x%08X\n", tmp); + WREG32(mmSRBM_SOFT_RESET, tmp); + tmp = RREG32(mmSRBM_SOFT_RESET); + + udelay(50); + + tmp &= ~srbm_soft_reset; + WREG32(mmSRBM_SOFT_RESET, tmp); + tmp = RREG32(mmSRBM_SOFT_RESET); + + /* Wait a little for things to settle down */ + udelay(50); + } return 0; } @@ -3148,7 +3213,6 @@ static int dce_v6_0_hpd_irq(struct amdgpu_device *adev, } return 0; - } static int dce_v6_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, @@ -3281,8 +3345,7 @@ static void dce_v6_0_ext_commit(struct drm_encoder *encoder) } -static void -dce_v6_0_ext_mode_set(struct drm_encoder *encoder, +static void dce_v6_0_ext_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { @@ -3294,8 +3357,7 @@ static void dce_v6_0_ext_disable(struct drm_encoder *encoder) } -static void -dce_v6_0_ext_dpms(struct drm_encoder *encoder, int mode) +static void dce_v6_0_ext_dpms(struct drm_encoder *encoder, int mode) { } @@ -3366,7 +3428,6 @@ static void dce_v6_0_encoder_add(struct amdgpu_device *adev, amdgpu_encoder->devices |= supported_device; return; } - } /* add a new one */ diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index f2edc0fece5b..07358546581f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1395,13 +1395,13 @@ static void dce_v8_0_audio_enable(struct amdgpu_device *adev, } static const u32 pin_offsets[7] = { - (0x1780 - 0x1780), - (0x1786 - 0x1780), - (0x178c - 0x1780), - (0x1792 - 0x1780), - (0x1798 - 0x1780), - (0x179d - 0x1780), - (0x17a4 - 0x1780), + AUD0_REGISTER_OFFSET, + AUD1_REGISTER_OFFSET, + AUD2_REGISTER_OFFSET, + AUD3_REGISTER_OFFSET, + AUD4_REGISTER_OFFSET, + AUD5_REGISTER_OFFSET, + AUD6_REGISTER_OFFSET, }; static int dce_v8_0_audio_init(struct amdgpu_device *adev) @@ -2887,7 +2887,7 @@ static int dce_v8_0_resume(struct amdgpu_ip_block *ip_block) return amdgpu_display_resume_helper(adev); } -static bool dce_v8_0_is_idle(void *handle) +static bool dce_v8_0_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f54617c6c071..6d514efb0a6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7583,9 +7583,9 @@ static int gfx_v10_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v10_0_hw_init(ip_block); } -static bool gfx_v10_0_is_idle(void *handle) +static bool gfx_v10_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 57f1e2b50e5a..2b3ba404955d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4787,9 +4787,9 @@ static int gfx_v11_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v11_0_hw_init(ip_block); } -static bool gfx_v11_0_is_idle(void *handle) +static bool gfx_v11_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, regGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 47490309045f..926fb536bbff 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -3695,9 +3695,9 @@ static int gfx_v12_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v12_0_hw_init(ip_block); } -static bool gfx_v12_0_is_idle(void *handle) +static bool gfx_v12_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, regGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index f26e2cdec07a..2f5cf87ede88 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -3167,9 +3167,9 @@ static int gfx_v6_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v6_0_hw_init(ip_block); } -static bool gfx_v6_0_is_idle(void *handle) +static bool gfx_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (RREG32(mmGRBM_STATUS) & GRBM_STATUS__GUI_ACTIVE_MASK) return false; @@ -3183,7 +3183,7 @@ static int gfx_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v6_0_is_idle(adev)) + if (gfx_v6_0_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 84745b2453ab..8181bd0e4f18 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4515,9 +4515,9 @@ static int gfx_v7_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v7_0_hw_init(ip_block); } -static bool gfx_v7_0_is_idle(void *handle) +static bool gfx_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (RREG32(mmGRBM_STATUS) & GRBM_STATUS__GUI_ACTIVE_MASK) return false; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 6add76ef75e8..d116a2e2f469 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4851,9 +4851,9 @@ static int gfx_v8_0_kcq_disable(struct amdgpu_device *adev) return r; } -static bool gfx_v8_0_is_idle(void *handle) +static bool gfx_v8_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32(mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE) || RREG32(mmGRBM_STATUS2) != 0x8) @@ -4892,7 +4892,7 @@ static int gfx_v8_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v8_0_is_idle(adev)) + if (gfx_v8_0_is_idle(ip_block)) return 0; udelay(1); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index e144bce938d5..d345285ea885 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2637,7 +2637,10 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev) u32 tmp; int i; - WREG32_FIELD15_RLC(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff); + if (!amdgpu_sriov_vf(adev) || + amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 2)) { + WREG32_FIELD15_RLC(GC, 0, GRBM_CNTL, READ_TIMEOUT, 0xff); + } gfx_v9_0_tiling_mode_table_init(adev); @@ -4042,7 +4045,8 @@ static int gfx_v9_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2)) + if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 2) && + !amdgpu_sriov_vf(adev)) gfx_v9_4_2_set_power_brake_sequence(adev); return r; @@ -4110,9 +4114,9 @@ static int gfx_v9_0_resume(struct amdgpu_ip_block *ip_block) return gfx_v9_0_hw_init(ip_block); } -static bool gfx_v9_0_is_idle(void *handle) +static bool gfx_v9_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; if (REG_GET_FIELD(RREG32_SOC15(GC, 0, mmGRBM_STATUS), GRBM_STATUS, GUI_ACTIVE)) @@ -4127,7 +4131,7 @@ static int gfx_v9_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v9_0_is_idle(adev)) + if (gfx_v9_0_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index c88564de50cd..476542b6e7b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -349,18 +349,7 @@ static void gfx_v9_4_3_init_golden_registers(struct amdgpu_device *adev) WREG32_SOC15(GC, dev_inst, regGB_ADDR_CONFIG, GOLDEN_GB_ADDR_CONFIG); - if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0)) { - WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, SPARE, 0x1); - } else { - /* Golden settings applied by driver for ASIC with rev_id 0 */ - if (adev->rev_id == 0) { - WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL1, - REDUCE_FIFO_DEPTH_BY_2, 2); - } else { - WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, - SPARE, 0x1); - } - } + WREG32_FIELD15_PREREG(GC, dev_inst, TCP_UTCL1_CNTL2, SPARE, 0x1); } } @@ -563,17 +552,6 @@ out: return err; } -static bool gfx_v9_4_3_should_disable_gfxoff(struct pci_dev *pdev) -{ - return true; -} - -static void gfx_v9_4_3_check_if_need_gfxoff(struct amdgpu_device *adev) -{ - if (gfx_v9_4_3_should_disable_gfxoff(adev->pdev)) - adev->pm.pp_feature &= ~PP_GFXOFF_MASK; -} - static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, const char *chip_name) { @@ -600,8 +578,6 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, adev->gfx.mec2_fw_version = adev->gfx.mec_fw_version; adev->gfx.mec2_feature_version = adev->gfx.mec_feature_version; - gfx_v9_4_3_check_if_need_gfxoff(adev); - out: if (err) amdgpu_ucode_release(&adev->gfx.mec_fw); @@ -896,9 +872,10 @@ static int gfx_v9_4_3_aca_bank_parser(struct aca_handle *handle, ACA_ERROR_TYPE_UE, 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); ret = aca_error_cache_log_bank_error(handle, &info, - ACA_ERROR_TYPE_CE, ACA_REG__MISC0__ERRCNT(misc0)); + bank->aca_err_type, + ACA_REG__MISC0__ERRCNT(misc0)); break; default: return -EINVAL; @@ -939,8 +916,6 @@ static const struct aca_info gfx_v9_4_3_aca_info = { static int gfx_v9_4_3_gpu_early_init(struct amdgpu_device *adev) { - u32 gb_addr_config; - adev->gfx.funcs = &gfx_v9_4_3_gfx_funcs; adev->gfx.ras = &gfx_v9_4_3_ras; @@ -949,9 +924,7 @@ static int gfx_v9_4_3_gpu_early_init(struct amdgpu_device *adev) adev->gfx.config.sc_prim_fifo_size_backend = 0x100; adev->gfx.config.sc_hiz_tile_fifo_size = 0x30; adev->gfx.config.sc_earlyz_tile_fifo_size = 0x4C0; - gb_addr_config = RREG32_SOC15(GC, GET_INST(GC, 0), regGB_ADDR_CONFIG); - - adev->gfx.config.gb_addr_config = gb_addr_config; + adev->gfx.config.gb_addr_config = GOLDEN_GB_ADDR_CONFIG; adev->gfx.config.gb_addr_config_fields.num_pipes = 1 << REG_GET_FIELD( @@ -1362,10 +1335,8 @@ static void gfx_v9_4_3_xcc_init_pg(struct amdgpu_device *adev, int xcc_id) { /* * Rlc save restore list is workable since v2_1. - * And it's needed by gfxoff feature. */ - if (adev->gfx.rlc.is_rlc_v2_1) - gfx_v9_4_3_xcc_enable_save_restore_machine(adev, xcc_id); + gfx_v9_4_3_xcc_enable_save_restore_machine(adev, xcc_id); } static void gfx_v9_4_3_xcc_disable_gpa_mode(struct amdgpu_device *adev, int xcc_id) @@ -2408,9 +2379,9 @@ static int gfx_v9_4_3_resume(struct amdgpu_ip_block *ip_block) return gfx_v9_4_3_hw_init(ip_block); } -static bool gfx_v9_4_3_is_idle(void *handle) +static bool gfx_v9_4_3_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, num_xcc; num_xcc = NUM_XCC(adev->gfx.xcc_mask); @@ -2428,7 +2399,7 @@ static int gfx_v9_4_3_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gfx_v9_4_3_is_idle(adev)) + if (gfx_v9_4_3_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 0e3ddea7b8e0..a7bfc9f41d0e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -92,12 +92,12 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) { uint64_t value; - /* Program the AGP BAR */ - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0); - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); - WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); - if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) { + /* Program the AGP BAR */ + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BASE, 0); + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24); + WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); + /* Program the system aperture low logical page number. */ WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index edf6cf42f141..95d894a231fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1076,7 +1076,7 @@ static int gmc_v10_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v10_0_is_idle(void *handle) +static bool gmc_v10_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v10.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index f86d0650a05e..ad099f136f84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -987,7 +987,7 @@ static int gmc_v11_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v11_0_is_idle(void *handle) +static bool gmc_v11_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v11.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index c6d45d0fb9d1..ea7c32d8380b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -984,7 +984,7 @@ static int gmc_v12_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v12_0_is_idle(void *handle) +static bool gmc_v12_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v11.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 2245dda92021..a992e79d9581 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -957,9 +957,9 @@ static int gmc_v6_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v6_0_is_idle(void *handle) +static bool gmc_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); @@ -976,7 +976,7 @@ static int gmc_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (gmc_v6_0_is_idle(adev)) + if (gmc_v6_0_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 9aac4b1101e3..83e39f16044a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -1142,9 +1142,9 @@ static int gmc_v7_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v7_0_is_idle(void *handle) +static bool gmc_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (tmp & (SRBM_STATUS__MCB_BUSY_MASK | SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 744081652d42..99ca08e9bdb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1263,9 +1263,9 @@ static int gmc_v8_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v8_0_is_idle(void *handle) +static bool gmc_v8_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (tmp & (SRBM_STATUS__MCB_BUSY_MASK | SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index a80f3e2bcba8..783e0c3b86b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1607,9 +1607,8 @@ static void gmc_v9_0_init_nps_details(struct amdgpu_device *adev) /* Mode detected by hardware and supported modes available */ if ((mode != UNKNOWN_MEMORY_PARTITION_MODE) && supp_modes) { - for (i = AMDGPU_NPS1_PARTITION_MODE; - supp_modes && i <= AMDGPU_NPS8_PARTITION_MODE; i++) { - if (supp_modes & BIT(i - 1)) + while ((i = ffs(supp_modes))) { + if (AMDGPU_ALL_NPS_MASK & BIT(i)) adev->gmc.supported_nps_modes |= BIT(i); supp_modes &= supp_modes - 1; } @@ -2543,7 +2542,7 @@ static int gmc_v9_0_resume(struct amdgpu_ip_block *ip_block) return 0; } -static bool gmc_v9_0_is_idle(void *handle) +static bool gmc_v9_0_is_idle(struct amdgpu_ip_block *ip_block) { /* MC is always ready in GMC v9.*/ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c index 8ac3d3282268..1317ede131b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c @@ -335,9 +335,9 @@ static int iceland_ih_resume(struct amdgpu_ip_block *ip_block) return iceland_ih_hw_init(ip_block); } -static bool iceland_ih_is_idle(void *handle) +static bool iceland_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY)) diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index 7198ddfaa8f4..eb4185dcbd1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -652,7 +652,7 @@ static int ih_v6_0_resume(struct amdgpu_ip_block *ip_block) return ih_v6_0_hw_init(ip_block); } -static bool ih_v6_0_is_idle(void *handle) +static bool ih_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c index 342b166c136d..068ed849dbad 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c @@ -631,7 +631,7 @@ static int ih_v6_1_resume(struct amdgpu_ip_block *ip_block) return ih_v6_1_hw_init(ip_block); } -static bool ih_v6_1_is_idle(void *handle) +static bool ih_v6_1_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c index 71c1c77035e0..40a3530e0453 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c @@ -621,7 +621,7 @@ static int ih_v7_0_resume(struct amdgpu_ip_block *ip_block) return ih_v7_0_hw_init(ip_block); } -static bool ih_v7_0_is_idle(void *handle) +static bool ih_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c index 964c29ef25dc..0027a639c7e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.c @@ -50,26 +50,29 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp_base = adev->rmmio_base; - isp->isp_cell = kcalloc(2, sizeof(struct mfd_cell), GFP_KERNEL); + isp->isp_cell = kcalloc(3, sizeof(struct mfd_cell), GFP_KERNEL); if (!isp->isp_cell) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd cell alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd cell alloc failed\n", __func__); goto failure; } - num_res = MAX_ISP410_MEM_RES + MAX_ISP410_SENSOR_RES + MAX_ISP410_INT_SRC; + num_res = MAX_ISP410_MEM_RES + MAX_ISP410_INT_SRC; isp->isp_res = kcalloc(num_res, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } isp->isp_pdata = kzalloc(sizeof(*isp->isp_pdata), GFP_KERNEL); if (!isp->isp_pdata) { r = -ENOMEM; - DRM_ERROR("%s: isp platform data alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp platform data alloc failed\n", __func__); goto failure; } @@ -88,14 +91,7 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp->isp_res[1].start = isp_base + ISP410_PHY0_OFFSET; isp->isp_res[1].end = isp_base + ISP410_PHY0_OFFSET + ISP410_PHY0_SIZE; - isp->isp_res[2].name = "isp_gpio_sensor0_reg"; - isp->isp_res[2].flags = IORESOURCE_MEM; - isp->isp_res[2].start = isp_base + ISP410_GPIO_SENSOR0_OFFSET; - isp->isp_res[2].end = isp_base + ISP410_GPIO_SENSOR0_OFFSET + - ISP410_GPIO_SENSOR0_SIZE; - - for (idx = MAX_ISP410_MEM_RES + MAX_ISP410_SENSOR_RES, int_idx = 0; - idx < num_res; idx++, int_idx++) { + for (idx = MAX_ISP410_MEM_RES, int_idx = 0; idx < num_res; idx++, int_idx++) { isp->isp_res[idx].name = "isp_4_1_0_irq"; isp->isp_res[idx].flags = IORESOURCE_IRQ; isp->isp_res[idx].start = @@ -110,11 +106,12 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp->isp_cell[0].platform_data = isp->isp_pdata; isp->isp_cell[0].pdata_size = sizeof(struct isp_platform_data); - isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), - GFP_KERNEL); + /* initialize isp i2c platform data */ + isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_i2c_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } @@ -129,9 +126,31 @@ static int isp_v4_1_0_hw_init(struct amdgpu_isp *isp) isp->isp_cell[1].platform_data = isp->isp_pdata; isp->isp_cell[1].pdata_size = sizeof(struct isp_platform_data); - r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 2); + /* initialize isp gpiochip platform data */ + isp->isp_gpio_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); + if (!isp->isp_gpio_res) { + r = -ENOMEM; + drm_err(&adev->ddev, + "%s: isp gpio res alloc failed\n", __func__); + goto failure; + } + + isp->isp_gpio_res[0].name = "isp_gpio_reg"; + isp->isp_gpio_res[0].flags = IORESOURCE_MEM; + isp->isp_gpio_res[0].start = isp_base + ISP410_GPIO_SENSOR_OFFSET; + isp->isp_gpio_res[0].end = isp_base + ISP410_GPIO_SENSOR_OFFSET + + ISP410_GPIO_SENSOR_SIZE; + + isp->isp_cell[2].name = "amdisp-pinctrl"; + isp->isp_cell[2].num_resources = 1; + isp->isp_cell[2].resources = &isp->isp_gpio_res[0]; + isp->isp_cell[2].platform_data = isp->isp_pdata; + isp->isp_cell[2].pdata_size = sizeof(struct isp_platform_data); + + r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 3); if (r) { - DRM_ERROR("%s: add mfd hotplug device failed\n", __func__); + drm_err(&adev->ddev, + "%s: add mfd hotplug device failed\n", __func__); goto failure; } @@ -143,6 +162,7 @@ failure: kfree(isp->isp_res); kfree(isp->isp_cell); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return r; } @@ -155,6 +175,7 @@ static int isp_v4_1_0_hw_fini(struct amdgpu_isp *isp) kfree(isp->isp_cell); kfree(isp->isp_pdata); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h index 7db24c0f1080..4d239198edd0 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_0.h @@ -42,8 +42,8 @@ #define ISP410_I2C0_OFFSET 0x66400 #define ISP410_I2C0_SIZE 0x100 -#define ISP410_GPIO_SENSOR0_OFFSET 0x6613C -#define ISP410_GPIO_SENSOR0_SIZE 0x4 +#define ISP410_GPIO_SENSOR_OFFSET 0x6613C +#define ISP410_GPIO_SENSOR_SIZE 0x54 void isp_v4_1_0_set_isp_funcs(struct amdgpu_isp *isp); diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index b56f27295468..69dd92f6e86d 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -50,27 +50,30 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp_base = adev->rmmio_base; - isp->isp_cell = kcalloc(2, sizeof(struct mfd_cell), GFP_KERNEL); + isp->isp_cell = kcalloc(3, sizeof(struct mfd_cell), GFP_KERNEL); if (!isp->isp_cell) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd cell alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd cell alloc failed\n", __func__); goto failure; } - num_res = MAX_ISP411_MEM_RES + MAX_ISP411_SENSOR_RES + MAX_ISP411_INT_SRC; + num_res = MAX_ISP411_MEM_RES + MAX_ISP411_INT_SRC; isp->isp_res = kcalloc(num_res, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } isp->isp_pdata = kzalloc(sizeof(*isp->isp_pdata), GFP_KERNEL); if (!isp->isp_pdata) { r = -ENOMEM; - DRM_ERROR("%s: isp platform data alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp platform data alloc failed\n", __func__); goto failure; } @@ -89,14 +92,7 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp->isp_res[1].start = isp_base + ISP411_PHY0_OFFSET; isp->isp_res[1].end = isp_base + ISP411_PHY0_OFFSET + ISP411_PHY0_SIZE; - isp->isp_res[2].name = "isp_4_1_1_sensor0_reg"; - isp->isp_res[2].flags = IORESOURCE_MEM; - isp->isp_res[2].start = isp_base + ISP411_GPIO_SENSOR0_OFFSET; - isp->isp_res[2].end = isp_base + ISP411_GPIO_SENSOR0_OFFSET + - ISP411_GPIO_SENSOR0_SIZE; - - for (idx = MAX_ISP411_MEM_RES + MAX_ISP411_SENSOR_RES, int_idx = 0; - idx < num_res; idx++, int_idx++) { + for (idx = MAX_ISP411_MEM_RES, int_idx = 0; idx < num_res; idx++, int_idx++) { isp->isp_res[idx].name = "isp_4_1_1_irq"; isp->isp_res[idx].flags = IORESOURCE_IRQ; isp->isp_res[idx].start = @@ -111,10 +107,12 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp->isp_cell[0].platform_data = isp->isp_pdata; isp->isp_cell[0].pdata_size = sizeof(struct isp_platform_data); + /* initialize isp i2c platform data */ isp->isp_i2c_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); if (!isp->isp_i2c_res) { r = -ENOMEM; - DRM_ERROR("%s: isp mfd res alloc failed\n", __func__); + drm_err(&adev->ddev, + "%s: isp mfd res alloc failed\n", __func__); goto failure; } @@ -129,9 +127,31 @@ static int isp_v4_1_1_hw_init(struct amdgpu_isp *isp) isp->isp_cell[1].platform_data = isp->isp_pdata; isp->isp_cell[1].pdata_size = sizeof(struct isp_platform_data); - r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 2); + /* initialize isp gpiochip platform data */ + isp->isp_gpio_res = kcalloc(1, sizeof(struct resource), GFP_KERNEL); + if (!isp->isp_gpio_res) { + r = -ENOMEM; + drm_err(&adev->ddev, + "%s: isp gpio res alloc failed\n", __func__); + goto failure; + } + + isp->isp_gpio_res[0].name = "isp_gpio_reg"; + isp->isp_gpio_res[0].flags = IORESOURCE_MEM; + isp->isp_gpio_res[0].start = isp_base + ISP411_GPIO_SENSOR_OFFSET; + isp->isp_gpio_res[0].end = isp_base + ISP411_GPIO_SENSOR_OFFSET + + ISP411_GPIO_SENSOR_SIZE; + + isp->isp_cell[2].name = "amdisp-pinctrl"; + isp->isp_cell[2].num_resources = 1; + isp->isp_cell[2].resources = &isp->isp_gpio_res[0]; + isp->isp_cell[2].platform_data = isp->isp_pdata; + isp->isp_cell[2].pdata_size = sizeof(struct isp_platform_data); + + r = mfd_add_hotplug_devices(isp->parent, isp->isp_cell, 3); if (r) { - DRM_ERROR("%s: add mfd hotplug device failed\n", __func__); + drm_err(&adev->ddev, + "%s: add mfd hotplug device failed\n", __func__); goto failure; } @@ -143,6 +163,7 @@ failure: kfree(isp->isp_res); kfree(isp->isp_cell); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return r; } @@ -155,6 +176,7 @@ static int isp_v4_1_1_hw_fini(struct amdgpu_isp *isp) kfree(isp->isp_cell); kfree(isp->isp_pdata); kfree(isp->isp_i2c_res); + kfree(isp->isp_gpio_res); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h index 40887ddeb08c..fe45d70d87f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.h @@ -33,7 +33,6 @@ #include "ivsrcid/isp/irqsrcs_isp_4_1.h" #define MAX_ISP411_MEM_RES 2 -#define MAX_ISP411_SENSOR_RES 1 #define MAX_ISP411_INT_SRC 8 #define ISP411_PHY0_OFFSET 0x66700 @@ -42,8 +41,8 @@ #define ISP411_I2C0_OFFSET 0x66400 #define ISP411_I2C0_SIZE 0x100 -#define ISP411_GPIO_SENSOR0_OFFSET 0x6613C -#define ISP411_GPIO_SENSOR0_SIZE 0x4 +#define ISP411_GPIO_SENSOR_OFFSET 0x6613C +#define ISP411_GPIO_SENSOR_SIZE 0x54 void isp_v4_1_1_set_isp_funcs(struct amdgpu_isp *isp); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 03b8b7cd5229..9e428e669ada 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -604,15 +604,15 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev) static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work); int cnt = 0; - mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + mutex_lock(&adev->vcn.inst[0].vcn1_jpeg1_workaround); if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec)) DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n"); - for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) { + for (cnt = 0; cnt < adev->vcn.inst[0].num_enc_rings; cnt++) { if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt])) DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt); } diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 75843a0e3bfb..4cde8a8bcc83 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -680,9 +680,9 @@ void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count) } } -static bool jpeg_v2_0_is_idle(void *handle) +static bool jpeg_v2_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return ((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) & UVD_JRBC_STATUS__RB_JOB_DONE_MASK) == @@ -707,7 +707,7 @@ static int jpeg_v2_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = (state == AMD_CG_STATE_GATE); if (enable) { - if (!jpeg_v2_0_is_idle(adev)) + if (!jpeg_v2_0_is_idle(ip_block)) return -EBUSY; jpeg_v2_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 0a2c1dee2430..8b39e114f3be 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -515,9 +515,9 @@ static void jpeg_v2_6_dec_ring_insert_end(struct amdgpu_ring *ring) amdgpu_ring_write(ring, (1 << (ring->me * 2 + 14))); } -static bool jpeg_v2_5_is_idle(void *handle) +static bool jpeg_v2_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { @@ -563,7 +563,7 @@ static int jpeg_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, continue; if (enable) { - if (!jpeg_v2_5_is_idle(adev)) + if (!jpeg_v2_5_is_idle(ip_block)) return -EBUSY; jpeg_v2_5_enable_clock_gating(adev, i); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index 9faa9c6809df..2f8510c2986b 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -470,9 +470,9 @@ static void jpeg_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v3_0_is_idle(void *handle) +static bool jpeg_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int ret = 1; ret &= (((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) & @@ -498,7 +498,7 @@ static int jpeg_v3_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = state == AMD_CG_STATE_GATE; if (enable) { - if (!jpeg_v3_0_is_idle(adev)) + if (!jpeg_v3_0_is_idle(ip_block)) return -EBUSY; jpeg_v3_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 292d4a234ea6..f17ec5414fd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -630,9 +630,9 @@ static void jpeg_v4_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v4_0_is_idle(void *handle) +static bool jpeg_v4_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int ret = 1; ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) & @@ -658,7 +658,7 @@ static int jpeg_v4_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = state == AMD_CG_STATE_GATE; if (enable) { - if (!jpeg_v4_0_is_idle(adev)) + if (!jpeg_v4_0_is_idle(ip_block)) return -EBUSY; jpeg_v4_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index 0588bb80f41e..5598a35f72af 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -634,12 +634,6 @@ static void jpeg_v4_0_3_stop_inst(struct amdgpu_device *adev, int inst) UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK, ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); - WREG32_SOC15(JPEG, jpeg_inst, regUVD_PGFSM_CONFIG, - 2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT); - SOC15_WAIT_ON_RREG(JPEG, jpeg_inst, regUVD_PGFSM_STATUS, - UVD_PGFSM_STATUS__UVDJ_PWR_OFF << - UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT, - UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK); } /** @@ -692,7 +686,7 @@ static uint64_t jpeg_v4_0_3_dec_ring_get_wptr(struct amdgpu_ring *ring) jpeg_v4_0_3_core_reg_offset(ring->pipe)); } -static void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) +void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) { /* JPEG engine access for HDP flush doesn't work when RRMT is enabled. * This is a workaround to avoid any HDP flush through JPEG ring. @@ -960,9 +954,9 @@ void jpeg_v4_0_3_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count) } } -static bool jpeg_v4_0_3_is_idle(void *handle) +static bool jpeg_v4_0_3_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; bool ret = false; int i, j; @@ -1004,7 +998,7 @@ static int jpeg_v4_0_3_set_clockgating_state(struct amdgpu_ip_block *ip_block, for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { if (enable) { - if (!jpeg_v4_0_3_is_idle(adev)) + if (!jpeg_v4_0_3_is_idle(ip_block)) return -EBUSY; jpeg_v4_0_3_enable_clock_gating(adev, i); } else { @@ -1110,24 +1104,20 @@ static void jpeg_v4_0_3_core_stall_reset(struct amdgpu_ring *ring) WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_UVD_JMI_CLIENT_STALL, reg_offset, 0x1F); - SOC15_WAIT_ON_RREG(JPEG, jpeg_inst, - regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS, - 0x1F, 0x1F); + SOC15_WAIT_ON_RREG_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS, + reg_offset, 0x1F, 0x1F); WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_JPEG_LMI_DROP, reg_offset, 0x1F); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regJPEG_CORE_RST_CTRL, - reg_offset, 1 << ring->pipe); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 1 << ring->pipe); WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_UVD_JMI_CLIENT_STALL, reg_offset, 0x00); WREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JMI0_JPEG_LMI_DROP, reg_offset, 0x00); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regJPEG_CORE_RST_CTRL, - reg_offset, 0x00); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00); } static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid) @@ -1338,8 +1328,8 @@ static int jpeg_v4_0_3_aca_bank_parser(struct aca_handle *handle, struct aca_ban 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h index 747a3e5f6856..a90bf370a002 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h @@ -56,6 +56,7 @@ void jpeg_v4_0_3_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq unsigned int flags); void jpeg_v4_0_3_dec_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned int vmid, uint64_t pd_addr); +void jpeg_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring); void jpeg_v4_0_3_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count); void jpeg_v4_0_3_dec_ring_insert_start(struct amdgpu_ring *ring); void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c index cbba1d9e8367..974030a5c03c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c @@ -648,9 +648,9 @@ static void jpeg_v4_0_5_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v4_0_5_is_idle(void *handle) +static bool jpeg_v4_0_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { @@ -693,7 +693,7 @@ static int jpeg_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, continue; if (enable) { - if (!jpeg_v4_0_5_is_idle(adev)) + if (!jpeg_v4_0_5_is_idle(ip_block)) return -EBUSY; jpeg_v4_0_5_enable_clock_gating(adev, i); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index 4a55e0cf39e4..31d213ccbe0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -559,9 +559,9 @@ static void jpeg_v5_0_0_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v5_0_0_is_idle(void *handle) +static bool jpeg_v5_0_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int ret = 1; ret &= (((RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS) & @@ -587,7 +587,7 @@ static int jpeg_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, bool enable = (state == AMD_CG_STATE_GATE) ? true : false; if (enable) { - if (!jpeg_v5_0_0_is_idle(adev)) + if (!jpeg_v5_0_0_is_idle(ip_block)) return -EBUSY; jpeg_v5_0_0_enable_clock_gating(adev); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index 6e3f522e9133..218e16b68f1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -190,6 +190,13 @@ static int jpeg_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; + if (!amdgpu_sriov_vf(adev)) { + adev->jpeg.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE; + r = amdgpu_jpeg_sysfs_reset_mask_init(adev); + if (r) + return r; + } + return 0; } @@ -209,6 +216,9 @@ static int jpeg_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) if (r) return r; + if (!amdgpu_sriov_vf(adev)) + amdgpu_jpeg_sysfs_reset_mask_fini(adev); + r = amdgpu_jpeg_sw_fini(adev); return r; @@ -239,6 +249,9 @@ static int jpeg_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) } return 0; } + if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100) + adev->jpeg.caps |= AMDGPU_JPEG_CAPS(RRMT_ENABLED); + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { jpeg_inst = GET_INST(JPEG, i); ring = adev->jpeg.inst[i].ring_dec; @@ -326,11 +339,10 @@ static int jpeg_v5_0_1_resume(struct amdgpu_ip_block *ip_block) return r; } -static int jpeg_v5_0_1_disable_antihang(struct amdgpu_device *adev, int inst_idx) +static void jpeg_v5_0_1_init_inst(struct amdgpu_device *adev, int i) { - int jpeg_inst; + int jpeg_inst = GET_INST(JPEG, i); - jpeg_inst = GET_INST(JPEG, inst_idx); /* disable anti hang mechanism */ WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), 0, ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); @@ -339,20 +351,75 @@ static int jpeg_v5_0_1_disable_antihang(struct amdgpu_device *adev, int inst_idx WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), 0, ~UVD_JPEG_POWER_STATUS__JPEG_PG_MODE_MASK); - return 0; + /* MJPEG global tiling registers */ + WREG32_SOC15(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* enable JMI channel */ + WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0, + ~UVD_JMI_CNTL__SOFT_RESET_MASK); } -static int jpeg_v5_0_1_enable_antihang(struct amdgpu_device *adev, int inst_idx) +static void jpeg_v5_0_1_deinit_inst(struct amdgpu_device *adev, int i) { - int jpeg_inst; + int jpeg_inst = GET_INST(JPEG, i); + /* reset JMI */ + WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), + UVD_JMI_CNTL__SOFT_RESET_MASK, + ~UVD_JMI_CNTL__SOFT_RESET_MASK); - jpeg_inst = GET_INST(JPEG, inst_idx); /* enable anti hang mechanism */ WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JPEG_POWER_STATUS), UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK, - ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); + ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK); +} - return 0; +static void jpeg_v5_0_1_init_jrbc(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + u32 reg, data, mask; + int jpeg_inst = GET_INST(JPEG, ring->me); + int reg_offset = ring->pipe ? jpeg_v5_0_1_core_reg_offset(ring->pipe) : 0; + + /* enable System Interrupt for JRBC */ + reg = SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN); + if (ring->pipe < AMDGPU_MAX_JPEG_RINGS_4_0_3) { + data = JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe; + mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << ring->pipe); + WREG32_P(reg, data, mask); + } else { + data = JPEG_SYS_INT_EN__DJRBC0_MASK << (ring->pipe+12); + mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << (ring->pipe+12)); + WREG32_P(reg, data, mask); + } + + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_LMI_JRBC_RB_VMID, + reg_offset, 0); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_CNTL, + reg_offset, + (0x00000001L | 0x00000002L)); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_LMI_JRBC_RB_64BIT_BAR_LOW, + reg_offset, lower_32_bits(ring->gpu_addr)); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, + reg_offset, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_RPTR, + reg_offset, 0); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_WPTR, + reg_offset, 0); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_CNTL, + reg_offset, 0x00000002L); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JRBC_RB_SIZE, + reg_offset, ring->ring_size / 4); + ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC_RB_WPTR, + reg_offset); } /** @@ -365,69 +432,13 @@ static int jpeg_v5_0_1_enable_antihang(struct amdgpu_device *adev, int inst_idx) static int jpeg_v5_0_1_start(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - int i, j, jpeg_inst, r; + int i, j; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { - jpeg_inst = GET_INST(JPEG, i); - - /* disable antihang */ - r = jpeg_v5_0_1_disable_antihang(adev, i); - if (r) - return r; - - /* MJPEG global tiling registers */ - WREG32_SOC15(JPEG, 0, regJPEG_DEC_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* enable JMI channel */ - WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), 0, - ~UVD_JMI_CNTL__SOFT_RESET_MASK); - + jpeg_v5_0_1_init_inst(adev, i); for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) { - int reg_offset = (j ? jpeg_v5_0_1_core_reg_offset(j) : 0); - u32 reg, data, mask; - ring = &adev->jpeg.inst[i].ring_dec[j]; - - /* enable System Interrupt for JRBC */ - reg = SOC15_REG_OFFSET(JPEG, jpeg_inst, regJPEG_SYS_INT_EN); - if (j < AMDGPU_MAX_JPEG_RINGS_4_0_3) { - data = JPEG_SYS_INT_EN__DJRBC0_MASK << j; - mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << j); - WREG32_P(reg, data, mask); - } else { - data = JPEG_SYS_INT_EN__DJRBC0_MASK << (j+12); - mask = ~(JPEG_SYS_INT_EN__DJRBC0_MASK << (j+12)); - WREG32_P(reg, data, mask); - } - - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_LMI_JRBC_RB_VMID, - reg_offset, 0); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_CNTL, - reg_offset, - (0x00000001L | 0x00000002L)); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_LMI_JRBC_RB_64BIT_BAR_LOW, - reg_offset, lower_32_bits(ring->gpu_addr)); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, - reg_offset, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_RPTR, - reg_offset, 0); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_WPTR, - reg_offset, 0); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_CNTL, - reg_offset, 0x00000002L); - WREG32_SOC15_OFFSET(JPEG, jpeg_inst, - regUVD_JRBC_RB_SIZE, - reg_offset, ring->ring_size / 4); - ring->wptr = RREG32_SOC15_OFFSET(JPEG, jpeg_inst, regUVD_JRBC_RB_WPTR, - reg_offset); + jpeg_v5_0_1_init_jrbc(ring); } } @@ -443,20 +454,10 @@ static int jpeg_v5_0_1_start(struct amdgpu_device *adev) */ static int jpeg_v5_0_1_stop(struct amdgpu_device *adev) { - int i, jpeg_inst, r; - - for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { - jpeg_inst = GET_INST(JPEG, i); - /* reset JMI */ - WREG32_P(SOC15_REG_OFFSET(JPEG, jpeg_inst, regUVD_JMI_CNTL), - UVD_JMI_CNTL__SOFT_RESET_MASK, - ~UVD_JMI_CNTL__SOFT_RESET_MASK); + int i; - /* enable antihang */ - r = jpeg_v5_0_1_enable_antihang(adev, i); - if (r) - return r; - } + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) + jpeg_v5_0_1_deinit_inst(adev, i); return 0; } @@ -516,9 +517,9 @@ static void jpeg_v5_0_1_dec_ring_set_wptr(struct amdgpu_ring *ring) } } -static bool jpeg_v5_0_1_is_idle(void *handle) +static bool jpeg_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; bool ret = false; int i, j; @@ -567,7 +568,7 @@ static int jpeg_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block, return 0; for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { - if (!jpeg_v5_0_1_is_idle(adev)) + if (!jpeg_v5_0_1_is_idle(ip_block)) return -EBUSY; } @@ -662,6 +663,41 @@ static int jpeg_v5_0_1_process_interrupt(struct amdgpu_device *adev, return 0; } +static void jpeg_v5_0_1_core_stall_reset(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + int jpeg_inst = GET_INST(JPEG, ring->me); + int reg_offset = ring->pipe ? jpeg_v5_0_1_core_reg_offset(ring->pipe) : 0; + + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_STALL, + reg_offset, 0x1F); + SOC15_WAIT_ON_RREG_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS, + reg_offset, 0x1F, 0x1F); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_JPEG_LMI_DROP, + reg_offset, 0x1F); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 1 << ring->pipe); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_UVD_JMI_CLIENT_STALL, + reg_offset, 0x00); + WREG32_SOC15_OFFSET(JPEG, jpeg_inst, + regUVD_JMI0_JPEG_LMI_DROP, + reg_offset, 0x00); + WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00); +} + +static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring, unsigned int vmid) +{ + if (amdgpu_sriov_vf(ring->adev)) + return -EOPNOTSUPP; + + jpeg_v5_0_1_core_stall_reset(ring); + jpeg_v5_0_1_init_jrbc(ring); + return amdgpu_ring_test_helper(ring); +} + static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = { .name = "jpeg_v5_0_1", .early_init = jpeg_v5_0_1_early_init, @@ -700,6 +736,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .emit_ib = jpeg_v4_0_3_dec_ring_emit_ib, .emit_fence = jpeg_v4_0_3_dec_ring_emit_fence, .emit_vm_flush = jpeg_v4_0_3_dec_ring_emit_vm_flush, + .emit_hdp_flush = jpeg_v4_0_3_ring_emit_hdp_flush, .test_ring = amdgpu_jpeg_dec_ring_test_ring, .test_ib = amdgpu_jpeg_dec_ring_test_ib, .insert_nop = jpeg_v4_0_3_dec_ring_nop, @@ -711,6 +748,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .emit_wreg = jpeg_v4_0_3_dec_ring_emit_wreg, .emit_reg_wait = jpeg_v4_0_3_dec_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, + .reset = jpeg_v5_0_1_ring_reset, }; static void jpeg_v5_0_1_set_dec_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h index 9de3272ef47f..efdab57324e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.h @@ -26,65 +26,76 @@ extern const struct amdgpu_ip_block_version jpeg_v5_0_1_ip_block; -#define regUVD_JRBC0_UVD_JRBC_RB_WPTR 0x0640 -#define regUVD_JRBC0_UVD_JRBC_RB_WPTR_BASE_IDX 1 -#define regUVD_JRBC0_UVD_JRBC_STATUS 0x0649 -#define regUVD_JRBC0_UVD_JRBC_STATUS_BASE_IDX 1 -#define regUVD_JRBC0_UVD_JRBC_RB_RPTR 0x064a -#define regUVD_JRBC0_UVD_JRBC_RB_RPTR_BASE_IDX 1 -#define regUVD_JRBC1_UVD_JRBC_RB_WPTR 0x0000 -#define regUVD_JRBC1_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC1_UVD_JRBC_STATUS 0x0009 -#define regUVD_JRBC1_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC1_UVD_JRBC_RB_RPTR 0x000a -#define regUVD_JRBC1_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC2_UVD_JRBC_RB_WPTR 0x0040 -#define regUVD_JRBC2_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC2_UVD_JRBC_STATUS 0x0049 -#define regUVD_JRBC2_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC2_UVD_JRBC_RB_RPTR 0x004a -#define regUVD_JRBC2_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC3_UVD_JRBC_RB_WPTR 0x0080 -#define regUVD_JRBC3_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC3_UVD_JRBC_STATUS 0x0089 -#define regUVD_JRBC3_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC3_UVD_JRBC_RB_RPTR 0x008a -#define regUVD_JRBC3_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC4_UVD_JRBC_RB_WPTR 0x00c0 -#define regUVD_JRBC4_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC4_UVD_JRBC_STATUS 0x00c9 -#define regUVD_JRBC4_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC4_UVD_JRBC_RB_RPTR 0x00ca -#define regUVD_JRBC4_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC5_UVD_JRBC_RB_WPTR 0x0100 -#define regUVD_JRBC5_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC5_UVD_JRBC_STATUS 0x0109 -#define regUVD_JRBC5_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC5_UVD_JRBC_RB_RPTR 0x010a -#define regUVD_JRBC5_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC6_UVD_JRBC_RB_WPTR 0x0140 -#define regUVD_JRBC6_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC6_UVD_JRBC_STATUS 0x0149 -#define regUVD_JRBC6_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC6_UVD_JRBC_RB_RPTR 0x014a -#define regUVD_JRBC6_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC7_UVD_JRBC_RB_WPTR 0x0180 -#define regUVD_JRBC7_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC7_UVD_JRBC_STATUS 0x0189 -#define regUVD_JRBC7_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC7_UVD_JRBC_RB_RPTR 0x018a -#define regUVD_JRBC7_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC8_UVD_JRBC_RB_WPTR 0x01c0 -#define regUVD_JRBC8_UVD_JRBC_RB_WPTR_BASE_IDX 0 -#define regUVD_JRBC8_UVD_JRBC_STATUS 0x01c9 -#define regUVD_JRBC8_UVD_JRBC_STATUS_BASE_IDX 0 -#define regUVD_JRBC8_UVD_JRBC_RB_RPTR 0x01ca -#define regUVD_JRBC8_UVD_JRBC_RB_RPTR_BASE_IDX 0 -#define regUVD_JRBC9_UVD_JRBC_RB_WPTR 0x0440 -#define regUVD_JRBC9_UVD_JRBC_RB_WPTR_BASE_IDX 1 -#define regUVD_JRBC9_UVD_JRBC_STATUS 0x0449 -#define regUVD_JRBC9_UVD_JRBC_STATUS_BASE_IDX 1 -#define regUVD_JRBC9_UVD_JRBC_RB_RPTR 0x044a -#define regUVD_JRBC9_UVD_JRBC_RB_RPTR_BASE_IDX 1 +#define regUVD_JRBC0_UVD_JRBC_RB_WPTR 0x0640 +#define regUVD_JRBC0_UVD_JRBC_RB_WPTR_BASE_IDX 1 +#define regUVD_JRBC0_UVD_JRBC_STATUS 0x0649 +#define regUVD_JRBC0_UVD_JRBC_STATUS_BASE_IDX 1 +#define regUVD_JRBC0_UVD_JRBC_RB_RPTR 0x064a +#define regUVD_JRBC0_UVD_JRBC_RB_RPTR_BASE_IDX 1 +#define regUVD_JRBC1_UVD_JRBC_RB_WPTR 0x0000 +#define regUVD_JRBC1_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC1_UVD_JRBC_STATUS 0x0009 +#define regUVD_JRBC1_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC1_UVD_JRBC_RB_RPTR 0x000a +#define regUVD_JRBC1_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC2_UVD_JRBC_RB_WPTR 0x0040 +#define regUVD_JRBC2_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC2_UVD_JRBC_STATUS 0x0049 +#define regUVD_JRBC2_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC2_UVD_JRBC_RB_RPTR 0x004a +#define regUVD_JRBC2_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC3_UVD_JRBC_RB_WPTR 0x0080 +#define regUVD_JRBC3_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC3_UVD_JRBC_STATUS 0x0089 +#define regUVD_JRBC3_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC3_UVD_JRBC_RB_RPTR 0x008a +#define regUVD_JRBC3_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC4_UVD_JRBC_RB_WPTR 0x00c0 +#define regUVD_JRBC4_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC4_UVD_JRBC_STATUS 0x00c9 +#define regUVD_JRBC4_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC4_UVD_JRBC_RB_RPTR 0x00ca +#define regUVD_JRBC4_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC5_UVD_JRBC_RB_WPTR 0x0100 +#define regUVD_JRBC5_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC5_UVD_JRBC_STATUS 0x0109 +#define regUVD_JRBC5_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC5_UVD_JRBC_RB_RPTR 0x010a +#define regUVD_JRBC5_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC6_UVD_JRBC_RB_WPTR 0x0140 +#define regUVD_JRBC6_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC6_UVD_JRBC_STATUS 0x0149 +#define regUVD_JRBC6_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC6_UVD_JRBC_RB_RPTR 0x014a +#define regUVD_JRBC6_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC7_UVD_JRBC_RB_WPTR 0x0180 +#define regUVD_JRBC7_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC7_UVD_JRBC_STATUS 0x0189 +#define regUVD_JRBC7_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC7_UVD_JRBC_RB_RPTR 0x018a +#define regUVD_JRBC7_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC8_UVD_JRBC_RB_WPTR 0x01c0 +#define regUVD_JRBC8_UVD_JRBC_RB_WPTR_BASE_IDX 0 +#define regUVD_JRBC8_UVD_JRBC_STATUS 0x01c9 +#define regUVD_JRBC8_UVD_JRBC_STATUS_BASE_IDX 0 +#define regUVD_JRBC8_UVD_JRBC_RB_RPTR 0x01ca +#define regUVD_JRBC8_UVD_JRBC_RB_RPTR_BASE_IDX 0 +#define regUVD_JRBC9_UVD_JRBC_RB_WPTR 0x0440 +#define regUVD_JRBC9_UVD_JRBC_RB_WPTR_BASE_IDX 1 +#define regUVD_JRBC9_UVD_JRBC_STATUS 0x0449 +#define regUVD_JRBC9_UVD_JRBC_STATUS_BASE_IDX 1 +#define regUVD_JRBC9_UVD_JRBC_RB_RPTR 0x044a +#define regUVD_JRBC9_UVD_JRBC_RB_RPTR_BASE_IDX 1 +#define regUVD_JMI0_JPEG_LMI_DROP 0x0663 +#define regUVD_JMI0_JPEG_LMI_DROP_BASE_IDX 1 +#define regUVD_JMI0_UVD_JMI_CLIENT_STALL 0x067a +#define regUVD_JMI0_UVD_JMI_CLIENT_STALL_BASE_IDX 1 +#define regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS 0x067b +#define regUVD_JMI0_UVD_JMI_CLIENT_CLEAN_STATUS_BASE_IDX 1 +#define regJPEG_CORE_RST_CTRL 0x072e +#define regJPEG_CORE_RST_CTRL_BASE_IDX 1 -#endif /* __JPEG_V5_0_0_H__ */ +#define regVCN_RRMT_CNTL 0x0940 +#define regVCN_RRMT_CNTL_BASE_IDX 1 + +#endif /* __JPEG_V5_0_1_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 747b05d9b3cf..7eee41187b7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -800,7 +800,7 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = { }; static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -835,7 +835,7 @@ static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, } static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -876,7 +876,7 @@ static int mes_v11_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, } static void mes_v11_0_free_ucode_buffers(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { amdgpu_bo_free_kernel(&adev->mes.data_fw_obj[pipe], &adev->mes.data_fw_gpu_addr[pipe], @@ -974,7 +974,7 @@ static void mes_v11_0_enable(struct amdgpu_device *adev, bool enable) /* This function is for backdoor MES firmware */ static int mes_v11_0_load_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe, bool prime_icache) + enum amdgpu_mes_pipe pipe, bool prime_icache) { int r; uint32_t data; @@ -1046,7 +1046,7 @@ static int mes_v11_0_load_microcode(struct amdgpu_device *adev, } static int mes_v11_0_allocate_eop_buf(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; u32 *eop; @@ -1257,7 +1257,7 @@ static int mes_v11_0_kiq_enable_queue(struct amdgpu_device *adev) } static int mes_v11_0_queue_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { struct amdgpu_ring *ring; int r; @@ -1340,7 +1340,7 @@ static int mes_v11_0_kiq_ring_init(struct amdgpu_device *adev) } static int mes_v11_0_mqd_sw_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r, mqd_size = sizeof(struct v11_compute_mqd); struct amdgpu_ring *ring; @@ -1647,6 +1647,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block) goto failure; } + r = amdgpu_mes_update_enforce_isolation(adev); + if (r) + goto failure; + out: /* * Disable KIQ ring usage from the driver once MES is enabled. @@ -1670,24 +1674,12 @@ static int mes_v11_0_hw_fini(struct amdgpu_ip_block *ip_block) static int mes_v11_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; - - r = amdgpu_mes_suspend(ip_block->adev); - if (r) - return r; - return mes_v11_0_hw_fini(ip_block); } static int mes_v11_0_resume(struct amdgpu_ip_block *ip_block) { - int r; - - r = mes_v11_0_hw_init(ip_block); - if (r) - return r; - - return amdgpu_mes_resume(ip_block->adev); + return mes_v11_0_hw_init(ip_block); } static int mes_v11_0_early_init(struct amdgpu_ip_block *ip_block) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 8d7cf40030f2..fdc435b62012 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -901,7 +901,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = { }; static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -935,7 +935,7 @@ static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev, } static int mes_v12_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; const struct mes_firmware_header_v1_0 *mes_hdr; @@ -969,7 +969,7 @@ static int mes_v12_0_allocate_ucode_data_buffer(struct amdgpu_device *adev, } static void mes_v12_0_free_ucode_buffers(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { amdgpu_bo_free_kernel(&adev->mes.data_fw_obj[pipe], &adev->mes.data_fw_gpu_addr[pipe], @@ -1075,7 +1075,7 @@ static void mes_v12_0_set_ucode_start_addr(struct amdgpu_device *adev) /* This function is for backdoor MES firmware */ static int mes_v12_0_load_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe, bool prime_icache) + enum amdgpu_mes_pipe pipe, bool prime_icache) { int r; uint32_t data; @@ -1139,7 +1139,7 @@ static int mes_v12_0_load_microcode(struct amdgpu_device *adev, } static int mes_v12_0_allocate_eop_buf(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r; u32 *eop; @@ -1360,7 +1360,7 @@ static int mes_v12_0_kiq_enable_queue(struct amdgpu_device *adev) } static int mes_v12_0_queue_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { struct amdgpu_ring *ring; int r; @@ -1460,7 +1460,7 @@ static int mes_v12_0_kiq_ring_init(struct amdgpu_device *adev) } static int mes_v12_0_mqd_sw_init(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) + enum amdgpu_mes_pipe pipe) { int r, mqd_size = sizeof(struct v12_compute_mqd); struct amdgpu_ring *ring; @@ -1762,6 +1762,10 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block) goto failure; } + r = amdgpu_mes_update_enforce_isolation(adev); + if (r) + goto failure; + out: /* * Disable KIQ ring usage from the driver once MES is enabled. @@ -1785,24 +1789,12 @@ static int mes_v12_0_hw_fini(struct amdgpu_ip_block *ip_block) static int mes_v12_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; - - r = amdgpu_mes_suspend(ip_block->adev); - if (r) - return r; - return mes_v12_0_hw_fini(ip_block); } static int mes_v12_0_resume(struct amdgpu_ip_block *ip_block) { - int r; - - r = mes_v12_0_hw_init(ip_block); - if (r) - return r; - - return amdgpu_mes_resume(ip_block->adev); + return mes_v12_0_hw_init(ip_block); } static int mes_v12_0_early_init(struct amdgpu_ip_block *ip_block) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c index 58d22f0d5a68..a54e7b929295 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c @@ -751,8 +751,8 @@ static int mmhub_v1_8_aca_bank_parser(struct aca_handle *handle, struct aca_bank 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 4dcb72d1bdda..5aadf24cb202 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -184,6 +184,9 @@ send_request: case IDH_REQ_RAS_ERROR_COUNT: event = IDH_RAS_ERROR_COUNT_READY; break; + case IDH_REQ_RAS_CPER_DUMP: + event = IDH_RAS_CPER_DUMP_READY; + break; default: break; } @@ -467,6 +470,16 @@ static int xgpu_nv_req_ras_err_count(struct amdgpu_device *adev) return xgpu_nv_send_access_requests(adev, IDH_REQ_RAS_ERROR_COUNT); } +static int xgpu_nv_req_ras_cper_dump(struct amdgpu_device *adev, u64 vf_rptr) +{ + uint32_t vf_rptr_hi, vf_rptr_lo; + + vf_rptr_hi = (uint32_t)(vf_rptr >> 32); + vf_rptr_lo = (uint32_t)(vf_rptr & 0xFFFFFFFF); + return xgpu_nv_send_access_requests_with_param( + adev, IDH_REQ_RAS_CPER_DUMP, vf_rptr_hi, vf_rptr_lo, 0); +} + const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .req_full_gpu = xgpu_nv_request_full_gpu_access, .rel_full_gpu = xgpu_nv_release_full_gpu_access, @@ -478,4 +491,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .ras_poison_handler = xgpu_nv_ras_poison_handler, .rcvd_ras_intr = xgpu_nv_rcvd_ras_intr, .req_ras_err_count = xgpu_nv_req_ras_err_count, + .req_ras_cper_dump = xgpu_nv_req_ras_cper_dump, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h index 9d61d76e1bf9..72c9fceb9d79 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h @@ -41,6 +41,7 @@ enum idh_request { IDH_READY_TO_RESET = 201, IDH_RAS_POISON = 202, IDH_REQ_RAS_ERROR_COUNT = 203, + IDH_REQ_RAS_CPER_DUMP = 204, }; enum idh_event { @@ -56,6 +57,7 @@ enum idh_event { IDH_PF_SOFT_FLR_NOTIFICATION, IDH_RAS_ERROR_DETECTED, IDH_RAS_ERROR_COUNT_READY = 11, + IDH_RAS_CPER_DUMP_READY = 14, IDH_TEXT_MESSAGE = 255, }; diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c index 1c727ccd03b1..4cd325149b63 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c @@ -625,7 +625,7 @@ static int navi10_ih_resume(struct amdgpu_ip_block *ip_block) return navi10_ih_hw_init(ip_block); } -static bool navi10_ih_is_idle(void *handle) +static bool navi10_ih_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c index 9900fe5c3bc3..9b4025c39e44 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.c @@ -473,52 +473,6 @@ const struct amdgpu_nbio_funcs nbif_v6_3_1_funcs = { }; -static void nbif_v6_3_1_sriov_ih_doorbell_range(struct amdgpu_device *adev, - bool use_doorbell, int doorbell_index) -{ -} - -static void nbif_v6_3_1_sriov_sdma_doorbell_range(struct amdgpu_device *adev, - int instance, bool use_doorbell, - int doorbell_index, - int doorbell_size) -{ -} - -static void nbif_v6_3_1_sriov_vcn_doorbell_range(struct amdgpu_device *adev, - bool use_doorbell, - int doorbell_index, int instance) -{ -} - -static void nbif_v6_3_1_sriov_gc_doorbell_init(struct amdgpu_device *adev) -{ -} - -const struct amdgpu_nbio_funcs nbif_v6_3_1_sriov_funcs = { - .get_hdp_flush_req_offset = nbif_v6_3_1_get_hdp_flush_req_offset, - .get_hdp_flush_done_offset = nbif_v6_3_1_get_hdp_flush_done_offset, - .get_pcie_index_offset = nbif_v6_3_1_get_pcie_index_offset, - .get_pcie_data_offset = nbif_v6_3_1_get_pcie_data_offset, - .get_rev_id = nbif_v6_3_1_get_rev_id, - .mc_access_enable = nbif_v6_3_1_mc_access_enable, - .get_memsize = nbif_v6_3_1_get_memsize, - .sdma_doorbell_range = nbif_v6_3_1_sriov_sdma_doorbell_range, - .vcn_doorbell_range = nbif_v6_3_1_sriov_vcn_doorbell_range, - .gc_doorbell_init = nbif_v6_3_1_sriov_gc_doorbell_init, - .enable_doorbell_aperture = nbif_v6_3_1_enable_doorbell_aperture, - .enable_doorbell_selfring_aperture = nbif_v6_3_1_enable_doorbell_selfring_aperture, - .ih_doorbell_range = nbif_v6_3_1_sriov_ih_doorbell_range, - .update_medium_grain_clock_gating = nbif_v6_3_1_update_medium_grain_clock_gating, - .update_medium_grain_light_sleep = nbif_v6_3_1_update_medium_grain_light_sleep, - .get_clockgating_state = nbif_v6_3_1_get_clockgating_state, - .ih_control = nbif_v6_3_1_ih_control, - .init_registers = nbif_v6_3_1_init_registers, - .remap_hdp_registers = nbif_v6_3_1_remap_hdp_registers, - .get_rom_offset = nbif_v6_3_1_get_rom_offset, - .set_reg_remap = nbif_v6_3_1_set_reg_remap, -}; - static int nbif_v6_3_1_set_ras_err_event_athub_irq_state(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type, diff --git a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h index 9ac4831d39e1..3afec715a9fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h +++ b/drivers/gpu/drm/amd/amdgpu/nbif_v6_3_1.h @@ -28,7 +28,6 @@ extern const struct nbio_hdp_flush_reg nbif_v6_3_1_hdp_flush_reg; extern const struct amdgpu_nbio_funcs nbif_v6_3_1_funcs; -extern const struct amdgpu_nbio_funcs nbif_v6_3_1_sriov_funcs; extern struct amdgpu_nbio_ras nbif_v6_3_1_ras; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 5d4a4e7fd97f..8068f384f56c 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -1035,7 +1035,7 @@ static int nv_common_resume(struct amdgpu_ip_block *ip_block) return nv_common_hw_init(ip_block); } -static bool nv_common_is_idle(void *handle) +static bool nv_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 135c5099bfb8..92ce580647cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -911,9 +911,9 @@ static int sdma_v2_4_resume(struct amdgpu_ip_block *ip_block) return sdma_v2_4_hw_init(ip_block); } -static bool sdma_v2_4_is_idle(void *handle) +static bool sdma_v2_4_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS2); if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 6e75a4a85f74..1c076bd1cf73 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -1200,9 +1200,9 @@ static int sdma_v3_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v3_0_hw_init(ip_block); } -static bool sdma_v3_0_is_idle(void *handle) +static bool sdma_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS2); if (tmp & (SRBM_STATUS2__SDMA_BUSY_MASK | diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index d31ee01383df..33ed2b158fcd 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -2015,9 +2015,9 @@ static int sdma_v4_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v4_0_hw_init(ip_block); } -static bool sdma_v4_0_is_idle(void *handle) +static bool sdma_v4_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 23a6bb16a0b1..fd34dc138081 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -30,6 +30,7 @@ #include "amdgpu_xcp.h" #include "amdgpu_ucode.h" #include "amdgpu_trace.h" +#include "amdgpu_reset.h" #include "sdma/sdma_4_4_2_offset.h" #include "sdma/sdma_4_4_2_sh_mask.h" @@ -105,6 +106,8 @@ static void sdma_v4_4_2_set_buffer_funcs(struct amdgpu_device *adev); static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev); static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev); static void sdma_v4_4_2_set_ras_funcs(struct amdgpu_device *adev); +static void sdma_v4_4_2_set_engine_reset_funcs(struct amdgpu_device *adev); +static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev); static u32 sdma_v4_4_2_get_reg_offset(struct amdgpu_device *adev, u32 instance, u32 offset) @@ -669,11 +672,12 @@ static uint32_t sdma_v4_4_2_rb_cntl(struct amdgpu_ring *ring, uint32_t rb_cntl) * @adev: amdgpu_device pointer * @i: instance to resume * @restore: used to restore wptr when restart + * @guilty: boolean indicating whether this queue is the guilty one (caused the timeout/error) * * Set up the gfx DMA ring buffers and enable them. * Returns 0 for success, error for failure. */ -static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, bool restore) +static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, bool restore, bool guilty) { struct amdgpu_ring *ring = &adev->sdma.instance[i].ring; u32 rb_cntl, ib_cntl, wptr_poll_cntl; @@ -681,6 +685,7 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b u32 doorbell; u32 doorbell_offset; u64 wptr_gpu_addr; + u64 rwptr; wb_offset = (ring->rptr_offs * 4); @@ -706,12 +711,20 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b /* before programing wptr to a less value, need set minor_ptr_update first */ WREG32_SDMA(i, regSDMA_GFX_MINOR_PTR_UPDATE, 1); + /* For the guilty queue, set RPTR to the current wptr to skip bad commands, + * It is not a guilty queue, restore cache_rptr and continue execution. + */ + if (guilty) + rwptr = ring->wptr; + else + rwptr = ring->cached_rptr; + /* Initialize the ring buffer's read and write pointers */ if (restore) { - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(ring->wptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(rwptr << 2)); } else { WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, 0); WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, 0); @@ -766,11 +779,12 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i, b * @adev: amdgpu_device pointer * @i: instance to resume * @restore: boolean to say restore needed or not + * @guilty: boolean indicating whether this queue is the guilty one (caused the timeout/error) * * Set up the page DMA ring buffers and enable them. * Returns 0 for success, error for failure. */ -static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, bool restore) +static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, bool restore, bool guilty) { struct amdgpu_ring *ring = &adev->sdma.instance[i].page; u32 rb_cntl, ib_cntl, wptr_poll_cntl; @@ -778,6 +792,7 @@ static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, u32 doorbell; u32 doorbell_offset; u64 wptr_gpu_addr; + u64 rwptr; wb_offset = (ring->rptr_offs * 4); @@ -785,12 +800,20 @@ static void sdma_v4_4_2_page_resume(struct amdgpu_device *adev, unsigned int i, rb_cntl = sdma_v4_4_2_rb_cntl(ring, rb_cntl); WREG32_SDMA(i, regSDMA_PAGE_RB_CNTL, rb_cntl); + /* For the guilty queue, set RPTR to the current wptr to skip bad commands, + * It is not a guilty queue, restore cache_rptr and continue execution. + */ + if (guilty) + rwptr = ring->wptr; + else + rwptr = ring->cached_rptr; + /* Initialize the ring buffer's read and write pointers */ if (restore) { - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, upper_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, lower_32_bits(ring->wptr << 2)); - WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, upper_32_bits(ring->wptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR_HI, upper_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_WPTR, lower_32_bits(rwptr << 2)); + WREG32_SDMA(i, regSDMA_PAGE_RB_WPTR_HI, upper_32_bits(rwptr << 2)); } else { WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR, 0); WREG32_SDMA(i, regSDMA_PAGE_RB_RPTR_HI, 0); @@ -966,9 +989,9 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev, uint32_t temp; WREG32_SDMA(i, regSDMA_SEM_WAIT_FAIL_TIMER_CNTL, 0); - sdma_v4_4_2_gfx_resume(adev, i, restore); + sdma_v4_4_2_gfx_resume(adev, i, restore, adev->sdma.gfx_guilty); if (adev->sdma.has_page_queue) - sdma_v4_4_2_page_resume(adev, i, restore); + sdma_v4_4_2_page_resume(adev, i, restore, adev->sdma.page_guilty); /* set utc l1 enable flag always to 1 */ temp = RREG32_SDMA(i, regSDMA_CNTL); @@ -1330,6 +1353,7 @@ static int sdma_v4_4_2_early_init(struct amdgpu_ip_block *ip_block) sdma_v4_4_2_set_vm_pte_funcs(adev); sdma_v4_4_2_set_irq_funcs(adev); sdma_v4_4_2_set_ras_funcs(adev); + sdma_v4_4_2_set_engine_reset_funcs(adev); return 0; } @@ -1351,6 +1375,12 @@ static int sdma_v4_4_2_late_init(struct amdgpu_ip_block *ip_block) if (!amdgpu_persistent_edc_harvesting_supported(adev)) amdgpu_ras_reset_error_count(adev, AMDGPU_RAS_BLOCK__SDMA); + /* The initialization is done in the late_init stage to ensure that the SMU + * initialization and capability setup are completed before we check the SDMA + * reset capability + */ + sdma_v4_4_2_update_reset_mask(adev); + return 0; } @@ -1458,7 +1488,6 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block) } } - /* TODO: Add queue reset mask when FW fully supports it */ adev->sdma.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring); @@ -1477,6 +1506,9 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block) r = amdgpu_sdma_sysfs_reset_mask_init(adev); if (r) return r; + /* Initialize guilty flags for GFX and PAGE queues */ + adev->sdma.gfx_guilty = false; + adev->sdma.page_guilty = false; return r; } @@ -1561,9 +1593,9 @@ static int sdma_v4_4_2_resume(struct amdgpu_ip_block *ip_block) return sdma_v4_4_2_hw_init(ip_block); } -static bool sdma_v4_4_2_is_idle(void *handle) +static bool sdma_v4_4_2_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { @@ -1602,25 +1634,83 @@ static int sdma_v4_4_2_soft_reset(struct amdgpu_ip_block *ip_block) return 0; } +static bool sdma_v4_4_2_is_queue_selected(struct amdgpu_device *adev, uint32_t instance_id, bool is_page_queue) +{ + uint32_t reg_offset = is_page_queue ? regSDMA_PAGE_CONTEXT_STATUS : regSDMA_GFX_CONTEXT_STATUS; + uint32_t context_status = RREG32(sdma_v4_4_2_get_reg_offset(adev, instance_id, reg_offset)); + + /* Check if the SELECTED bit is set */ + return (context_status & SDMA_GFX_CONTEXT_STATUS__SELECTED_MASK) != 0; +} + +static bool sdma_v4_4_2_ring_is_guilty(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t instance_id = ring->me; + + return sdma_v4_4_2_is_queue_selected(adev, instance_id, false); +} + +static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t instance_id = ring->me; + + if (!adev->sdma.has_page_queue) + return false; + + return sdma_v4_4_2_is_queue_selected(adev, instance_id, true); +} + static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) { struct amdgpu_device *adev = ring->adev; - int i, r; + u32 id = GET_INST(SDMA0, ring->me); + return amdgpu_sdma_reset_engine(adev, id, true); +} + +static int sdma_v4_4_2_stop_queue(struct amdgpu_device *adev, uint32_t instance_id) +{ u32 inst_mask; + uint64_t rptr; + struct amdgpu_ring *ring = &adev->sdma.instance[instance_id].ring; if (amdgpu_sriov_vf(adev)) return -EINVAL; + /* Check if this queue is the guilty one */ + adev->sdma.gfx_guilty = sdma_v4_4_2_is_queue_selected(adev, instance_id, false); + if (adev->sdma.has_page_queue) + adev->sdma.page_guilty = sdma_v4_4_2_is_queue_selected(adev, instance_id, true); + + /* Cache the rptr before reset, after the reset, + * all of the registers will be reset to 0 + */ + rptr = amdgpu_ring_get_rptr(ring); + ring->cached_rptr = rptr; + /* Cache the rptr for the page queue if it exists */ + if (adev->sdma.has_page_queue) { + struct amdgpu_ring *page_ring = &adev->sdma.instance[instance_id].page; + rptr = amdgpu_ring_get_rptr(page_ring); + page_ring->cached_rptr = rptr; + } + /* stop queue */ inst_mask = 1 << ring->me; sdma_v4_4_2_inst_gfx_stop(adev, inst_mask); if (adev->sdma.has_page_queue) sdma_v4_4_2_inst_page_stop(adev, inst_mask); - r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, ring->me)); - if (r) - return r; + return 0; +} + +static int sdma_v4_4_2_restore_queue(struct amdgpu_device *adev, uint32_t instance_id) +{ + int i; + u32 inst_mask; + struct amdgpu_ring *ring = &adev->sdma.instance[instance_id].ring; + inst_mask = 1 << ring->me; udelay(50); for (i = 0; i < adev->usec_timeout; i++) { @@ -1638,6 +1728,16 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid) return sdma_v4_4_2_inst_start(adev, inst_mask, true); } +static struct sdma_on_reset_funcs sdma_v4_4_2_engine_reset_funcs = { + .pre_reset = sdma_v4_4_2_stop_queue, + .post_reset = sdma_v4_4_2_restore_queue, +}; + +static void sdma_v4_4_2_set_engine_reset_funcs(struct amdgpu_device *adev) +{ + amdgpu_sdma_register_on_reset_callbacks(adev, &sdma_v4_4_2_engine_reset_funcs); +} + static int sdma_v4_4_2_set_trap_irq_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source, unsigned type, @@ -1683,6 +1783,9 @@ static int sdma_v4_4_2_process_trap_irq(struct amdgpu_device *adev, case 0: amdgpu_fence_process(&adev->sdma.instance[i].ring); break; + case 1: + amdgpu_fence_process(&adev->sdma.instance[i].page); + break; default: break; } @@ -2029,6 +2132,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_ring_funcs = { .emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, .reset = sdma_v4_4_2_reset_queue, + .is_guilty = sdma_v4_4_2_ring_is_guilty, }; static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = { @@ -2060,6 +2164,8 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = { .emit_wreg = sdma_v4_4_2_ring_emit_wreg, .emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, + .reset = sdma_v4_4_2_reset_queue, + .is_guilty = sdma_v4_4_2_page_ring_is_guilty, }; static void sdma_v4_4_2_set_ring_funcs(struct amdgpu_device *adev) @@ -2231,6 +2337,35 @@ static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev) adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances; } +/** + * sdma_v4_4_2_update_reset_mask - update reset mask for SDMA + * @adev: Pointer to the AMDGPU device structure + * + * This function update reset mask for SDMA and sets the supported + * reset types based on the IP version and firmware versions. + * + */ +static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev) +{ + + /* + * the user queue relies on MEC fw and pmfw when the sdma queue do reset. + * it needs to check both of them at here to skip old mec and pmfw. + */ + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(9, 4, 3): + case IP_VERSION(9, 4, 4): + if ((adev->gfx.mec_fw_version >= 0xb0) && amdgpu_dpm_reset_sdma_is_supported(adev)) + adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; + break; + case IP_VERSION(9, 5, 0): + /*TODO: enable the queue reset flag until fw supported */ + default: + break; + } + +} + const struct amdgpu_ip_block_version sdma_v4_4_2_ip_block = { .type = AMD_IP_BLOCK_TYPE_SDMA, .major = 4, @@ -2397,8 +2532,8 @@ static int sdma_v4_4_2_aca_bank_parser(struct aca_handle *handle, struct aca_ban 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 377efb2b8d0e..0dce59f4f6e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1530,9 +1530,9 @@ static int sdma_v5_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v5_0_hw_init(ip_block); } -static bool sdma_v5_0_is_idle(void *handle) +static bool sdma_v5_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index ce05d895f977..2b39a03ff0c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1435,9 +1435,9 @@ static int sdma_v5_2_resume(struct amdgpu_ip_block *ip_block) return sdma_v5_2_hw_init(ip_block); } -static bool sdma_v5_2_is_idle(void *handle) +static bool sdma_v5_2_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 373703d1596d..c214c3d2149b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1429,9 +1429,9 @@ static int sdma_v6_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v6_0_hw_init(ip_block); } -static bool sdma_v6_0_is_idle(void *handle) +static bool sdma_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index 9eb8f4f9f302..b2706221df99 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1430,9 +1430,9 @@ static int sdma_v7_0_resume(struct amdgpu_ip_block *ip_block) return sdma_v7_0_hw_init(ip_block); } -static bool sdma_v7_0_is_idle(void *handle) +static bool sdma_v7_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 i; for (i = 0; i < adev->sdma.num_instances; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index 77ef7da2e4fe..f90e07375396 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -909,7 +909,7 @@ static const u32 hainan_mgcg_cgcg_init[] = /* XXX: update when we support VCE */ #if 0 -/* tahiti, pitcarin, verde */ +/* tahiti, pitcairn, verde */ static const struct amdgpu_video_codec_info tahiti_video_codecs_encode_array[] = { { @@ -940,7 +940,7 @@ static const struct amdgpu_video_codecs hainan_video_codecs_encode = .codec_array = NULL, }; -/* tahiti, pitcarin, verde, oland */ +/* tahiti, pitcairn, verde, oland */ static const struct amdgpu_video_codec_info tahiti_video_codecs_decode_array[] = { { @@ -1888,7 +1888,7 @@ static int si_vce_send_vcepll_ctlreq(struct amdgpu_device *adev) WREG32_SMC_P(CG_VCEPLL_FUNC_CNTL, 0, ~UPLL_CTLREQ_MASK); if (i == SI_MAX_CTLACKS_ASSERTION_WAIT) { - DRM_ERROR("Timeout setting UVD clocks!\n"); + DRM_ERROR("Timeout setting VCE clocks!\n"); return -ETIMEDOUT; } @@ -2644,7 +2644,7 @@ static int si_common_resume(struct amdgpu_ip_block *ip_block) return si_common_hw_init(ip_block); } -static bool si_common_is_idle(void *handle) +static bool si_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c index dbd78d5345a4..e2089c8da71b 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c @@ -541,9 +541,9 @@ static int si_dma_resume(struct amdgpu_ip_block *ip_block) return si_dma_hw_init(ip_block); } -static bool si_dma_is_idle(void *handle) +static bool si_dma_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(SRBM_STATUS2); @@ -559,7 +559,7 @@ static int si_dma_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (si_dma_is_idle(adev)) + if (si_dma_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c index a32b6243c1f8..5c38e1fb1dca 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c @@ -210,9 +210,9 @@ static int si_ih_resume(struct amdgpu_ip_block *ip_block) return si_ih_hw_init(ip_block); } -static bool si_ih_is_idle(void *handle) +static bool si_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(SRBM_STATUS); if (tmp & SRBM_STATUS__IH_BUSY_MASK) @@ -227,7 +227,7 @@ static int si_ih_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (si_ih_is_idle(adev)) + if (si_ih_is_idle(ip_block)) return 0; udelay(1); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 2c6d2099e215..8732f766947e 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1360,7 +1360,7 @@ static int soc15_common_resume(struct amdgpu_ip_block *ip_block) return soc15_common_hw_init(ip_block); } -static bool soc15_common_is_idle(void *handle) +static bool soc15_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 7925cbb61d0d..dd5d04c068f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -952,7 +952,7 @@ static int soc21_common_resume(struct amdgpu_ip_block *ip_block) return soc21_common_hw_init(ip_block); } -static bool soc21_common_is_idle(void *handle) +static bool soc21_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index 4e506c91e978..972b449ab89f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -531,7 +531,7 @@ static int soc24_common_resume(struct amdgpu_ip_block *ip_block) return soc24_common_hw_init(ip_block); } -static bool soc24_common_is_idle(void *handle) +static bool soc24_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c index 0968e551f7b5..7d17ae56f901 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c @@ -353,9 +353,9 @@ static int tonga_ih_resume(struct amdgpu_ip_block *ip_block) return tonga_ih_hw_init(ip_block); } -static bool tonga_ih_is_idle(void *handle) +static bool tonga_ih_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 tmp = RREG32(mmSRBM_STATUS); if (REG_GET_FIELD(tmp, SRBM_STATUS, IH_BUSY)) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 5830e799c0a3..5dbaebb592b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -98,7 +98,7 @@ static void uvd_v3_1_ring_emit_ib(struct amdgpu_ring *ring, } /** - * uvd_v3_1_ring_emit_fence - emit an fence & trap command + * uvd_v3_1_ring_emit_fence - emit a fence & trap command * * @ring: amdgpu_ring pointer * @addr: address @@ -242,7 +242,7 @@ static void uvd_v3_1_mc_resume(struct amdgpu_device *adev) uint64_t addr; uint32_t size; - /* programm the VCPU memory controller bits 0-27 */ + /* program the VCPU memory controller bits 0-27 */ addr = (adev->uvd.inst->gpu_addr + AMDGPU_UVD_FIRMWARE_OFFSET) >> 3; size = AMDGPU_UVD_FIRMWARE_SIZE(adev) >> 3; WREG32(mmUVD_VCPU_CACHE_OFFSET0, addr); @@ -416,7 +416,7 @@ static int uvd_v3_1_start(struct amdgpu_device *adev) /* Set the write pointer delay */ WREG32(mmUVD_RBC_RB_WPTR_CNTL, 0); - /* programm the 4GB memory segment for rptr and ring buffer */ + /* Program the 4GB memory segment for rptr and ring buffer */ WREG32(mmUVD_LMI_EXT40_ADDR, upper_32_bits(ring->gpu_addr) | (0x7 << 16) | (0x1 << 31)); @@ -758,9 +758,9 @@ static int uvd_v3_1_resume(struct amdgpu_ip_block *ip_block) return uvd_v3_1_hw_init(ip_block); } -static bool uvd_v3_1_is_idle(void *handle) +static bool uvd_v3_1_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index f93079e09215..4b96fd583772 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -302,7 +302,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) /* enable VCPU clock */ WREG32(mmUVD_VCPU_CNTL, 1 << 9); - /* disable interupt */ + /* disable interrupt */ WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1)); #ifdef __BIG_ENDIAN @@ -312,6 +312,7 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) #endif WREG32(mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl); WREG32(mmUVD_MP_SWAP_CNTL, mp_swap_cntl); + /* initialize UVD memory controller */ WREG32(mmUVD_LMI_CTRL, 0x203108); @@ -658,9 +659,9 @@ static void uvd_v4_2_set_dcm(struct amdgpu_device *adev, WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2); } -static bool uvd_v4_2_is_idle(void *handle) +static bool uvd_v4_2_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index 2295c8713d61..71409ad8b7ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -580,9 +580,9 @@ static void uvd_v5_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) } } -static bool uvd_v5_0_is_idle(void *handle) +static bool uvd_v5_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 070a0624c2c5..1c07b701d0e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -1143,9 +1143,9 @@ static void uvd_v6_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, vmid); } -static bool uvd_v6_0_is_idle(void *handle) +static bool uvd_v6_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS) & SRBM_STATUS__UVD_BUSY_MASK); } @@ -1156,7 +1156,7 @@ static int uvd_v6_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) { - if (uvd_v6_0_is_idle(adev)) + if (uvd_v6_0_is_idle(ip_block)) return 0; } return -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c index c633b7ff2943..8c8c02606d25 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c @@ -201,9 +201,9 @@ static void vce_v2_0_mc_resume(struct amdgpu_device *adev) WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1); } -static bool vce_v2_0_is_idle(void *handle) +static bool vce_v2_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return !(RREG32(mmSRBM_STATUS2) & SRBM_STATUS2__VCE_BUSY_MASK); } @@ -214,7 +214,7 @@ static int vce_v2_0_wait_for_idle(struct amdgpu_ip_block *ip_block) unsigned i; for (i = 0; i < adev->usec_timeout; i++) { - if (vce_v2_0_is_idle(adev)) + if (vce_v2_0_is_idle(ip_block)) return 0; } return -ETIMEDOUT; @@ -280,7 +280,7 @@ static int vce_v2_0_stop(struct amdgpu_device *adev) if (vce_v2_0_lmi_clean(adev)) { - DRM_INFO("vce is not idle \n"); + DRM_INFO("VCE is not idle \n"); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 01248a3982ba..708123899c41 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -597,9 +597,9 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx) WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1); } -static bool vce_v3_0_is_idle(void *handle) +static bool vce_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; u32 mask = 0; mask |= (adev->vce.harvest_config & AMDGPU_VCE_HARVEST_VCE0) ? 0 : SRBM_STATUS2__VCE0_BUSY_MASK; @@ -614,7 +614,7 @@ static int vce_v3_0_wait_for_idle(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (i = 0; i < adev->usec_timeout; i++) - if (vce_v3_0_is_idle(adev)) + if (vce_v3_0_is_idle(ip_block)) return 0; return -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 5ea96c983517..21b57c29bf7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -81,14 +81,14 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_1_0[] = { SOC15_REG_ENTRY_STR(VCN, 0, mmUVD_DPG_PAUSE) }; -static int vcn_v1_0_stop(struct amdgpu_device *adev); +static int vcn_v1_0_stop(struct amdgpu_vcn_inst *vinst); static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v1_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v1_0_idle_work_handler(struct work_struct *work); static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); @@ -105,7 +105,8 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - adev->vcn.num_enc_rings = 2; + adev->vcn.inst[0].num_enc_rings = 2; + adev->vcn.inst[0].set_pg_state = vcn_v1_0_set_pg_state; vcn_v1_0_set_dec_ring_funcs(adev); vcn_v1_0_set_enc_ring_funcs(adev); @@ -113,7 +114,7 @@ static int vcn_v1_0_early_init(struct amdgpu_ip_block *ip_block) jpeg_v1_0_early_init(ip_block); - return amdgpu_vcn_early_init(adev); + return amdgpu_vcn_early_init(adev, 0); } /** @@ -138,23 +139,23 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) return r; /* VCN ENC TRAP */ - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); if (r) return r; } - r = amdgpu_vcn_sw_init(adev); + r = amdgpu_vcn_sw_init(adev, 0); if (r) return r; /* Override the work func */ - adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler; + adev->vcn.inst[0].idle_work.work.func = vcn_v1_0_idle_work_handler; - amdgpu_vcn_setup_ucode(adev); + amdgpu_vcn_setup_ucode(adev, 0); - r = amdgpu_vcn_resume(adev); + r = amdgpu_vcn_resume(adev, 0); if (r) return r; @@ -166,18 +167,18 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - adev->vcn.internal.scratch9 = adev->vcn.inst->external.scratch9 = + adev->vcn.inst[0].internal.scratch9 = adev->vcn.inst->external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = adev->vcn.inst->external.data0 = + adev->vcn.inst[0].internal.data0 = adev->vcn.inst->external.data0 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = adev->vcn.inst->external.data1 = + adev->vcn.inst[0].internal.data1 = adev->vcn.inst->external.data1 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = adev->vcn.inst->external.cmd = + adev->vcn.inst[0].internal.cmd = adev->vcn.inst->external.cmd = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = adev->vcn.inst->external.nop = + adev->vcn.inst[0].internal.nop = adev->vcn.inst->external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i); ring = &adev->vcn.inst->ring_enc[i]; @@ -189,7 +190,7 @@ static int vcn_v1_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - adev->vcn.pause_dpg_mode = vcn_v1_0_pause_dpg_mode; + adev->vcn.inst[0].pause_dpg_mode = vcn_v1_0_pause_dpg_mode; if (amdgpu_vcnfw_log) { volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; @@ -223,13 +224,13 @@ static int vcn_v1_0_sw_fini(struct amdgpu_ip_block *ip_block) int r; struct amdgpu_device *adev = ip_block->adev; - r = amdgpu_vcn_suspend(adev); + r = amdgpu_vcn_suspend(adev, 0); if (r) return r; jpeg_v1_0_sw_fini(ip_block); - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, 0); kfree(adev->vcn.ip_dump); @@ -253,7 +254,7 @@ static int vcn_v1_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { ring = &adev->vcn.inst->ring_enc[i]; r = amdgpu_ring_test_helper(ring); if (r) @@ -276,13 +277,14 @@ static int vcn_v1_0_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v1_0_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_vcn_inst *vinst = adev->vcn.inst; - cancel_delayed_work_sync(&adev->vcn.idle_work); + cancel_delayed_work_sync(&vinst->idle_work); if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, 0, mmUVD_STATUS))) { - vcn_v1_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, 0, mmUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } return 0; @@ -301,7 +303,7 @@ static int vcn_v1_0_suspend(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; bool idle_work_unexecuted; - idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work); + idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work); if (idle_work_unexecuted) { if (adev->pm.dpm_enabled) amdgpu_dpm_enable_vcn(adev, false, 0); @@ -311,7 +313,7 @@ static int vcn_v1_0_suspend(struct amdgpu_ip_block *ip_block) if (r) return r; - r = amdgpu_vcn_suspend(adev); + r = amdgpu_vcn_suspend(adev, 0); return r; } @@ -327,7 +329,7 @@ static int vcn_v1_0_resume(struct amdgpu_ip_block *ip_block) { int r; - r = amdgpu_vcn_resume(ip_block->adev); + r = amdgpu_vcn_resume(ip_block->adev, 0); if (r) return r; @@ -339,12 +341,13 @@ static int vcn_v1_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v1_0_mc_resume_spg_mode - memory controller programming * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev) +static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -410,8 +413,9 @@ static void vcn_v1_0_mc_resume_spg_mode(struct amdgpu_device *adev) adev->gfx.config.gb_addr_config); } -static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev) +static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -485,12 +489,13 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev) /** * vcn_v1_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev) +static void vcn_v1_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data; /* JPEG disable CGC */ @@ -611,12 +616,13 @@ static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev) /** * vcn_v1_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: Pointer to the VCN instance structure * * Enable clock gating for VCN block */ -static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev) +static void vcn_v1_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; /* enable JPEG CGC */ @@ -680,8 +686,10 @@ static void vcn_v1_0_enable_clock_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel) +static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel) { + struct amdgpu_device *adev = vinst->adev; uint32_t reg_data = 0; /* disable JPEG CGC */ @@ -734,8 +742,9 @@ static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t s WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SUVD_CGC_CTRL, 0, 0xFFFFFFFF, sram_sel); } -static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev) +static void vcn_1_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -779,8 +788,9 @@ static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data); } -static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev) +static void vcn_1_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -823,12 +833,13 @@ static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev) /** * vcn_v1_0_start_spg_mode - start VCN block * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Setup and start the VCN block */ -static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_start_spg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; uint32_t lmi_swap_cntl; @@ -837,13 +848,13 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) /* disable byte swapping */ lmi_swap_cntl = 0; - vcn_1_0_disable_static_power_gating(adev); + vcn_1_0_disable_static_power_gating(vinst); tmp = RREG32_SOC15(UVD, 0, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY; WREG32_SOC15(UVD, 0, mmUVD_STATUS, tmp); /* disable clock gating */ - vcn_v1_0_disable_clock_gating(adev); + vcn_v1_0_disable_clock_gating(vinst); /* disable interupt */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0, @@ -885,7 +896,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - vcn_v1_0_mc_resume_spg_mode(adev); + vcn_v1_0_mc_resume_spg_mode(vinst); WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK_1_0, 0x10); WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0, @@ -1001,8 +1012,9 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; uint32_t lmi_swap_cntl; @@ -1010,7 +1022,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) /* disable byte swapping */ lmi_swap_cntl = 0; - vcn_1_0_enable_static_power_gating(adev); + vcn_1_0_enable_static_power_gating(vinst); /* enable dynamic power gating mode */ tmp = RREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS); @@ -1019,7 +1031,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS, tmp); /* enable clock gating */ - vcn_v1_0_clock_gating_dpg_mode(adev, 0); + vcn_v1_0_clock_gating_dpg_mode(vinst, 0); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -1068,7 +1080,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0xFFFFFFFF, 0); - vcn_v1_0_mc_resume_dpg_mode(adev); + vcn_v1_0_mc_resume_dpg_mode(vinst); WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_REG_XX_MASK, 0x10, 0xFFFFFFFF, 0); WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK, 0x3, 0xFFFFFFFF, 0); @@ -1085,7 +1097,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MASTINT_EN, UVD_MASTINT_EN__VCPU_EN_MASK, UVD_MASTINT_EN__VCPU_EN_MASK, 0); - vcn_v1_0_clock_gating_dpg_mode(adev, 1); + vcn_v1_0_clock_gating_dpg_mode(vinst, 1); /* setup mmUVD_LMI_CTRL */ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_CTRL, (8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) | @@ -1145,21 +1157,24 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v1_0_start(struct amdgpu_device *adev) +static int vcn_v1_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + return (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ? - vcn_v1_0_start_dpg_mode(adev) : vcn_v1_0_start_spg_mode(adev); + vcn_v1_0_start_dpg_mode(vinst) : vcn_v1_0_start_spg_mode(vinst); } /** * vcn_v1_0_stop_spg_mode - stop VCN block * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * stop the VCN block */ -static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_stop_spg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; int tmp; SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); @@ -1199,13 +1214,14 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_STATUS, 0); - vcn_v1_0_enable_clock_gating(adev); - vcn_1_0_enable_static_power_gating(adev); + vcn_v1_0_enable_clock_gating(vinst); + vcn_1_0_enable_static_power_gating(vinst); return 0; } -static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev) +static int vcn_v1_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t tmp; /* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */ @@ -1237,21 +1253,24 @@ static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v1_0_stop(struct amdgpu_device *adev) +static int vcn_v1_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; int r; if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - r = vcn_v1_0_stop_dpg_mode(adev); + r = vcn_v1_0_stop_dpg_mode(vinst); else - r = vcn_v1_0_stop_spg_mode(adev); + r = vcn_v1_0_stop_spg_mode(vinst); return r; } -static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; int ret_code; uint32_t reg_data = 0; uint32_t reg_data2 = 0; @@ -1377,9 +1396,9 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, return 0; } -static bool vcn_v1_0_is_idle(void *handle) +static bool vcn_v1_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE); } @@ -1399,16 +1418,17 @@ static int vcn_v1_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, enum amd_clockgating_state state) { struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_vcn_inst *vinst = adev->vcn.inst; bool enable = (state == AMD_CG_STATE_GATE); if (enable) { /* wait for STATUS to clear */ - if (!vcn_v1_0_is_idle(adev)) + if (!vcn_v1_0_is_idle(ip_block)) return -EBUSY; - vcn_v1_0_enable_clock_gating(adev); + vcn_v1_0_enable_clock_gating(vinst); } else { /* disable HW gating and enable Sw gating */ - vcn_v1_0_disable_clock_gating(adev); + vcn_v1_0_disable_clock_gating(vinst); } return 0; } @@ -1800,8 +1820,8 @@ static void vcn_v1_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t coun } } -static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v1_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { /* This doesn't actually powergate the VCN block. * That's done in the dpm code via the SMC. This @@ -1811,28 +1831,29 @@ static int vcn_v1_0_set_powergating_state(struct amdgpu_ip_block *ip_block, * the smc and the hw blocks */ int ret; - struct amdgpu_device *adev = ip_block->adev; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v1_0_stop(adev); + ret = vcn_v1_0_stop(vinst); else - ret = vcn_v1_0_start(adev); + ret = vcn_v1_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; + return ret; } static void vcn_v1_0_idle_work_handler(struct work_struct *work) { - struct amdgpu_device *adev = - container_of(work, struct amdgpu_device, vcn.idle_work.work); + struct amdgpu_vcn_inst *vcn_inst = + container_of(work, struct amdgpu_vcn_inst, idle_work.work); + struct amdgpu_device *adev = vcn_inst->adev; unsigned int fences = 0, i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]); if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { @@ -1848,7 +1869,7 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work) else new_state.jpeg = VCN_DPG_STATE__UNPAUSE; - adev->vcn.pause_dpg_mode(adev, 0, &new_state); + adev->vcn.inst->pause_dpg_mode(vcn_inst, &new_state); } fences += amdgpu_fence_count_emitted(adev->jpeg.inst->ring_dec); @@ -1862,16 +1883,16 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work) amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_GATE); } else { - schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + schedule_delayed_work(&adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT); } } static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.inst[0].idle_work); - mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + mutex_lock(&adev->vcn.inst[0].vcn1_jpeg1_workaround); if (amdgpu_fence_wait_empty(ring->adev->jpeg.inst->ring_dec)) DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n"); @@ -1897,7 +1918,7 @@ void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks) struct dpg_pause_state new_state; unsigned int fences = 0, i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]); if (fences) @@ -1915,14 +1936,14 @@ void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks) else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) new_state.jpeg = VCN_DPG_STATE__PAUSE; - adev->vcn.pause_dpg_mode(adev, 0, &new_state); + adev->vcn.inst->pause_dpg_mode(adev->vcn.inst, &new_state); } } void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring) { - schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT); - mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround); + schedule_delayed_work(&ring->adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT); + mutex_unlock(&ring->adev->vcn.inst[0].vcn1_jpeg1_workaround); } static void vcn_v1_0_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p) @@ -1997,7 +2018,7 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .is_idle = vcn_v1_0_is_idle, .wait_for_idle = vcn_v1_0_wait_for_idle, .set_clockgating_state = vcn_v1_0_set_clockgating_state, - .set_powergating_state = vcn_v1_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v1_0_dump_ip_state, .print_ip_state = vcn_v1_0_print_ip_state, }; @@ -2056,11 +2077,11 @@ static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, uint32_t reg = amdgpu_ib_get_value(ib, i); uint32_t val = amdgpu_ib_get_value(ib, i + 1); - if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + if (reg == PACKET0(p->adev->vcn.inst[0].internal.data0, 0)) { msg_lo = val; - } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + } else if (reg == PACKET0(p->adev->vcn.inst[0].internal.data1, 0)) { msg_hi = val; - } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + } else if (reg == PACKET0(p->adev->vcn.inst[0].internal.cmd, 0)) { r = vcn_v1_0_validate_bo(p, job, ((u64)msg_hi) << 32 | msg_lo); if (r) @@ -2145,7 +2166,7 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) adev->vcn.inst->ring_enc[i].funcs = &vcn_v1_0_enc_ring_vm_funcs; } @@ -2156,7 +2177,7 @@ static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = { static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev) { - adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 2; + adev->vcn.inst->irq.num_types = adev->vcn.inst[0].num_enc_rings + 2; adev->vcn.inst->irq.funcs = &vcn_v1_0_irq_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index e42cfc731ad8..8e7a36f26e9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -92,10 +92,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_2_0[] = { static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v2_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static int vcn_v2_0_start_sriov(struct amdgpu_device *adev); /** * vcn_v2_0_early_init - set function pointers and load microcode @@ -110,15 +110,16 @@ static int vcn_v2_0_early_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; if (amdgpu_sriov_vf(adev)) - adev->vcn.num_enc_rings = 1; + adev->vcn.inst[0].num_enc_rings = 1; else - adev->vcn.num_enc_rings = 2; + adev->vcn.inst[0].num_enc_rings = 2; + adev->vcn.inst->set_pg_state = vcn_v2_0_set_pg_state; vcn_v2_0_set_dec_ring_funcs(adev); vcn_v2_0_set_enc_ring_funcs(adev); vcn_v2_0_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + return amdgpu_vcn_early_init(adev, 0); } /** @@ -145,7 +146,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) return r; /* VCN ENC TRAP */ - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); @@ -153,13 +154,13 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - r = amdgpu_vcn_sw_init(adev); + r = amdgpu_vcn_sw_init(adev, 0); if (r) return r; - amdgpu_vcn_setup_ucode(adev); + amdgpu_vcn_setup_ucode(adev, 0); - r = amdgpu_vcn_resume(adev); + r = amdgpu_vcn_resume(adev, 0); if (r) return r; @@ -175,25 +176,25 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; - adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; - adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; - adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; adev->vcn.inst->external.scratch9 = SOC15_REG_OFFSET(UVD, 0, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; adev->vcn.inst->external.data0 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; adev->vcn.inst->external.data1 = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; adev->vcn.inst->external.cmd = SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; + adev->vcn.inst[0].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; adev->vcn.inst->external.nop = SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i); ring = &adev->vcn.inst->ring_enc[i]; @@ -210,7 +211,7 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - adev->vcn.pause_dpg_mode = vcn_v2_0_pause_dpg_mode; + adev->vcn.inst[0].pause_dpg_mode = vcn_v2_0_pause_dpg_mode; r = amdgpu_virt_alloc_mm_table(adev); if (r) @@ -254,11 +255,11 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); + r = amdgpu_vcn_suspend(adev, 0); if (r) return r; - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, 0); kfree(adev->vcn.ip_dump); @@ -292,7 +293,7 @@ static int vcn_v2_0_hw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) ring->sched.ready = false; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { ring = &adev->vcn.inst->ring_enc[i]; r = amdgpu_ring_test_helper(ring); if (r) @@ -312,13 +313,14 @@ static int vcn_v2_0_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v2_0_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_vcn_inst *vinst = adev->vcn.inst; - cancel_delayed_work_sync(&adev->vcn.idle_work); + cancel_delayed_work_sync(&vinst->idle_work); if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, 0, mmUVD_STATUS))) - vcn_v2_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, 0, mmUVD_STATUS))) + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); return 0; } @@ -338,7 +340,7 @@ static int vcn_v2_0_suspend(struct amdgpu_ip_block *ip_block) if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + r = amdgpu_vcn_suspend(ip_block->adev, 0); return r; } @@ -354,7 +356,7 @@ static int vcn_v2_0_resume(struct amdgpu_ip_block *ip_block) { int r; - r = amdgpu_vcn_resume(ip_block->adev); + r = amdgpu_vcn_resume(ip_block->adev, 0); if (r) return r; @@ -366,12 +368,13 @@ static int vcn_v2_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v2_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer + * @vinst: Pointer to the VCN instance structure * * Let the VCN memory controller know it's offsets */ -static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) +static void vcn_v2_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -426,8 +429,10 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config); } -static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirect) +static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[0].fw->size + 4); uint32_t offset; @@ -525,12 +530,13 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec /** * vcn_v2_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v2_0_disable_clock_gating(struct amdgpu_device *adev) +static void vcn_v2_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data; if (amdgpu_sriov_vf(adev)) @@ -634,9 +640,10 @@ static void vcn_v2_0_disable_clock_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev, +static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, uint8_t sram_sel, uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; uint32_t reg_data = 0; /* enable sw clock gating control */ @@ -685,12 +692,13 @@ static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v2_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v2_0_enable_clock_gating(struct amdgpu_device *adev) +static void vcn_v2_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (amdgpu_sriov_vf(adev)) @@ -743,8 +751,9 @@ static void vcn_v2_0_enable_clock_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_0_disable_static_power_gating(struct amdgpu_device *adev) +static void vcn_v2_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (amdgpu_sriov_vf(adev)) @@ -792,8 +801,9 @@ static void vcn_v2_0_disable_static_power_gating(struct amdgpu_device *adev) WREG32_SOC15(VCN, 0, mmUVD_POWER_STATUS, data); } -static void vcn_v2_0_enable_static_power_gating(struct amdgpu_device *adev) +static void vcn_v2_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t data = 0; if (amdgpu_sriov_vf(adev)) @@ -834,13 +844,14 @@ static void vcn_v2_0_enable_static_power_gating(struct amdgpu_device *adev) } } -static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) +static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; - vcn_v2_0_enable_static_power_gating(adev); + vcn_v2_0_enable_static_power_gating(vinst); /* enable dynamic power gating mode */ tmp = RREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS); @@ -852,7 +863,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) adev->vcn.inst->dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst->dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v2_0_clock_gating_dpg_mode(adev, 0, indirect); + vcn_v2_0_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -901,7 +912,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v2_0_mc_resume_dpg_mode(adev, indirect); + vcn_v2_0_mc_resume_dpg_mode(vinst, indirect); WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( UVD, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect); @@ -969,8 +980,9 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) return 0; } -static int vcn_v2_0_start(struct amdgpu_device *adev) +static int vcn_v2_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr; struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec; uint32_t rb_bufsz, tmp; @@ -981,16 +993,16 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) amdgpu_dpm_enable_vcn(adev, true, 0); if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - return vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram); + return vcn_v2_0_start_dpg_mode(vinst, adev->vcn.inst->indirect_sram); - vcn_v2_0_disable_static_power_gating(adev); + vcn_v2_0_disable_static_power_gating(vinst); /* set uvd status busy */ tmp = RREG32_SOC15(UVD, 0, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY; WREG32_SOC15(UVD, 0, mmUVD_STATUS, tmp); /*SW clock gating */ - vcn_v2_0_disable_clock_gating(adev); + vcn_v2_0_disable_clock_gating(vinst); /* enable VCPU clock */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CNTL), @@ -1034,7 +1046,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - vcn_v2_0_mc_resume(adev); + vcn_v2_0_mc_resume(vinst); /* release VCPU reset to boot */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), 0, @@ -1142,12 +1154,13 @@ static int vcn_v2_0_start(struct amdgpu_device *adev) return 0; } -static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev) +static int vcn_v2_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v2_0_pause_dpg_mode(adev, 0, &state); + vcn_v2_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); @@ -1172,13 +1185,14 @@ static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev) return 0; } -static int vcn_v2_0_stop(struct amdgpu_device *adev) +static int vcn_v2_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; uint32_t tmp; int r; if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v2_0_stop_dpg_mode(adev); + r = vcn_v2_0_stop_dpg_mode(vinst); if (r) return r; goto power_off; @@ -1230,8 +1244,8 @@ static int vcn_v2_0_stop(struct amdgpu_device *adev) /* clear status */ WREG32_SOC15(VCN, 0, mmUVD_STATUS, 0); - vcn_v2_0_enable_clock_gating(adev); - vcn_v2_0_enable_static_power_gating(adev); + vcn_v2_0_enable_clock_gating(vinst); + vcn_v2_0_enable_static_power_gating(vinst); power_off: if (adev->pm.dpm_enabled) @@ -1240,9 +1254,11 @@ power_off: return 0; } -static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v2_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct amdgpu_ring *ring; uint32_t reg_data = 0; int ret_code; @@ -1317,9 +1333,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, return 0; } -static bool vcn_v2_0_is_idle(void *handle) +static bool vcn_v2_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; return (RREG32_SOC15(VCN, 0, mmUVD_STATUS) == UVD_STATUS__IDLE); } @@ -1346,12 +1362,12 @@ static int vcn_v2_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, if (enable) { /* wait for STATUS to clear */ - if (!vcn_v2_0_is_idle(adev)) + if (!vcn_v2_0_is_idle(ip_block)) return -EBUSY; - vcn_v2_0_enable_clock_gating(adev); + vcn_v2_0_enable_clock_gating(&adev->vcn.inst[0]); } else { /* disable HW gating and enable Sw gating */ - vcn_v2_0_disable_clock_gating(adev); + vcn_v2_0_disable_clock_gating(&adev->vcn.inst[0]); } return 0; } @@ -1421,9 +1437,9 @@ void vcn_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, 0); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1)); } @@ -1438,7 +1454,7 @@ void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[0].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_END << 1)); } @@ -1458,7 +1474,7 @@ void vcn_v2_0_dec_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count) WARN_ON(ring->wptr % 2 || count % 2); for (i = 0; i < count / 2; i++) { - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.nop, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.nop, 0)); amdgpu_ring_write(ring, 0); } } @@ -1479,25 +1495,25 @@ void vcn_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq, struct amdgpu_device *adev = ring->adev; WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.context_id, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.context_id, 0)); amdgpu_ring_write(ring, seq); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, addr & 0xffffffff); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_FENCE << 1)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, 0); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, 0); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_TRAP << 1)); } @@ -1520,14 +1536,14 @@ void vcn_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_device *adev = ring->adev; unsigned vmid = AMDGPU_JOB_GET_VMID(job); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_vmid, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_vmid, 0)); amdgpu_ring_write(ring, vmid); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_bar_low, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_bar_low, 0)); amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_bar_high, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_bar_high, 0)); amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.ib_size, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.ib_size, 0)); amdgpu_ring_write(ring, ib->length_dw); } @@ -1536,16 +1552,16 @@ void vcn_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, reg << 2); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, val); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.gp_scratch8, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.gp_scratch8, 0)); amdgpu_ring_write(ring, mask); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_REG_READ_COND_WAIT << 1)); } @@ -1570,13 +1586,13 @@ void vcn_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, { struct amdgpu_device *adev = ring->adev; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data0, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data0, 0)); amdgpu_ring_write(ring, reg << 2); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.data1, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.data1, 0)); amdgpu_ring_write(ring, val); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_WRITE_REG << 1)); } @@ -1777,9 +1793,9 @@ int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring) r = amdgpu_ring_alloc(ring, 4); if (r) return r; - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.cmd, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.cmd, 0)); amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1)); - amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0)); + amdgpu_ring_write(ring, PACKET0(adev->vcn.inst[ring->me].internal.scratch9, 0)); amdgpu_ring_write(ring, 0xDEADBEEF); amdgpu_ring_commit(ring); for (i = 0; i < adev->usec_timeout; i++) { @@ -1796,8 +1812,8 @@ int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring) } -static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v2_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { /* This doesn't actually powergate the VCN block. * That's done in the dpm code via the SMC. This @@ -1807,23 +1823,24 @@ static int vcn_v2_0_set_powergating_state(struct amdgpu_ip_block *ip_block, * the smc and the hw blocks */ int ret; - struct amdgpu_device *adev = ip_block->adev; + struct amdgpu_device *adev = vinst->adev; if (amdgpu_sriov_vf(adev)) { - adev->vcn.cur_state = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v2_0_stop(adev); + ret = vcn_v2_0_stop(vinst); else - ret = vcn_v2_0_start(adev); + ret = vcn_v2_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; + return ret; } @@ -1862,7 +1879,7 @@ static int vcn_v2_0_start_mmsch(struct amdgpu_device *adev, adev->vcn.inst->ring_dec.wptr_old = 0; vcn_v2_0_dec_ring_set_wptr(&adev->vcn.inst->ring_dec); - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) { adev->vcn.inst->ring_enc[i].wptr = 0; adev->vcn.inst->ring_enc[i].wptr_old = 0; vcn_v2_0_enc_ring_set_wptr(&adev->vcn.inst->ring_enc[i]); @@ -1988,7 +2005,7 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev) SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE); - for (r = 0; r < adev->vcn.num_enc_rings; ++r) { + for (r = 0; r < adev->vcn.inst[0].num_enc_rings; ++r) { ring = &adev->vcn.inst->ring_enc[r]; ring->wptr = 0; MMSCH_V2_0_INSERT_DIRECT_WT( @@ -2104,7 +2121,7 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = { .is_idle = vcn_v2_0_is_idle, .wait_for_idle = vcn_v2_0_wait_for_idle, .set_clockgating_state = vcn_v2_0_set_clockgating_state, - .set_powergating_state = vcn_v2_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v2_0_dump_ip_state, .print_ip_state = vcn_v2_0_print_ip_state, }; @@ -2177,7 +2194,7 @@ static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev) { int i; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) + for (i = 0; i < adev->vcn.inst[0].num_enc_rings; ++i) adev->vcn.inst->ring_enc[i].funcs = &vcn_v2_0_enc_ring_vm_funcs; } @@ -2188,7 +2205,7 @@ static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = { static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev) { - adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst->irq.num_types = adev->vcn.inst[0].num_enc_rings + 1; adev->vcn.inst->irq.funcs = &vcn_v2_0_irq_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 105e59f6132b..dff1a8859036 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -95,10 +95,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_2_5[] = { static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v2_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static int vcn_v2_5_sriov_start(struct amdgpu_device *adev); static void vcn_v2_5_set_ras_funcs(struct amdgpu_device *adev); @@ -118,11 +118,13 @@ static int amdgpu_ih_clientid_vcns[] = { static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; if (amdgpu_sriov_vf(adev)) { adev->vcn.num_vcn_inst = 2; adev->vcn.harvest_config = 0; - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + adev->vcn.inst[i].num_enc_rings = 1; } else { u32 harvest; int i; @@ -131,13 +133,12 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block) harvest = RREG32_SOC15(VCN, i, mmCC_UVD_HARVESTING); if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK) adev->vcn.harvest_config |= 1 << i; + adev->vcn.inst[i].num_enc_rings = 2; } if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 | - AMDGPU_VCN_HARVEST_VCN1)) + AMDGPU_VCN_HARVEST_VCN1)) /* both instances are harvested, disable the block */ return -ENOENT; - - adev->vcn.num_enc_rings = 2; } vcn_v2_5_set_dec_ring_funcs(adev); @@ -145,7 +146,15 @@ static int vcn_v2_5_early_init(struct amdgpu_ip_block *ip_block) vcn_v2_5_set_irq_funcs(adev); vcn_v2_5_set_ras_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + adev->vcn.inst[i].set_pg_state = vcn_v2_5_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } /** @@ -164,6 +173,8 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; for (j = 0; j < adev->vcn.num_vcn_inst; j++) { + volatile struct amdgpu_fw_shared *fw_shared; + if (adev->vcn.harvest_config & (1 << j)) continue; /* VCN DEC TRAP */ @@ -173,7 +184,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) return r; /* VCN ENC TRAP */ - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j], i + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[j].irq); if (r) @@ -185,39 +196,33 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].ras_poison_irq); if (r) return r; - } - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; + r = amdgpu_vcn_sw_init(adev, j); + if (r) + return r; - amdgpu_vcn_setup_ucode(adev); + amdgpu_vcn_setup_ucode(adev, j); - r = amdgpu_vcn_resume(adev); - if (r) - return r; + r = amdgpu_vcn_resume(adev, j); + if (r) + return r; - for (j = 0; j < adev->vcn.num_vcn_inst; j++) { - volatile struct amdgpu_fw_shared *fw_shared; + adev->vcn.inst[j].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - if (adev->vcn.harvest_config & (1 << j)) - continue; - adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; - adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; - adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; - adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - - adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; adev->vcn.inst[j].external.scratch9 = SOC15_REG_OFFSET(VCN, j, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; adev->vcn.inst[j].external.data0 = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; adev->vcn.inst[j].external.data1 = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; adev->vcn.inst[j].external.cmd = SOC15_REG_OFFSET(VCN, j, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; + adev->vcn.inst[j].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; adev->vcn.inst[j].external.nop = SOC15_REG_OFFSET(VCN, j, mmUVD_NO_OP); ring = &adev->vcn.inst[j].ring_dec; @@ -237,7 +242,7 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i); ring = &adev->vcn.inst[j].ring_enc[i]; @@ -265,6 +270,9 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[j].pause_dpg_mode = vcn_v2_5_pause_dpg_mode; } if (amdgpu_sriov_vf(adev)) { @@ -273,9 +281,6 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v2_5_pause_dpg_mode; - r = amdgpu_vcn_ras_sw_init(adev); if (r) return r; @@ -319,15 +324,18 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; - - r = amdgpu_vcn_sw_fini(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -366,7 +374,7 @@ static int vcn_v2_5_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { ring = &adev->vcn.inst[j].ring_enc[i]; r = amdgpu_ring_test_helper(ring); if (r) @@ -390,19 +398,21 @@ static int vcn_v2_5_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + cancel_delayed_work_sync(&vinst->idle_work); + if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && + (vinst->cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, i, mmUVD_STATUS))) - vcn_v2_5_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) - amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); + amdgpu_irq_put(adev, &vinst->ras_poison_irq, 0); } return 0; @@ -417,15 +427,20 @@ static int vcn_v2_5_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v2_5_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v2_5_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -437,11 +452,14 @@ static int vcn_v2_5_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v2_5_hw_init(ip_block); @@ -451,13 +469,14 @@ static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v2_5_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @i: instance to resume + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v2_5_mc_resume(struct amdgpu_device *adev, int i) +static void vcn_v2_5_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t size; uint32_t offset; @@ -510,8 +529,11 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev, int i) AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); } -static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst_idx].fw->size + 4); uint32_t offset; @@ -609,13 +631,14 @@ static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx /** * vcn_v2_5_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @i: instance to disable clockgating on + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev, int i) +static void vcn_v2_5_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t data; if (adev->vcn.harvest_config & (1 << i)) @@ -721,9 +744,11 @@ static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev, int i) WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev, - uint8_t sram_sel, int inst_idx, uint8_t indirect) +static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; /* enable sw clock gating control */ @@ -772,13 +797,14 @@ static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v2_5_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @i: instance to enable clockgating on + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev, int i) +static void vcn_v2_5_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t data = 0; if (adev->vcn.harvest_config & (1 << i)) @@ -829,9 +855,11 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev, int i) WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx, +static void vcn_v2_6_enable_ras(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; if (amdgpu_ip_version(adev, UVD_HWIP, 0) != IP_VERSION(2, 6, 0)) @@ -856,8 +884,10 @@ static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx, tmp, 0, indirect); } -static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; @@ -875,7 +905,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v2_5_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v2_5_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -924,7 +954,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v2_5_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v2_5_mc_resume_dpg_mode(vinst, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect); @@ -935,7 +965,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, 0, mmUVD_LMI_CTRL2), 0, 0, indirect); - vcn_v2_6_enable_ras(adev, inst_idx, indirect); + vcn_v2_6_enable_ras(vinst, indirect); /* unblock VCPU register access */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( @@ -1000,8 +1030,10 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo return 0; } -static int vcn_v2_5_start(struct amdgpu_device *adev, int i) +static int vcn_v2_5_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; struct amdgpu_ring *ring; @@ -1015,7 +1047,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev, int i) amdgpu_dpm_enable_vcn(adev, true, i); if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - return vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram); + return vcn_v2_5_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); /* disable register anti-hang mechanism */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), 0, @@ -1029,7 +1061,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev, int i) return 0; /* SW clock gating */ - vcn_v2_5_disable_clock_gating(adev, i); + vcn_v2_5_disable_clock_gating(vinst); /* enable VCPU clock */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), @@ -1074,7 +1106,7 @@ static int vcn_v2_5_start(struct amdgpu_device *adev, int i) (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - vcn_v2_5_mc_resume(adev, i); + vcn_v2_5_mc_resume(vinst); /* VCN global tiling registers */ WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG, @@ -1379,8 +1411,10 @@ static int vcn_v2_5_sriov_start(struct amdgpu_device *adev) return vcn_v2_5_mmsch_start(adev, &adev->virt.mm_table); } -static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static int vcn_v2_5_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; /* Wait for power status to be 1 */ @@ -1407,20 +1441,25 @@ static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) return 0; } -static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) +static int vcn_v2_5_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t tmp; int r; if (adev->vcn.harvest_config & (1 << i)) return 0; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - return vcn_v2_5_stop_dpg_mode(adev, i); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + r = vcn_v2_5_stop_dpg_mode(vinst); + goto done; + } /* wait for vcn idle */ r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); if (r) - return r; + goto done; tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | UVD_LMI_STATUS__READ_CLEAN_MASK | @@ -1428,7 +1467,7 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); if (r) - return r; + goto done; /* block LMI UMC channel */ tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2); @@ -1439,7 +1478,7 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); if (r) - return r; + goto done; /* block VCPU register access */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), @@ -1458,22 +1497,25 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev, int i) /* clear status */ WREG32_SOC15(VCN, i, mmUVD_STATUS, 0); - vcn_v2_5_enable_clock_gating(adev, i); + vcn_v2_5_enable_clock_gating(vinst); /* enable register anti-hang mechanism */ WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); +done: if (adev->pm.dpm_enabled) amdgpu_dpm_enable_vcn(adev, false, i); - return 0; + return r; } -static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v2_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct amdgpu_ring *ring; uint32_t reg_data = 0; int ret_code = 0; @@ -1743,16 +1785,16 @@ static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev) for (j = 0; j < adev->vcn.num_vcn_inst; ++j) { if (adev->vcn.harvest_config & (1 << j)) continue; - for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + for (i = 0; i < adev->vcn.inst[j].num_enc_rings; ++i) { adev->vcn.inst[j].ring_enc[i].funcs = &vcn_v2_5_enc_ring_vm_funcs; adev->vcn.inst[j].ring_enc[i].me = j; } } } -static bool vcn_v2_5_is_idle(void *handle) +static bool vcn_v2_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1793,39 +1835,39 @@ static int vcn_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, return 0; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (enable) { - if (!vcn_v2_5_is_idle(adev)) + if (!vcn_v2_5_is_idle(ip_block)) return -EBUSY; - vcn_v2_5_enable_clock_gating(adev, i); + vcn_v2_5_enable_clock_gating(vinst); } else { - vcn_v2_5_disable_clock_gating(adev, i); + vcn_v2_5_disable_clock_gating(vinst); } } return 0; } -static int vcn_v2_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v2_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret = 0, i; + struct amdgpu_device *adev = vinst->adev; + int ret; if (amdgpu_sriov_vf(adev)) return 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (state == AMD_PG_STATE_GATE) - ret |= vcn_v2_5_stop(adev, i); - else - ret |= vcn_v2_5_start(adev, i); - } + if (state == AMD_PG_STATE_GATE) + ret = vcn_v2_5_stop(vinst); + else + ret = vcn_v2_5_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1902,10 +1944,10 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev) for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs; - adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v2_6_ras_irq_funcs; } } @@ -1982,7 +2024,7 @@ static const struct amd_ip_funcs vcn_v2_5_ip_funcs = { .is_idle = vcn_v2_5_is_idle, .wait_for_idle = vcn_v2_5_wait_for_idle, .set_clockgating_state = vcn_v2_5_set_clockgating_state, - .set_powergating_state = vcn_v2_5_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v2_5_dump_ip_state, .print_ip_state = vcn_v2_5_print_ip_state, }; @@ -1999,7 +2041,7 @@ static const struct amd_ip_funcs vcn_v2_6_ip_funcs = { .is_idle = vcn_v2_5_is_idle, .wait_for_idle = vcn_v2_5_wait_for_idle, .set_clockgating_state = vcn_v2_5_set_clockgating_state, - .set_powergating_state = vcn_v2_5_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v2_5_dump_ip_state, .print_ip_state = vcn_v2_5_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 63ddd4cca910..22ae1939476f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -105,10 +105,10 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev); static void vcn_v3_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev); static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v3_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring); @@ -124,11 +124,13 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; if (amdgpu_sriov_vf(adev)) { adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID; adev->vcn.harvest_config = 0; - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) + adev->vcn.inst[i].num_enc_rings = 1; } else { if (adev->vcn.harvest_config == (AMDGPU_VCN_HARVEST_VCN0 | @@ -136,18 +138,27 @@ static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block) /* both instances are harvested, disable the block */ return -ENOENT; - if (amdgpu_ip_version(adev, UVD_HWIP, 0) == - IP_VERSION(3, 0, 33)) - adev->vcn.num_enc_rings = 0; - else - adev->vcn.num_enc_rings = 2; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (amdgpu_ip_version(adev, UVD_HWIP, 0) == + IP_VERSION(3, 0, 33)) + adev->vcn.inst[i].num_enc_rings = 0; + else + adev->vcn.inst[i].num_enc_rings = 2; + } } vcn_v3_0_set_dec_ring_funcs(adev); vcn_v3_0_set_enc_ring_funcs(adev); vcn_v3_0_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + adev->vcn.inst[i].set_pg_state = vcn_v3_0_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + return 0; } /** @@ -166,16 +177,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) uint32_t *ptr; struct amdgpu_device *adev = ip_block->adev; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - /* * Note: doorbell assignment is fixed for SRIOV multiple VCN engines * Formula: @@ -195,22 +196,32 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; - adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; - adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; - adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; - adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + + adev->vcn.inst[i].internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET; - adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET; adev->vcn.inst[i].external.scratch9 = SOC15_REG_OFFSET(VCN, i, mmUVD_SCRATCH9); - adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET; adev->vcn.inst[i].external.data0 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA0); - adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET; adev->vcn.inst[i].external.data1 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA1); - adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET; adev->vcn.inst[i].external.cmd = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_CMD); - adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; + adev->vcn.inst[i].internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET; adev->vcn.inst[i].external.nop = SOC15_REG_OFFSET(VCN, i, mmUVD_NO_OP); /* VCN DEC TRAP */ @@ -224,7 +235,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) ring = &adev->vcn.inst[i].ring_dec; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) { - ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1); + ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1); } else { ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i; } @@ -236,7 +247,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(j); /* VCN ENC TRAP */ @@ -248,7 +259,7 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) ring = &adev->vcn.inst[i].ring_enc[j]; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) { - ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1 + j; + ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.inst[i].num_enc_rings + 1) + 1 + j; } else { ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i; } @@ -274,6 +285,9 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v3_0_pause_dpg_mode; } if (amdgpu_sriov_vf(adev)) { @@ -281,8 +295,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v3_0_pause_dpg_mode; /* Allocate memory for VCN IP Dump buffer */ ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL); @@ -325,14 +337,18 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -370,7 +386,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block) ring->sched.ready = true; } - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) { ring->sched.ready = false; @@ -398,7 +414,7 @@ static int vcn_v3_0_hw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; r = amdgpu_ring_test_helper(ring); if (r) @@ -422,17 +438,19 @@ static int vcn_v3_0_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, i, mmUVD_STATUS))) { - vcn_v3_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, i, mmUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } } @@ -449,15 +467,20 @@ static int vcn_v3_0_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v3_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v3_0_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -469,11 +492,14 @@ static int vcn_v3_0_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v3_0_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v3_0_hw_init(ip_block); @@ -483,13 +509,14 @@ static int vcn_v3_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v3_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst].fw->size + 4); uint32_t offset; @@ -538,8 +565,11 @@ static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst) AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared))); } -static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[inst_idx].fw->size + 4); uint32_t offset; @@ -634,8 +664,10 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } -static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -685,8 +717,10 @@ static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int WREG32_SOC15(VCN, inst, mmUVD_POWER_STATUS, data); } -static void vcn_v3_0_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -733,13 +767,14 @@ static void vcn_v3_0_enable_static_power_gating(struct amdgpu_device *adev, int /** * vcn_v3_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: Pointer to the VCN instance structure * * Disable clock gating for VCN block */ -static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; /* VCN disable CGC */ @@ -866,9 +901,12 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_CTRL, data); } -static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_device *adev, - uint8_t sram_sel, int inst_idx, uint8_t indirect) +static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; /* enable sw clock gating control */ @@ -917,13 +955,14 @@ static void vcn_v3_0_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v3_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: Pointer to the VCN instance structure * * Enable clock gating for VCN block */ -static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v3_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; /* enable VCN CGC */ @@ -982,8 +1021,10 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_CTRL, data); } -static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; @@ -1001,7 +1042,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v3_0_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v3_0_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -1050,7 +1091,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v3_0_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v3_0_mc_resume_dpg_mode(vinst, indirect); WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, mmUVD_REG_XX_MASK), 0x10, 0, indirect); @@ -1134,192 +1175,188 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo return 0; } -static int vcn_v3_0_start(struct amdgpu_device *adev) +static int vcn_v3_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t rb_bufsz, tmp; - int i, j, k, r; + int j, k, r; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, true, i); - } + if (adev->vcn.harvest_config & (1 << i)) + return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, true, i); - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v3_0_start_dpg_mode(vinst, vinst->indirect_sram); - /* disable VCN power gating */ - vcn_v3_0_disable_static_power_gating(adev, i); + /* disable VCN power gating */ + vcn_v3_0_disable_static_power_gating(vinst); - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp); + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp); - /*SW clock gating */ - vcn_v3_0_disable_clock_gating(adev, i); + /* SW clock gating */ + vcn_v3_0_disable_clock_gating(vinst); - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp); - - /* setup mmUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp | - UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | - UVD_LMI_CTRL__MASK_MC_URGENT_MASK | - UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | - UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); - - /* setup mmUVD_MPC_CNTL */ - tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL); - tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; - tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; - WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp); - - /* setup UVD_MPC_SET_MUXA0 */ - WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0, - ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); - - /* setup UVD_MPC_SET_MUXB0 */ - WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0, - ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); - - /* setup mmUVD_MPC_SET_MUX */ - WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX, - ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | - (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - - vcn_v3_0_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, mmUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - for (j = 0; j < 10; ++j) { - uint32_t status; + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, i, mmUVD_STATUS); - if (status & 2) - break; - mdelay(10); - } - r = 0; - if (status & 2) - break; + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp); + /* setup mmUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp | + UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__MASK_MC_URGENT_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); + + /* setup mmUVD_MPC_CNTL */ + tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL); + tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; + tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; + WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp); + + /* setup UVD_MPC_SET_MUXA0 */ + WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0, + ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); + + /* setup UVD_MPC_SET_MUXB0 */ + WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0, + ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); + + /* setup mmUVD_MPC_SET_MUX */ + WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX, + ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | + (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); + + vcn_v3_0_mc_resume(vinst); + + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, mmUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + for (j = 0; j < 10; ++j) { + uint32_t status; + + for (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, i, mmUVD_STATUS); + if (status & 2) + break; mdelay(10); - r = -1; } + r = 0; + if (status & 2) + break; - if (r) { - DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i); - return r; - } + DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + mdelay(10); + r = -1; + } - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + if (r) { + DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i); + return r; + } - WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - ring = &adev->vcn.inst[i].ring_dec; - /* force RBC into idle state */ - rb_bufsz = order_base_2(ring->ring_size); - tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz); - tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1); - tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1); - tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1); - tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); - WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); + WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0); - /* programm the RB_BASE for ring buffer */ - WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, - lower_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, - upper_32_bits(ring->gpu_addr)); + ring = &adev->vcn.inst[i].ring_dec; + /* force RBC into idle state */ + rb_bufsz = order_base_2(ring->ring_size); + tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz); + tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1); + tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1); + tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1); + tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); + WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp); - /* Initialize the ring buffer's read and write pointers */ - WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0); + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); - WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0); - ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR); - WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR, - lower_32_bits(ring->wptr)); - fw_shared->rb.wptr = lower_32_bits(ring->wptr); - fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET); - - if (amdgpu_ip_version(adev, UVD_HWIP, 0) != - IP_VERSION(3, 0, 33)) { - fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr)); - WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); - WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4); - fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET); - - fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); - ring = &adev->vcn.inst[i].ring_enc[1]; - WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr)); - WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr)); - WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr); - WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4); - fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET); - } + /* programm the RB_BASE for ring buffer */ + WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW, + lower_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH, + upper_32_bits(ring->gpu_addr)); + + /* Initialize the ring buffer's read and write pointers */ + WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0); + + WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0); + ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR); + WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR, + lower_32_bits(ring->wptr)); + fw_shared->rb.wptr = lower_32_bits(ring->wptr); + fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET); + + if (amdgpu_ip_version(adev, UVD_HWIP, 0) != + IP_VERSION(3, 0, 33)) { + fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr)); + WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); + WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4); + fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET); + + fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET); + ring = &adev->vcn.inst[i].ring_enc[1]; + WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr)); + WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr)); + WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr); + WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4); + fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET); } return 0; @@ -1434,7 +1471,7 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE); - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; ring->wptr = 0; rb_addr = ring->gpu_addr; @@ -1534,12 +1571,14 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) return 0; } -static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static int vcn_v3_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + vcn_v3_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, @@ -1565,86 +1604,87 @@ static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) return 0; } -static int vcn_v3_0_stop(struct amdgpu_device *adev) +static int vcn_v3_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; uint32_t tmp; - int i, r = 0; - - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + int r = 0; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v3_0_stop_dpg_mode(adev, i); - continue; - } + if (adev->vcn.harvest_config & (1 << i)) + return 0; - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + r = vcn_v3_0_stop_dpg_mode(vinst); + goto done; + } - tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | - UVD_LMI_STATUS__READ_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp); - tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK| - UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | + UVD_LMI_STATUS__READ_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp); + tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK| + UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - /* reset VCPU */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp); + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp); - /* clear status */ - WREG32_SOC15(VCN, i, mmUVD_STATUS, 0); + /* clear status */ + WREG32_SOC15(VCN, i, mmUVD_STATUS, 0); - /* apply HW clock gating */ - vcn_v3_0_enable_clock_gating(adev, i); + /* apply HW clock gating */ + vcn_v3_0_enable_clock_gating(vinst); - /* enable VCN power gating */ - vcn_v3_0_enable_static_power_gating(adev, i); - } + /* enable VCN power gating */ + vcn_v3_0_enable_static_power_gating(vinst); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); - return 0; + return r; } -static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state) +static int vcn_v3_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t reg_data = 0; @@ -1928,11 +1968,11 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, uint32_t reg = amdgpu_ib_get_value(ib, i); uint32_t val = amdgpu_ib_get_value(ib, i + 1); - if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data0, 0)) { msg_lo = val; - } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + } else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.data1, 0)) { msg_hi = val; - } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) && + } else if (reg == PACKET0(p->adev->vcn.inst[ring->me].internal.cmd, 0) && val == 0) { r = vcn_v3_0_dec_msg(p, job, ((u64)msg_hi) << 32 | msg_lo); @@ -2096,16 +2136,16 @@ static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { + for (j = 0; j < adev->vcn.inst[i].num_enc_rings; ++j) { adev->vcn.inst[i].ring_enc[j].funcs = &vcn_v3_0_enc_ring_vm_funcs; adev->vcn.inst[i].ring_enc[j].me = i; } } } -static bool vcn_v3_0_is_idle(void *handle) +static bool vcn_v3_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -2144,46 +2184,47 @@ static int vcn_v3_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, mmUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v3_0_enable_clock_gating(adev, i); + vcn_v3_0_enable_clock_gating(vinst); } else { - vcn_v3_0_disable_clock_gating(adev, i); + vcn_v3_0_disable_clock_gating(vinst); } } return 0; } -static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v3_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + struct amdgpu_device *adev = vinst->adev; + int ret = 0; /* for SRIOV, guest should not control VCN Power-gating * MMSCH FW should control Power-gating and clock-gating * guest should avoid touching CGC and PG */ if (amdgpu_sriov_vf(adev)) { - adev->vcn.cur_state = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v3_0_stop(adev); + ret = vcn_v3_0_stop(vinst); else - ret = vcn_v3_0_start(adev); + ret = vcn_v3_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -2248,7 +2289,7 @@ static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v3_0_irq_funcs; } } @@ -2326,7 +2367,7 @@ static const struct amd_ip_funcs vcn_v3_0_ip_funcs = { .is_idle = vcn_v3_0_is_idle, .wait_for_idle = vcn_v3_0_wait_for_idle, .set_clockgating_state = vcn_v3_0_set_clockgating_state, - .set_powergating_state = vcn_v3_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v3_0_dump_ip_state, .print_ip_state = vcn_v3_0_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 00551d6f0370..c6f6392c1c20 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -96,10 +96,10 @@ static int amdgpu_ih_clientid_vcns[] = { static int vcn_v4_0_start_sriov(struct amdgpu_device *adev); static void vcn_v4_0_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v4_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v4_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev); @@ -114,7 +114,7 @@ static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev); static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - int i; + int i, r; if (amdgpu_sriov_vf(adev)) { adev->vcn.harvest_config = VCN_HARVEST_MMSCH; @@ -126,14 +126,23 @@ static int vcn_v4_0_early_init(struct amdgpu_ip_block *ip_block) } } - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v4_0_set_unified_ring_funcs(adev); vcn_v4_0_set_irq_funcs(adev); vcn_v4_0_set_ras_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v4_0_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } static int vcn_v4_0_fw_shared_init(struct amdgpu_device *adev, int inst_idx) @@ -176,20 +185,20 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0); uint32_t *ptr; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { if (adev->vcn.harvest_config & (1 << i)) continue; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + /* Init instance 0 sched_score to 1, so it's scheduled after other instances */ if (i == 0) atomic_set(&adev->vcn.inst[i].sched_score, 1); @@ -211,7 +220,8 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) ring = &adev->vcn.inst[i].ring_enc[0]; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) - ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * (adev->vcn.num_enc_rings + 1) + 1; + ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * + (adev->vcn.inst[i].num_enc_rings + 1) + 1; else ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i; ring->vm_hub = AMDGPU_MMHUB0(0); @@ -223,6 +233,9 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) return r; vcn_v4_0_fw_shared_init(adev, i); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_pause_dpg_mode; } /* TODO: Add queue reset mask when FW fully supports it */ @@ -235,8 +248,6 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v4_0_pause_dpg_mode; r = amdgpu_vcn_ras_sw_init(adev); if (r) @@ -288,16 +299,23 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev); + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -359,20 +377,23 @@ static int vcn_v4_0_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && + (vinst->cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, i, regUVD_STATUS))) { - vcn_v4_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) - amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); + amdgpu_irq_put(adev, &vinst->ras_poison_irq, 0); } return 0; @@ -387,15 +408,20 @@ static int vcn_v4_0_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v4_0_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -407,11 +433,14 @@ static int vcn_v4_0_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v4_0_hw_init(ip_block); @@ -421,13 +450,14 @@ static int vcn_v4_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v4_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -481,14 +511,16 @@ static void vcn_v4_0_mc_resume(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; hdr = (const struct common_firmware_header *)adev->vcn.inst[inst_idx].fw->data; @@ -588,13 +620,14 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx /** * vcn_v4_0_disable_static_power_gating - disable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable static power gating for VCN block */ -static void vcn_v4_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -653,13 +686,14 @@ static void vcn_v4_0_disable_static_power_gating(struct amdgpu_device *adev, int /** * vcn_v4_0_enable_static_power_gating - enable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable static power gating for VCN block */ -static void vcn_v4_0_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -708,13 +742,14 @@ static void vcn_v4_0_enable_static_power_gating(struct amdgpu_device *adev, int /** * vcn_v4_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v4_0_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -819,16 +854,18 @@ static void vcn_v4_0_disable_clock_gating(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -876,13 +913,14 @@ static void vcn_v4_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, u /** * vcn_v4_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -932,9 +970,11 @@ static void vcn_v4_0_enable_clock_gating(struct amdgpu_device *adev, int inst) WREG32_SOC15(VCN, inst, regUVD_SUVD_CGC_CTRL, data); } -static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx, +static void vcn_v4_0_enable_ras(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) @@ -957,14 +997,15 @@ static void vcn_v4_0_enable_ras(struct amdgpu_device *adev, int inst_idx, /** * vcn_v4_0_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; @@ -982,7 +1023,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v4_0_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v4_0_disable_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -1030,7 +1071,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v4_0_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v4_0_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -1042,7 +1083,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( VCN, inst_idx, regUVD_LMI_CTRL2), tmp, 0, indirect); - vcn_v4_0_enable_ras(adev, inst_idx, indirect); + vcn_v4_0_enable_ras(vinst, indirect); /* enable master interrupt */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( @@ -1086,183 +1127,179 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo /** * vcn_v4_0_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v4_0_start(struct amdgpu_device *adev) +static int vcn_v4_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; - int i, j, k, r; + int j, k, r; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, true, i); - } + if (adev->vcn.harvest_config & (1 << i)) + return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, true, i); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v4_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v4_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - /* disable VCN power gating */ - vcn_v4_0_disable_static_power_gating(adev, i); - - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); - - /*SW clock gating */ - vcn_v4_0_disable_clock_gating(adev, i); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp | - UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | - UVD_LMI_CTRL__MASK_MC_URGENT_MASK | - UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | - UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); - - /* setup regUVD_MPC_CNTL */ - tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL); - tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; - tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; - WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); - - /* setup UVD_MPC_SET_MUXA0 */ - WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0, - ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); - - /* setup UVD_MPC_SET_MUXB0 */ - WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0, - ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); - - /* setup UVD_MPC_SET_MUX */ - WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX, - ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | - (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - - vcn_v4_0_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - for (j = 0; j < 10; ++j) { - uint32_t status; - - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, i, regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - if (amdgpu_emu_mode == 1) - msleep(1); - } + /* disable VCN power gating */ + vcn_v4_0_disable_static_power_gating(vinst); + + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); + + /*SW clock gating */ + vcn_v4_0_disable_clock_gating(vinst); - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp | + UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__MASK_MC_URGENT_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); + + /* setup regUVD_MPC_CNTL */ + tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL); + tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; + tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; + WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); + + /* setup UVD_MPC_SET_MUXA0 */ + WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0, + ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); + + /* setup UVD_MPC_SET_MUXB0 */ + WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0, + ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); + + /* setup UVD_MPC_SET_MUX */ + WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX, + ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | + (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); + + vcn_v4_0_mc_resume(vinst); + + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + for (j = 0; j < 10; ++j) { + uint32_t status; + + for (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, i, regUVD_STATUS); + if (status & 2) + break; + mdelay(10); + if (amdgpu_emu_mode == 1) + msleep(1); + } + + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); - - WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); - - tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); + + WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); + + tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -1518,17 +1555,18 @@ static int vcn_v4_0_start_sriov(struct amdgpu_device *adev) /** * vcn_v4_0_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v4_0_pause_dpg_mode(adev, inst_idx, &state); + vcn_v4_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); @@ -1548,87 +1586,87 @@ static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v4_0_stop(struct amdgpu_device *adev) +static int vcn_v4_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; uint32_t tmp; - int i, r = 0; - - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + int r = 0; - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; + if (adev->vcn.harvest_config & (1 << i)) + return 0; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v4_0_stop_dpg_mode(adev, i); - continue; - } + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v4_0_stop_dpg_mode(vinst); + r = 0; + goto done; + } - tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | - UVD_LMI_STATUS__READ_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp); - tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | - UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | + UVD_LMI_STATUS__READ_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp); + tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | + UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - /* reset VCPU */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - /* clear status */ - WREG32_SOC15(VCN, i, regUVD_STATUS, 0); + /* clear status */ + WREG32_SOC15(VCN, i, regUVD_STATUS, 0); - /* apply HW clock gating */ - vcn_v4_0_enable_clock_gating(adev, i); + /* apply HW clock gating */ + vcn_v4_0_enable_clock_gating(vinst); - /* enable VCN power gating */ - vcn_v4_0_enable_static_power_gating(adev, i); - } + /* enable VCN power gating */ + vcn_v4_0_enable_static_power_gating(vinst); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); return 0; } @@ -1636,15 +1674,16 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev) /** * vcn_v4_0_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v4_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; int ret_code; @@ -1964,13 +2003,13 @@ static void vcn_v4_0_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v4_0_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v4_0_is_idle(void *handle) +static bool vcn_v4_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -2024,54 +2063,48 @@ static int vcn_v4_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v4_0_enable_clock_gating(adev, i); + vcn_v4_0_enable_clock_gating(vinst); } else { - vcn_v4_0_disable_clock_gating(adev, i); + vcn_v4_0_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v4_0_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v4_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v4_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + struct amdgpu_device *adev = vinst->adev; + int ret = 0; /* for SRIOV, guest should not control VCN Power-gating * MMSCH FW should control Power-gating and clock-gating * guest should avoid touching CGC and PG */ if (amdgpu_sriov_vf(adev)) { - adev->vcn.cur_state = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v4_0_stop(adev); + ret = vcn_v4_0_stop(vinst); else - ret = vcn_v4_0_start(adev); + ret = vcn_v4_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -2163,10 +2196,10 @@ static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v4_0_irq_funcs; - adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v4_0_ras_irq_funcs; } } @@ -2244,7 +2277,7 @@ static const struct amd_ip_funcs vcn_v4_0_ip_funcs = { .is_idle = vcn_v4_0_is_idle, .wait_for_idle = vcn_v4_0_wait_for_idle, .set_clockgating_state = vcn_v4_0_set_clockgating_state, - .set_powergating_state = vcn_v4_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v4_0_dump_ip_state, .print_ip_state = vcn_v4_0_print_ip_state, }; 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 75211366f8f6..7446ecc55714 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -31,6 +31,7 @@ #include "soc15d.h" #include "soc15_hw_ip.h" #include "vcn_v2_0.h" +#include "vcn_v4_0_3.h" #include "mmsch_v4_0_3.h" #include "vcn/vcn_4_0_3_offset.h" @@ -87,10 +88,10 @@ static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = { static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev); static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v4_0_3_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v4_0_3_unified_ring_set_wptr(struct amdgpu_ring *ring); static void vcn_v4_0_3_set_ras_funcs(struct amdgpu_device *adev); static void vcn_v4_0_3_enable_ras(struct amdgpu_device *adev, @@ -111,15 +112,25 @@ static inline bool vcn_v4_0_3_normalizn_reqd(struct amdgpu_device *adev) static int vcn_v4_0_3_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v4_0_3_set_unified_ring_funcs(adev); vcn_v4_0_3_set_irq_funcs(adev); vcn_v4_0_3_set_ras_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v4_0_3_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } static int vcn_v4_0_3_fw_shared_init(struct amdgpu_device *adev, int inst_idx) @@ -151,16 +162,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3); uint32_t *ptr; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - /* VCN DEC TRAP */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); @@ -168,6 +169,17 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) return r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + vcn_inst = GET_INST(VCN, i); ring = &adev->vcn.inst[i].ring_enc[0]; @@ -191,6 +203,9 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) return r; vcn_v4_0_3_fw_shared_init(adev, i); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode; } /* TODO: Add queue reset mask when FW fully supports it */ @@ -203,9 +218,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode; - if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) { r = amdgpu_vcn_ras_sw_init(adev); if (r) { @@ -256,16 +268,23 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev); + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -349,11 +368,16 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; - if (adev->vcn.cur_state != AMD_PG_STATE_GATE) - vcn_v4_0_3_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + cancel_delayed_work_sync(&vinst->idle_work); + + if (vinst->cur_state != AMD_PG_STATE_GATE) + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); + } return 0; } @@ -367,15 +391,20 @@ static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_3_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v4_0_3_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } - return r; + return 0; } /** @@ -387,11 +416,14 @@ static int vcn_v4_0_3_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_3_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v4_0_3_hw_init(ip_block); @@ -401,13 +433,14 @@ static int vcn_v4_0_3_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v4_0_3_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst_idx: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_3_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size, vcn_inst; const struct common_firmware_header *hdr; @@ -475,14 +508,16 @@ static void vcn_v4_0_3_mc_resume(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_3_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -589,13 +624,14 @@ static void vcn_v4_0_3_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v4_0_3_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst_idx: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t data; int vcn_inst; @@ -682,16 +718,18 @@ static void vcn_v4_0_3_disable_clock_gating(struct amdgpu_device *adev, int inst /** * vcn_v4_0_3_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -733,13 +771,14 @@ static void vcn_v4_0_3_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v4_0_3_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst_idx: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t data; int vcn_inst; @@ -784,14 +823,16 @@ static void vcn_v4_0_3_enable_clock_gating(struct amdgpu_device *adev, int inst_ /** * vcn_v4_0_3_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; @@ -819,7 +860,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b } /* enable clock gating */ - vcn_v4_0_3_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v4_0_3_disable_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -869,7 +910,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v4_0_3_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v4_0_3_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -1116,186 +1157,185 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev) /** * vcn_v4_0_3_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v4_0_3_start(struct amdgpu_device *adev) +static int vcn_v4_0_3_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; - int i, j, k, r, vcn_inst; + int j, k, r, vcn_inst; uint32_t tmp; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v4_0_3_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v4_0_3_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - vcn_inst = GET_INST(VCN, i); - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | - UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp); - - /*SW clock gating */ - vcn_v4_0_3_disable_clock_gating(adev, i); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, - ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, - tmp | UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | - UVD_LMI_CTRL__MASK_MC_URGENT_MASK | - UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | - UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); - - /* setup regUVD_MPC_CNTL */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL); - tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; - tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; - WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp); - - /* setup UVD_MPC_SET_MUXA0 */ - WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXA0, - ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); - - /* setup UVD_MPC_SET_MUXB0 */ - WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXB0, - ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); - - /* setup UVD_MPC_SET_MUX */ - WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUX, - ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | - (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - - vcn_v4_0_3_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + vcn_inst = GET_INST(VCN, i); + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | + UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp); - for (j = 0; j < 10; ++j) { - uint32_t status; + /* SW clock gating */ + vcn_v4_0_3_disable_clock_gating(vinst); - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, vcn_inst, - regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - } - r = 0; - if (status & 2) - break; + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, + ~UVD_VCPU_CNTL__CLK_EN_MASK); - DRM_DEV_ERROR(adev->dev, - "VCN decode not responding, trying to reset the VCPU!!!\n"); - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, - regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, - regUVD_VCPU_CNTL), - 0, ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, + tmp | UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__MASK_MC_URGENT_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); + + /* setup regUVD_MPC_CNTL */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL); + tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; + tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; + WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp); + + /* setup UVD_MPC_SET_MUXA0 */ + WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXA0, + ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); + + /* setup UVD_MPC_SET_MUXB0 */ + WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUXB0, + ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); + + /* setup UVD_MPC_SET_MUX */ + WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_SET_MUX, + ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | + (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); + + vcn_v4_0_3_mc_resume(vinst); + + /* VCN global tiling registers */ + WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + for (j = 0; j < 10; ++j) { + uint32_t status; + + for (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, vcn_inst, + regUVD_STATUS); + if (status & 2) + break; mdelay(10); - r = -1; } + r = 0; + if (status & 2) + break; - if (r) { - DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n"); - return r; - } + DRM_DEV_ERROR(adev->dev, + "VCN decode not responding, trying to reset the VCPU!!!\n"); + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, + regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, + regUVD_VCPU_CNTL), + 0, ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + mdelay(10); + r = -1; + } - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + if (r) { + DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n"); + return r; + } - ring = &adev->vcn.inst[i].ring_enc[0]; - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + + ring = &adev->vcn.inst[i].ring_enc[0]; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - /* program the RB_BASE for ring buffer */ - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, - lower_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, - upper_32_bits(ring->gpu_addr)); + /* program the RB_BASE for ring buffer */ + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, + lower_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, + upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, - ring->ring_size / sizeof(uint32_t)); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, + ring->ring_size / sizeof(uint32_t)); - /* resetting ring, fw should not check RB ring */ - tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK); - WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + /* resetting ring, fw should not check RB ring */ + tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK); + WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - /* Initialize the ring buffer's read and write pointers */ - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0); + /* Initialize the ring buffer's read and write pointers */ + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0); - tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB_EN_MASK; - WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB_EN_MASK; + WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR); - fw_shared->sq.queue_mode &= - cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF)); + ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR); + fw_shared->sq.queue_mode &= + cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF)); - } return 0; } /** * vcn_v4_0_3_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; int vcn_inst; @@ -1321,82 +1361,83 @@ static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_3_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v4_0_3_stop(struct amdgpu_device *adev) +static int vcn_v4_0_3_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; - int i, r = 0, vcn_inst; + int r = 0, vcn_inst; uint32_t tmp; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - vcn_inst = GET_INST(VCN, i); + vcn_inst = GET_INST(VCN, i); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v4_0_3_stop_dpg_mode(adev, i); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v4_0_3_stop_dpg_mode(vinst); + goto Done; + } - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, - UVD_STATUS__IDLE, 0x7); - if (r) - goto Done; - - tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | - UVD_LMI_STATUS__READ_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, - tmp); - if (r) - goto Done; - - /* stall UMC channel */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp); - tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | - UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, - tmp); - if (r) - goto Done; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, + UVD_STATUS__IDLE, 0x7); + if (r) + goto Done; + + tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | + UVD_LMI_STATUS__READ_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, + tmp); + if (r) + goto Done; + + /* stall UMC channel */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp); + tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | + UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, + tmp); + if (r) + goto Done; - /* Unblock VCPU Register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + /* Unblock VCPU Register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - /* reset LMI UMC/LMI/VCPU */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); + /* reset LMI UMC/LMI/VCPU */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); - /* clear VCN status */ - WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0); + /* clear VCN status */ + WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0); + + /* apply HW clock gating */ + vcn_v4_0_3_enable_clock_gating(vinst); - /* apply HW clock gating */ - vcn_v4_0_3_enable_clock_gating(adev, i); - } Done: return 0; } @@ -1404,14 +1445,13 @@ Done: /** * vcn_v4_0_3_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v4_0_3_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { return 0; @@ -1455,8 +1495,8 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring) regUVD_RB_WPTR); } -static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, - uint32_t val, uint32_t mask) +void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val, uint32_t mask) { /* Use normalized offsets when required */ if (vcn_v4_0_3_normalizn_reqd(ring->adev)) @@ -1468,7 +1508,8 @@ static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t amdgpu_ring_write(ring, val); } -static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val) +void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val) { /* Use normalized offsets when required */ if (vcn_v4_0_3_normalizn_reqd(ring->adev)) @@ -1479,8 +1520,8 @@ static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg amdgpu_ring_write(ring, val); } -static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, - unsigned int vmid, uint64_t pd_addr) +void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, + unsigned int vmid, uint64_t pd_addr) { struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->vm_hub]; @@ -1492,7 +1533,7 @@ static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, lower_32_bits(pd_addr), 0xffffffff); } -static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) +void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring) { /* VCN engine access for HDP flush doesn't work when RRMT is enabled. * This is a workaround to avoid any HDP flush through VCN ring. @@ -1575,13 +1616,13 @@ static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v4_0_3_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v4_0_3_is_idle(void *handle) +static bool vcn_v4_0_3_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1629,51 +1670,45 @@ static int vcn_v4_0_3_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (enable) { if (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v4_0_3_enable_clock_gating(adev, i); + vcn_v4_0_3_enable_clock_gating(vinst); } else { - vcn_v4_0_3_disable_clock_gating(adev, i); + vcn_v4_0_3_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v4_0_3_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v4_0_3_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + struct amdgpu_device *adev = vinst->adev; + int ret = 0; /* for SRIOV, guest should not control VCN Power-gating * MMSCH FW should control Power-gating and clock-gating * guest should avoid touching CGC and PG */ if (amdgpu_sriov_vf(adev)) { - adev->vcn.cur_state = AMD_PG_STATE_UNGATE; + vinst->cur_state = AMD_PG_STATE_UNGATE; return 0; } - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v4_0_3_stop(adev); + ret = vcn_v4_0_3_stop(vinst); else - ret = vcn_v4_0_3_start(adev); + ret = vcn_v4_0_3_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1835,7 +1870,7 @@ static const struct amd_ip_funcs vcn_v4_0_3_ip_funcs = { .is_idle = vcn_v4_0_3_is_idle, .wait_for_idle = vcn_v4_0_3_wait_for_idle, .set_clockgating_state = vcn_v4_0_3_set_clockgating_state, - .set_powergating_state = vcn_v4_0_3_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v4_0_3_dump_ip_state, .print_ip_state = vcn_v4_0_3_print_ip_state, }; @@ -1930,8 +1965,8 @@ static int vcn_v4_0_3_aca_bank_parser(struct aca_handle *handle, struct aca_bank 1ULL); break; case ACA_SMU_TYPE_CE: - bank->aca_err_type = ACA_ERROR_TYPE_CE; - ret = aca_error_cache_log_bank_error(handle, &info, ACA_ERROR_TYPE_CE, + bank->aca_err_type = ACA_BANK_ERR_CE_DE_DECODE(bank); + ret = aca_error_cache_log_bank_error(handle, &info, bank->aca_err_type, ACA_REG__MISC0__ERRCNT(misc0)); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h index 0b046114373a..03572a1d0c9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.h @@ -26,4 +26,13 @@ extern const struct amdgpu_ip_block_version vcn_v4_0_3_ip_block; +void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val, uint32_t mask); + +void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, + uint32_t val); +void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring, + unsigned int vmid, uint64_t pd_addr); +void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring); + #endif /* __VCN_V4_0_3_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index 5d757e7de9db..ba603b2246e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -95,10 +95,10 @@ static int amdgpu_ih_clientid_vcns[] = { static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v4_0_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring); /** @@ -112,13 +112,26 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v4_0_5_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; + + if (amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(4, 0, 6)) + adev->vcn.per_inst_fw = true; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v4_0_5_set_unified_ring_funcs(adev); vcn_v4_0_5_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v4_0_5_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } /** @@ -136,15 +149,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5); uint32_t *ptr; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_vcn4_fw_shared *fw_shared; @@ -152,6 +156,16 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) if (adev->vcn.harvest_config & (1 << i)) continue; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + atomic_set(&adev->vcn.inst[i].sched_score, 0); /* VCN UNIFIED TRAP */ @@ -170,7 +184,7 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + - i * (adev->vcn.num_enc_rings + 1) + 1; + i * (adev->vcn.inst[i].num_enc_rings + 1) + 1; else ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i; @@ -195,6 +209,9 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_5_pause_dpg_mode; } if (amdgpu_sriov_vf(adev)) { @@ -203,9 +220,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block) return r; } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v4_0_5_pause_dpg_mode; - /* Allocate memory for VCN IP Dump buffer */ ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL); if (!ptr) { @@ -247,15 +261,19 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev)) amdgpu_virt_free_mm_table(adev); - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; - r = amdgpu_vcn_sw_fini(adev); + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -300,16 +318,19 @@ static int vcn_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, i, regUVD_STATUS))) { - vcn_v4_0_5_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, i, regUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } } @@ -326,13 +347,18 @@ static int vcn_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_5_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v4_0_5_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } return r; } @@ -346,11 +372,14 @@ static int vcn_v4_0_5_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v4_0_5_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v4_0_5_hw_init(ip_block); @@ -360,13 +389,14 @@ static int vcn_v4_0_5_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v4_0_5_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -420,14 +450,16 @@ static void vcn_v4_0_5_mc_resume(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_5_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -534,13 +566,14 @@ static void vcn_v4_0_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v4_0_5_disable_static_power_gating - disable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable static power gating for VCN block */ -static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -593,13 +626,14 @@ static void vcn_v4_0_5_disable_static_power_gating(struct amdgpu_device *adev, i /** * vcn_v4_0_5_enable_static_power_gating - enable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable static power gating for VCN block */ -static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -635,13 +669,14 @@ static void vcn_v4_0_5_enable_static_power_gating(struct amdgpu_device *adev, in /** * vcn_v4_0_5_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -746,16 +781,18 @@ static void vcn_v4_0_5_disable_clock_gating(struct amdgpu_device *adev, int inst /** * vcn_v4_0_5_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -803,13 +840,14 @@ static void vcn_v4_0_5_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v4_0_5_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG) @@ -862,14 +900,16 @@ static void vcn_v4_0_5_enable_clock_gating(struct amdgpu_device *adev, int inst) /** * vcn_v4_0_5_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; @@ -888,7 +928,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b (uint32_t *)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr; /* enable clock gating */ - vcn_v4_0_5_disable_clock_gating_dpg_mode(adev, 0, inst_idx, indirect); + vcn_v4_0_5_disable_clock_gating_dpg_mode(vinst, 0, indirect); /* enable VCPU clock */ tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); @@ -936,7 +976,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect); - vcn_v4_0_5_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v4_0_5_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -989,184 +1029,180 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b /** * vcn_v4_0_5_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v4_0_5_start(struct amdgpu_device *adev) +static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; - int i, j, k, r; + int j, k, r; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, true, i); - } + if (adev->vcn.harvest_config & (1 << i)) + return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, true, i); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v4_0_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v4_0_5_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - /* disable VCN power gating */ - vcn_v4_0_5_disable_static_power_gating(adev, i); - - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); - - /*SW clock gating */ - vcn_v4_0_5_disable_clock_gating(adev, i); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp | - UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | - UVD_LMI_CTRL__MASK_MC_URGENT_MASK | - UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | - UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); - - /* setup regUVD_MPC_CNTL */ - tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL); - tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; - tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; - WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); - - /* setup UVD_MPC_SET_MUXA0 */ - WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0, - ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); - - /* setup UVD_MPC_SET_MUXB0 */ - WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0, - ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | - (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | - (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); - - /* setup UVD_MPC_SET_MUX */ - WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX, - ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | - (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | - (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); - - vcn_v4_0_5_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - for (j = 0; j < 10; ++j) { - uint32_t status; - - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, i, regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - if (amdgpu_emu_mode == 1) - msleep(1); - } + /* disable VCN power gating */ + vcn_v4_0_5_disable_static_power_gating(vinst); + + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); + + /* SW clock gating */ + vcn_v4_0_5_disable_clock_gating(vinst); + + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp | + UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__MASK_MC_URGENT_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); + + /* setup regUVD_MPC_CNTL */ + tmp = RREG32_SOC15(VCN, i, regUVD_MPC_CNTL); + tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK; + tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT; + WREG32_SOC15(VCN, i, regUVD_MPC_CNTL, tmp); + + /* setup UVD_MPC_SET_MUXA0 */ + WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXA0, + ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT))); + + /* setup UVD_MPC_SET_MUXB0 */ + WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUXB0, + ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) | + (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) | + (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT))); + + /* setup UVD_MPC_SET_MUX */ + WREG32_SOC15(VCN, i, regUVD_MPC_SET_MUX, + ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) | + (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) | + (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT))); + + vcn_v4_0_5_mc_resume(vinst); + + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + for (j = 0; j < 10; ++j) { + uint32_t status; + + for (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, i, regUVD_STATUS); + if (status & 2) + break; + mdelay(10); + if (amdgpu_emu_mode == 1) + msleep(1); + } - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, - "VCN[%d] is not responding, trying to reset VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, + "VCN[%d] is not responding, trying to reset VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); - - WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); - - tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); + + WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); + + tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -1174,13 +1210,14 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev) /** * vcn_v4_0_5_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; /* Wait for power status to be 1 */ @@ -1202,103 +1239,104 @@ static void vcn_v4_0_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v4_0_5_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v4_0_5_stop(struct amdgpu_device *adev) +static int vcn_v4_0_5_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn4_fw_shared *fw_shared; uint32_t tmp; - int i, r = 0; + int r = 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + if (adev->vcn.harvest_config & (1 << i)) + return 0; - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v4_0_5_stop_dpg_mode(adev, i); - continue; - } - - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v4_0_5_stop_dpg_mode(vinst); + r = 0; + goto done; + } - tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | - UVD_LMI_STATUS__READ_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp); - tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | - UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | + UVD_LMI_STATUS__READ_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp); + tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | + UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - /* reset VCPU */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - /* clear status */ - WREG32_SOC15(VCN, i, regUVD_STATUS, 0); + /* clear status */ + WREG32_SOC15(VCN, i, regUVD_STATUS, 0); - /* apply HW clock gating */ - vcn_v4_0_5_enable_clock_gating(adev, i); + /* apply HW clock gating */ + vcn_v4_0_5_enable_clock_gating(vinst); - /* enable VCN power gating */ - vcn_v4_0_5_enable_static_power_gating(adev, i); - } + /* enable VCN power gating */ + vcn_v4_0_5_enable_static_power_gating(vinst); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); - return 0; + return r; } /** * vcn_v4_0_5_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v4_0_5_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; int ret_code; @@ -1452,13 +1490,13 @@ static void vcn_v4_0_5_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v4_0_5_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v4_0_5_is_idle(void *handle) +static bool vcn_v4_0_5_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1512,45 +1550,38 @@ static int vcn_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v4_0_5_enable_clock_gating(adev, i); + vcn_v4_0_5_enable_clock_gating(vinst); } else { - vcn_v4_0_5_disable_clock_gating(adev, i); + vcn_v4_0_5_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v4_0_5_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v4_0_5_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v4_0_5_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + int ret = 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v4_0_5_stop(adev); + ret = vcn_v4_0_5_stop(vinst); else - ret = vcn_v4_0_5_start(adev); + ret = vcn_v4_0_5_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1618,7 +1649,7 @@ static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v4_0_5_irq_funcs; } } @@ -1696,7 +1727,7 @@ static const struct amd_ip_funcs vcn_v4_0_5_ip_funcs = { .is_idle = vcn_v4_0_5_is_idle, .wait_for_idle = vcn_v4_0_5_wait_for_idle, .set_clockgating_state = vcn_v4_0_5_set_clockgating_state, - .set_powergating_state = vcn_v4_0_5_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v4_0_5_dump_ip_state, .print_ip_state = vcn_v4_0_5_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index b6d78381ebfb..d99d05f42f1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -78,10 +78,10 @@ static int amdgpu_ih_clientid_vcns[] = { static void vcn_v5_0_0_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); -static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_device *adev, - int inst_idx, struct dpg_pause_state *new_state); +static int vcn_v5_0_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); +static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state); static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring); /** @@ -95,14 +95,24 @@ static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v5_0_0_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v5_0_0_set_unified_ring_funcs(adev); vcn_v5_0_0_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v5_0_0_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; } void vcn_v5_0_0_alloc_ip_dump(struct amdgpu_device *adev) @@ -133,22 +143,22 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i, r; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_vcn5_fw_shared *fw_shared; if (adev->vcn.harvest_config & (1 << i)) continue; + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + atomic_set(&adev->vcn.inst[i].sched_score, 0); /* VCN UNIFIED TRAP */ @@ -181,15 +191,15 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block) if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + adev->vcn.inst[i].pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode; } /* TODO: Add queue reset mask when FW fully supports it */ adev->vcn.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]); - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) - adev->vcn.pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode; - vcn_v5_0_0_alloc_ip_dump(adev); r = amdgpu_vcn_sysfs_reset_mask_init(adev); @@ -226,16 +236,23 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block) drm_dev_exit(idx); } - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); - r = amdgpu_vcn_sw_fini(adev); + + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -280,16 +297,19 @@ static int vcn_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block) struct amdgpu_device *adev = ip_block->adev; int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; + + cancel_delayed_work_sync(&vinst->idle_work); + if (!amdgpu_sriov_vf(adev)) { if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || - (adev->vcn.cur_state != AMD_PG_STATE_GATE && - RREG32_SOC15(VCN, i, regUVD_STATUS))) { - vcn_v5_0_0_set_powergating_state(ip_block, AMD_PG_STATE_GATE); + (vinst->cur_state != AMD_PG_STATE_GATE && + RREG32_SOC15(VCN, i, regUVD_STATUS))) { + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); } } } @@ -306,13 +326,18 @@ static int vcn_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block) */ static int vcn_v5_0_0_suspend(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; r = vcn_v5_0_0_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(ip_block->adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } return r; } @@ -326,11 +351,14 @@ static int vcn_v5_0_0_suspend(struct amdgpu_ip_block *ip_block) */ static int vcn_v5_0_0_resume(struct amdgpu_ip_block *ip_block) { - int r; + struct amdgpu_device *adev = ip_block->adev; + int r, i; - r = amdgpu_vcn_resume(ip_block->adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v5_0_0_hw_init(ip_block); @@ -340,13 +368,14 @@ static int vcn_v5_0_0_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v5_0_0_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -400,14 +429,16 @@ static void vcn_v5_0_0_mc_resume(struct amdgpu_device *adev, int inst) /** * vcn_v5_0_0_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -510,13 +541,14 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v5_0_0_disable_static_power_gating - disable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable static power gating for VCN block */ -static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data = 0; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -577,13 +609,14 @@ static void vcn_v5_0_0_disable_static_power_gating(struct amdgpu_device *adev, i /** * vcn_v5_0_0_enable_static_power_gating - enable VCN static power gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable static power gating for VCN block */ -static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t data; if (adev->pg_flags & AMD_PG_SUPPORT_VCN) { @@ -623,12 +656,11 @@ static void vcn_v5_0_0_enable_static_power_gating(struct amdgpu_device *adev, in /** * vcn_v5_0_0_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { return; } @@ -637,15 +669,15 @@ static void vcn_v5_0_0_disable_clock_gating(struct amdgpu_device *adev, int inst /** * vcn_v5_0_0_disable_clock_gating_dpg_mode - disable VCN clock gating dpg mode * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * @sram_sel: sram select - * @inst_idx: instance number index * @indirect: indirectly write sram * * Disable clock gating for VCN block with dpg mode */ -static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t sram_sel, - int inst_idx, uint8_t indirect) +static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_vcn_inst *vinst, + uint8_t sram_sel, + uint8_t indirect) { return; } @@ -654,12 +686,11 @@ static void vcn_v5_0_0_disable_clock_gating_dpg_mode(struct amdgpu_device *adev, /** * vcn_v5_0_0_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { return; } @@ -667,14 +698,16 @@ static void vcn_v5_0_0_enable_clock_gating(struct amdgpu_device *adev, int inst) /** * vcn_v5_0_0_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; uint32_t tmp; @@ -714,7 +747,7 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( VCN, inst_idx, regUVD_LMI_CTRL), tmp, 0, indirect); - vcn_v5_0_0_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v5_0_0_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -766,155 +799,151 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b /** * vcn_v5_0_0_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v5_0_0_start(struct amdgpu_device *adev) +static int vcn_v5_0_0_start(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn5_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; - int i, j, k, r; + int j, k, r; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, true, i); - } + if (adev->vcn.harvest_config & (1 << i)) + return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, true, i); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v5_0_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v5_0_0_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - /* disable VCN power gating */ - vcn_v5_0_0_disable_static_power_gating(adev, i); - - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp | - UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | - UVD_LMI_CTRL__MASK_MC_URGENT_MASK | - UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | - UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); - - vcn_v5_0_0_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - for (j = 0; j < 10; ++j) { - uint32_t status; - - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, i, regUVD_STATUS); - if (status & 2) - break; - mdelay(10); - if (amdgpu_emu_mode == 1) - msleep(1); - } + /* disable VCN power gating */ + vcn_v5_0_0_disable_static_power_gating(vinst); + + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, i, regUVD_STATUS, tmp); + + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, i, regUVD_LMI_CTRL, tmp | + UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__MASK_MC_URGENT_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); + + vcn_v5_0_0_mc_resume(vinst); - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + /* VCN global tiling registers */ + WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + for (j = 0; j < 10; ++j) { + uint32_t status; + + for (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, i, regUVD_STATUS); + if (status & 2) + break; + mdelay(10); + if (amdgpu_emu_mode == 1) + msleep(1); + } + + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, - "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, + "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); - - WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); - - tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); - WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); - - tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + ring = &adev->vcn.inst[i].ring_enc[0]; + WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); + + WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0); + + tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR); + WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR); + + tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -922,17 +951,18 @@ static int vcn_v5_0_0_start(struct amdgpu_device *adev) /** * vcn_v5_0_0_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; - vcn_v5_0_0_pause_dpg_mode(adev, inst_idx, &state); + vcn_v5_0_0_pause_dpg_mode(vinst, &state); /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1, @@ -952,100 +982,101 @@ static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v5_0_0_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v5_0_0_stop(struct amdgpu_device *adev) +static int vcn_v5_0_0_stop(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; volatile struct amdgpu_vcn5_fw_shared *fw_shared; uint32_t tmp; - int i, r = 0; + int r = 0; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->vcn.harvest_config & (1 << i)) - continue; + if (adev->vcn.harvest_config & (1 << i)) + return 0; - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v5_0_0_stop_dpg_mode(adev, i); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v5_0_0_stop_dpg_mode(vinst); + r = 0; + goto done; + } - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + goto done; - tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | - UVD_LMI_STATUS__READ_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | + UVD_LMI_STATUS__READ_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; + + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp); + tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | + UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); + if (r) + goto done; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, i, regUVD_LMI_CTRL2, tmp); - tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | - UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* reset VCPU */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); - - /* clear status */ - WREG32_SOC15(VCN, i, regUVD_STATUS, 0); - - /* enable VCN power gating */ - vcn_v5_0_0_enable_static_power_gating(adev, i); - } + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - if (adev->pm.dpm_enabled) - amdgpu_dpm_enable_vcn(adev, false, i); - } + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - return 0; + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp); + + /* clear status */ + WREG32_SOC15(VCN, i, regUVD_STATUS, 0); + + /* enable VCN power gating */ + vcn_v5_0_0_enable_static_power_gating(vinst); + +done: + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_vcn(adev, false, i); + + return r; } /** * vcn_v5_0_0_pause_dpg_mode - VCN pause with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @new_state: pause state * * Pause dpg mode for VCN block */ -static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, - struct dpg_pause_state *new_state) +static int vcn_v5_0_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst, + struct dpg_pause_state *new_state) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t reg_data = 0; int ret_code; @@ -1192,13 +1223,13 @@ static void vcn_v5_0_0_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v5_0_0_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v5_0_0_is_idle(void *handle) +static bool vcn_v5_0_0_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { @@ -1252,45 +1283,38 @@ static int vcn_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (adev->vcn.harvest_config & (1 << i)) continue; if (enable) { if (RREG32_SOC15(VCN, i, regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v5_0_0_enable_clock_gating(adev, i); + vcn_v5_0_0_enable_clock_gating(vinst); } else { - vcn_v5_0_0_disable_clock_gating(adev, i); + vcn_v5_0_0_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v5_0_0_set_powergating_state - set VCN block powergating state - * - * @ip_block: amdgpu_ip_block pointer - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v5_0_0_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + int ret = 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v5_0_0_stop(adev); + ret = vcn_v5_0_0_stop(vinst); else - ret = vcn_v5_0_0_start(adev); + ret = vcn_v5_0_0_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1358,7 +1382,7 @@ static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev) if (adev->vcn.harvest_config & (1 << i)) continue; - adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].irq.num_types = adev->vcn.inst[i].num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v5_0_0_irq_funcs; } } @@ -1436,7 +1460,7 @@ static const struct amd_ip_funcs vcn_v5_0_0_ip_funcs = { .is_idle = vcn_v5_0_0_is_idle, .wait_for_idle = vcn_v5_0_0_wait_for_idle, .set_clockgating_state = vcn_v5_0_0_set_clockgating_state, - .set_powergating_state = vcn_v5_0_0_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v5_0_0_dump_ip_state, .print_ip_state = vcn_v5_0_0_print_ip_state, }; 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 288a77179036..581d8629b9d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -29,6 +29,7 @@ #include "soc15d.h" #include "soc15_hw_ip.h" #include "vcn_v2_0.h" +#include "vcn_v4_0_3.h" #include "vcn/vcn_5_0_0_offset.h" #include "vcn/vcn_5_0_0_sh_mask.h" @@ -40,8 +41,8 @@ static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev); static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev); -static int vcn_v5_0_1_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state); +static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state); static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring); /** @@ -55,14 +56,40 @@ static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v5_0_1_early_init(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i, r; - /* re-use enc ring as unified ring */ - adev->vcn.num_enc_rings = 1; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) + /* re-use enc ring as unified ring */ + adev->vcn.inst[i].num_enc_rings = 1; vcn_v5_0_1_set_unified_ring_funcs(adev); vcn_v5_0_1_set_irq_funcs(adev); - return amdgpu_vcn_early_init(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + adev->vcn.inst[i].set_pg_state = vcn_v5_0_1_set_pg_state; + + r = amdgpu_vcn_early_init(adev, i); + if (r) + return r; + } + + return 0; +} + +static void vcn_v5_0_1_fw_shared_init(struct amdgpu_device *adev, int inst_idx) +{ + struct amdgpu_vcn5_fw_shared *fw_shared; + + fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; + + if (fw_shared->sq.is_enabled) + return; + fw_shared->present_flag_0 = + cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE); + fw_shared->sq.is_enabled = 1; + + if (amdgpu_vcnfw_log) + amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst_idx]); } /** @@ -78,16 +105,6 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_ring *ring; int i, r, vcn_inst; - r = amdgpu_vcn_sw_init(adev); - if (r) - return r; - - amdgpu_vcn_setup_ucode(adev); - - r = amdgpu_vcn_resume(adev); - if (r) - return r; - /* VCN UNIFIED TRAP */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_5_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst->irq); @@ -95,10 +112,18 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) return r; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn5_fw_shared *fw_shared; - vcn_inst = GET_INST(VCN, i); + r = amdgpu_vcn_sw_init(adev, i); + if (r) + return r; + + amdgpu_vcn_setup_ucode(adev, i); + + r = amdgpu_vcn_resume(adev, i); + if (r) + return r; + ring = &adev->vcn.inst[i].ring_enc[0]; ring->use_doorbell = true; ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 9 * vcn_inst; @@ -111,12 +136,7 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block) if (r) return r; - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE); - fw_shared->sq.is_enabled = true; - - if (amdgpu_vcnfw_log) - amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); + vcn_v5_0_1_fw_shared_init(adev, i); } /* TODO: Add queue reset mask when FW fully supports it */ @@ -142,7 +162,7 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) if (drm_dev_enter(adev_to_drm(adev), &idx)) { for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + volatile struct amdgpu_vcn5_fw_shared *fw_shared; fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; fw_shared->present_flag_0 = 0; @@ -152,17 +172,23 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block) drm_dev_exit(idx); } - r = amdgpu_vcn_suspend(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(adev, i); + if (r) + return r; + } - r = amdgpu_vcn_sw_fini(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_sw_fini(adev, i); + if (r) + return r; + } amdgpu_vcn_sysfs_reset_mask_fini(adev); kfree(adev->vcn.ip_dump); - return r; + return 0; } /** @@ -178,6 +204,8 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) struct amdgpu_ring *ring; int i, r, vcn_inst; + if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100) + adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED); for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { vcn_inst = GET_INST(VCN, i); ring = &adev->vcn.inst[i].ring_enc[0]; @@ -188,6 +216,9 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) 9 * vcn_inst), adev->vcn.inst[i].aid_id); + /* Re-init fw_shared, if required */ + vcn_v5_0_1_fw_shared_init(adev, i); + r = amdgpu_ring_test_helper(ring); if (r) return r; @@ -206,8 +237,15 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block) static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + int i; - cancel_delayed_work_sync(&adev->vcn.idle_work); + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + + cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work); + if (vinst->cur_state != AMD_PG_STATE_GATE) + vinst->set_pg_state(vinst, AMD_PG_STATE_GATE); + } return 0; } @@ -222,13 +260,17 @@ static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block) static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - int r; + int r, i; r = vcn_v5_0_1_hw_fini(ip_block); if (r) return r; - r = amdgpu_vcn_suspend(adev); + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + r = amdgpu_vcn_suspend(ip_block->adev, i); + if (r) + return r; + } return r; } @@ -243,11 +285,18 @@ static int vcn_v5_0_1_suspend(struct amdgpu_ip_block *ip_block) static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - int r; + int r, i; - r = amdgpu_vcn_resume(adev); - if (r) - return r; + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + + if (amdgpu_in_reset(adev)) + vinst->cur_state = AMD_PG_STATE_GATE; + + r = amdgpu_vcn_resume(ip_block->adev, i); + if (r) + return r; + } r = vcn_v5_0_1_hw_init(ip_block); @@ -257,13 +306,14 @@ static int vcn_v5_0_1_resume(struct amdgpu_ip_block *ip_block) /** * vcn_v5_0_1_mc_resume - memory controller programming * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Let the VCN memory controller know it's offsets */ -static void vcn_v5_0_1_mc_resume(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_1_mc_resume(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst = vinst->inst; uint32_t offset, size, vcn_inst; const struct common_firmware_header *hdr; @@ -313,20 +363,22 @@ static void vcn_v5_0_1_mc_resume(struct amdgpu_device *adev, int inst) upper_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr)); WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_OFFSET0, 0); WREG32_SOC15(VCN, vcn_inst, regUVD_VCPU_NONCACHE_SIZE0, - AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared))); + AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared))); } /** * vcn_v5_0_1_mc_resume_dpg_mode - memory controller programming for dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Let the VCN memory controller know it's offsets with dpg mode */ -static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t offset, size; const struct common_firmware_header *hdr; @@ -421,7 +473,7 @@ static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i VCN, 0, regUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect); WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( VCN, 0, regUVD_VCPU_NONCACHE_SIZE0), - AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn4_fw_shared)), 0, indirect); + AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_vcn5_fw_shared)), 0, indirect); /* VCN global tiling registers */ WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( @@ -431,39 +483,39 @@ static void vcn_v5_0_1_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_i /** * vcn_v5_0_1_disable_clock_gating - disable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Disable clock gating for VCN block */ -static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_1_disable_clock_gating(struct amdgpu_vcn_inst *vinst) { } /** * vcn_v5_0_1_enable_clock_gating - enable VCN clock gating * - * @adev: amdgpu_device pointer - * @inst: instance number + * @vinst: VCN instance * * Enable clock gating for VCN block */ -static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_device *adev, int inst) +static void vcn_v5_0_1_enable_clock_gating(struct amdgpu_vcn_inst *vinst) { } /** * vcn_v5_0_1_start_dpg_mode - VCN start with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * @indirect: indirectly write sram * * Start VCN block with dpg mode */ -static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect) +static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst, + bool indirect) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared = + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; + volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr; struct amdgpu_ring *ring; int vcn_inst; @@ -510,7 +562,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( VCN, 0, regUVD_LMI_CTRL), tmp, 0, indirect); - vcn_v5_0_1_mc_resume_dpg_mode(adev, inst_idx, indirect); + vcn_v5_0_1_mc_resume_dpg_mode(vinst, indirect); tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT); tmp |= UVD_VCPU_CNTL__CLK_EN_MASK; @@ -564,150 +616,148 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b /** * vcn_v5_0_1_start - VCN start * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Start VCN block */ -static int vcn_v5_0_1_start(struct amdgpu_device *adev) +static int vcn_v5_0_1_start(struct amdgpu_vcn_inst *vinst) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; + volatile struct amdgpu_vcn5_fw_shared *fw_shared; struct amdgpu_ring *ring; uint32_t tmp; - int i, j, k, r, vcn_inst; + int j, k, r, vcn_inst; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - r = vcn_v5_0_1_start_dpg_mode(adev, i, adev->vcn.indirect_sram); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) + return vcn_v5_0_1_start_dpg_mode(vinst, adev->vcn.inst[i].indirect_sram); - vcn_inst = GET_INST(VCN, i); + vcn_inst = GET_INST(VCN, i); - /* set VCN status busy */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; - WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp); - - /* enable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); - - /* disable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0, - ~UVD_MASTINT_EN__VCPU_EN_MASK); - - /* enable LMI MC and UMC channels */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0, - ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); - - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); - tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); - - /* setup regUVD_LMI_CTRL */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL); - WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, tmp | - UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | - UVD_LMI_CTRL__MASK_MC_URGENT_MASK | - UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | - UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); - - vcn_v5_0_1_mc_resume(adev, i); - - /* VCN global tiling registers */ - WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG, - adev->gfx.config.gb_addr_config); - - /* unblock VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* release VCPU reset to boot */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - for (j = 0; j < 10; ++j) { - uint32_t status; - - for (k = 0; k < 100; ++k) { - status = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS); - if (status & 2) - break; - mdelay(100); - if (amdgpu_emu_mode == 1) - msleep(20); - } + /* set VCN status busy */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY; + WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp); + + /* enable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK); + + /* disable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0, + ~UVD_MASTINT_EN__VCPU_EN_MASK); + + /* enable LMI MC and UMC channels */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); + + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); + tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); + + /* setup regUVD_LMI_CTRL */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL); + WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL, tmp | + UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__MASK_MC_URGENT_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK); + + vcn_v5_0_1_mc_resume(vinst); - if (amdgpu_emu_mode == 1) { - r = -1; - if (status & 2) { - r = 0; - break; - } - } else { + /* VCN global tiling registers */ + WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG, + adev->gfx.config.gb_addr_config); + + /* unblock VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), 0, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* release VCPU reset to boot */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + for (j = 0; j < 10; ++j) { + uint32_t status; + + for (k = 0; k < 100; ++k) { + status = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS); + if (status & 2) + break; + mdelay(100); + if (amdgpu_emu_mode == 1) + msleep(20); + } + + if (amdgpu_emu_mode == 1) { + r = -1; + if (status & 2) { r = 0; - if (status & 2) - break; - - dev_err(adev->dev, - "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - mdelay(10); - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - mdelay(10); - r = -1; + break; } + } else { + r = 0; + if (status & 2) + break; + + dev_err(adev->dev, + "VCN[%d] is not responding, trying to reset the VCPU!!!\n", i); + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + mdelay(10); + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + mdelay(10); + r = -1; } + } - if (r) { - dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); - return r; - } + if (r) { + dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i); + return r; + } - /* enable master interrupt */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), - UVD_MASTINT_EN__VCPU_EN_MASK, - ~UVD_MASTINT_EN__VCPU_EN_MASK); + /* enable master interrupt */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), + UVD_MASTINT_EN__VCPU_EN_MASK, + ~UVD_MASTINT_EN__VCPU_EN_MASK); - /* clear the busy bit of VCN_STATUS */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, - ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); + /* clear the busy bit of VCN_STATUS */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0, + ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); - ring = &adev->vcn.inst[i].ring_enc[0]; + ring = &adev->vcn.inst[i].ring_enc[0]; - WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL, - ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | - VCN_RB1_DB_CTRL__EN_MASK); + WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL, + ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | + VCN_RB1_DB_CTRL__EN_MASK); - /* Read DB_CTRL to flush the write DB_CTRL command. */ - RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL); + /* Read DB_CTRL to flush the write DB_CTRL command. */ + RREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO, ring->gpu_addr); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE, ring->ring_size / 4); - tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); - tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); - WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0); + tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); + tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK); + WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET; + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0); - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR); - WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp); - ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR); + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR); + WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, tmp); + ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR); - tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); - tmp |= VCN_RB_ENABLE__RB1_EN_MASK; - WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); - fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); - } + tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE); + tmp |= VCN_RB_ENABLE__RB1_EN_MASK; + WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp); + fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); return 0; } @@ -715,13 +765,14 @@ static int vcn_v5_0_1_start(struct amdgpu_device *adev) /** * vcn_v5_0_1_stop_dpg_mode - VCN stop with dpg mode * - * @adev: amdgpu_device pointer - * @inst_idx: instance number index + * @vinst: VCN instance * * Stop VCN block with dpg mode */ -static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) +static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_vcn_inst *vinst) { + struct amdgpu_device *adev = vinst->adev; + int inst_idx = vinst->inst; uint32_t tmp; int vcn_inst; @@ -743,75 +794,75 @@ static void vcn_v5_0_1_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) /** * vcn_v5_0_1_stop - VCN stop * - * @adev: amdgpu_device pointer + * @vinst: VCN instance * * Stop VCN block */ -static int vcn_v5_0_1_stop(struct amdgpu_device *adev) +static int vcn_v5_0_1_stop(struct amdgpu_vcn_inst *vinst) { - volatile struct amdgpu_vcn4_fw_shared *fw_shared; + struct amdgpu_device *adev = vinst->adev; + int i = vinst->inst; + volatile struct amdgpu_vcn5_fw_shared *fw_shared; uint32_t tmp; - int i, r = 0, vcn_inst; + int r = 0, vcn_inst; - for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { - vcn_inst = GET_INST(VCN, i); + vcn_inst = GET_INST(VCN, i); - fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; - fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; + fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr; + fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF; - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { - vcn_v5_0_1_stop_dpg_mode(adev, i); - continue; - } + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + vcn_v5_0_1_stop_dpg_mode(vinst); + return 0; + } - /* wait for vcn idle */ - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); - if (r) - return r; + /* wait for vcn idle */ + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7); + if (r) + return r; - tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | - UVD_LMI_STATUS__READ_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_MASK | - UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK | + UVD_LMI_STATUS__READ_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_MASK | + UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp); + if (r) + return r; - /* disable LMI UMC channel */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2); - tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp); - tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | - UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; - r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp); - if (r) - return r; + /* disable LMI UMC channel */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2); + tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2, tmp); + tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | + UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; + r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_LMI_STATUS, tmp, tmp); + if (r) + return r; - /* block VCPU register access */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), - UVD_RB_ARB_CTRL__VCPU_DIS_MASK, - ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); - - /* reset VCPU */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), - UVD_VCPU_CNTL__BLK_RST_MASK, - ~UVD_VCPU_CNTL__BLK_RST_MASK); - - /* disable VCPU clock */ - WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, - ~(UVD_VCPU_CNTL__CLK_EN_MASK)); - - /* apply soft reset */ - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); - tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); - tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; - WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); - - /* clear status */ - WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0); - } + /* block VCPU register access */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL), + UVD_RB_ARB_CTRL__VCPU_DIS_MASK, + ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK); + + /* reset VCPU */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), + UVD_VCPU_CNTL__BLK_RST_MASK, + ~UVD_VCPU_CNTL__BLK_RST_MASK); + + /* disable VCPU clock */ + WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0, + ~(UVD_VCPU_CNTL__CLK_EN_MASK)); + + /* apply soft reset */ + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); + tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET); + tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK; + WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp); + + /* clear status */ + WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0); return 0; } @@ -883,16 +934,17 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .get_rptr = vcn_v5_0_1_unified_ring_get_rptr, .get_wptr = vcn_v5_0_1_unified_ring_get_wptr, .set_wptr = vcn_v5_0_1_unified_ring_set_wptr, - .emit_frame_size = - SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + - SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + - 4 + /* vcn_v2_0_enc_ring_emit_vm_flush */ - 5 + 5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */ - 1, /* vcn_v2_0_enc_ring_insert_end */ + .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + + 4 + /* vcn_v2_0_enc_ring_emit_vm_flush */ + 5 + + 5 + /* vcn_v2_0_enc_ring_emit_fence x2 vm fence */ + 1, /* vcn_v2_0_enc_ring_insert_end */ .emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */ .emit_ib = vcn_v2_0_enc_ring_emit_ib, .emit_fence = vcn_v2_0_enc_ring_emit_fence, - .emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush, + .emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush, + .emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush, .test_ring = amdgpu_vcn_enc_ring_test_ring, .test_ib = amdgpu_vcn_unified_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, @@ -900,8 +952,8 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = { .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = amdgpu_vcn_ring_begin_use, .end_use = amdgpu_vcn_ring_end_use, - .emit_wreg = vcn_v2_0_enc_ring_emit_wreg, - .emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait, + .emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg, + .emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, }; @@ -927,13 +979,13 @@ static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev) /** * vcn_v5_0_1_is_idle - check VCN block is idle * - * @handle: amdgpu_device pointer + * @ip_block: Pointer to the amdgpu_ip_block structure * * Check whether VCN block is idle */ -static bool vcn_v5_0_1_is_idle(void *handle) +static bool vcn_v5_0_1_is_idle(struct amdgpu_ip_block *ip_block) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_device *adev = ip_block->adev; int i, ret = 1; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) @@ -980,42 +1032,35 @@ static int vcn_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block, int i; for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { + struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[i]; + if (enable) { if (RREG32_SOC15(VCN, GET_INST(VCN, i), regUVD_STATUS) != UVD_STATUS__IDLE) return -EBUSY; - vcn_v5_0_1_enable_clock_gating(adev, i); + vcn_v5_0_1_enable_clock_gating(vinst); } else { - vcn_v5_0_1_disable_clock_gating(adev, i); + vcn_v5_0_1_disable_clock_gating(vinst); } } return 0; } -/** - * vcn_v5_0_1_set_powergating_state - set VCN block powergating state - * - * @ip_block: Pointer to the amdgpu_ip_block for this hw instance. - * @state: power gating state - * - * Set VCN block powergating state - */ -static int vcn_v5_0_1_set_powergating_state(struct amdgpu_ip_block *ip_block, - enum amd_powergating_state state) +static int vcn_v5_0_1_set_pg_state(struct amdgpu_vcn_inst *vinst, + enum amd_powergating_state state) { - struct amdgpu_device *adev = ip_block->adev; - int ret; + int ret = 0; - if (state == adev->vcn.cur_state) + if (state == vinst->cur_state) return 0; if (state == AMD_PG_STATE_GATE) - ret = vcn_v5_0_1_stop(adev); + ret = vcn_v5_0_1_stop(vinst); else - ret = vcn_v5_0_1_start(adev); + ret = vcn_v5_0_1_start(vinst); if (!ret) - adev->vcn.cur_state = state; + vinst->cur_state = state; return ret; } @@ -1098,7 +1143,7 @@ static const struct amd_ip_funcs vcn_v5_0_1_ip_funcs = { .soft_reset = NULL, .post_soft_reset = NULL, .set_clockgating_state = vcn_v5_0_1_set_clockgating_state, - .set_powergating_state = vcn_v5_0_1_set_powergating_state, + .set_powergating_state = vcn_set_powergating_state, .dump_ip_state = vcn_v5_0_0_dump_ip_state, .print_ip_state = vcn_v5_0_0_print_ip_state, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h index 82ac709f44bf..8fd90bd10807 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.h @@ -24,6 +24,9 @@ #ifndef __VCN_v5_0_1_H__ #define __VCN_v5_0_1_H__ +#define regVCN_RRMT_CNTL 0x0940 +#define regVCN_RRMT_CNTL_BASE_IDX 1 + extern const struct amdgpu_ip_block_version vcn_v5_0_1_ip_block; #endif /* __VCN_v5_0_1_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index 98fc6941159e..eb16916c6473 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -555,7 +555,7 @@ static int vega10_ih_resume(struct amdgpu_ip_block *ip_block) return vega10_ih_hw_init(ip_block); } -static bool vega10_ih_is_idle(void *handle) +static bool vega10_ih_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index e9e3b2ed4b7b..faa0dd75dd6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -651,7 +651,7 @@ static int vega20_ih_resume(struct amdgpu_ip_block *ip_block) return vega20_ih_hw_init(ip_block); } -static bool vega20_ih_is_idle(void *handle) +static bool vega20_ih_is_idle(struct amdgpu_ip_block *ip_block) { /* todo */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 12fe571787f4..3bbbb75242d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -1736,7 +1736,7 @@ static int vi_common_resume(struct amdgpu_ip_block *ip_block) return vi_common_hw_init(ip_block); } -static bool vi_common_is_idle(void *handle) +static bool vi_common_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile index 0d3d8972240d..0ce08113c9f0 100644 --- a/drivers/gpu/drm/amd/amdkfd/Makefile +++ b/drivers/gpu/drm/amd/amdkfd/Makefile @@ -27,7 +27,6 @@ AMDKFD_FILES := $(AMDKFD_PATH)/kfd_module.o \ $(AMDKFD_PATH)/kfd_device.o \ $(AMDKFD_PATH)/kfd_chardev.o \ $(AMDKFD_PATH)/kfd_topology.o \ - $(AMDKFD_PATH)/kfd_pasid.o \ $(AMDKFD_PATH)/kfd_doorbell.o \ $(AMDKFD_PATH)/kfd_flat_memory.o \ $(AMDKFD_PATH)/kfd_process.o \ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 433de9e9a77e..1e9dd00620bf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -212,6 +212,11 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties, return -EINVAL; } + if (args->ring_size < KFD_MIN_QUEUE_RING_SIZE) { + args->ring_size = KFD_MIN_QUEUE_RING_SIZE; + pr_debug("Size lower. clamped to KFD_MIN_QUEUE_RING_SIZE"); + } + if (!access_ok((const void __user *) args->read_pointer_address, sizeof(uint32_t))) { pr_err("Can't access read pointer\n"); @@ -461,6 +466,11 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p, return -EINVAL; } + if (args->ring_size < KFD_MIN_QUEUE_RING_SIZE) { + args->ring_size = KFD_MIN_QUEUE_RING_SIZE; + pr_debug("Size lower. clamped to KFD_MIN_QUEUE_RING_SIZE"); + } + properties.queue_address = args->ring_base_address; properties.queue_size = args->ring_size; properties.queue_percent = args->queue_percentage & 0xFF; @@ -596,7 +606,8 @@ static int kfd_ioctl_set_memory_policy(struct file *filep, default_policy, alternate_policy, (void __user *)args->alternate_aperture_base, - args->alternate_aperture_size)) + args->alternate_aperture_size, + args->misc_process_flag)) err = -EINVAL; out: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 70b3ae0b74fe..4a7180b46b71 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -2133,9 +2133,6 @@ static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size, bool ext_cpu = KFD_GC_VERSION(kdev) != IP_VERSION(9, 4, 3); int mem_bw = 819200, weight = ext_cpu ? KFD_CRAT_XGMI_WEIGHT : KFD_CRAT_INTRA_SOCKET_WEIGHT; - uint32_t bandwidth = ext_cpu ? amdgpu_amdkfd_get_xgmi_bandwidth_mbytes( - kdev->adev, NULL, true) : mem_bw; - /* * with host gpu xgmi link, host can access gpu memory whether * or not pcie bar type is large, so always create bidirectional @@ -2144,8 +2141,16 @@ static int kfd_fill_gpu_direct_io_link_to_cpu(int *avail_size, sub_type_hdr->flags |= CRAT_IOLINK_FLAGS_BI_DIRECTIONAL; sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_XGMI; sub_type_hdr->weight_xgmi = weight; - sub_type_hdr->minimum_bandwidth_mbs = bandwidth; - sub_type_hdr->maximum_bandwidth_mbs = bandwidth; + if (ext_cpu) { + amdgpu_xgmi_get_bandwidth(kdev->adev, NULL, + AMDGPU_XGMI_BW_MODE_PER_LINK, + AMDGPU_XGMI_BW_UNIT_MBYTES, + &sub_type_hdr->minimum_bandwidth_mbs, + &sub_type_hdr->maximum_bandwidth_mbs); + } else { + sub_type_hdr->minimum_bandwidth_mbs = mem_bw; + sub_type_hdr->maximum_bandwidth_mbs = mem_bw; + } } else { sub_type_hdr->io_interface_type = CRAT_IOLINK_TYPE_PCIEXPRESS; sub_type_hdr->minimum_bandwidth_mbs = @@ -2198,12 +2203,12 @@ static int kfd_fill_gpu_xgmi_link_to_gpu(int *avail_size, if (use_ta_info) { sub_type_hdr->weight_xgmi = KFD_CRAT_XGMI_WEIGHT * - amdgpu_amdkfd_get_xgmi_hops_count(kdev->adev, peer_kdev->adev); - sub_type_hdr->maximum_bandwidth_mbs = - amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->adev, - peer_kdev->adev, false); - sub_type_hdr->minimum_bandwidth_mbs = sub_type_hdr->maximum_bandwidth_mbs ? - amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(kdev->adev, NULL, true) : 0; + amdgpu_xgmi_get_hops_count(kdev->adev, peer_kdev->adev); + amdgpu_xgmi_get_bandwidth(kdev->adev, peer_kdev->adev, + AMDGPU_XGMI_BW_MODE_PER_PEER, + AMDGPU_XGMI_BW_UNIT_MBYTES, + &sub_type_hdr->minimum_bandwidth_mbs, + &sub_type_hdr->maximum_bandwidth_mbs); } else { bool is_single_hop = kdev->kfd == peer_kdev->kfd; int weight = is_single_hop ? KFD_CRAT_INTRA_SOCKET_WEIGHT : diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 9d20e169ec4a..b9c82be6ce13 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -590,9 +590,13 @@ static int kfd_gws_init(struct kfd_node *node) && kfd->mec2_fw_version >= 0x6b) || (KFD_GC_VERSION(node) >= IP_VERSION(11, 0, 0) && KFD_GC_VERSION(node) < IP_VERSION(12, 0, 0) - && mes_rev >= 68)))) + && mes_rev >= 68) || + (KFD_GC_VERSION(node) >= IP_VERSION(12, 0, 0))))) { + if (KFD_GC_VERSION(node) >= IP_VERSION(12, 0, 0)) + node->adev->gds.gws_size = 64; ret = amdgpu_amdkfd_alloc_gws(node->adev, node->adev->gds.gws_size, &node->gws); + } return ret; } @@ -1600,6 +1604,11 @@ int kfd_debugfs_hang_hws(struct kfd_node *dev) return -EINVAL; } + if (dev->kfd->shared_resources.enable_mes) { + dev_err(dev->adev->dev, "Inducing MES hang is not supported\n"); + return -EINVAL; + } + return dqm_debugfs_hang_hws(dev->dqm); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 195085079eb2..2afcc1b4856a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -36,6 +36,7 @@ #include "kfd_kernel_queue.h" #include "amdgpu_amdkfd.h" #include "amdgpu_reset.h" +#include "amdgpu_sdma.h" #include "mes_v11_api_def.h" #include "kfd_debug.h" @@ -66,7 +67,8 @@ static inline void deallocate_hqd(struct device_queue_manager *dqm, static int allocate_hqd(struct device_queue_manager *dqm, struct queue *q); static int allocate_sdma_queue(struct device_queue_manager *dqm, struct queue *q, const uint32_t *restore_sdma_id); -static void kfd_process_hw_exception(struct work_struct *work); + +static int reset_queues_on_hws_hang(struct device_queue_manager *dqm, bool is_sdma); static inline enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type) @@ -170,7 +172,7 @@ static void kfd_hws_hang(struct device_queue_manager *dqm) /* * Issue a GPU reset if HWS is unresponsive */ - schedule_work(&dqm->hw_exception_work); + amdgpu_amdkfd_gpu_reset(dqm->dev->adev); } static int convert_to_mes_queue_type(int queue_type) @@ -207,21 +209,6 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (!down_read_trylock(&adev->reset_domain->sem)) return -EIO; - if (!pdd->proc_ctx_cpu_ptr) { - r = amdgpu_amdkfd_alloc_gtt_mem(adev, - AMDGPU_MES_PROC_CTX_SIZE, - &pdd->proc_ctx_bo, - &pdd->proc_ctx_gpu_addr, - &pdd->proc_ctx_cpu_ptr, - false); - if (r) { - dev_err(adev->dev, - "failed to allocate process context bo\n"); - return r; - } - memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); - } - memset(&queue_input, 0x0, sizeof(struct mes_add_queue_input)); queue_input.process_id = pdd->pasid; queue_input.page_table_base_addr = qpd->page_table_base; @@ -1755,7 +1742,6 @@ static int initialize_cpsch(struct device_queue_manager *dqm) dqm->active_cp_queue_count = 0; dqm->gws_queue_count = 0; dqm->active_runlist = false; - INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception); dqm->trap_debug_vmid = 0; init_sdma_bitmaps(dqm); @@ -2222,8 +2208,7 @@ static struct queue *find_queue_by_address(struct device_queue_manager *dqm, uin return NULL; } -/* only for compute queue */ -static int reset_queues_on_hws_hang(struct device_queue_manager *dqm) +static int reset_hung_queues(struct device_queue_manager *dqm) { int r = 0, reset_count = 0, i; @@ -2276,6 +2261,104 @@ reset_fail: return r; } +static bool sdma_has_hang(struct device_queue_manager *dqm) +{ + int engine_start = dqm->dev->node_id * get_num_all_sdma_engines(dqm); + int engine_end = engine_start + get_num_all_sdma_engines(dqm); + int num_queues_per_eng = dqm->dev->kfd->device_info.num_sdma_queues_per_engine; + int i, j; + + for (i = engine_start; i < engine_end; i++) { + for (j = 0; j < num_queues_per_eng; j++) { + if (!dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j)) + continue; + + return true; + } + } + + return false; +} + +static bool set_sdma_queue_as_reset(struct device_queue_manager *dqm, + uint32_t doorbell_off) +{ + struct device_process_node *cur; + struct qcm_process_device *qpd; + struct queue *q; + + list_for_each_entry(cur, &dqm->queues, list) { + qpd = cur->qpd; + list_for_each_entry(q, &qpd->queues_list, list) { + if ((q->properties.type == KFD_QUEUE_TYPE_SDMA || + q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) && + q->properties.doorbell_off == doorbell_off) { + set_queue_as_reset(dqm, q, qpd); + return true; + } + } + } + + return false; +} + +static int reset_hung_queues_sdma(struct device_queue_manager *dqm) +{ + int engine_start = dqm->dev->node_id * get_num_all_sdma_engines(dqm); + int engine_end = engine_start + get_num_all_sdma_engines(dqm); + int num_queues_per_eng = dqm->dev->kfd->device_info.num_sdma_queues_per_engine; + int r = 0, i, j; + + if (dqm->is_hws_hang) + return -EIO; + + /* Scan for hung HW queues and reset engine. */ + dqm->detect_hang_count = 0; + for (i = engine_start; i < engine_end; i++) { + for (j = 0; j < num_queues_per_eng; j++) { + uint32_t doorbell_off = + dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j); + + if (!doorbell_off) + continue; + + /* Reset engine and check. */ + if (amdgpu_sdma_reset_engine(dqm->dev->adev, i, false) || + dqm->dev->kfd2kgd->hqd_sdma_get_doorbell(dqm->dev->adev, i, j) || + !set_sdma_queue_as_reset(dqm, doorbell_off)) { + r = -ENOTRECOVERABLE; + goto reset_fail; + } + + /* Should only expect one queue active per engine */ + dqm->detect_hang_count++; + break; + } + } + + /* Signal process reset */ + if (dqm->detect_hang_count) + kfd_signal_reset_event(dqm->dev); + else + r = -ENOTRECOVERABLE; + +reset_fail: + dqm->detect_hang_count = 0; + + return r; +} + +static int reset_queues_on_hws_hang(struct device_queue_manager *dqm, bool is_sdma) +{ + while (halt_if_hws_hang) + schedule(); + + if (!amdgpu_gpu_recovery) + return -ENOTRECOVERABLE; + + return is_sdma ? reset_hung_queues_sdma(dqm) : reset_hung_queues(dqm); +} + /* dqm->lock mutex has to be locked before calling this function */ static int unmap_queues_cpsch(struct device_queue_manager *dqm, enum kfd_unmap_queues_filter filter, @@ -2326,16 +2409,13 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, * check those fields */ mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]; - if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) { - while (halt_if_hws_hang) - schedule(); - if (reset_queues_on_hws_hang(dqm)) { - dqm->is_hws_hang = true; - kfd_hws_hang(dqm); - retval = -ETIME; - goto out; - } - } + if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd) && + reset_queues_on_hws_hang(dqm, false)) + goto reset_fail; + + /* Check for SDMA hang and attempt SDMA reset */ + if (sdma_has_hang(dqm) && reset_queues_on_hws_hang(dqm, true)) + goto reset_fail; /* We need to reset the grace period value for this device */ if (grace_period != USE_DEFAULT_GRACE_PERIOD) { @@ -2346,10 +2426,15 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, pm_release_ib(&dqm->packet_mgr); dqm->active_runlist = false; - out: up_read(&dqm->dev->adev->reset_domain->sem); return retval; + +reset_fail: + dqm->is_hws_hang = true; + kfd_hws_hang(dqm); + up_read(&dqm->dev->adev->reset_domain->sem); + return -ETIME; } /* only for compute queue */ @@ -2506,20 +2591,13 @@ failed_try_destroy_debugged_queue: return retval; } -/* - * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to - * stay in user mode. - */ -#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL -/* APE1 limit is inclusive and 64K aligned. */ -#define APE1_LIMIT_ALIGNMENT 0xFFFF - static bool set_cache_memory_policy(struct device_queue_manager *dqm, struct qcm_process_device *qpd, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size) + uint64_t alternate_aperture_size, + u32 misc_process_properties) { bool retval = true; @@ -2528,41 +2606,17 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm, dqm_lock(dqm); - if (alternate_aperture_size == 0) { - /* base > limit disables APE1 */ - qpd->sh_mem_ape1_base = 1; - qpd->sh_mem_ape1_limit = 0; - } else { - /* - * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]}, - * SH_MEM_APE1_BASE[31:0], 0x0000 } - * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]}, - * SH_MEM_APE1_LIMIT[31:0], 0xFFFF } - * Verify that the base and size parameters can be - * represented in this format and convert them. - * Additionally restrict APE1 to user-mode addresses. - */ - - uint64_t base = (uintptr_t)alternate_aperture_base; - uint64_t limit = base + alternate_aperture_size - 1; - - if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 || - (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) { - retval = false; - goto out; - } - - qpd->sh_mem_ape1_base = base >> 16; - qpd->sh_mem_ape1_limit = limit >> 16; - } - retval = dqm->asic_ops.set_cache_memory_policy( dqm, qpd, default_policy, alternate_policy, alternate_aperture_base, - alternate_aperture_size); + alternate_aperture_size, + misc_process_properties); + + if (retval) + goto out; if ((dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) && (qpd->vmid != 0)) program_sh_mem_settings(dqm, qpd); @@ -3095,13 +3149,6 @@ int kfd_evict_process_device(struct kfd_process_device *pdd) return ret; } -static void kfd_process_hw_exception(struct work_struct *work) -{ - struct device_queue_manager *dqm = container_of(work, - struct device_queue_manager, hw_exception_work); - amdgpu_amdkfd_gpu_reset(dqm->dev->adev); -} - int reserve_debug_trap_vmid(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 09ab36f8e8c6..122eb745e9c4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -174,7 +174,8 @@ struct device_queue_manager_ops { enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); int (*process_termination)(struct device_queue_manager *dqm, struct qcm_process_device *qpd); @@ -210,7 +211,8 @@ struct device_queue_manager_asic_ops { enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); void (*init_sdma_vm)(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); @@ -269,7 +271,6 @@ struct device_queue_manager { /* hw exception */ bool is_hws_hang; bool is_resetting; - struct work_struct hw_exception_work; struct kfd_mem_obj hiq_sdma_mqd; bool sched_running; bool sched_halt; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c index d4d95c7f2e5d..0508ef5a41d7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c @@ -27,12 +27,21 @@ #include "oss/oss_2_4_sh_mask.h" #include "gca/gfx_7_2_sh_mask.h" +/* + * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to + * stay in user mode. + */ +#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL +/* APE1 limit is inclusive and 64K aligned. */ +#define APE1_LIMIT_ALIGNMENT 0xFFFF + static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, struct qcm_process_device *qpd, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); static int update_qpd_cik(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm(struct device_queue_manager *dqm, @@ -80,10 +89,41 @@ static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size) + uint64_t alternate_aperture_size, + u32 misc_process_properties) { uint32_t default_mtype; uint32_t ape1_mtype; + unsigned int temp; + bool retval = true; + + if (alternate_aperture_size == 0) { + /* base > limit disables APE1 */ + qpd->sh_mem_ape1_base = 1; + qpd->sh_mem_ape1_limit = 0; + } else { + /* + * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]}, + * SH_MEM_APE1_BASE[31:0], 0x0000 } + * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]}, + * SH_MEM_APE1_LIMIT[31:0], 0xFFFF } + * Verify that the base and size parameters can be + * represented in this format and convert them. + * Additionally restrict APE1 to user-mode addresses. + */ + + uint64_t base = (uintptr_t)alternate_aperture_base; + uint64_t limit = base + alternate_aperture_size - 1; + + if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 || + (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) { + retval = false; + goto out; + } + + qpd->sh_mem_ape1_base = base >> 16; + qpd->sh_mem_ape1_limit = limit >> 16; + } default_mtype = (default_policy == cache_policy_coherent) ? MTYPE_NONCACHED : @@ -97,37 +137,22 @@ static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, | ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED) | DEFAULT_MTYPE(default_mtype) | APE1_MTYPE(ape1_mtype); - - return true; -} - -static int update_qpd_cik(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) -{ - struct kfd_process_device *pdd; - unsigned int temp; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - ALIGNMENT_MODE(SH_MEM_ALIGNMENT_MODE_UNALIGNED) | - DEFAULT_MTYPE(MTYPE_NONCACHED) | - APE1_MTYPE(MTYPE_NONCACHED); - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } - /* On dGPU we're always in GPUVM64 addressing mode with 64-bit * aperture addresses. */ - temp = get_sh_mem_bases_nybble_64(pdd); + temp = get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd)); qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); pr_debug("is32bit process: %d sh_mem_bases nybble: 0x%X and register 0x%X\n", qpd->pqm->process->is_32bit_user_mode, temp, qpd->sh_mem_bases); +out: + return retval; +} + +static int update_qpd_cik(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c index 245a90dfc2f6..ba6e3d747ccd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c @@ -31,10 +31,18 @@ static int update_qpd_v10(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v10(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v10(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v10( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v10; asic_ops->update_qpd = update_qpd_v10; asic_ops->init_sdma_vm = init_sdma_vm_v10; asic_ops->mqd_manager_init = mqd_manager_init_v10; @@ -49,27 +57,28 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } -static int update_qpd_v10(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) +static bool set_cache_memory_policy_v10(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) { - struct kfd_process_device *pdd; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | - (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } - - qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd); + qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases); + return true; +} +static int update_qpd_v10(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c index 2e129da7acb4..8b447d04558f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v11.c @@ -30,10 +30,18 @@ static int update_qpd_v11(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v11(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v11(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v11( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v11; asic_ops->update_qpd = update_qpd_v11; asic_ops->init_sdma_vm = init_sdma_vm_v11; asic_ops->mqd_manager_init = mqd_manager_init_v11; @@ -48,28 +56,29 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } -static int update_qpd_v11(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) +static bool set_cache_memory_policy_v11(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) { - struct kfd_process_device *pdd; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | - (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } + qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd); + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases); + return true; +} +static int update_qpd_v11(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c index 4f3295b29dfb..3550da3a46f9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12.c @@ -30,10 +30,18 @@ static int update_qpd_v12(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v12(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v12(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v12( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v12; asic_ops->update_qpd = update_qpd_v12; asic_ops->init_sdma_vm = init_sdma_vm_v12; asic_ops->mqd_manager_init = mqd_manager_init_v12; @@ -48,28 +56,29 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } -static int update_qpd_v12(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) +static bool set_cache_memory_policy_v12(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) { - struct kfd_process_device *pdd; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - (SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | - (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } + qpd->sh_mem_config = (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); - qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd); + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); pr_debug("sh_mem_bases 0x%X\n", qpd->sh_mem_bases); + return true; +} +static int update_qpd_v12(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c index 67137e674f1d..d794c8172b40 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c @@ -30,10 +30,18 @@ static int update_qpd_v9(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm_v9(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd); +static bool set_cache_memory_policy_v9(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties); void device_queue_manager_init_v9( struct device_queue_manager_asic_ops *asic_ops) { + asic_ops->set_cache_memory_policy = set_cache_memory_policy_v9; asic_ops->update_qpd = update_qpd_v9; asic_ops->init_sdma_vm = init_sdma_vm_v9; asic_ops->mqd_manager_init = mqd_manager_init_v9; @@ -48,10 +56,43 @@ static uint32_t compute_sh_mem_bases_64bit(struct kfd_process_device *pdd) private_base; } +static bool set_cache_memory_policy_v9(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + enum cache_policy default_policy, + enum cache_policy alternate_policy, + void __user *alternate_aperture_base, + uint64_t alternate_aperture_size, + u32 misc_process_properties) +{ + qpd->sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; + + if (dqm->dev->kfd->noretry) + qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT; + + if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 3) || + KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4) || + KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 5, 0)) + qpd->sh_mem_config |= (1 << SH_MEM_CONFIG__F8_MODE__SHIFT); + + if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 5, 0)) { + if (misc_process_properties & KFD_PROC_FLAG_MFMA_HIGH_PRECISION) + qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__PRECISION_MODE__SHIFT; + } + + qpd->sh_mem_ape1_limit = 0; + qpd->sh_mem_ape1_base = 0; + qpd->sh_mem_bases = compute_sh_mem_bases_64bit(qpd_to_pdd(qpd)); + + pr_debug("sh_mem_bases 0x%X sh_mem_config 0x%X\n", qpd->sh_mem_bases, + qpd->sh_mem_config); + return true; +} + static int update_qpd_v9(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { - struct kfd_process_device *pdd; + struct kfd_process_device *pdd = qpd_to_pdd(qpd); pdd = qpd_to_pdd(qpd); @@ -64,8 +105,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm, qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT; if (KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 3) || - KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4) || - KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 5, 0)) + KFD_GC_VERSION(dqm->dev->kfd) == IP_VERSION(9, 4, 4)) qpd->sh_mem_config |= (1 << SH_MEM_CONFIG__F8_MODE__SHIFT); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c index b291ee0fab94..dad83356e976 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c @@ -27,12 +27,21 @@ #include "gca/gfx_8_0_sh_mask.h" #include "oss/oss_3_0_sh_mask.h" +/* + * Low bits must be 0000/FFFF as required by HW, high bits must be 0 to + * stay in user mode. + */ +#define APE1_FIXED_BITS_MASK 0xFFFF80000000FFFFULL +/* APE1 limit is inclusive and 64K aligned. */ +#define APE1_LIMIT_ALIGNMENT 0xFFFF + static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, struct qcm_process_device *qpd, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size); + uint64_t alternate_aperture_size, + u32 misc_process_properties); static int update_qpd_vi(struct device_queue_manager *dqm, struct qcm_process_device *qpd); static void init_sdma_vm(struct device_queue_manager *dqm, @@ -81,10 +90,41 @@ static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, enum cache_policy default_policy, enum cache_policy alternate_policy, void __user *alternate_aperture_base, - uint64_t alternate_aperture_size) + uint64_t alternate_aperture_size, + u32 misc_process_properties) { uint32_t default_mtype; uint32_t ape1_mtype; + unsigned int temp; + bool retval = true; + + if (alternate_aperture_size == 0) { + /* base > limit disables APE1 */ + qpd->sh_mem_ape1_base = 1; + qpd->sh_mem_ape1_limit = 0; + } else { + /* + * In FSA64, APE1_Base[63:0] = { 16{SH_MEM_APE1_BASE[31]}, + * SH_MEM_APE1_BASE[31:0], 0x0000 } + * APE1_Limit[63:0] = { 16{SH_MEM_APE1_LIMIT[31]}, + * SH_MEM_APE1_LIMIT[31:0], 0xFFFF } + * Verify that the base and size parameters can be + * represented in this format and convert them. + * Additionally restrict APE1 to user-mode addresses. + */ + + uint64_t base = (uintptr_t)alternate_aperture_base; + uint64_t limit = base + alternate_aperture_size - 1; + + if (limit <= base || (base & APE1_FIXED_BITS_MASK) != 0 || + (limit & APE1_FIXED_BITS_MASK) != APE1_LIMIT_ALIGNMENT) { + retval = false; + goto out; + } + + qpd->sh_mem_ape1_base = base >> 16; + qpd->sh_mem_ape1_limit = limit >> 16; + } default_mtype = (default_policy == cache_policy_coherent) ? MTYPE_UC : @@ -100,40 +140,21 @@ static bool set_cache_memory_policy_vi(struct device_queue_manager *dqm, default_mtype << SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | ape1_mtype << SH_MEM_CONFIG__APE1_MTYPE__SHIFT; - return true; -} - -static int update_qpd_vi(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) -{ - struct kfd_process_device *pdd; - unsigned int temp; - - pdd = qpd_to_pdd(qpd); - - /* check if sh_mem_config register already configured */ - if (qpd->sh_mem_config == 0) { - qpd->sh_mem_config = - SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT | - MTYPE_UC << - SH_MEM_CONFIG__DEFAULT_MTYPE__SHIFT | - MTYPE_UC << - SH_MEM_CONFIG__APE1_MTYPE__SHIFT; - - qpd->sh_mem_ape1_limit = 0; - qpd->sh_mem_ape1_base = 0; - } - /* On dGPU we're always in GPUVM64 addressing mode with 64-bit * aperture addresses. */ - temp = get_sh_mem_bases_nybble_64(pdd); + temp = get_sh_mem_bases_nybble_64(qpd_to_pdd(qpd)); qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); pr_debug("sh_mem_bases nybble: 0x%X and register 0x%X\n", temp, qpd->sh_mem_bases); +out: + return retval; +} +static int update_qpd_vi(struct device_queue_manager *dqm, + struct qcm_process_device *qpd) +{ return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index 2eff37aaf827..1695dd78ede8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; - m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; + pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index 68dbc0399c87..3c0ae28c5923 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; - m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c index 2b72d5b4949b..565858b9044d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c @@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; - m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index ff417d5361c4..3014925d95ff 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -183,6 +183,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd, m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK | 0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT; + m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; + m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT; m->cp_mqd_base_addr_lo = lower_32_bits(addr); @@ -245,7 +248,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m = get_mqd(mqd); - m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; + m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK; m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c deleted file mode 100644 index 8896426e0556..000000000000 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR MIT -/* - * Copyright 2014-2022 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -#include <linux/types.h> -#include "kfd_priv.h" -#include "amdgpu_ids.h" - -static unsigned int pasid_bits = 16; -static bool pasids_allocated; /* = false */ - -u32 kfd_pasid_alloc(void) -{ - int r = amdgpu_pasid_alloc(pasid_bits); - - if (r > 0) { - pasids_allocated = true; - return r; - } - - return 0; -} - -void kfd_pasid_free(u32 pasid) -{ - amdgpu_pasid_free(pasid); -} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 59619f794b6b..bb09c873a9a5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -289,7 +289,6 @@ struct kfd_node { /* Global GWS resource shared between processes */ void *gws; - bool gws_debug_workaround; /* Clients watching SMI events */ struct list_head smi_clients; @@ -1364,8 +1363,6 @@ int pqm_update_mqd(struct process_queue_manager *pqm, unsigned int qid, struct mqd_update_info *minfo); int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void *gws); -struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm, - unsigned int qid); struct queue *pqm_get_user_queue(struct process_queue_manager *pqm, unsigned int qid); int pqm_get_wave_state(struct process_queue_manager *pqm, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 1067afdb456e..7c0c24732481 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -35,6 +35,7 @@ #include <linux/pm_runtime.h> #include "amdgpu_amdkfd.h" #include "amdgpu.h" +#include "amdgpu_reset.h" struct mm_struct; @@ -838,6 +839,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) return ERR_PTR(-EINVAL); } + /* If the process just called exec(3), it is possible that the + * cleanup of the kfd_process (following the release of the mm + * of the old process image) is still in the cleanup work queue. + * Make sure to drain any job before trying to recreate any + * resource for this process. + */ + flush_workqueue(kfd_process_wq); + /* * take kfd processes mutex before starting of process creation * so there won't be a case where two threads of the same process @@ -858,14 +867,6 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) if (process) { pr_debug("Process already found\n"); } else { - /* If the process just called exec(3), it is possible that the - * cleanup of the kfd_process (following the release of the mm - * of the old process image) is still in the cleanup work queue. - * Make sure to drain any job before trying to recreate any - * resource for this process. - */ - flush_workqueue(kfd_process_wq); - process = create_process(thread); if (IS_ERR(process)) goto out; @@ -1133,6 +1134,17 @@ static void kfd_process_remove_sysfs(struct kfd_process *p) p->kobj = NULL; } +/* + * If any GPU is ongoing reset, wait for reset complete. + */ +static void kfd_process_wait_gpu_reset_complete(struct kfd_process *p) +{ + int i; + + for (i = 0; i < p->n_pdds; i++) + flush_workqueue(p->pdds[i]->dev->adev->reset_domain->wq); +} + /* No process locking is needed in this function, because the process * is not findable any more. We must assume that no other thread is * using it any more, otherwise we couldn't safely free the process @@ -1147,6 +1159,11 @@ static void kfd_process_wq_release(struct work_struct *work) kfd_process_dequeue_from_all_devices(p); pqm_uninit(&p->pqm); + /* + * If GPU in reset, user queues may still running, wait for reset complete. + */ + kfd_process_wait_gpu_reset_complete(p); + /* Signal the eviction fence after user mode queues are * destroyed. This allows any BOs to be freed without * triggering pointless evictions or waiting for fences. diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index d7947311cbbd..7eb370b68159 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -363,10 +363,26 @@ int pqm_create_queue(struct process_queue_manager *pqm, if (retval != 0) return retval; + /* Register process if this is the first queue */ if (list_empty(&pdd->qpd.queues_list) && list_empty(&pdd->qpd.priv_queue_list)) dev->dqm->ops.register_process(dev->dqm, &pdd->qpd); + /* Allocate proc_ctx_bo only if MES is enabled and this is the first queue */ + if (!pdd->proc_ctx_cpu_ptr && dev->kfd->shared_resources.enable_mes) { + retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (retval) { + dev_err(dev->adev->dev, "failed to allocate process context bo\n"); + return retval; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + pqn = kzalloc(sizeof(*pqn), GFP_KERNEL); if (!pqn) { retval = -ENOMEM; @@ -532,7 +548,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) pr_err("Pasid 0x%x destroy queue %d failed, ret %d\n", pdd->pasid, pqn->q->properties.queue_id, retval); - if (retval != -ETIME) + if (retval != -ETIME && retval != -EIO) goto err_destroy_queue; } kfd_procfs_del_queue(pqn->q); @@ -652,19 +668,6 @@ int pqm_update_mqd(struct process_queue_manager *pqm, return 0; } -struct kernel_queue *pqm_get_kernel_queue( - struct process_queue_manager *pqm, - unsigned int qid) -{ - struct process_queue_node *pqn; - - pqn = get_queue_by_qid(pqm, qid); - if (pqn && pqn->kq) - return pqn->kq; - - return NULL; -} - struct queue *pqm_get_user_queue(struct process_queue_manager *pqm, unsigned int qid) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index 62c635e9d1aa..4afff7094caf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -276,8 +276,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope /* EOP buffer is not required for all ASICs */ if (properties->eop_ring_buffer_address) { if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) { - pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n", - properties->eop_buf_bo->tbo.base.size, + pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n", + properties->eop_ring_buffer_size, topo_dev->node_props.eop_buffer_size); err = -EINVAL; goto out_err_unreserve; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index db3034b00dac..1a38ac75abbd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3011,7 +3011,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, /* check if this page fault time stamp is before svms->checkpoint_ts */ if (svms->checkpoint_ts[gpuidx] != 0) { - if (amdgpu_ih_ts_after(ts, svms->checkpoint_ts[gpuidx])) { + if (amdgpu_ih_ts_after_or_equal(ts, svms->checkpoint_ts[gpuidx])) { pr_debug("draining retry fault, drop fault 0x%llx\n", addr); r = 0; goto out; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index dbc5595e999a..27e7356eed6f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -519,6 +519,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->gpu->kfd->mec_fw_version); sysfs_show_32bit_prop(buffer, offs, "capability", dev->node_props.capability); + sysfs_show_32bit_prop(buffer, offs, "capability2", + dev->node_props.capability2); sysfs_show_64bit_prop(buffer, offs, "debug_prop", dev->node_props.debug_prop); sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version", @@ -1981,6 +1983,9 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev) if (kfd_dbg_has_ttmps_always_setup(dev->gpu)) dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID; + if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE) + dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED; + if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) { if (KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 3) || KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 4)) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index f06c9db7ddde..3de8ec0043bb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -51,6 +51,7 @@ struct kfd_node_properties { uint32_t cpu_core_id_base; uint32_t simd_id_base; uint32_t capability; + uint32_t capability2; uint64_t debug_prop; uint32_t max_waves_per_simd; uint32_t lds_size_in_kb; 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 16e4eb474eec..6a54f1cfa125 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -321,7 +321,7 @@ static int dm_crtc_get_scanoutpos(struct amdgpu_device *adev, int crtc, return 0; } -static bool dm_is_idle(void *handle) +static bool dm_is_idle(struct amdgpu_ip_block *ip_block) { /* XXX todo */ return true; @@ -1625,75 +1625,130 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev) return false; } -static const struct dmi_system_id hpd_disconnect_quirk_table[] = { +struct amdgpu_dm_quirks { + bool aux_hpd_discon; + bool support_edp0_on_dp1; +}; + +static struct amdgpu_dm_quirks quirk_entries = { + .aux_hpd_discon = false, + .support_edp0_on_dp1 = false +}; + +static int edp0_on_dp1_callback(const struct dmi_system_id *id) +{ + quirk_entries.support_edp0_on_dp1 = true; + return 0; +} + +static int aux_hpd_discon_callback(const struct dmi_system_id *id) +{ + quirk_entries.aux_hpd_discon = true; + return 0; +} + +static const struct dmi_system_id dmi_quirk_table[] = { { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"), }, }, { + .callback = aux_hpd_discon_callback, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"), }, }, + { + .callback = edp0_on_dp1_callback, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite mt645 G8 Mobile Thin Client"), + }, + }, + { + .callback = edp0_on_dp1_callback, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"), + }, + }, {} /* TODO: refactor this from a fixed table to a dynamic option */ }; -static void retrieve_dmi_info(struct amdgpu_display_manager *dm) +static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_data *init_data) { - const struct dmi_system_id *dmi_id; + int dmi_id; + struct drm_device *dev = dm->ddev; dm->aux_hpd_discon_quirk = false; + init_data->flags.support_edp0_on_dp1 = false; + + dmi_id = dmi_check_system(dmi_quirk_table); - dmi_id = dmi_first_match(hpd_disconnect_quirk_table); - if (dmi_id) { + if (!dmi_id) + return; + + if (quirk_entries.aux_hpd_discon) { dm->aux_hpd_discon_quirk = true; - DRM_INFO("aux_hpd_discon_quirk attached\n"); + drm_info(dev, "aux_hpd_discon_quirk attached\n"); + } + if (quirk_entries.support_edp0_on_dp1) { + init_data->flags.support_edp0_on_dp1 = true; + drm_info(dev, "aux_hpd_discon_quirk attached\n"); } } @@ -2002,7 +2057,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0)) init_data.num_virtual_links = 1; - retrieve_dmi_info(&adev->dm); + retrieve_dmi_info(&adev->dm, &init_data); if (adev->dm.bb_from_dmub) init_data.bb_from_dmub = adev->dm.bb_from_dmub; @@ -3031,10 +3086,11 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, } +DEFINE_FREE(state_release, struct dc_state *, if (_T) dc_state_release(_T)) + static enum dc_status amdgpu_dm_commit_zero_streams(struct dc *dc) { - struct dc_state *context = NULL; - enum dc_status res = DC_ERROR_UNEXPECTED; + struct dc_state *context __free(state_release) = NULL; int i; struct dc_stream_state *del_streams[MAX_PIPES]; int del_streams_count = 0; @@ -3044,7 +3100,7 @@ static enum dc_status amdgpu_dm_commit_zero_streams(struct dc *dc) context = dc_state_create_current_copy(dc); if (context == NULL) - goto context_alloc_fail; + return DC_ERROR_UNEXPECTED; /* First remove from context all streams */ for (i = 0; i < context->stream_count; i++) { @@ -3055,25 +3111,20 @@ static enum dc_status amdgpu_dm_commit_zero_streams(struct dc *dc) /* Remove all planes for removed streams and then remove the streams */ for (i = 0; i < del_streams_count; i++) { - if (!dc_state_rem_all_planes_for_stream(dc, del_streams[i], context)) { - res = DC_FAIL_DETACH_SURFACES; - goto fail; - } + enum dc_status res; + + if (!dc_state_rem_all_planes_for_stream(dc, del_streams[i], context)) + return DC_FAIL_DETACH_SURFACES; res = dc_state_remove_stream(dc, context, del_streams[i]); if (res != DC_OK) - goto fail; + return res; } params.streams = context->streams; params.stream_count = context->stream_count; - res = dc_commit_streams(dc, ¶ms); - -fail: - dc_state_release(context); -context_alloc_fail: - return res; + return dc_commit_streams(dc, ¶ms); } static void hpd_rx_irq_work_suspend(struct amdgpu_display_manager *dm) @@ -3090,9 +3141,10 @@ static int dm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; struct amdgpu_display_manager *dm = &adev->dm; - int ret = 0; if (amdgpu_in_reset(adev)) { + enum dc_status res; + mutex_lock(&dm->dc_lock); dc_allow_idle_optimizations(adev->dm.dc, false); @@ -3102,13 +3154,17 @@ static int dm_suspend(struct amdgpu_ip_block *ip_block) if (dm->cached_dc_state) dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); - amdgpu_dm_commit_zero_streams(dm->dc); + res = amdgpu_dm_commit_zero_streams(dm->dc); + if (res != DC_OK) { + drm_err(adev_to_drm(adev), "Failed to commit zero streams: %d\n", res); + return -EINVAL; + } amdgpu_dm_irq_suspend(adev); hpd_rx_irq_work_suspend(dm); - return ret; + return 0; } WARN_ON(adev->dm.cached_state); @@ -3245,14 +3301,14 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, struct dc_scaling_info scaling_infos[MAX_SURFACES]; struct dc_flip_addrs flip_addrs[MAX_SURFACES]; struct dc_stream_update stream_update; - } *bundle; + } *bundle __free(kfree); int k, m; bundle = kzalloc(sizeof(*bundle), GFP_KERNEL); if (!bundle) { drm_err(dm->ddev, "Failed to allocate update bundle\n"); - goto cleanup; + return; } for (k = 0; k < dc_state->stream_count; k++) { @@ -3272,9 +3328,24 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state, &bundle->stream_update, bundle->surface_updates); } +} -cleanup: - kfree(bundle); +static void apply_delay_after_dpcd_poweroff(struct amdgpu_device *adev, + struct dc_sink *sink) +{ + struct dc_panel_patch *ppatch = NULL; + + if (!sink) + return; + + ppatch = &sink->edid_caps.panel_patch; + if (ppatch->wait_after_dpcd_poweroff_ms) { + msleep(ppatch->wait_after_dpcd_poweroff_ms); + drm_dbg_driver(adev_to_drm(adev), + "%s: adding a %ds delay as w/a for panel\n", + __func__, + ppatch->wait_after_dpcd_poweroff_ms / 1000); + } } static int dm_resume(struct amdgpu_ip_block *ip_block) @@ -3323,7 +3394,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) r = dm_dmub_hw_init(adev); if (r) - DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); + drm_err(adev_to_drm(adev), "DMUB interface failed to initialize: status=%d\n", r); dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D0); dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0); @@ -3363,6 +3434,11 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) return 0; } + + /* leave display off for S4 sequence */ + if (adev->in_s4) + return 0; + /* Recreate dc_state - DC invalidates it when setting power state to S3. */ dc_state_release(dm_state->context); dm_state->context = dc_state_create(dm->dc, NULL); @@ -3398,6 +3474,7 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) /* Do detection*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { + bool ret; if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) continue; @@ -3414,17 +3491,20 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) if (aconnector->mst_root) continue; - mutex_lock(&aconnector->hpd_lock); + guard(mutex)(&aconnector->hpd_lock); if (!dc_link_detect_connection_type(aconnector->dc_link, &new_connection_type)) - DRM_ERROR("KMS: Failed to detect connector\n"); + drm_err(adev_to_drm(adev), "KMS: Failed to detect connector\n"); if (aconnector->base.force && new_connection_type == dc_connection_none) { emulated_link_detect(aconnector->dc_link); } else { - mutex_lock(&dm->dc_lock); + guard(mutex)(&dm->dc_lock); dc_exit_ips_for_hw_access(dm->dc); - dc_link_detect(aconnector->dc_link, DETECT_REASON_RESUMEFROMS3S4); - mutex_unlock(&dm->dc_lock); + ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_RESUMEFROMS3S4); + if (ret) { + /* w/a delay for certain panels */ + apply_delay_after_dpcd_poweroff(adev, aconnector->dc_sink); + } } if (aconnector->fake_enable && aconnector->dc_link->local_sink) @@ -3434,7 +3514,6 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; amdgpu_dm_update_connector_after_detect(aconnector); - mutex_unlock(&aconnector->hpd_lock); } drm_connector_list_iter_end(&iter); @@ -3603,12 +3682,14 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector) caps->min_input_signal = min_input_signal_override; } +DEFINE_FREE(sink_release, struct dc_sink *, if (_T) dc_sink_release(_T)) + void amdgpu_dm_update_connector_after_detect( struct amdgpu_dm_connector *aconnector) { struct drm_connector *connector = &aconnector->base; + struct dc_sink *sink __free(sink_release) = NULL; struct drm_device *dev = connector->dev; - struct dc_sink *sink; /* MST handled by drm_mst framework */ if (aconnector->mst_mgr.mst_state == true) @@ -3630,7 +3711,7 @@ void amdgpu_dm_update_connector_after_detect( * For S3 resume with headless use eml_sink to fake stream * because on resume connector->sink is set to NULL */ - mutex_lock(&dev->mode_config.mutex); + guard(mutex)(&dev->mode_config.mutex); if (sink) { if (aconnector->dc_sink) { @@ -3655,10 +3736,6 @@ void amdgpu_dm_update_connector_after_detect( } } - mutex_unlock(&dev->mode_config.mutex); - - if (sink) - dc_sink_release(sink); return; } @@ -3666,10 +3743,8 @@ void amdgpu_dm_update_connector_after_detect( * TODO: temporary guard to look for proper fix * if this sink is MST sink, we should not do anything */ - if (sink && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - dc_sink_release(sink); + if (sink && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) return; - } if (aconnector->dc_sink == sink) { /* @@ -3678,15 +3753,13 @@ void amdgpu_dm_update_connector_after_detect( */ drm_dbg_kms(dev, "DCHPD: connector_id=%d: dc_sink didn't change.\n", aconnector->connector_id); - if (sink) - dc_sink_release(sink); return; } drm_dbg_kms(dev, "DCHPD: connector_id=%d: Old sink=%p New sink=%p\n", aconnector->connector_id, aconnector->dc_sink, sink); - mutex_lock(&dev->mode_config.mutex); + guard(mutex)(&dev->mode_config.mutex); /* * 1. Update status of the drm connector @@ -3748,12 +3821,7 @@ void amdgpu_dm_update_connector_after_detect( connector->state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; } - mutex_unlock(&dev->mode_config.mutex); - update_subconnector_property(aconnector); - - if (sink) - dc_sink_release(sink); } static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) @@ -3773,7 +3841,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) * In case of failure or MST no need to update connector status or notify the OS * since (for MST case) MST does this in its own context. */ - mutex_lock(&aconnector->hpd_lock); + guard(mutex)(&aconnector->hpd_lock); if (adev->dm.hdcp_workqueue) { hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index); @@ -3785,7 +3853,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) aconnector->timing_changed = false; if (!dc_link_detect_connection_type(aconnector->dc_link, &new_connection_type)) - DRM_ERROR("KMS: Failed to detect connector\n"); + drm_err(adev_to_drm(adev), "KMS: Failed to detect connector\n"); if (aconnector->base.force && new_connection_type == dc_connection_none) { emulated_link_detect(aconnector->dc_link); @@ -3797,11 +3865,13 @@ 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 { - mutex_lock(&adev->dm.dc_lock); - dc_exit_ips_for_hw_access(dc); - ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); - mutex_unlock(&adev->dm.dc_lock); + scoped_guard(mutex, &adev->dm.dc_lock) { + dc_exit_ips_for_hw_access(dc); + ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + } if (ret) { + /* w/a delay for certain panels */ + apply_delay_after_dpcd_poweroff(adev, aconnector->dc_sink); amdgpu_dm_update_connector_after_detect(aconnector); drm_modeset_lock_all(dev); @@ -3812,8 +3882,6 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) drm_kms_helper_connector_hotplug_event(connector); } } - mutex_unlock(&aconnector->hpd_lock); - } static void handle_hpd_irq(void *param) @@ -4653,48 +4721,40 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, int bl_idx) { -#if defined(CONFIG_ACPI) - struct amdgpu_dm_backlight_caps caps; + struct amdgpu_dm_backlight_caps *caps = &dm->backlight_caps[bl_idx]; - memset(&caps, 0, sizeof(caps)); - - if (dm->backlight_caps[bl_idx].caps_valid) + if (caps->caps_valid) return; - amdgpu_acpi_get_backlight_caps(&caps); +#if defined(CONFIG_ACPI) + amdgpu_acpi_get_backlight_caps(caps); /* validate the firmware value is sane */ - if (caps.caps_valid) { - int spread = caps.max_input_signal - caps.min_input_signal; + if (caps->caps_valid) { + int spread = caps->max_input_signal - caps->min_input_signal; - if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || - caps.min_input_signal < 0 || + if (caps->max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + caps->min_input_signal < 0 || spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || spread < AMDGPU_DM_MIN_SPREAD) { DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n", - caps.min_input_signal, caps.max_input_signal); - caps.caps_valid = false; + caps->min_input_signal, caps->max_input_signal); + caps->caps_valid = false; } } - if (caps.caps_valid) { - dm->backlight_caps[bl_idx].caps_valid = true; - if (caps.aux_support) - return; - dm->backlight_caps[bl_idx].min_input_signal = caps.min_input_signal; - dm->backlight_caps[bl_idx].max_input_signal = caps.max_input_signal; - } else { - dm->backlight_caps[bl_idx].min_input_signal = - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; - dm->backlight_caps[bl_idx].max_input_signal = - AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + if (!caps->caps_valid) { + caps->min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; + caps->max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + caps->caps_valid = true; } #else - if (dm->backlight_caps[bl_idx].aux_support) + if (caps->aux_support) return; - dm->backlight_caps[bl_idx].min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; - dm->backlight_caps[bl_idx].max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + caps->min_input_signal = AMDGPU_DM_DEFAULT_MIN_BACKLIGHT; + caps->max_input_signal = AMDGPU_DM_DEFAULT_MAX_BACKLIGHT; + caps->caps_valid = true; #endif } @@ -4720,10 +4780,38 @@ static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *c uint32_t brightness) { unsigned int min, max; + u8 prev_signal = 0, prev_lum = 0; if (!get_brightness_range(caps, &min, &max)) return brightness; + for (int i = 0; i < caps->data_points; i++) { + u8 signal, lum; + + if (amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE) + break; + + signal = caps->luminance_data[i].input_signal; + lum = caps->luminance_data[i].luminance; + + /* + * brightness == signal: luminance is percent numerator + * brightness < signal: interpolate between previous and current luminance numerator + * brightness > signal: find next data point + */ + if (brightness < signal) + lum = prev_lum + DIV_ROUND_CLOSEST((lum - prev_lum) * + (brightness - prev_signal), + signal - prev_signal); + else if (brightness > signal) { + prev_signal = signal; + prev_lum = lum; + continue; + } + brightness = DIV_ROUND_CLOSEST(lum * brightness, 101); + break; + } + // Rescale 0..255 to min..max return min + DIV_ROUND_CLOSEST((max - min) * brightness, AMDGPU_MAX_BL_LEVEL); @@ -4748,19 +4836,19 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { - struct amdgpu_dm_backlight_caps caps; + struct amdgpu_dm_backlight_caps *caps; struct dc_link *link; u32 brightness; bool rc, reallow_idle = false; amdgpu_dm_update_backlight_caps(dm, bl_idx); - caps = dm->backlight_caps[bl_idx]; + caps = &dm->backlight_caps[bl_idx]; dm->brightness[bl_idx] = user_brightness; /* update scratch register */ if (bl_idx == 0) amdgpu_atombios_scratch_regs_set_backlight_level(dm->adev, dm->brightness[bl_idx]); - brightness = convert_brightness_from_user(&caps, dm->brightness[bl_idx]); + brightness = convert_brightness_from_user(caps, dm->brightness[bl_idx]); link = (struct dc_link *)dm->backlight_link[bl_idx]; /* Change brightness based on AUX property */ @@ -4770,7 +4858,7 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, reallow_idle = true; } - if (caps.aux_support) { + if (caps->aux_support) { rc = dc_link_set_backlight_level_nits(link, true, brightness, AUX_BL_DEFAULT_TRANSITION_TIME_MS); if (!rc) @@ -4887,6 +4975,8 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) } else props.brightness = AMDGPU_MAX_BL_LEVEL; + if (caps.data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) + drm_info(drm, "Using custom brightness curve\n"); props.max_brightness = AMDGPU_MAX_BL_LEVEL; props.type = BACKLIGHT_RAW; @@ -7295,8 +7385,14 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector) struct dc_link *dc_link = aconnector->dc_link; struct dc_sink *dc_em_sink = aconnector->dc_em_sink; const struct drm_edid *drm_edid; + struct i2c_adapter *ddc; + + if (dc_link && dc_link->aux_mode) + ddc = &aconnector->dm_dp_aux.aux.ddc; + else + ddc = &aconnector->i2c->base; - drm_edid = drm_edid_read(connector); + drm_edid = drm_edid_read_ddc(connector, ddc); drm_edid_connector_update(connector, drm_edid); if (!drm_edid) { DRM_ERROR("No EDID found on connector: %s.\n", connector->name); @@ -7341,14 +7437,21 @@ static int get_modes(struct drm_connector *connector) static void create_eml_sink(struct amdgpu_dm_connector *aconnector) { struct drm_connector *connector = &aconnector->base; + struct dc_link *dc_link = aconnector->dc_link; struct dc_sink_init_data init_params = { .link = aconnector->dc_link, .sink_signal = SIGNAL_TYPE_VIRTUAL }; const struct drm_edid *drm_edid; const struct edid *edid; + struct i2c_adapter *ddc; + + if (dc_link && dc_link->aux_mode) + ddc = &aconnector->dm_dp_aux.aux.ddc; + else + ddc = &aconnector->i2c->base; - drm_edid = drm_edid_read(connector); + drm_edid = drm_edid_read_ddc(connector, ddc); drm_edid_connector_update(connector, drm_edid); if (!drm_edid) { DRM_ERROR("No EDID found on connector: %s.\n", connector->name); @@ -12655,3 +12758,10 @@ bool dm_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned int count, { return dc_dmub_srv_cmd_run_list(ctx->dmub_srv, count, cmd, wait_type); } + +void dm_acpi_process_phy_transition_interlock( + const struct dc_context *ctx, + struct dm_process_phy_transition_init_params process_phy_transition_init_params) +{ + // Not yet implemented +} 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 acead14ab45d..385faaca6e26 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -151,6 +151,18 @@ struct idle_workqueue { bool running; }; +#define MAX_LUMINANCE_DATA_POINTS 99 + +/** + * struct amdgpu_dm_luminance_data - Custom luminance data + * @luminance: Luminance in percent + * @input_signal: Input signal in range 0-255 + */ +struct amdgpu_dm_luminance_data { + u8 luminance; + u8 input_signal; +} __packed; + /** * struct amdgpu_dm_backlight_caps - Information about backlight * @@ -195,6 +207,14 @@ struct amdgpu_dm_backlight_caps { * @dc_level: the default brightness if booted on DC */ u8 dc_level; + /** + * @data_points: the number of custom luminance data points + */ + u8 data_points; + /** + * @luminance_data: custom luminance data + */ + struct amdgpu_dm_luminance_data luminance_data[MAX_LUMINANCE_DATA_POINTS]; }; /** 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 fbd80d8545a8..2cd35392e2da 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 @@ -55,16 +55,21 @@ static u32 edid_extract_panel_id(struct edid *edid) (u32)EDID_PRODUCT_ID(edid); } -static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) +static void apply_edid_quirks(struct drm_device *dev, struct edid *edid, struct dc_edid_caps *edid_caps) { uint32_t panel_id = edid_extract_panel_id(edid); switch (panel_id) { + /* Workaround for monitors that need a delay after detecting the link */ + case drm_edid_encode_panel_id('G', 'B', 'T', 0x3215): + drm_dbg_driver(dev, "Add 10s delay for link detection for panel id %X\n", panel_id); + edid_caps->panel_patch.wait_after_dpcd_poweroff_ms = 10000; + break; /* Workaround for some monitors which does not work well with FAMS */ case drm_edid_encode_panel_id('S', 'A', 'M', 0x0E5E): case drm_edid_encode_panel_id('S', 'A', 'M', 0x7053): case drm_edid_encode_panel_id('S', 'A', 'M', 0x71AC): - DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id); + drm_dbg_driver(dev, "Disabling FAMS on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_fams = true; break; /* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */ @@ -73,11 +78,11 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A): case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1): case drm_edid_encode_panel_id('M', 'S', 'F', 0x1003): - DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); + drm_dbg_driver(dev, "Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.remove_sink_ext_caps = true; break; case drm_edid_encode_panel_id('S', 'D', 'C', 0x4154): - DRM_DEBUG_DRIVER("Disabling VSC on monitor with panel id %X\n", panel_id); + drm_dbg_driver(dev, "Disabling VSC on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_colorimetry = true; break; default: @@ -101,6 +106,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( { struct amdgpu_dm_connector *aconnector = link->priv; struct drm_connector *connector = &aconnector->base; + struct drm_device *dev = connector->dev; struct edid *edid_buf = edid ? (struct edid *) edid->raw_edid : NULL; struct cea_sad *sads; int sad_count = -1; @@ -130,7 +136,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; - apply_edid_quirks(edid_buf, edid_caps); + apply_edid_quirks(dev, edid_buf, edid_caps); sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 3390f0d8420a..2b63cbab0e87 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -473,7 +473,7 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev) unregister_all_irq_handlers(adev); } -int amdgpu_dm_irq_suspend(struct amdgpu_device *adev) +void amdgpu_dm_irq_suspend(struct amdgpu_device *adev) { int src; struct list_head *hnd_list_h; @@ -511,10 +511,9 @@ int amdgpu_dm_irq_suspend(struct amdgpu_device *adev) } DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); - return 0; } -int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) +void amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) { int src; struct list_head *hnd_list_h, *hnd_list_l; @@ -522,7 +521,7 @@ int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) DM_IRQ_TABLE_LOCK(adev, irq_table_flags); - DRM_DEBUG_KMS("DM_IRQ: early resume\n"); + drm_dbg(adev_to_drm(adev), "DM_IRQ: early resume\n"); /* re-enable short pulse interrupts HW interrupt */ for (src = DC_IRQ_SOURCE_HPD1RX; src <= DC_IRQ_SOURCE_HPD6RX; src++) { @@ -533,11 +532,9 @@ int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev) } DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); - - return 0; } -int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) +void amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) { int src; struct list_head *hnd_list_h, *hnd_list_l; @@ -545,7 +542,7 @@ int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) DM_IRQ_TABLE_LOCK(adev, irq_table_flags); - DRM_DEBUG_KMS("DM_IRQ: resume\n"); + drm_dbg(adev_to_drm(adev), "DM_IRQ: resume\n"); /** * Renable HW interrupt for HPD and only since FLIP and VBLANK @@ -559,7 +556,6 @@ int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev) } DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); - return 0; } /* @@ -894,6 +890,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev) struct drm_device *dev = adev_to_drm(adev); struct drm_connector *connector; struct drm_connector_list_iter iter; + int i; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -920,6 +917,12 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev) } } drm_connector_list_iter_end(&iter); + + /* Update reference counts for HPDs */ + for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) { + if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1)) + drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i); + } } /** @@ -935,6 +938,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev) struct drm_device *dev = adev_to_drm(adev); struct drm_connector *connector; struct drm_connector_list_iter iter; + int i; drm_connector_list_iter_begin(dev, &iter); drm_for_each_connector_iter(connector, &iter) { @@ -960,4 +964,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev) } } drm_connector_list_iter_end(&iter); + + /* Update reference counts for HPDs */ + for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) { + if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1)) + drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i); + } } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h index 2349238a626b..ba17c23b2706 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h @@ -90,14 +90,14 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev); * amdgpu_dm_irq_suspend - disable ASIC interrupt during suspend. * */ -int amdgpu_dm_irq_suspend(struct amdgpu_device *adev); +void amdgpu_dm_irq_suspend(struct amdgpu_device *adev); /** * amdgpu_dm_irq_resume_early - enable HPDRX ASIC interrupts during resume. * amdgpu_dm_irq_resume - enable ASIC interrupt during resume. * */ -int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev); -int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev); +void amdgpu_dm_irq_resume_early(struct amdgpu_device *adev); +void amdgpu_dm_irq_resume_late(struct amdgpu_device *adev); #endif /* __AMDGPU_DM_IRQ_H__ */ 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 056b17198956..7ceedf626d23 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 @@ -1632,6 +1632,9 @@ int pre_validate_dsc(struct drm_atomic_state *state, connector = amdgpu_dm_find_first_crtc_matching_connector(state, state->crtcs[ind].ptr); + if (!connector) + continue; + drm_new_conn_state = drm_atomic_get_new_connector_state(state, connector); 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 fcb0e900a38a..0090e08d5057 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 @@ -277,8 +277,11 @@ static int amdgpu_dm_plane_validate_dcc(struct amdgpu_device *adev, if (!dcc->enable) return 0; - if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || - !dc->cap_funcs.get_dcc_compression_cap) + if (adev->family < AMDGPU_FAMILY_GC_12_0_0 && + format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) + return -EINVAL; + + if (!dc->cap_funcs.get_dcc_compression_cap) return -EINVAL; input.format = format; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index 104f03868266..e140b7a04d72 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -30,23 +30,6 @@ #include "amdgpu_dm.h" #include "modules/power/power_helpers.h" -static bool is_specific_oled_panel(struct dc_link *link) -{ - if (!link->dpcd_sink_ext_caps.bits.oled) - return false; - - /* Disable PSR-SU for some OLED panels to avoid glitches */ - if (link->dpcd_caps.sink_dev_id == 0xBA4159) { - uint8_t sink_dev_id_str1[] = {'4', '0', 'C', 'U', '1'}; - - if (!memcmp(link->dpcd_caps.sink_dev_id_str, sink_dev_id_str1, - sizeof(sink_dev_id_str1))) - return true; - } - - return false; -} - static bool link_supports_psrsu(struct dc_link *link) { struct dc *dc = link->ctx->dc; @@ -57,9 +40,6 @@ static bool link_supports_psrsu(struct dc_link *link) if (dc->ctx->dce_version < DCN_VERSION_3_1) return false; - if (is_specific_oled_panel(link)) - return false; - if (!is_psr_su_specific_panel(link)) return false; @@ -74,7 +54,8 @@ static bool link_supports_psrsu(struct dc_link *link) if (amdgpu_dc_debug_mask & DC_DISABLE_PSR_SU) return false; - return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub); + /* Temporarily disable PSR-SU to avoid glitches */ + return false; } /* diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index 7d18f372ce7a..2c645dffec18 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -101,7 +101,6 @@ static void init_dig_encoder_control(struct bios_parser *bp) bp->cmd_tbl.dig_encoder_control = encoder_control_digx_v1_5; break; default: - dm_output_to_console("Don't have dig_encoder_control for v%d\n", version); bp->cmd_tbl.dig_encoder_control = encoder_control_fallback; break; } @@ -210,6 +209,7 @@ static enum bp_result encoder_control_fallback( ****************************************************************************** *****************************************************************************/ + static enum bp_result transmitter_control_v1_6( struct bios_parser *bp, struct bp_transmitter_control *cntl); @@ -238,7 +238,6 @@ static void init_transmitter_control(struct bios_parser *bp) bp->cmd_tbl.transmitter_control = transmitter_control_v1_7; break; default: - dm_output_to_console("Don't have transmitter_control for v%d\n", crev); bp->cmd_tbl.transmitter_control = transmitter_control_fallback; break; } @@ -325,6 +324,21 @@ static void transmitter_control_dmcub_v1_7( dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } +static struct dc_link *get_link_by_phy_id(struct dc *p_dc, uint32_t phy_id) +{ + struct dc_link *link = NULL; + + // Get Transition Bitmask from dc_link structure associated with PHY + for (uint8_t link_id = 0; link_id < MAX_LINKS; link_id++) { + if (phy_id == p_dc->links[link_id]->link_enc->transmitter) { + link = p_dc->links[link_id]; + break; + } + } + + return link; +} + static enum bp_result transmitter_control_v1_7( struct bios_parser *bp, struct bp_transmitter_control *cntl) @@ -363,7 +377,37 @@ static enum bp_result transmitter_control_v1_7( if (bp->base.ctx->dc->ctx->dmub_srv && bp->base.ctx->dc->debug.dmub_command_table) { + struct dm_process_phy_transition_init_params process_phy_transition_init_params = {0}; + struct dc_link *link = get_link_by_phy_id(bp->base.ctx->dc, dig_v1_7.phyid); + bool is_phy_transition_interlock_allowed = false; + uint8_t action = dig_v1_7.action; + + if (link) { + if (link->phy_transition_bitmask && + (action == TRANSMITTER_CONTROL_ENABLE || action == TRANSMITTER_CONTROL_DISABLE)) { + is_phy_transition_interlock_allowed = true; + + // Prepare input parameters for processing ACPI retimers + process_phy_transition_init_params.action = action; + process_phy_transition_init_params.display_port_lanes_count = cntl->lanes_number; + process_phy_transition_init_params.phy_id = dig_v1_7.phyid; + process_phy_transition_init_params.signal = cntl->signal; + process_phy_transition_init_params.sym_clock_10khz = dig_v1_7.symclk_units.symclk_10khz; + process_phy_transition_init_params.display_port_link_rate = link->cur_link_settings.link_rate; + process_phy_transition_init_params.transition_bitmask = link->phy_transition_bitmask; + } + } + + // Handle PRE_OFF_TO_ON: Process ACPI PHY Transition Interlock + if (is_phy_transition_interlock_allowed && action == TRANSMITTER_CONTROL_ENABLE) + dm_acpi_process_phy_transition_interlock(bp->base.ctx, process_phy_transition_init_params); + transmitter_control_dmcub_v1_7(bp->base.ctx->dmub_srv, &dig_v1_7); + + // Handle POST_ON_TO_OFF: Process ACPI PHY Transition Interlock + if (is_phy_transition_interlock_allowed && action == TRANSMITTER_CONTROL_DISABLE) + dm_acpi_process_phy_transition_interlock(bp->base.ctx, process_phy_transition_init_params); + return BP_RESULT_OK; } @@ -408,8 +452,6 @@ static void init_set_pixel_clock(struct bios_parser *bp) bp->cmd_tbl.set_pixel_clock = set_pixel_clock_v7; break; default: - dm_output_to_console("Don't have set_pixel_clock for v%d\n", - BIOS_CMD_TABLE_PARA_REVISION(setpixelclock)); bp->cmd_tbl.set_pixel_clock = set_pixel_clock_fallback; break; } @@ -554,7 +596,6 @@ static void init_set_crtc_timing(struct bios_parser *bp) set_crtc_using_dtd_timing_v3; break; default: - dm_output_to_console("Don't have set_crtc_timing for v%d\n", dtd_version); bp->cmd_tbl.set_crtc_timing = NULL; break; } @@ -671,8 +712,6 @@ static void init_enable_crtc(struct bios_parser *bp) bp->cmd_tbl.enable_crtc = enable_crtc_v1; break; default: - dm_output_to_console("Don't have enable_crtc for v%d\n", - BIOS_CMD_TABLE_PARA_REVISION(enablecrtc)); bp->cmd_tbl.enable_crtc = NULL; break; } @@ -864,8 +903,6 @@ static void init_set_dce_clock(struct bios_parser *bp) bp->cmd_tbl.set_dce_clock = set_dce_clock_v2_1; break; default: - dm_output_to_console("Don't have set_dce_clock for v%d\n", - BIOS_CMD_TABLE_PARA_REVISION(setdceclock)); bp->cmd_tbl.set_dce_clock = NULL; break; } @@ -1046,3 +1083,4 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) init_enable_lvtma_control(bp); } + diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c index e317a3615147..91bc8a06e2cf 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.c @@ -293,3 +293,107 @@ uint8_t dal_cmd_table_helper_encoder_id_to_atom( return ENCODER_OBJECT_ID_NONE; } } + +uint8_t phy_id_to_atom(enum transmitter t) +{ + uint8_t atom_phy_id; + + switch (t) { + case TRANSMITTER_UNIPHY_A: + atom_phy_id = ATOM_PHY_ID_UNIPHYA; + break; + case TRANSMITTER_UNIPHY_B: + atom_phy_id = ATOM_PHY_ID_UNIPHYB; + break; + case TRANSMITTER_UNIPHY_C: + atom_phy_id = ATOM_PHY_ID_UNIPHYC; + break; + case TRANSMITTER_UNIPHY_D: + atom_phy_id = ATOM_PHY_ID_UNIPHYD; + break; + case TRANSMITTER_UNIPHY_E: + atom_phy_id = ATOM_PHY_ID_UNIPHYE; + break; + case TRANSMITTER_UNIPHY_F: + atom_phy_id = ATOM_PHY_ID_UNIPHYF; + break; + case TRANSMITTER_UNIPHY_G: + atom_phy_id = ATOM_PHY_ID_UNIPHYG; + break; + default: + atom_phy_id = ATOM_PHY_ID_UNIPHYA; + break; + } + return atom_phy_id; +} + +uint8_t clock_source_id_to_atom_phy_clk_src_id( + enum clock_source_id id) +{ + uint8_t atom_phy_clk_src_id = 0; + + switch (id) { + case CLOCK_SOURCE_ID_PLL0: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; + break; + case CLOCK_SOURCE_ID_PLL1: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; + break; + case CLOCK_SOURCE_ID_PLL2: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; + break; + case CLOCK_SOURCE_ID_EXTERNAL: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; + break; + default: + atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; + break; + } + + return atom_phy_clk_src_id >> 2; +} + +bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) +{ + bool result = false; + + if (atom_engine_id != NULL) + switch (id) { + case ENGINE_ID_DIGA: + *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGB: + *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGC: + *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGD: + *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGE: + *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGF: + *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DIGG: + *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; + result = true; + break; + case ENGINE_ID_DACA: + *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; + result = true; + break; + default: + break; + } + + return result; +} diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h index dfd30aaf4032..547700e119a6 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper.h @@ -59,4 +59,12 @@ uint8_t dal_cmd_table_helper_transmitter_bp_to_atom( uint8_t dal_cmd_table_helper_encoder_id_to_atom( enum encoder_id id); + +uint8_t phy_id_to_atom(enum transmitter t); + +uint8_t clock_source_id_to_atom_phy_clk_src_id( + enum clock_source_id id); + +bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c index bad4e4711b4f..268e2414b34f 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c @@ -88,8 +88,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2( return true; default: - /* Unsupported DCE */ - BREAK_TO_DEBUGGER(); + *h = dal_cmd_tbl_helper_dce112_get_table2(); return false; } } diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c b/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c index 11bf247bb180..3099128223df 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce110/command_table_helper_dce110.c @@ -31,39 +31,6 @@ #include "../command_table_helper.h" -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP; @@ -94,32 +61,6 @@ static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) return atom_dig_mode; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t hpd_sel_to_atom(enum hpd_source_id id) { uint8_t atom_hpd_sel = 0; @@ -207,51 +148,6 @@ static bool clock_source_id_to_atom( return result; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) { uint8_t atom_action = 0; diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c index 755b6e33140a..349f0e5d5856 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper2_dce112.c @@ -29,40 +29,9 @@ #include "include/bios_parser_types.h" -#include "../command_table_helper2.h" - -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; +#include "../command_table_helper.h" - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} +#include "../command_table_helper2.h" static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { @@ -91,32 +60,6 @@ static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) return atom_dig_mode; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t hpd_sel_to_atom(enum hpd_source_id id) { uint8_t atom_hpd_sel = 0; @@ -209,51 +152,6 @@ static bool clock_source_id_to_atom( return result; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) { uint8_t atom_action = 0; diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c index 06b4f7fa4a50..1a5fefcde8af 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce112/command_table_helper_dce112.c @@ -31,39 +31,6 @@ #include "../command_table_helper.h" -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V6_DP; @@ -91,32 +58,6 @@ static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) return atom_dig_mode; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t hpd_sel_to_atom(enum hpd_source_id id) { uint8_t atom_hpd_sel = 0; @@ -209,51 +150,6 @@ static bool clock_source_id_to_atom( return result; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) { uint8_t atom_action = 0; diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c index 710221b4f5c5..01ccc803040c 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce60/command_table_helper_dce60.c @@ -58,51 +58,6 @@ static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) return atom_action; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static bool clock_source_id_to_atom( enum clock_source_id id, uint32_t *atom_pll_id) @@ -149,32 +104,6 @@ static bool clock_source_id_to_atom( return result; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP; @@ -270,39 +199,6 @@ static uint8_t dig_encoder_sel_to_atom(enum engine_id id) return atom_dig_encoder_sel; } -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t disp_power_gating_action_to_atom( enum bp_pipe_control_action action) { diff --git a/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c b/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c index 8b30b558cf1f..2ec5264536c7 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c +++ b/drivers/gpu/drm/amd/display/dc/bios/dce80/command_table_helper_dce80.c @@ -58,51 +58,6 @@ static uint8_t encoder_action_to_atom(enum bp_encoder_control_action action) return atom_action; } -static bool engine_bp_to_atom(enum engine_id id, uint32_t *atom_engine_id) -{ - bool result = false; - - if (atom_engine_id != NULL) - switch (id) { - case ENGINE_ID_DIGA: - *atom_engine_id = ASIC_INT_DIG1_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGB: - *atom_engine_id = ASIC_INT_DIG2_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGC: - *atom_engine_id = ASIC_INT_DIG3_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGD: - *atom_engine_id = ASIC_INT_DIG4_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGE: - *atom_engine_id = ASIC_INT_DIG5_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGF: - *atom_engine_id = ASIC_INT_DIG6_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DIGG: - *atom_engine_id = ASIC_INT_DIG7_ENCODER_ID; - result = true; - break; - case ENGINE_ID_DACA: - *atom_engine_id = ASIC_INT_DAC1_ENCODER_ID; - result = true; - break; - default: - break; - } - - return result; -} - static bool clock_source_id_to_atom( enum clock_source_id id, uint32_t *atom_pll_id) @@ -149,32 +104,6 @@ static bool clock_source_id_to_atom( return result; } -static uint8_t clock_source_id_to_atom_phy_clk_src_id( - enum clock_source_id id) -{ - uint8_t atom_phy_clk_src_id = 0; - - switch (id) { - case CLOCK_SOURCE_ID_PLL0: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P0PLL; - break; - case CLOCK_SOURCE_ID_PLL1: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - case CLOCK_SOURCE_ID_PLL2: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P2PLL; - break; - case CLOCK_SOURCE_ID_EXTERNAL: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_REFCLK_SRC_EXT; - break; - default: - atom_phy_clk_src_id = ATOM_TRANSMITTER_CONFIG_V5_P1PLL; - break; - } - - return atom_phy_clk_src_id >> 2; -} - static uint8_t signal_type_to_atom_dig_mode(enum signal_type s) { uint8_t atom_dig_mode = ATOM_TRANSMITTER_DIGMODE_V5_DP; @@ -270,39 +199,6 @@ static uint8_t dig_encoder_sel_to_atom(enum engine_id id) return atom_dig_encoder_sel; } -static uint8_t phy_id_to_atom(enum transmitter t) -{ - uint8_t atom_phy_id; - - switch (t) { - case TRANSMITTER_UNIPHY_A: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - case TRANSMITTER_UNIPHY_B: - atom_phy_id = ATOM_PHY_ID_UNIPHYB; - break; - case TRANSMITTER_UNIPHY_C: - atom_phy_id = ATOM_PHY_ID_UNIPHYC; - break; - case TRANSMITTER_UNIPHY_D: - atom_phy_id = ATOM_PHY_ID_UNIPHYD; - break; - case TRANSMITTER_UNIPHY_E: - atom_phy_id = ATOM_PHY_ID_UNIPHYE; - break; - case TRANSMITTER_UNIPHY_F: - atom_phy_id = ATOM_PHY_ID_UNIPHYF; - break; - case TRANSMITTER_UNIPHY_G: - atom_phy_id = ATOM_PHY_ID_UNIPHYG; - break; - default: - atom_phy_id = ATOM_PHY_ID_UNIPHYA; - break; - } - return atom_phy_id; -} - static uint8_t disp_power_gating_action_to_atom( enum bp_pipe_control_action action) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index df29d28d89c9..af722519a1fa 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -201,16 +201,26 @@ static void dcn35_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state * struct pipe_ctx *pipe = safe_to_lower ? &context->res_ctx.pipe_ctx[i] : &dc->current_state->res_ctx.pipe_ctx[i]; + struct link_encoder *new_pipe_link_enc = new_pipe->link_res.dio_link_enc; + struct link_encoder *pipe_link_enc = pipe->link_res.dio_link_enc; bool stream_changed_otg_dig_on = false; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; + + if (!dc->config.unify_link_enc_assignment) { + if (new_pipe->stream) + new_pipe_link_enc = new_pipe->stream->link_enc; + if (pipe->stream) + pipe_link_enc = pipe->stream->link_enc; + } + stream_changed_otg_dig_on = old_pipe->stream && new_pipe->stream && old_pipe->stream != new_pipe->stream && old_pipe->stream_res.tg == new_pipe->stream_res.tg && - new_pipe->stream->link_enc && !new_pipe->stream->dpms_off && - new_pipe->stream->link_enc->funcs->is_dig_enabled && - new_pipe->stream->link_enc->funcs->is_dig_enabled( - new_pipe->stream->link_enc) && + new_pipe_link_enc && !new_pipe->stream->dpms_off && + new_pipe_link_enc->funcs->is_dig_enabled && + new_pipe_link_enc->funcs->is_dig_enabled( + new_pipe_link_enc) && new_pipe->stream_res.stream_enc && new_pipe->stream_res.stream_enc->funcs->is_fifo_enabled && new_pipe->stream_res.stream_enc->funcs->is_fifo_enabled(new_pipe->stream_res.stream_enc); @@ -226,7 +236,7 @@ static void dcn35_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state * if (!has_active_hpo && !dccg->ctx->dc->link_srv->dp_is_128b_132b_signal(pipe) && (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) || - !pipe->stream->link_enc) && !stream_changed_otg_dig_on)) { + !pipe_link_enc) && !stream_changed_otg_dig_on)) { /* This w/a should not trigger when we have a dig active */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 05ad7a9af4ff..e71ea21401f5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -905,7 +905,8 @@ void dc_stream_set_static_screen_params(struct dc *dc, static void dc_destruct(struct dc *dc) { // reset link encoder assignment table on destruct - if (dc->res_pool && dc->res_pool->funcs->link_encs_assign) + if (dc->res_pool && dc->res_pool->funcs->link_encs_assign && + !dc->config.unify_link_enc_assignment) link_enc_cfg_init(dc, dc->current_state); if (dc->current_state) { @@ -1201,6 +1202,8 @@ static void dc_update_visual_confirm_color(struct dc *dc, struct dc_state *conte get_surface_tile_visual_confirm_color(pipe_ctx, &(pipe_ctx->visual_confirm_color)); else if (dc->debug.visual_confirm == VISUAL_CONFIRM_HW_CURSOR) get_cursor_visual_confirm_color(pipe_ctx, &(pipe_ctx->visual_confirm_color)); + else if (dc->debug.visual_confirm == VISUAL_CONFIRM_DCC) + get_dcc_visual_confirm_color(dc, pipe_ctx, &(pipe_ctx->visual_confirm_color)); else { if (dc->ctx->dce_version < DCN_VERSION_2_0) color_space_to_black_color( @@ -3955,6 +3958,9 @@ static void commit_planes_for_stream(struct dc *dc, if (update_type == UPDATE_TYPE_FULL && dc->optimized_required) hwss_process_outstanding_hw_updates(dc, dc->current_state); + if (update_type != UPDATE_TYPE_FAST && dc->res_pool->funcs->prepare_mcache_programming) + dc->res_pool->funcs->prepare_mcache_programming(dc, context); + for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; @@ -4013,9 +4019,6 @@ static void commit_planes_for_stream(struct dc *dc, odm_pipe->ttu_regs.min_ttu_vblank = MAX_TTU; } - if (update_type != UPDATE_TYPE_FAST && dc->res_pool->funcs->prepare_mcache_programming) - dc->res_pool->funcs->prepare_mcache_programming(dc, context); - if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) if (top_pipe_to_program && top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { @@ -4937,7 +4940,8 @@ static bool full_update_required(struct dc *dc, stream_update->lut3d_func || stream_update->pending_test_pattern || stream_update->crtc_timing_adjust || - stream_update->scaler_sharpener_update)) + stream_update->scaler_sharpener_update || + stream_update->hw_cursor_req)) return true; if (stream) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c index af1ea5792560..650e89825968 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c @@ -51,126 +51,6 @@ DC_LOG_BANDWIDTH_CALCS(__VA_ARGS__); \ } while (0) -void pre_surface_trace( - struct dc *dc, - const struct dc_plane_state *const *plane_states, - int surface_count) -{ - int i; - DC_LOGGER_INIT(dc->ctx->logger); - - for (i = 0; i < surface_count; i++) { - const struct dc_plane_state *plane_state = plane_states[i]; - - SURFACE_TRACE("Planes %d:\n", i); - - SURFACE_TRACE( - "plane_state->visible = %d;\n" - "plane_state->flip_immediate = %d;\n" - "plane_state->address.type = %d;\n" - "plane_state->address.grph.addr.quad_part = 0x%llX;\n" - "plane_state->address.grph.meta_addr.quad_part = 0x%llX;\n" - "plane_state->scaling_quality.h_taps = %d;\n" - "plane_state->scaling_quality.v_taps = %d;\n" - "plane_state->scaling_quality.h_taps_c = %d;\n" - "plane_state->scaling_quality.v_taps_c = %d;\n", - plane_state->visible, - plane_state->flip_immediate, - plane_state->address.type, - plane_state->address.grph.addr.quad_part, - plane_state->address.grph.meta_addr.quad_part, - plane_state->scaling_quality.h_taps, - plane_state->scaling_quality.v_taps, - plane_state->scaling_quality.h_taps_c, - plane_state->scaling_quality.v_taps_c); - - SURFACE_TRACE( - "plane_state->src_rect.x = %d;\n" - "plane_state->src_rect.y = %d;\n" - "plane_state->src_rect.width = %d;\n" - "plane_state->src_rect.height = %d;\n" - "plane_state->dst_rect.x = %d;\n" - "plane_state->dst_rect.y = %d;\n" - "plane_state->dst_rect.width = %d;\n" - "plane_state->dst_rect.height = %d;\n" - "plane_state->clip_rect.x = %d;\n" - "plane_state->clip_rect.y = %d;\n" - "plane_state->clip_rect.width = %d;\n" - "plane_state->clip_rect.height = %d;\n", - plane_state->src_rect.x, - plane_state->src_rect.y, - plane_state->src_rect.width, - plane_state->src_rect.height, - plane_state->dst_rect.x, - plane_state->dst_rect.y, - plane_state->dst_rect.width, - plane_state->dst_rect.height, - plane_state->clip_rect.x, - plane_state->clip_rect.y, - plane_state->clip_rect.width, - plane_state->clip_rect.height); - - SURFACE_TRACE( - "plane_state->plane_size.surface_size.x = %d;\n" - "plane_state->plane_size.surface_size.y = %d;\n" - "plane_state->plane_size.surface_size.width = %d;\n" - "plane_state->plane_size.surface_size.height = %d;\n" - "plane_state->plane_size.surface_pitch = %d;\n", - plane_state->plane_size.surface_size.x, - plane_state->plane_size.surface_size.y, - plane_state->plane_size.surface_size.width, - plane_state->plane_size.surface_size.height, - plane_state->plane_size.surface_pitch); - - - SURFACE_TRACE( - "plane_state->tiling_info.gfx8.num_banks = %d;\n" - "plane_state->tiling_info.gfx8.bank_width = %d;\n" - "plane_state->tiling_info.gfx8.bank_width_c = %d;\n" - "plane_state->tiling_info.gfx8.bank_height = %d;\n" - "plane_state->tiling_info.gfx8.bank_height_c = %d;\n" - "plane_state->tiling_info.gfx8.tile_aspect = %d;\n" - "plane_state->tiling_info.gfx8.tile_aspect_c = %d;\n" - "plane_state->tiling_info.gfx8.tile_split = %d;\n" - "plane_state->tiling_info.gfx8.tile_split_c = %d;\n" - "plane_state->tiling_info.gfx8.tile_mode = %d;\n" - "plane_state->tiling_info.gfx8.tile_mode_c = %d;\n", - plane_state->tiling_info.gfx8.num_banks, - plane_state->tiling_info.gfx8.bank_width, - plane_state->tiling_info.gfx8.bank_width_c, - plane_state->tiling_info.gfx8.bank_height, - plane_state->tiling_info.gfx8.bank_height_c, - plane_state->tiling_info.gfx8.tile_aspect, - plane_state->tiling_info.gfx8.tile_aspect_c, - plane_state->tiling_info.gfx8.tile_split, - plane_state->tiling_info.gfx8.tile_split_c, - plane_state->tiling_info.gfx8.tile_mode, - plane_state->tiling_info.gfx8.tile_mode_c); - - SURFACE_TRACE( - "plane_state->tiling_info.gfx8.pipe_config = %d;\n" - "plane_state->tiling_info.gfx8.array_mode = %d;\n" - "plane_state->color_space = %d;\n" - "plane_state->dcc.enable = %d;\n" - "plane_state->format = %d;\n" - "plane_state->rotation = %d;\n" - "plane_state->stereo_format = %d;\n", - plane_state->tiling_info.gfx8.pipe_config, - plane_state->tiling_info.gfx8.array_mode, - plane_state->color_space, - plane_state->dcc.enable, - plane_state->format, - plane_state->rotation, - plane_state->stereo_format); - - SURFACE_TRACE("plane_state->tiling_info.gfx9.swizzle = %d;\n", - plane_state->tiling_info.gfx9.swizzle); - - SURFACE_TRACE("\n"); - } - SURFACE_TRACE("\n"); -} - void update_surface_trace( struct dc *dc, const struct dc_surface_update *updates, 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 6b514fd03f16..e0277728268a 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 @@ -34,6 +34,7 @@ #include "dc_state_priv.h" #define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0])) +#define MAX_NUM_MCACHE 8 /* used as index in array of black_color_format */ enum black_color_format { @@ -553,6 +554,53 @@ void get_cursor_visual_confirm_color( } } +void get_dcc_visual_confirm_color( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct tg_color *color) +{ + const uint32_t MCACHE_ID_UNASSIGNED = 0xF; + + if (!pipe_ctx->plane_state->dcc.enable) { + color->color_r_cr = 0; /* black - DCC disabled */ + color->color_g_y = 0; + color->color_b_cb = 0; + return; + } + + if (dc->ctx->dce_version < DCN_VERSION_4_01) { + color->color_r_cr = MAX_TG_COLOR_VALUE; /* red - DCC enabled */ + color->color_g_y = 0; + color->color_b_cb = 0; + return; + } + + uint32_t first_id = pipe_ctx->mcache_regs.main.p0.mcache_id_first; + uint32_t second_id = pipe_ctx->mcache_regs.main.p0.mcache_id_second; + + if (first_id != MCACHE_ID_UNASSIGNED && second_id != MCACHE_ID_UNASSIGNED && first_id != second_id) { + color->color_r_cr = MAX_TG_COLOR_VALUE/2; /* grey - 2 mcache */ + color->color_g_y = MAX_TG_COLOR_VALUE/2; + color->color_b_cb = MAX_TG_COLOR_VALUE/2; + } + + else if (first_id != MCACHE_ID_UNASSIGNED || second_id != MCACHE_ID_UNASSIGNED) { + const struct tg_color id_colors[MAX_NUM_MCACHE] = { + {0, MAX_TG_COLOR_VALUE, 0}, /* green */ + {0, 0, MAX_TG_COLOR_VALUE}, /* blue */ + {MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE, 0}, /* yellow */ + {MAX_TG_COLOR_VALUE, 0, MAX_TG_COLOR_VALUE}, /* magenta */ + {0, MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE}, /* cyan */ + {MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE}, /* white */ + {MAX_TG_COLOR_VALUE/2, 0, 0}, /* dark red */ + {0, MAX_TG_COLOR_VALUE/2, 0}, /* dark green */ + }; + + uint32_t assigned_id = (first_id != MCACHE_ID_UNASSIGNED) ? first_id : second_id; + *color = id_colors[assigned_id]; + } +} + void set_p_state_switch_method( struct dc *dc, struct dc_state *context, @@ -564,6 +612,7 @@ void set_p_state_switch_method( if (!dc->ctx || !dc->ctx->dmub_srv || !pipe_ctx || !vba) return; + pipe_ctx->p_state_type = P_STATE_UNKNOWN; if (vba->DRAMClockChangeSupport[vba->VoltageLevel][vba->maxMpcComb] != dm_dram_clock_change_unsupported) { /* MCLK switching is supported */ 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 7eb91612b60d..ea404435c9b9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1472,7 +1472,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx) DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger); /* Invalid input */ - if (!plane_state->dst_rect.width || + if (!plane_state || + !plane_state->dst_rect.width || !plane_state->dst_rect.height || !plane_state->src_rect.width || !plane_state->src_rect.height) { @@ -4925,7 +4926,10 @@ bool pipe_need_reprogram( return true; /* DIG link encoder resource assignment for stream changed. */ - if (pipe_ctx_old->stream->ctx->dc->res_pool->funcs->link_encs_assign) { + if (pipe_ctx_old->stream->ctx->dc->config.unify_link_enc_assignment) { + if (pipe_ctx_old->link_res.dio_link_enc != pipe_ctx->link_res.dio_link_enc) + return true; + } else if (pipe_ctx_old->stream->ctx->dc->res_pool->funcs->link_encs_assign) { bool need_reprogram = false; struct dc *dc = pipe_ctx_old->stream->ctx->dc; struct link_encoder *link_enc_prev = @@ -5191,7 +5195,7 @@ void get_audio_check(struct audio_info *aud_modes, } } -static struct link_encoder *get_temp_dio_link_enc( +struct link_encoder *get_temp_dio_link_enc( const struct resource_context *res_ctx, const struct resource_pool *const pool, const struct dc_link *link) 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 e8134c47fe0d..0478dd856d8c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -201,7 +201,8 @@ struct dc_stream_state *dc_copy_stream(const struct dc_stream_state *stream) dc_stream_assign_stream_id(new_stream); /* If using dynamic encoder assignment, wait till stream committed to assign encoder. */ - if (new_stream->ctx->dc->res_pool->funcs->link_encs_assign) + if (new_stream->ctx->dc->res_pool->funcs->link_encs_assign && + !new_stream->ctx->dc->config.unify_link_enc_assignment) new_stream->link_enc = NULL; kref_init(&new_stream->refcount); diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 5e96913bcab1..a62c4893e5ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -53,7 +53,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.321" +#define DC_VER "3.2.323" /** * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC @@ -495,6 +495,7 @@ enum visual_confirm { VISUAL_CONFIRM_FAMS2 = 19, VISUAL_CONFIRM_HW_CURSOR = 20, VISUAL_CONFIRM_VABC = 21, + VISUAL_CONFIRM_DCC = 22, }; enum dc_psr_power_opts { @@ -1083,6 +1084,7 @@ struct dc_debug_options { unsigned int enable_oled_edp_power_up_opt; bool enable_hblank_borrow; bool force_subvp_df_throttle; + uint32_t acpi_transition_bitmasks[MAX_PIPES]; }; @@ -1806,6 +1808,7 @@ struct dc_link { struct dc_panel_config panel_config; struct phy_state phy_state; + uint32_t phy_transition_bitmask; // BW ALLOCATON USB4 ONLY struct dc_dpia_bw_alloc dpia_bw_alloc_config; bool skip_implict_edp_power_control; 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 ae6e2d8552ac..1f4f11adc491 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -300,6 +300,19 @@ union lane_align_status_updated { uint8_t raw; }; +union link_service_irq_vector_esi0 { + struct { + uint8_t DP_LINK_RX_CAP_CHANGED:1; + uint8_t DP_LINK_STATUS_CHANGED:1; + uint8_t DP_LINK_STREAM_STATUS_CHANGED:1; + uint8_t DP_LINK_HDMI_LINK_STATUS_CHANGED:1; + uint8_t DP_LINK_CONNECTED_OFF_ENTRY_REQUESTED:1; + uint8_t DP_LINK_TUNNELING_IRQ:1; + uint8_t reserved:2; + } bits; + uint8_t raw; +}; + union lane_adjust { struct { uint8_t VOLTAGE_SWING_LANE:2; @@ -410,14 +423,6 @@ union dwnstream_port_caps_byte3_hdmi { uint8_t raw; }; -union hdmi_sink_encoded_link_bw_support { - struct { - uint8_t HDMI_SINK_ENCODED_LINK_BW_SUPPORT:3; - uint8_t RESERVED:5; - } bits; - uint8_t raw; -}; - union hdmi_encoded_link_bw { struct { uint8_t FRL_MODE:1; // Bit 0 @@ -470,8 +475,10 @@ union sink_status { uint8_t raw; }; -/*6-byte structure corresponding to 6 registers (200h-205h) -read during handling of HPD-IRQ*/ +/* 7-byte structure corresponding to 6 registers (200h-205h) + * and LINK_SERVICE_IRQ_ESI0 (2005h) for tunneling IRQ + * read during handling of HPD-IRQ + */ union hpd_irq_data { struct { union sink_count sink_cnt;/* 200h */ @@ -479,9 +486,10 @@ union hpd_irq_data { union lane_status lane01_status;/* 202h */ union lane_status lane23_status;/* 203h */ union lane_align_status_updated lane_status_updated;/* 204h */ - union sink_status sink_status; + union sink_status sink_status;/* 205h */ + union link_service_irq_vector_esi0 link_service_irq_esi0;/* 2005h */ } bytes; - uint8_t raw[6]; + uint8_t raw[7]; }; union down_stream_port_count { @@ -1128,6 +1136,8 @@ struct dc_lttpr_caps { union dp_128b_132b_supported_lttpr_link_rates supported_128b_132b_rates; union dp_alpm_lttpr_cap alpm; uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1]; + uint8_t lttpr_ieee_oui[3]; + uint8_t lttpr_device_id[6]; }; struct dc_dongle_dfp_cap_ext { @@ -1218,6 +1228,8 @@ struct dpcd_caps { struct replay_info pr_info; 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) */ + uint8_t mso_cap_sst_links_supported; }; union dpcd_sink_ext_caps { @@ -1391,6 +1403,12 @@ struct dp_trace { #ifndef DP_BRANCH_VENDOR_SPECIFIC_START #define DP_BRANCH_VENDOR_SPECIFIC_START 0x50C #endif +#ifndef DP_LTTPR_IEEE_OUI +#define DP_LTTPR_IEEE_OUI 0xF003D +#endif +#ifndef DP_LTTPR_DEVICE_ID +#define DP_LTTPR_DEVICE_ID 0xF0040 +#endif /** USB4 DPCD BW Allocation Registers Chapter 10.7 **/ #ifndef DP_TUNNELING_CAPABILITIES #define DP_TUNNELING_CAPABILITIES 0xE000D /* 1.4a */ @@ -1428,4 +1446,20 @@ struct dp_trace { #ifndef REQUESTED_BW #define REQUESTED_BW 0xE0031 /* 1.4a */ #endif +# ifndef DP_TUNNELING_BW_ALLOC_BITS_MASK +# define DP_TUNNELING_BW_ALLOC_BITS_MASK (0x0F << 0) +# endif +# ifndef DP_TUNNELING_BW_REQUEST_FAILED +# define DP_TUNNELING_BW_REQUEST_FAILED (1 << 0) +# endif +# ifndef DP_TUNNELING_BW_REQUEST_SUCCEEDED +# define DP_TUNNELING_BW_REQUEST_SUCCEEDED (1 << 1) +# endif +# ifndef DP_TUNNELING_ESTIMATED_BW_CHANGED +# define DP_TUNNELING_ESTIMATED_BW_CHANGED (1 << 2) +# endif +# ifndef DP_TUNNELING_BW_ALLOC_CAP_CHANGED +# define DP_TUNNELING_BW_ALLOC_CAP_CHANGED (1 << 3) +# endif + #endif /* DC_DP_TYPES_H */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index e60898c2df01..acd3b373a18e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -181,6 +181,7 @@ struct dc_panel_patch { uint8_t blankstream_before_otg_off; bool oled_optimize_display_on; unsigned int force_mst_blocked_discovery; + unsigned int wait_after_dpcd_poweroff_ms; }; struct dc_edid_caps { diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h index 160c299419b7..a9b88f5e0c04 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h @@ -379,53 +379,55 @@ struct dccg_mask { DCCG401_REG_FIELD_LIST(uint32_t) }; +#define DCCG_REG_VARIABLE_LIST \ + uint32_t DPPCLK_DTO_CTRL; \ + uint32_t DPPCLK_DTO_PARAM[6]; \ + uint32_t REFCLK_CNTL; \ + uint32_t DISPCLK_FREQ_CHANGE_CNTL; \ + uint32_t OTG_PIXEL_RATE_CNTL[MAX_PIPES]; \ + uint32_t HDMICHARCLK_CLOCK_CNTL[6]; \ + uint32_t PHYASYMCLK_CLOCK_CNTL; \ + uint32_t PHYBSYMCLK_CLOCK_CNTL; \ + uint32_t PHYCSYMCLK_CLOCK_CNTL; \ + uint32_t PHYDSYMCLK_CLOCK_CNTL; \ + uint32_t PHYESYMCLK_CLOCK_CNTL; \ + uint32_t DTBCLK_DTO_MODULO[MAX_PIPES]; \ + uint32_t DTBCLK_DTO_PHASE[MAX_PIPES]; \ + uint32_t DCCG_AUDIO_DTBCLK_DTO_MODULO; \ + uint32_t DCCG_AUDIO_DTBCLK_DTO_PHASE; \ + uint32_t DCCG_AUDIO_DTO_SOURCE; \ + uint32_t DPSTREAMCLK_CNTL; \ + uint32_t HDMISTREAMCLK_CNTL; \ + uint32_t SYMCLK32_SE_CNTL; \ + uint32_t SYMCLK32_LE_CNTL; \ + uint32_t DENTIST_DISPCLK_CNTL; \ + uint32_t DSCCLK_DTO_CTRL; \ + uint32_t DSCCLK0_DTO_PARAM; \ + uint32_t DSCCLK1_DTO_PARAM; \ + uint32_t DSCCLK2_DTO_PARAM; \ + uint32_t DSCCLK3_DTO_PARAM; \ + uint32_t DPSTREAMCLK_ROOT_GATE_DISABLE; \ + uint32_t DPSTREAMCLK_GATE_DISABLE; \ + uint32_t DCCG_GATE_DISABLE_CNTL; \ + uint32_t DCCG_GATE_DISABLE_CNTL2; \ + uint32_t DCCG_GATE_DISABLE_CNTL3; \ + uint32_t HDMISTREAMCLK0_DTO_PARAM; \ + uint32_t DCCG_GATE_DISABLE_CNTL4; \ + uint32_t OTG_PIXEL_RATE_DIV; \ + uint32_t DTBCLK_P_CNTL; \ + uint32_t DPPCLK_CTRL; \ + uint32_t DCCG_GATE_DISABLE_CNTL5; \ + uint32_t DCCG_GATE_DISABLE_CNTL6; \ + uint32_t DCCG_GLOBAL_FGCG_REP_CNTL; \ + uint32_t SYMCLKA_CLOCK_ENABLE; \ + uint32_t SYMCLKB_CLOCK_ENABLE; \ + uint32_t SYMCLKC_CLOCK_ENABLE; \ + uint32_t SYMCLKD_CLOCK_ENABLE; \ + uint32_t SYMCLKE_CLOCK_ENABLE; \ + uint32_t DP_DTO_MODULO[MAX_PIPES]; \ + uint32_t DP_DTO_PHASE[MAX_PIPES] struct dccg_registers { - uint32_t DPPCLK_DTO_CTRL; - uint32_t DPPCLK_DTO_PARAM[6]; - uint32_t REFCLK_CNTL; - uint32_t DISPCLK_FREQ_CHANGE_CNTL; - uint32_t OTG_PIXEL_RATE_CNTL[MAX_PIPES]; - uint32_t HDMICHARCLK_CLOCK_CNTL[6]; - uint32_t PHYASYMCLK_CLOCK_CNTL; - uint32_t PHYBSYMCLK_CLOCK_CNTL; - uint32_t PHYCSYMCLK_CLOCK_CNTL; - uint32_t PHYDSYMCLK_CLOCK_CNTL; - uint32_t PHYESYMCLK_CLOCK_CNTL; - uint32_t DTBCLK_DTO_MODULO[MAX_PIPES]; - uint32_t DTBCLK_DTO_PHASE[MAX_PIPES]; - uint32_t DCCG_AUDIO_DTBCLK_DTO_MODULO; - uint32_t DCCG_AUDIO_DTBCLK_DTO_PHASE; - uint32_t DCCG_AUDIO_DTO_SOURCE; - uint32_t DPSTREAMCLK_CNTL; - uint32_t HDMISTREAMCLK_CNTL; - uint32_t SYMCLK32_SE_CNTL; - uint32_t SYMCLK32_LE_CNTL; - uint32_t DENTIST_DISPCLK_CNTL; - uint32_t DSCCLK_DTO_CTRL; - uint32_t DSCCLK0_DTO_PARAM; - uint32_t DSCCLK1_DTO_PARAM; - uint32_t DSCCLK2_DTO_PARAM; - uint32_t DSCCLK3_DTO_PARAM; - uint32_t DPSTREAMCLK_ROOT_GATE_DISABLE; - uint32_t DPSTREAMCLK_GATE_DISABLE; - uint32_t DCCG_GATE_DISABLE_CNTL; - uint32_t DCCG_GATE_DISABLE_CNTL2; - uint32_t DCCG_GATE_DISABLE_CNTL3; - uint32_t HDMISTREAMCLK0_DTO_PARAM; - uint32_t DCCG_GATE_DISABLE_CNTL4; - uint32_t OTG_PIXEL_RATE_DIV; - uint32_t DTBCLK_P_CNTL; - uint32_t DPPCLK_CTRL; - uint32_t DCCG_GATE_DISABLE_CNTL5; - uint32_t DCCG_GATE_DISABLE_CNTL6; - uint32_t DCCG_GLOBAL_FGCG_REP_CNTL; - uint32_t SYMCLKA_CLOCK_ENABLE; - uint32_t SYMCLKB_CLOCK_ENABLE; - uint32_t SYMCLKC_CLOCK_ENABLE; - uint32_t SYMCLKD_CLOCK_ENABLE; - uint32_t SYMCLKE_CLOCK_ENABLE; - uint32_t DP_DTO_MODULO[MAX_PIPES]; - uint32_t DP_DTO_PHASE[MAX_PIPES]; + DCCG_REG_VARIABLE_LIST; }; struct dcn_dccg { diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c index 332094ad2b05..ffd172231fdf 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c @@ -531,7 +531,7 @@ static void dccg401_enable_dpstreamclk(struct dccg *dccg, int otg_inst, int dp_h DPSTREAMCLK_ROOT_GATE_DISABLE, 1); } -static void dccg401_disable_dpstreamclk(struct dccg *dccg, int dp_hpo_inst) +void dccg401_disable_dpstreamclk(struct dccg *dccg, int dp_hpo_inst) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h index b9905c73e754..55e8718aad22 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.h @@ -208,6 +208,8 @@ void dccg401_enable_symclk32_le( void dccg401_disable_symclk32_le( struct dccg *dccg, int hpo_le_inst); +void dccg401_disable_dpstreamclk(struct dccg *dccg, int dp_hpo_inst); +void dccg401_set_dto_dscclk(struct dccg *dccg, uint32_t inst); void dccg401_set_ref_dscclk(struct dccg *dccg, uint32_t dsc_inst); void dccg401_set_src_sel( @@ -228,14 +230,11 @@ void dccg401_set_dp_dto( const struct dp_dto_params *params); void dccg401_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst); void dccg401_disable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst); - void dccg401_set_dto_dscclk(struct dccg *dccg, uint32_t inst); void dccg401_set_dtbclk_p_src( struct dccg *dccg, enum streamclk_source src, uint32_t otg_inst); - - struct dccg *dccg401_create( struct dc_context *ctx, const struct dccg_registers *regs, diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c index e5fb0e8333e4..e691a1cf3356 100644 --- a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c @@ -239,6 +239,7 @@ static const struct timing_generator_funcs dce60_tg_funcs = { dce60_timing_generator_enable_advanced_request, .configure_crc = dce60_configure_crc, .get_crc = dce110_get_crc, + .is_two_pixels_per_container = dce110_is_two_pixels_per_container, }; void dce60_timing_generator_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c index ea0c9a9d0bd6..9972911330b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.c @@ -137,9 +137,9 @@ static const struct link_encoder_funcs dcn35_link_enc_funcs = { .hw_init = dcn35_link_encoder_init, .setup = dcn35_link_encoder_setup, .enable_tmds_output = dcn10_link_encoder_enable_tmds_output, - .enable_dp_output = dcn31_link_encoder_enable_dp_output, - .enable_dp_mst_output = dcn31_link_encoder_enable_dp_mst_output, - .disable_output = dcn31_link_encoder_disable_output, + .enable_dp_output = dcn35_link_encoder_enable_dp_output, + .enable_dp_mst_output = dcn35_link_encoder_enable_dp_mst_output, + .disable_output = dcn35_link_encoder_disable_output, .dp_set_lane_settings = dcn10_link_encoder_dp_set_lane_settings, .dp_set_phy_pattern = dcn10_link_encoder_dp_set_phy_pattern, .update_mst_stream_allocation_table = @@ -297,6 +297,50 @@ static void link_encoder_disable(struct dcn10_link_encoder *enc10) REG_UPDATE(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, 0); } +void dcn35_link_encoder_enable_dp_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + + if (!enc->ctx->dc->config.unify_link_enc_assignment) + dcn31_link_encoder_enable_dp_output(enc, link_settings, clock_source); + else { + DC_LOG_DEBUG("%s: enc_id(%d)\n", __func__, enc->preferred_engine); + dcn20_link_encoder_enable_dp_output(enc, link_settings, clock_source); + } +} + +void dcn35_link_encoder_enable_dp_mst_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + + if (!enc->ctx->dc->config.unify_link_enc_assignment) + dcn31_link_encoder_enable_dp_mst_output(enc, link_settings, clock_source); + else { + DC_LOG_DEBUG("%s: enc_id(%d)\n", __func__, enc->preferred_engine); + dcn10_link_encoder_enable_dp_mst_output(enc, link_settings, clock_source); + } +} + +void dcn35_link_encoder_disable_output( + struct link_encoder *enc, + enum signal_type signal) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + + if (!enc->ctx->dc->config.unify_link_enc_assignment) + dcn31_link_encoder_disable_output(enc, signal); + else { + DC_LOG_DEBUG("%s: enc_id(%d)\n", __func__, enc->preferred_engine); + dcn10_link_encoder_disable_output(enc, signal); + } +} + void dcn35_link_encoder_enable_dpia_output( struct link_encoder *enc, const struct dc_link_settings *link_settings, diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h index f9d4221f4b43..5712e6553fab 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_link_encoder.h @@ -145,6 +145,29 @@ enum signal_type dcn35_get_dig_mode(struct link_encoder *enc); void dcn35_link_encoder_setup(struct link_encoder *enc, enum signal_type signal); /* + * Enable DP transmitter and its encoder. + */ +void dcn35_link_encoder_enable_dp_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source); + +/* + * Enable DP transmitter and its encoder in MST mode. + */ +void dcn35_link_encoder_enable_dp_mst_output( + struct link_encoder *enc, + const struct dc_link_settings *link_settings, + enum clock_source_id clock_source); + +/* + * Disable transmitter and its encoder. + */ +void dcn35_link_encoder_disable_output( + struct link_encoder *enc, + enum signal_type signal); + +/* * Enable DP transmitter and its encoder for dpia port. */ void dcn35_link_encoder_enable_dpia_output( diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c index 4bab180e1938..d5fa551dd3c9 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.c @@ -100,7 +100,7 @@ void enc401_stream_encoder_dvi_set_stream_attribute( } /* setup stream encoder in hdmi mode */ -static void enc401_stream_encoder_hdmi_set_stream_attribute( +void enc401_stream_encoder_hdmi_set_stream_attribute( struct stream_encoder *enc, struct dc_crtc_timing *crtc_timing, int actual_pix_clk_khz, diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h index 25cc8f72d8d3..d6b00cd246b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dio/dcn401/dcn401_dio_stream_encoder.h @@ -232,4 +232,9 @@ void enc401_stream_encoder_map_to_link( uint32_t stream_enc_inst, uint32_t link_enc_inst); void enc401_read_state(struct stream_encoder *enc, struct enc_state *s); +void enc401_stream_encoder_hdmi_set_stream_attribute( + struct stream_encoder *enc, + struct dc_crtc_timing *crtc_timing, + int actual_pix_clk_khz, + bool enable_audio); #endif /* __DC_DIO_STREAM_ENCODER_DCN401_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h index f81e5a4e1d6d..7b9c22c45453 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services.h @@ -291,6 +291,13 @@ bool dm_execute_dmub_cmd(const struct dc_context *ctx, union dmub_rb_cmd *cmd, e bool dm_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned int count, union dmub_rb_cmd *cmd, enum dm_dmub_wait_type wait_type); /* + * ACPI Interfaces + */ +void dm_acpi_process_phy_transition_interlock( + const struct dc_context *ctx, + struct dm_process_phy_transition_init_params process_phy_transition_init_params); + +/* * Debug and verification hooks */ diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h index facf269c4326..bf63da266a18 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h @@ -275,4 +275,30 @@ enum dm_dmub_wait_type { DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY, }; +enum dm_acpi_transition_link_type { + hdmi_tmds, + hdmi_frl, + dp_8b_10b, + dp_128b_132b, + none +}; + +struct dm_process_phy_transition_init_params { + uint32_t phy_id; + uint8_t action; + uint32_t sym_clock_10khz; + enum signal_type signal; + enum dc_lane_count display_port_lanes_count; + enum dc_link_rate display_port_link_rate; + uint32_t transition_bitmask; + uint8_t hdmi_frl_num_lanes; +}; + +struct dm_process_phy_transition_input_params { + uint32_t phy_id; + uint32_t transition_id; + uint32_t phy_configuration; + uint32_t data_rate; +}; + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c index aac0a0ae2966..88789987bdbc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c @@ -178,82 +178,6 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_0_soc = { }; -void optc3_fpu_set_vrr_m_const(struct timing_generator *optc, - double vtotal_avg) -{ - struct optc *optc1 = DCN10TG_FROM_TG(optc); - double vtotal_min, vtotal_max; - double ratio, modulo, phase; - uint32_t vblank_start; - uint32_t v_total_mask_value = 0; - - dc_assert_fp_enabled(); - - /* Compute VTOTAL_MIN and VTOTAL_MAX, so that - * VOTAL_MAX - VTOTAL_MIN = 1 - */ - v_total_mask_value = 16; - vtotal_min = dcn_bw_floor(vtotal_avg); - vtotal_max = dcn_bw_ceil(vtotal_avg); - - /* Check that bottom VBLANK is at least 2 lines tall when running with - * VTOTAL_MIN. Note that VTOTAL registers are defined as 'total number - * of lines in a frame - 1'. - */ - REG_GET(OTG_V_BLANK_START_END, OTG_V_BLANK_START, - &vblank_start); - ASSERT(vtotal_min >= vblank_start + 1); - - /* Special case where the average frame rate can be achieved - * without using the DTO - */ - if (vtotal_min == vtotal_max) { - REG_SET(OTG_V_TOTAL, 0, OTG_V_TOTAL, (uint32_t)vtotal_min); - - optc->funcs->set_vtotal_min_max(optc, 0, 0); - REG_SET(OTG_M_CONST_DTO0, 0, OTG_M_CONST_DTO_PHASE, 0); - REG_SET(OTG_M_CONST_DTO1, 0, OTG_M_CONST_DTO_MODULO, 0); - REG_UPDATE_3(OTG_V_TOTAL_CONTROL, - OTG_V_TOTAL_MIN_SEL, 0, - OTG_V_TOTAL_MAX_SEL, 0, - OTG_SET_V_TOTAL_MIN_MASK_EN, 0); - return; - } - - ratio = vtotal_max - vtotal_avg; - modulo = 65536.0 * 65536.0 - 1.0; /* 2^32 - 1 */ - phase = ratio * modulo; - - /* Special cases where the DTO phase gets rounded to 0 or - * to DTO modulo - */ - if (phase <= 0 || phase >= modulo) { - REG_SET(OTG_V_TOTAL, 0, OTG_V_TOTAL, - phase <= 0 ? - (uint32_t)vtotal_max : (uint32_t)vtotal_min); - REG_SET(OTG_V_TOTAL_MIN, 0, OTG_V_TOTAL_MIN, 0); - REG_SET(OTG_V_TOTAL_MAX, 0, OTG_V_TOTAL_MAX, 0); - REG_SET(OTG_M_CONST_DTO0, 0, OTG_M_CONST_DTO_PHASE, 0); - REG_SET(OTG_M_CONST_DTO1, 0, OTG_M_CONST_DTO_MODULO, 0); - REG_UPDATE_3(OTG_V_TOTAL_CONTROL, - OTG_V_TOTAL_MIN_SEL, 0, - OTG_V_TOTAL_MAX_SEL, 0, - OTG_SET_V_TOTAL_MIN_MASK_EN, 0); - return; - } - REG_UPDATE_6(OTG_V_TOTAL_CONTROL, - OTG_V_TOTAL_MIN_SEL, 1, - OTG_V_TOTAL_MAX_SEL, 1, - OTG_SET_V_TOTAL_MIN_MASK_EN, 1, - OTG_SET_V_TOTAL_MIN_MASK, v_total_mask_value, - OTG_VTOTAL_MID_REPLACING_MIN_EN, 0, - OTG_VTOTAL_MID_REPLACING_MAX_EN, 0); - REG_SET(OTG_V_TOTAL, 0, OTG_V_TOTAL, (uint32_t)vtotal_min); - optc->funcs->set_vtotal_min_max(optc, vtotal_min, vtotal_max); - REG_SET(OTG_M_CONST_DTO0, 0, OTG_M_CONST_DTO_PHASE, (uint32_t)phase); - REG_SET(OTG_M_CONST_DTO1, 0, OTG_M_CONST_DTO_MODULO, (uint32_t)modulo); -} - void dcn30_fpu_populate_dml_writeback_from_context( struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h index cab864095ce7..e3b6ad6a8784 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.h @@ -29,9 +29,6 @@ #include "core_types.h" #include "dcn20/dcn20_optc.h" -void optc3_fpu_set_vrr_m_const(struct timing_generator *optc, - double vtotal_avg); - void dcn30_fpu_populate_dml_writeback_from_context( struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index cee1b351e105..f1fe49401bc0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -281,10 +281,10 @@ static void CalculateDynamicMetadataParameters( double DISPCLK, double DCFClkDeepSleep, double PixelClock, - long HTotal, - long VBlank, - long DynamicMetadataTransmittedBytes, - long DynamicMetadataLinesBeforeActiveRequired, + unsigned int HTotal, + unsigned int VBlank, + unsigned int DynamicMetadataTransmittedBytes, + int DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP, double *Tsetup, @@ -3265,8 +3265,8 @@ static double CalculateWriteBackDelay( static void CalculateDynamicMetadataParameters(int MaxInterDCNTileRepeaters, double DPPCLK, double DISPCLK, - double DCFClkDeepSleep, double PixelClock, long HTotal, long VBlank, long DynamicMetadataTransmittedBytes, - long DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP, + double DCFClkDeepSleep, double PixelClock, unsigned int HTotal, unsigned int VBlank, unsigned int DynamicMetadataTransmittedBytes, + int DynamicMetadataLinesBeforeActiveRequired, int InterlaceEnable, bool ProgressiveToInterlaceUnitInOPP, double *Tsetup, double *Tdmbf, double *Tdmec, double *Tdmsks) { double TotalRepeaterDelayTime = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 6f490d8d7038..56dda686e299 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -626,6 +626,7 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, * - Not TMZ surface */ if (pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe && !dcn32_is_center_timing(pipe) && + !pipe->stream->hw_cursor_req && !(pipe->stream->timing.pix_clk_100hz / 10000 > DCN3_2_MAX_SUBVP_PIXEL_RATE_MHZ) && (!dcn32_is_psr_capable(pipe) || (context->stream_count == 1 && dc->caps.dmub_caps.subvp_psr)) && dc_state_get_pipe_subvp_type(context, pipe) == SUBVP_NONE && diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c index 412e75eb4704..12ff65b6a7e5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c @@ -122,17 +122,6 @@ void print__data_rq_misc_params_st(struct display_mode_lib *mode_lib, const stru dml_print("DML_RQ_DLG_CALC: =====================================\n"); } -void print__rq_dlg_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_rq_dlg_params_st *rq_dlg_param) -{ - dml_print("DML_RQ_DLG_CALC: =====================================\n"); - dml_print("DML_RQ_DLG_CALC: DISPLAY_RQ_DLG_PARAM_ST\n"); - dml_print("DML_RQ_DLG_CALC: <LUMA>\n"); - print__data_rq_dlg_params_st(mode_lib, &rq_dlg_param->rq_l); - dml_print("DML_RQ_DLG_CALC: <CHROMA>\n"); - print__data_rq_dlg_params_st(mode_lib, &rq_dlg_param->rq_c); - dml_print("DML_RQ_DLG_CALC: =====================================\n"); -} - void print__dlg_sys_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_dlg_sys_params_st *dlg_sys_param) { dml_print("DML_RQ_DLG_CALC: =====================================\n"); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h index ebcd717744e5..2bc64c4081dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h @@ -35,7 +35,6 @@ void print__rq_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dp void print__data_rq_sizing_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_sizing_params_st *rq_sizing); void print__data_rq_dlg_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_dlg_params_st *rq_dlg_param); void print__data_rq_misc_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_misc_params_st *rq_misc_param); -void print__rq_dlg_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_rq_dlg_params_st *rq_dlg_param); void print__dlg_sys_params_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_dlg_sys_params_st *dlg_sys_param); void print__data_rq_regs_st(struct display_mode_lib *mode_lib, const struct _vcs_dpi_display_data_rq_regs_st *rq_regs); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c index 3664980d1574..bb863c8c6b39 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4.c @@ -44,7 +44,7 @@ struct dml2_core_ip_params core_dcn4_ip_caps_base = { .dppclk_delay_scl_lb_only = 16, .dppclk_delay_cnvc_formatter = 28, .dppclk_delay_cnvc_cursor = 6, - .cursor_buffer_size = 42, + .cursor_buffer_size = 24, .cursor_chunk_size = 2, .dispclk_delay_subtotal = 125, .max_inter_dcn_tile_repeaters = 8, @@ -141,9 +141,8 @@ bool core_dcn4_initialize(struct dml2_core_initialize_in_out *in_out) core->clean_me_up.mode_lib.ip.subvp_fw_processing_delay_us = core_dcn4_ip_caps_base.subvp_pstate_allow_width_us; core->clean_me_up.mode_lib.ip.subvp_swath_height_margin_lines = core_dcn4_ip_caps_base.subvp_swath_height_margin_lines; } else { - memcpy(&core->clean_me_up.mode_lib.ip, &core_dcn4_ip_caps_base, sizeof(struct dml2_core_ip_params)); + memcpy(&core->clean_me_up.mode_lib.ip, &core_dcn4_ip_caps_base, sizeof(struct dml2_core_ip_params)); patch_ip_params_with_ip_caps(&core->clean_me_up.mode_lib.ip, in_out->ip_caps); - core->clean_me_up.mode_lib.ip.imall_supported = false; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c index 78c93a502518..4c33d99ca7e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c @@ -5058,7 +5058,7 @@ static void CalculateExtraLatency( double HostVMInefficiencyFactorPrefetch, unsigned int HostVMMinPageSize, enum dml2_qos_param_type qos_type, - bool max_oustanding_when_urgent_expected, + bool max_outstanding_when_urgent_expected, unsigned int max_outstanding_requests, unsigned int request_size_bytes_luma[], unsigned int request_size_bytes_chroma[], @@ -5106,7 +5106,7 @@ static void CalculateExtraLatency( if (qos_type == dml2_qos_param_type_dcn4x) { *ExtraLatency_sr = dchub_arb_to_ret_delay / DCFCLK; *ExtraLatency = *ExtraLatency_sr; - if (max_oustanding_when_urgent_expected) + if (max_outstanding_when_urgent_expected) *ExtraLatency = *ExtraLatency + (ROBBufferSizeInKByte * 1024 - max_outstanding_requests * max_request_size_bytes) / ReturnBW; } else { *ExtraLatency_sr = dchub_arb_to_ret_delay / DCFCLK + RoundTripPingLatencyCycles / FabricClock + ReorderingBytes / ReturnBW; @@ -5121,7 +5121,7 @@ static void CalculateExtraLatency( dml2_printf("DML::%s: qos_type=%u\n", __func__, qos_type); dml2_printf("DML::%s: hostvm_mode=%u\n", __func__, hostvm_mode); dml2_printf("DML::%s: Tex_trips=%u\n", __func__, Tex_trips); - dml2_printf("DML::%s: max_oustanding_when_urgent_expected=%u\n", __func__, max_oustanding_when_urgent_expected); + dml2_printf("DML::%s: max_outstanding_when_urgent_expected=%u\n", __func__, max_outstanding_when_urgent_expected); dml2_printf("DML::%s: FabricClock=%f\n", __func__, FabricClock); dml2_printf("DML::%s: DCFCLK=%f\n", __func__, DCFCLK); dml2_printf("DML::%s: ReturnBW=%f\n", __func__, ReturnBW); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h index dfe54112a9c6..4e502f0a6d20 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h @@ -1571,7 +1571,7 @@ struct dml2_core_calcs_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport_param unsigned int *DSTYAfterScaler; bool UnboundedRequestEnabled; unsigned int CompressedBufferSizeInkByte; - bool max_oustanding_when_urgent_expected; + bool max_outstanding_when_urgent_expected; unsigned int max_outstanding_requests; unsigned int max_request_size_bytes; unsigned int *meta_row_height_l; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c index 1ed21c1b86a5..a966abd40788 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c @@ -532,26 +532,6 @@ static void calculate_odm_slices(const struct dc_stream_state *stream, unsigned odm_slice_end_x[odm_factor - 1] = stream->src.width - 1; } -static bool is_plane_in_odm_slice(const struct dc_plane_state *plane, unsigned int slice_index, unsigned int *odm_slice_end_x, unsigned int num_slices) -{ - unsigned int slice_start_x, slice_end_x; - - if (slice_index == 0) - slice_start_x = 0; - else - slice_start_x = odm_slice_end_x[slice_index - 1] + 1; - - slice_end_x = odm_slice_end_x[slice_index]; - - if (plane->clip_rect.x + plane->clip_rect.width < slice_start_x) - return false; - - if (plane->clip_rect.x > slice_end_x) - return false; - - return true; -} - static void add_odm_slice_to_odm_tree(struct dml2_context *ctx, struct dc_state *state, struct dc_pipe_mapping_scratch *scratch, @@ -791,12 +771,6 @@ static void map_pipes_for_plane(struct dml2_context *ctx, struct dc_state *state sort_pipes_for_splitting(&scratch->pipe_pool); for (odm_slice_index = 0; odm_slice_index < scratch->odm_info.odm_factor; odm_slice_index++) { - // We build the tree for one ODM slice at a time. - // Each ODM slice shares a common OPP - if (!is_plane_in_odm_slice(plane, odm_slice_index, scratch->odm_info.odm_slice_end_x, scratch->odm_info.odm_factor)) { - continue; - } - // Now we have a list of all pipes to be used for this plane/stream, now setup the tree. scratch->odm_info.next_higher_pipe_for_odm_slice[odm_slice_index] = add_plane_to_blend_tree(ctx, state, plane, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index f829d5ac7c8e..2061d43b92e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -557,6 +557,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc, } if (dml2->v20.dml_core_ctx.project == dml_project_dcn35 || + dml2->v20.dml_core_ctx.project == dml_project_dcn36 || dml2->v20.dml_core_ctx.project == dml_project_dcn351) { int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0, max_dtbclk_mhz = 0, max_fclk_mhz = 0, max_uclk_mhz = 0, max_socclk_mhz = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 45584e2f5dfe..939ee0708bd2 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -33,7 +33,6 @@ #include "dml2_dc_resource_mgmt.h" #include "dml21_wrapper.h" - static void initialize_dml2_ip_params(struct dml2_context *dml2, const struct dc *in_dc, struct ip_params_st *out) { if (dml2->config.use_native_soc_bb_construction) @@ -792,7 +791,7 @@ bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options // TODO : Temporarily add DCN_VERSION_3_2 for N-1 validation. Remove DCN_VERSION_3_2 after N-1 validation phase is complete. if ((in_dc->debug.using_dml21) && (in_dc->ctx->dce_version == DCN_VERSION_4_01 - )) + )) return dml21_create(in_dc, dml2, config); // Allocate Mode Lib Ctx diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c index 40acebd13e46..abf439e743f2 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c @@ -425,11 +425,6 @@ bool dpp3_get_optimal_number_of_taps( int min_taps_y, min_taps_c; enum lb_memory_config lb_config; - if (scl_data->viewport.width > scl_data->h_active && - dpp->ctx->dc->debug.max_downscale_src_width != 0 && - scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) - return false; - /* * Set default taps if none are provided * From programming guide: taps = min{ ceil(2*H_RATIO,1), 8} for downscaling @@ -467,6 +462,12 @@ bool dpp3_get_optimal_number_of_taps( else scl_data->taps.h_taps_c = in_taps->h_taps_c; + // Avoid null data in the scl data with this early return, proceed non-adaptive calcualtion first + if (scl_data->viewport.width > scl_data->h_active && + dpp->ctx->dc->debug.max_downscale_src_width != 0 && + scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width) + return false; + /*Ensure we can support the requested number of vtaps*/ min_taps_y = dc_fixpt_ceil(scl_data->ratios.vert); min_taps_c = dc_fixpt_ceil(scl_data->ratios.vert_c); diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h index 4bc85aaf17da..ecaa976e1f52 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h @@ -567,80 +567,82 @@ type ISHARP_NLDELTA_SCLIP_PIVOT_N; \ type ISHARP_NLDELTA_SCLIP_SLOPE_N +#define DPP_REG_VARIABLE_LIST_DCN401 \ + DPP_DCN3_REG_VARIABLE_LIST_COMMON; \ + uint32_t CURSOR0_FP_SCALE_BIAS_G_Y; \ + uint32_t CURSOR0_FP_SCALE_BIAS_RB_CRCB; \ + uint32_t CUR0_MATRIX_MODE; \ + uint32_t CUR0_MATRIX_C11_C12_A; \ + uint32_t CUR0_MATRIX_C13_C14_A; \ + uint32_t CUR0_MATRIX_C21_C22_A; \ + uint32_t CUR0_MATRIX_C23_C24_A; \ + uint32_t CUR0_MATRIX_C31_C32_A; \ + uint32_t CUR0_MATRIX_C33_C34_A; \ + uint32_t CUR0_MATRIX_C11_C12_B; \ + uint32_t CUR0_MATRIX_C13_C14_B; \ + uint32_t CUR0_MATRIX_C21_C22_B; \ + uint32_t CUR0_MATRIX_C23_C24_B; \ + uint32_t CUR0_MATRIX_C31_C32_B; \ + uint32_t CUR0_MATRIX_C33_C34_B; \ + uint32_t DSCL_SC_MODE; \ + uint32_t DSCL_EASF_H_MODE; \ + uint32_t DSCL_EASF_H_BF_CNTL; \ + uint32_t DSCL_EASF_H_RINGEST_EVENTAP_REDUCE; \ + uint32_t DSCL_EASF_H_RINGEST_EVENTAP_GAIN; \ + uint32_t DSCL_EASF_H_BF_FINAL_MAX_MIN; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG0; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG1; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG2; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG3; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG4; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG5; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG6; \ + uint32_t DSCL_EASF_H_BF1_PWL_SEG7; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG0; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG1; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG2; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG3; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG4; \ + uint32_t DSCL_EASF_H_BF3_PWL_SEG5; \ + uint32_t DSCL_EASF_V_MODE; \ + uint32_t DSCL_EASF_V_BF_CNTL; \ + uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL1; \ + uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL2; \ + uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL3; \ + uint32_t DSCL_EASF_V_RINGEST_EVENTAP_REDUCE; \ + uint32_t DSCL_EASF_V_RINGEST_EVENTAP_GAIN; \ + uint32_t DSCL_EASF_V_BF_FINAL_MAX_MIN; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG0; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG1; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG2; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG3; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG4; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG5; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG6; \ + uint32_t DSCL_EASF_V_BF1_PWL_SEG7; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG0; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG1; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG2; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG3; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG4; \ + uint32_t DSCL_EASF_V_BF3_PWL_SEG5; \ + uint32_t DSCL_SC_MATRIX_C0C1; \ + uint32_t DSCL_SC_MATRIX_C2C3; \ + uint32_t ISHARP_MODE; \ + uint32_t ISHARP_NOISEDET_THRESHOLD; \ + uint32_t ISHARP_NOISE_GAIN_PWL; \ + uint32_t ISHARP_LBA_PWL_SEG0; \ + uint32_t ISHARP_LBA_PWL_SEG1; \ + uint32_t ISHARP_LBA_PWL_SEG2; \ + uint32_t ISHARP_LBA_PWL_SEG3; \ + uint32_t ISHARP_LBA_PWL_SEG4; \ + uint32_t ISHARP_LBA_PWL_SEG5; \ + uint32_t ISHARP_DELTA_CTRL; \ + uint32_t ISHARP_DELTA_DATA; \ + uint32_t ISHARP_DELTA_INDEX; \ + uint32_t ISHARP_NLDELTA_SOFT_CLIP struct dcn401_dpp_registers { - DPP_DCN3_REG_VARIABLE_LIST_COMMON; - uint32_t CURSOR0_FP_SCALE_BIAS_G_Y; - uint32_t CURSOR0_FP_SCALE_BIAS_RB_CRCB; - uint32_t CUR0_MATRIX_MODE; - uint32_t CUR0_MATRIX_C11_C12_A; - uint32_t CUR0_MATRIX_C13_C14_A; - uint32_t CUR0_MATRIX_C21_C22_A; - uint32_t CUR0_MATRIX_C23_C24_A; - uint32_t CUR0_MATRIX_C31_C32_A; - uint32_t CUR0_MATRIX_C33_C34_A; - uint32_t CUR0_MATRIX_C11_C12_B; - uint32_t CUR0_MATRIX_C13_C14_B; - uint32_t CUR0_MATRIX_C21_C22_B; - uint32_t CUR0_MATRIX_C23_C24_B; - uint32_t CUR0_MATRIX_C31_C32_B; - uint32_t CUR0_MATRIX_C33_C34_B; - uint32_t DSCL_SC_MODE; - uint32_t DSCL_EASF_H_MODE; - uint32_t DSCL_EASF_H_BF_CNTL; - uint32_t DSCL_EASF_H_RINGEST_EVENTAP_REDUCE; - uint32_t DSCL_EASF_H_RINGEST_EVENTAP_GAIN; - uint32_t DSCL_EASF_H_BF_FINAL_MAX_MIN; - uint32_t DSCL_EASF_H_BF1_PWL_SEG0; - uint32_t DSCL_EASF_H_BF1_PWL_SEG1; - uint32_t DSCL_EASF_H_BF1_PWL_SEG2; - uint32_t DSCL_EASF_H_BF1_PWL_SEG3; - uint32_t DSCL_EASF_H_BF1_PWL_SEG4; - uint32_t DSCL_EASF_H_BF1_PWL_SEG5; - uint32_t DSCL_EASF_H_BF1_PWL_SEG6; - uint32_t DSCL_EASF_H_BF1_PWL_SEG7; - uint32_t DSCL_EASF_H_BF3_PWL_SEG0; - uint32_t DSCL_EASF_H_BF3_PWL_SEG1; - uint32_t DSCL_EASF_H_BF3_PWL_SEG2; - uint32_t DSCL_EASF_H_BF3_PWL_SEG3; - uint32_t DSCL_EASF_H_BF3_PWL_SEG4; - uint32_t DSCL_EASF_H_BF3_PWL_SEG5; - uint32_t DSCL_EASF_V_MODE; - uint32_t DSCL_EASF_V_BF_CNTL; - uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL1; - uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL2; - uint32_t DSCL_EASF_V_RINGEST_3TAP_CNTL3; - uint32_t DSCL_EASF_V_RINGEST_EVENTAP_REDUCE; - uint32_t DSCL_EASF_V_RINGEST_EVENTAP_GAIN; - uint32_t DSCL_EASF_V_BF_FINAL_MAX_MIN; - uint32_t DSCL_EASF_V_BF1_PWL_SEG0; - uint32_t DSCL_EASF_V_BF1_PWL_SEG1; - uint32_t DSCL_EASF_V_BF1_PWL_SEG2; - uint32_t DSCL_EASF_V_BF1_PWL_SEG3; - uint32_t DSCL_EASF_V_BF1_PWL_SEG4; - uint32_t DSCL_EASF_V_BF1_PWL_SEG5; - uint32_t DSCL_EASF_V_BF1_PWL_SEG6; - uint32_t DSCL_EASF_V_BF1_PWL_SEG7; - uint32_t DSCL_EASF_V_BF3_PWL_SEG0; - uint32_t DSCL_EASF_V_BF3_PWL_SEG1; - uint32_t DSCL_EASF_V_BF3_PWL_SEG2; - uint32_t DSCL_EASF_V_BF3_PWL_SEG3; - uint32_t DSCL_EASF_V_BF3_PWL_SEG4; - uint32_t DSCL_EASF_V_BF3_PWL_SEG5; - uint32_t DSCL_SC_MATRIX_C0C1; - uint32_t DSCL_SC_MATRIX_C2C3; - uint32_t ISHARP_MODE; - uint32_t ISHARP_NOISEDET_THRESHOLD; - uint32_t ISHARP_NOISE_GAIN_PWL; - uint32_t ISHARP_LBA_PWL_SEG0; - uint32_t ISHARP_LBA_PWL_SEG1; - uint32_t ISHARP_LBA_PWL_SEG2; - uint32_t ISHARP_LBA_PWL_SEG3; - uint32_t ISHARP_LBA_PWL_SEG4; - uint32_t ISHARP_LBA_PWL_SEG5; - uint32_t ISHARP_DELTA_CTRL; - uint32_t ISHARP_DELTA_DATA; - uint32_t ISHARP_DELTA_INDEX; - uint32_t ISHARP_NLDELTA_SOFT_CLIP; + DPP_REG_VARIABLE_LIST_DCN401; }; struct dcn401_dpp_shift { diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c index 03b4ac2f1991..0d2ae21abbdd 100644 --- a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.c @@ -262,7 +262,7 @@ void dcn31_hpo_dp_link_enc_set_link_test_pattern( } } -static void fill_stream_allocation_row_info( +void dcn31_fill_stream_allocation_row_info( const struct link_mst_stream_allocation *stream_allocation, uint32_t *src, uint32_t *slots) @@ -296,7 +296,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( /* we should clean-up table each time */ if (table->stream_count >= 1) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[0], &src, &slots); @@ -310,7 +310,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( SAT_SLOT_COUNT, slots); if (table->stream_count >= 2) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[1], &src, &slots); @@ -324,7 +324,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( SAT_SLOT_COUNT, slots); if (table->stream_count >= 3) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[2], &src, &slots); @@ -338,7 +338,7 @@ void dcn31_hpo_dp_link_enc_update_stream_allocation_table( SAT_SLOT_COUNT, slots); if (table->stream_count >= 4) { - fill_stream_allocation_row_info( + dcn31_fill_stream_allocation_row_info( &table->stream_allocations[3], &src, &slots); diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h index 51f5781325e8..40859660e4dc 100644 --- a/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn31/dcn31_hpo_dp_link_encoder.h @@ -226,4 +226,10 @@ void dcn31_hpo_dp_link_enc_set_ffe( const struct dc_link_settings *link_settings, uint8_t ffe_preset); + +void dcn31_fill_stream_allocation_row_info( + const struct link_mst_stream_allocation *stream_allocation, + uint32_t *src, + uint32_t *slots); + #endif // __DAL_DCN31_HPO_LINK_ENCODER_H__ diff --git a/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h b/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h index 48ef3d29b370..bea4e1a8ff90 100644 --- a/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/hpo/dcn32/dcn32_hpo_dp_link_encoder.h @@ -62,4 +62,7 @@ void hpo_dp_link_encoder32_construct(struct dcn31_hpo_dp_link_encoder *enc31, const struct dcn31_hpo_dp_link_encoder_shift *hpo_le_shift, const struct dcn31_hpo_dp_link_encoder_mask *hpo_le_mask); +bool dcn32_hpo_dp_link_enc_is_in_alt_mode( + struct hpo_dp_link_encoder *enc); + #endif // __DAL_DCN32_HPO_DP_LINK_ENCODER_H__ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h index 09049aa3c4f3..f66a38f43a09 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h @@ -1244,6 +1244,7 @@ struct dce_hwseq_registers { type DOMAIN24_PGFSM_PWR_STATUS; \ type DOMAIN25_PGFSM_PWR_STATUS; \ type DOMAIN_DESIRED_PWR_STATE; + struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) HWSEQ_DCN_REG_FIELD_LIST(uint8_t) 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 8280e3652171..9c9947fc5d44 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 @@ -1153,9 +1153,12 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) struct timing_generator *tg = pipe_ctx->stream_res.tg; struct dtbclk_dto_params dto_params = {0}; int dp_hpo_inst; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal)) { pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets( pipe_ctx->stream_res.stream_enc); 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 b158eb1045a1..a5a3e0823e21 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 @@ -3020,9 +3020,12 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) enum phyd32clk_clock_source phyd32clk; int dp_hpo_inst; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { dto_params.otg_inst = tg->inst; dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c index f698062f1e90..288e9dd9205d 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c @@ -621,7 +621,8 @@ void dcn31_reset_hw_ctx_wrap( } /* New dc_state in the process of being applied to hardware. */ - link_enc_cfg_set_transient_mode(dc, dc->current_state, context); + if (!dc->config.unify_link_enc_assignment) + link_enc_cfg_set_transient_mode(dc, dc->current_state, context); } void dcn31_setup_hpo_hw_control(const struct dce_hwseq *hws, bool enable) 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 c4a37a95e812..39668d8cc13a 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 @@ -927,9 +927,12 @@ void dcn401_enable_stream(struct pipe_ctx *pipe_ctx) int dp_hpo_inst = 0; unsigned int tmds_div = PIXEL_RATE_DIV_NA; unsigned int unused_div = PIXEL_RATE_DIV_NA; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + dcn401_enable_stream_calc(pipe_ctx, &dp_hpo_inst, &phyd32clk, &tmds_div, &early_control); 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 599fa41fd75f..2b1a2a00648a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h @@ -517,6 +517,11 @@ void get_cursor_visual_confirm_color( struct pipe_ctx *pipe_ctx, struct tg_color *color); +void get_dcc_visual_confirm_color( + struct dc *dc, + struct pipe_ctx *pipe_ctx, + struct tg_color *color); + void set_p_state_switch_method( struct dc *dc, struct dc_state *context, diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 042e04f924a2..9458187b834d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -647,4 +647,9 @@ void resource_init_common_dml2_callbacks(struct dc *dc, struct dml2_configuratio int resource_calculate_det_for_stream(struct dc_state *state, struct pipe_ctx *otg_master); bool resource_is_hpo_acquired(struct dc_state *context); + +struct link_encoder *get_temp_dio_link_enc( + const struct resource_context *res_ctx, + const struct resource_pool *const pool, + const struct dc_link *link); #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c index 06faa461067b..b68bcc9fca0a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c @@ -48,9 +48,16 @@ void set_dio_throttled_vcp_size(struct pipe_ctx *pipe_ctx, void setup_dio_stream_encoder(struct pipe_ctx *pipe_ctx) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + if (!link_enc) { + ASSERT(link_enc); + return; + } + link_enc->funcs->connect_dig_be_to_fe(link_enc, pipe_ctx->stream_res.stream_enc->id, true); if (dc_is_dp_signal(pipe_ctx->stream->signal)) @@ -71,9 +78,16 @@ void setup_dio_stream_encoder(struct pipe_ctx *pipe_ctx) void reset_dio_stream_encoder(struct pipe_ctx *pipe_ctx) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + if (!link_enc) { + ASSERT(link_enc); + return; + } + if (!stream_enc) return; @@ -142,7 +156,14 @@ void enable_dio_dp_link_output(struct dc_link *link, enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } if (dc_is_dp_sst_signal(signal)) link_enc->funcs->enable_dp_output( @@ -162,11 +183,16 @@ void disable_dio_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; - if (link_enc != NULL) - link_enc->funcs->disable_output(link_enc, signal); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } + link_enc->funcs->disable_output(link_enc, signal); link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); } @@ -175,7 +201,14 @@ void set_dio_dp_link_test_pattern(struct dc_link *link, const struct link_resource *link_res, struct encoder_set_dp_phy_pattern_param *tp_params) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } link_enc->funcs->dp_set_phy_pattern(link_enc, tp_params); link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN); @@ -186,7 +219,14 @@ void set_dio_dp_lane_settings(struct dc_link *link, const struct dc_link_settings *link_settings, const struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } link_enc->funcs->dp_set_lane_settings(link_enc, link_settings, lane_settings); } @@ -195,9 +235,15 @@ void update_dio_stream_allocation_table(struct dc_link *link, const struct link_resource *link_res, const struct link_mst_stream_allocation_table *table) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + if (!link_enc) { + ASSERT(link_enc); + return; + } - ASSERT(link_enc); link_enc->funcs->update_mst_stream_allocation_table(link_enc, table); } @@ -282,7 +328,10 @@ static const struct link_hwss dio_link_hwss = { bool can_use_dio_link_hwss(const struct dc_link *link, const struct link_resource *link_res) { - return link->link_enc != NULL; + if (!link->dc->config.unify_link_enc_assignment) + return link->link_enc != NULL; + else + return link_res->dio_link_enc != NULL; } /** diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c index a6d1d7641ab4..e1dff4e3f446 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio_fixed_vs_pe_retimer.c @@ -127,7 +127,10 @@ static void set_dio_fixed_vs_pe_retimer_dp_link_test_pattern(struct dc_link *lin const struct link_resource *link_res, struct encoder_set_dp_phy_pattern_param *tp_params) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (!set_dio_fixed_vs_pe_retimer_dp_link_test_pattern_override( link, link_res, tp_params, get_dio_link_hwss())) { diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c index 36adf95744fe..81bf3c5e1fdf 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c @@ -35,12 +35,15 @@ static void update_dpia_stream_allocation_table(struct dc_link *link, const struct link_resource *link_res, const struct link_mst_stream_allocation_table *table) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; static enum dc_status status; uint8_t mst_alloc_slots = 0, prev_mst_slots_in_use = 0xFF; int i; DC_LOGGER_INIT(link->ctx->logger); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + for (i = 0; i < table->stream_count; i++) mst_alloc_slots += table->stream_allocations[i].slot_count; @@ -61,7 +64,10 @@ static void set_dio_dpia_link_test_pattern(struct dc_link *link, if (tp_params->dp_phy_pattern != DP_TEST_PATTERN_VIDEO_MODE) return; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (!link_enc) return; @@ -83,31 +89,28 @@ static void enable_dpia_link_output(struct dc_link *link, enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + DC_LOGGER_INIT(link->ctx->logger); + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc != NULL) { - if (link->dc->config.enable_dpia_pre_training && link_enc->funcs->enable_dpia_output) { + if (link->dc->config.enable_dpia_pre_training || link->dc->config.unify_link_enc_assignment) { uint8_t fec_rdy = link->dc->link_srv->dp_should_enable_fec(link); uint8_t digmode = dc_is_dp_sst_signal(signal) ? DIG_SST_MODE : DIG_MST_MODE; - link_enc->funcs->enable_dpia_output( - link_enc, - link_settings, - link->ddc_hw_inst, - digmode, - fec_rdy); - } else { - if (dc_is_dp_sst_signal(signal)) - link_enc->funcs->enable_dp_output( + if (link_enc->funcs->enable_dpia_output) + link_enc->funcs->enable_dpia_output( link_enc, link_settings, - clock_source); + link->ddc_hw_inst, + digmode, + fec_rdy); else - link_enc->funcs->enable_dp_mst_output( - link_enc, - link_settings, - clock_source); - } + DC_LOG_ERROR("%s: link encoder does not support enable_dpia_output\n", __func__); + } else + enable_dio_dp_link_output(link, link_res, signal, clock_source, link_settings); } @@ -119,13 +122,20 @@ static void disable_dpia_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + struct link_encoder *link_enc = link_res->dio_link_enc; + DC_LOGGER_INIT(link->ctx->logger); + + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc != NULL) { - if (link->dc->config.enable_dpia_pre_training && link_enc->funcs->disable_dpia_output) { + if (link->dc->config.enable_dpia_pre_training || link->dc->config.unify_link_enc_assignment) { uint8_t digmode = dc_is_dp_sst_signal(signal) ? DIG_SST_MODE : DIG_MST_MODE; - link_enc->funcs->disable_dpia_output(link_enc, link->ddc_hw_inst, digmode); + if (link_enc->funcs->disable_dpia_output) + link_enc->funcs->disable_dpia_output(link_enc, link->ddc_hw_inst, digmode); + else + DC_LOG_ERROR("%s: link encoder does not support disable_dpia_output\n", __func__); } else link_enc->funcs->disable_output(link_enc, signal); } @@ -154,8 +164,10 @@ static const struct link_hwss dpia_link_hwss = { bool can_use_dpia_link_hwss(const struct dc_link *link, const struct link_resource *link_res) { - return link->is_dig_mapping_flexible && - link->dc->res_pool->funcs->link_encs_assign; + if (!link->dc->config.unify_link_enc_assignment) + return link->is_dig_mapping_flexible && link->dc->res_pool->funcs->link_encs_assign; + else + return link->is_dig_mapping_flexible && link_res->dio_link_enc != NULL; } const struct link_hwss *get_dpia_link_hwss(void) 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 550e1a098fa2..cc9191a5c9e6 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -816,7 +816,10 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, { bool destrictive = false; struct dc_link_settings max_link_cap; - bool is_link_enc_unavailable = link->link_enc && + bool is_link_enc_unavailable = false; + + if (!link->dc->config.unify_link_enc_assignment) + is_link_enc_unavailable = link->link_enc && link->dc->res_pool->funcs->link_encs_assign && !link_enc_cfg_is_link_enc_avail( link->ctx->dc, 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 ec7de9c01fab..321fd1785370 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -652,15 +652,15 @@ static void write_i2c_redriver_setting( static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) { struct cp_psp *cp_psp = &pipe_ctx->stream->ctx->cp_psp; - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct cp_psp_stream_config config = {0}; enum dp_panel_mode panel_mode = dp_get_panel_mode(pipe_ctx->stream->link); if (cp_psp == NULL || cp_psp->funcs.update_stream_config == NULL) return; - - link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); ASSERT(link_enc); if (link_enc == NULL) return; @@ -1924,7 +1924,7 @@ static void disable_link_dp(struct dc_link *link, if (link_dp_get_encoding_format(&link_settings) == DP_8b_10b_ENCODING) { - dp_set_fec_enable(link, false); + dp_set_fec_enable(link, link_res, false); dp_set_fec_ready(link, link_res, false); } } @@ -2122,7 +2122,7 @@ static enum dc_status enable_link_dp(struct dc_state *state, fec_enable = true; if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) - dp_set_fec_enable(link, fec_enable); + dp_set_fec_enable(link, &pipe_ctx->link_res, fec_enable); // during mode set we do DP_SET_POWER off then on, aux writes are lost if (link->dpcd_sink_ext_caps.bits.oled == 1 || @@ -2461,7 +2461,7 @@ void link_set_dpms_on( struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->sink->link; enum dc_status status; - struct link_encoder *link_enc; + 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); @@ -2486,7 +2486,8 @@ void link_set_dpms_on( } } - link_enc = link_enc_cfg_get_link_enc(link); + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); if (!dc_is_virtual_signal(pipe_ctx->stream->signal) 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 e3e7fcb07f19..a77410122636 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 @@ -250,21 +250,21 @@ static uint32_t intersect_frl_link_bw_support( { uint32_t supported_bw_in_kbps = max_supported_frl_bw_in_kbps; - // HDMI_ENCODED_LINK_BW bits are only valid if HDMI Link Configuration bit is 1 (FRL mode) - if (hdmi_encoded_link_bw.bits.FRL_MODE) { - if (hdmi_encoded_link_bw.bits.BW_48Gbps) - supported_bw_in_kbps = 48000000; - else if (hdmi_encoded_link_bw.bits.BW_40Gbps) - supported_bw_in_kbps = 40000000; - else if (hdmi_encoded_link_bw.bits.BW_32Gbps) - supported_bw_in_kbps = 32000000; - else if (hdmi_encoded_link_bw.bits.BW_24Gbps) - supported_bw_in_kbps = 24000000; - else if (hdmi_encoded_link_bw.bits.BW_18Gbps) - supported_bw_in_kbps = 18000000; - else if (hdmi_encoded_link_bw.bits.BW_9Gbps) - supported_bw_in_kbps = 9000000; - } + /* Skip checking FRL_MODE bit, as certain PCON will clear + * it despite supporting the link BW indicated in the other bits. + */ + if (hdmi_encoded_link_bw.bits.BW_48Gbps) + supported_bw_in_kbps = 48000000; + else if (hdmi_encoded_link_bw.bits.BW_40Gbps) + supported_bw_in_kbps = 40000000; + else if (hdmi_encoded_link_bw.bits.BW_32Gbps) + supported_bw_in_kbps = 32000000; + else if (hdmi_encoded_link_bw.bits.BW_24Gbps) + supported_bw_in_kbps = 24000000; + else if (hdmi_encoded_link_bw.bits.BW_18Gbps) + supported_bw_in_kbps = 18000000; + else if (hdmi_encoded_link_bw.bits.BW_9Gbps) + supported_bw_in_kbps = 9000000; return supported_bw_in_kbps; } @@ -330,9 +330,12 @@ bool dp_is_fec_supported(const struct dc_link *link) /* TODO - use asic cap instead of link_enc->features * we no longer know which link enc to use for this link before commit */ - struct link_encoder *link_enc = NULL; + struct resource_context *res_ctx = &link->dc->current_state->res_ctx; + struct resource_pool *res_pool = link->dc->res_pool; + struct link_encoder *link_enc = get_temp_dio_link_enc(res_ctx, res_pool, link); - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); return (dc_is_dp_signal(link->connector_signal) && link_enc && @@ -1572,10 +1575,18 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link) /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ is_lttpr_present = dp_is_lttpr_present(link); - if (is_lttpr_present) + DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); + + if (is_lttpr_present) { CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); - DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); + core_link_read_dpcd(link, DP_LTTPR_IEEE_OUI, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui)); + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), "LTTPR IEEE OUI: "); + + core_link_read_dpcd(link, DP_LTTPR_DEVICE_ID, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id)); + CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), "LTTPR Device ID: "); + } + return status; } @@ -2089,18 +2100,32 @@ void detect_edp_sink_caps(struct dc_link *link) core_link_read_dpcd(link, DP_SINK_EMISSION_RATE, (uint8_t *)&link->dpcd_caps.edp_oled_emission_rate, sizeof(link->dpcd_caps.edp_oled_emission_rate)); + + /* + * Read Multi-SST (Single Stream Transport) capability + * for eDP version 1.4 or higher. + */ + if (link->dpcd_caps.dpcd_rev.raw >= DP_EDP_14) + core_link_read_dpcd( + link, + DP_EDP_MSO_LINK_CAPABILITIES, + (uint8_t *)&link->dpcd_caps.mso_cap_sst_links_supported, + sizeof(link->dpcd_caps.mso_cap_sst_links_supported)); } bool dp_get_max_link_enc_cap(const struct dc_link *link, struct dc_link_settings *max_link_enc_cap) { - struct link_encoder *link_enc = NULL; + struct resource_context *res_ctx = &link->dc->current_state->res_ctx; + struct resource_pool *res_pool = link->dc->res_pool; + struct link_encoder *link_enc = get_temp_dio_link_enc(res_ctx, res_pool, link); if (!max_link_enc_cap) { DC_LOG_ERROR("%s: Could not return max link encoder caps", __func__); return false; } - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); if (link_enc && link_enc->funcs->get_max_link_cap) { @@ -2128,10 +2153,13 @@ struct dc_link_settings dp_get_max_link_cap(struct dc_link *link) struct dc_link_settings max_link_cap = {0}; enum dc_link_rate lttpr_max_link_rate; enum dc_link_rate cable_max_link_rate; - struct link_encoder *link_enc = NULL; + struct resource_context *res_ctx = &link->dc->current_state->res_ctx; + struct resource_pool *res_pool = link->dc->res_pool; + struct link_encoder *link_enc = get_temp_dio_link_enc(res_ctx, res_pool, link); bool is_uhbr13_5_supported = true; - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); /* get max link encoder capability */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h index 8f0ce97f2362..0ce0af3ddbeb 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h @@ -67,6 +67,7 @@ bool dp_is_128b_132b_signal(struct pipe_ctx *pipe_ctx); /* Initialize output parameter lt_settings. */ void dp_decide_training_settings( struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_setting, struct link_training_settings *lt_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index 0f1c411523a2..a5541b8fc95b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -356,6 +356,32 @@ out: return ret; } +/* + * Handle DP BW allocation status register + * + * @link: pointer to the dc_link struct instance + * @status: content of DP tunneling status DPCD register + * + * return: none + */ +void link_dp_dpia_handle_bw_alloc_status(struct dc_link *link, uint8_t status) +{ + if (status & DP_TUNNELING_BW_REQUEST_SUCCEEDED) { + DC_LOG_DEBUG("%s: BW Allocation request succeeded on link(%d)", + __func__, link->link_index); + } else if (status & DP_TUNNELING_BW_REQUEST_FAILED) { + DC_LOG_DEBUG("%s: BW Allocation request failed on link(%d) allocated/estimated BW=%d", + __func__, link->link_index, link->dpia_bw_alloc_config.estimated_bw); + } else if (status & DP_TUNNELING_ESTIMATED_BW_CHANGED) { + DC_LOG_DEBUG("%s: Estimated BW changed on link(%d) new estimated BW=%d", + __func__, link->link_index, link->dpia_bw_alloc_config.estimated_bw); + } + + core_link_write_dpcd( + link, DP_TUNNELING_STATUS, + &status, sizeof(status)); +} + void dpia_handle_bw_alloc_response(struct dc_link *link, uint8_t bw, uint8_t result) { int bw_needed = 0; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h index 3b6d8494f9d5..1b240a2f6ce0 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.h @@ -108,4 +108,14 @@ bool dpia_validate_usb4_bw(struct dc_link **link, int *bw_needed, const unsigned */ int link_dp_dpia_get_dp_overhead_in_dp_tunneling(struct dc_link *link); +/* + * Handle DP BW allocation status register + * + * @link: pointer to the dc_link struct instance + * @status: content of DP tunneling status register + * + * return: none + */ +void link_dp_dpia_handle_bw_alloc_status(struct dc_link *link, uint8_t status); + #endif /* DC_INC_LINK_DP_DPIA_BW_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c index a08403c022ea..5be00e4ce10b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c @@ -37,6 +37,7 @@ #include "link/accessories/link_dp_trace.h" #include "link/link_dpms.h" #include "dm_helpers.h" +#include "link_dp_dpia_bw.h" #define DC_LOGGER \ link->ctx->logger @@ -286,6 +287,30 @@ void dp_handle_link_loss(struct dc_link *link) } } +static void dp_handle_tunneling_irq(struct dc_link *link) +{ + enum dc_status retval; + uint8_t tunneling_status = 0; + + retval = core_link_read_dpcd( + link, DP_TUNNELING_STATUS, + &tunneling_status, + sizeof(tunneling_status)); + + if (retval == DC_OK) { + DC_LOG_HW_HPD_IRQ("%s: Got DP tunneling status on link %d status=0x%x", + __func__, link->link_index, tunneling_status); + + if (tunneling_status & DP_TUNNELING_BW_ALLOC_BITS_MASK) + link_dp_dpia_handle_bw_alloc_status(link, tunneling_status); + } + + tunneling_status = DP_TUNNELING_IRQ; + core_link_write_dpcd( + link, DP_LINK_SERVICE_IRQ_VECTOR_ESI0, + &tunneling_status, 1); +} + static void read_dpcd204h_on_irq_hpd(struct dc_link *link, union hpd_irq_data *irq_data) { enum dc_status retval; @@ -319,13 +344,19 @@ enum dc_status dp_read_hpd_rx_irq_data( * * For DP 1.4 we need to read those from 2002h range. */ - if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14) + if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14) { retval = core_link_read_dpcd( link, DP_SINK_COUNT, irq_data->raw, - sizeof(union hpd_irq_data)); - else { + DP_SINK_STATUS - DP_SINK_COUNT + 1); + + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + retval = core_link_read_dpcd( + link, DP_LINK_SERVICE_IRQ_VECTOR_ESI0, + &irq_data->bytes.link_service_irq_esi0.raw, 1); + } + } else { /* Read 14 bytes in a single read and then copy only the required fields. * This is more efficient than doing it in two separate AUX reads. */ @@ -346,6 +377,7 @@ enum dc_status dp_read_hpd_rx_irq_data( irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI]; irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI]; irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI]; + irq_data->bytes.link_service_irq_esi0.raw = tmp[DP_LINK_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI]; /* * This display doesn't have correct values in DPCD200Eh. @@ -488,6 +520,11 @@ bool dp_handle_hpd_rx_irq(struct dc_link *link, dp_trace_link_loss_increment(link); } + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (hpd_irq_dpcd_data.bytes.link_service_irq_esi0.bits.DP_LINK_TUNNELING_IRQ) + dp_handle_tunneling_irq(link); + } + if (link->type == dc_connection_sst_branch && hpd_irq_dpcd_data.bytes.sink_cnt.bits.SINK_COUNT != link->dpcd_sink_count) diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c index c27ffec5d84f..49521ac4b0e8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c @@ -142,11 +142,12 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource * if the sink supports it and leave it enabled on link. * If FEC is not supported, disable it. */ - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = link_res->dio_link_enc; enum dc_status status = DC_OK; uint8_t fec_config = 0; - link_enc = link_enc_cfg_get_link_enc(link); + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); ASSERT(link_enc); if (link_enc->funcs->fec_set_ready == NULL) return DC_NOT_SUPPORTED; @@ -176,13 +177,14 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource return status; } -void dp_set_fec_enable(struct dc_link *link, bool enable) +void dp_set_fec_enable(struct dc_link *link, const struct link_resource *link_res, bool enable) { - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = link_res->dio_link_enc; - link_enc = link_enc_cfg_get_link_enc(link); - ASSERT(link_enc); - if (link_enc->funcs->fec_set_enable == NULL) + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + + if (link_enc == NULL || link_enc->funcs == NULL || link_enc->funcs->fec_set_enable == NULL) return; if (enable && dp_should_enable_fec(link)) { diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h index 1eb0619d6710..ab1c1f8f1f8b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.h @@ -52,7 +52,8 @@ void dp_set_drive_settings( enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource *link_res, bool ready); -void dp_set_fec_enable(struct dc_link *link, bool enable); +void dp_set_fec_enable(struct dc_link *link, + const struct link_resource *link_res, bool enable); void dpcd_write_rx_power_ctrl(struct dc_link *link, bool on); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 751c18e592ea..613298d21d03 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -801,19 +801,23 @@ enum dc_dp_training_pattern decide_cr_training_pattern( } enum dc_dp_training_pattern decide_eq_training_pattern(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc; + struct link_encoder *link_enc = link_res->dio_link_enc; struct encoder_feature_support *enc_caps; struct dpcd_caps *rx_caps = &link->dpcd_caps; enum dc_dp_training_pattern pattern = DP_TRAINING_PATTERN_SEQUENCE_2; - link_enc = link_enc_cfg_get_link_enc(link); - ASSERT(link_enc); - enc_caps = &link_enc->features; - switch (link_dp_get_encoding_format(link_settings)) { case DP_8b_10b_ENCODING: + if (!link->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); + + if (!link_enc) + break; + + enc_caps = &link_enc->features; if (enc_caps->flags.bits.IS_TPS4_CAPABLE && rx_caps->max_down_spread.bits.TPS4_SUPPORTED) pattern = DP_TRAINING_PATTERN_SEQUENCE_4; @@ -886,13 +890,14 @@ void dp_decide_lane_settings( void dp_decide_training_settings( struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings) { if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) - decide_8b_10b_training_settings(link, link_settings, lt_settings); + decide_8b_10b_training_settings(link, link_res, link_settings, lt_settings); else if (link_dp_get_encoding_format(link_settings) == DP_128b_132b_ENCODING) - decide_128b_132b_training_settings(link, link_settings, lt_settings); + decide_128b_132b_training_settings(link, link_res, link_settings, lt_settings); } @@ -1556,6 +1561,7 @@ enum link_training_result dp_perform_link_training( /* decide training settings */ dp_decide_training_settings( link, + link_res, link_settings, <_settings); @@ -1569,7 +1575,8 @@ enum link_training_result dp_perform_link_training( /* configure link prior to entering training mode */ dpcd_configure_lttpr_mode(link, <_settings); - dp_set_fec_ready(link, link_res, lt_settings.should_set_fec_ready); + if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) + dp_set_fec_ready(link, link_res, lt_settings.should_set_fec_ready); dpcd_configure_channel_coding(link, <_settings); /* enter training mode: diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h index 0b18aa35c33c..574b083e0936 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h @@ -104,6 +104,7 @@ void start_clock_recovery_pattern_early(struct dc_link *link, void dp_decide_training_settings( struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings); @@ -117,6 +118,7 @@ enum dc_dp_training_pattern decide_cr_training_pattern( const struct dc_link_settings *link_settings); enum dc_dp_training_pattern decide_eq_training_pattern(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings); enum lttpr_mode dp_decide_lttpr_mode(struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c index db87cfe37b5c..11565f187ac7 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.c @@ -204,6 +204,7 @@ enum link_training_result dp_perform_128b_132b_link_training( struct link_training_settings legacy_settings; decide_8b_10b_training_settings(link, + link_res, <_settings->link_settings, &legacy_settings); return dp_perform_8b_10b_link_training(link, link_res, &legacy_settings); @@ -227,6 +228,7 @@ enum link_training_result dp_perform_128b_132b_link_training( } void decide_128b_132b_training_settings(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings) { @@ -238,7 +240,7 @@ void decide_128b_132b_training_settings(struct dc_link *link, LINK_SPREAD_05_DOWNSPREAD_30KHZ; lt_settings->pattern_for_cr = decide_cr_training_pattern(link_settings); - lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_settings); + lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_res, link_settings); lt_settings->eq_pattern_time = 2500; lt_settings->eq_wait_time_limit = 400000; lt_settings->eq_loop_count_limit = 20; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h index 2147f24efc8b..901a42edafa1 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_128b_132b.h @@ -34,6 +34,7 @@ enum link_training_result dp_perform_128b_132b_link_training( struct link_training_settings *lt_settings); void decide_128b_132b_training_settings(struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_settings, struct link_training_settings *lt_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c index ae95ec48e572..34d2e097ca2e 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c @@ -93,7 +93,8 @@ static uint32_t get_eq_training_aux_rd_interval( } void decide_8b_10b_training_settings( - struct dc_link *link, + struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_setting, struct link_training_settings *lt_settings) { @@ -115,7 +116,7 @@ void decide_8b_10b_training_settings( LINK_SPREAD_DISABLED : LINK_SPREAD_05_DOWNSPREAD_30KHZ; lt_settings->eq_pattern_time = get_eq_training_aux_rd_interval(link, link_setting); lt_settings->pattern_for_cr = decide_cr_training_pattern(link_setting); - lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_setting); + lt_settings->pattern_for_eq = decide_eq_training_pattern(link, link_res, link_setting); lt_settings->enhanced_framing = 1; lt_settings->should_set_fec_ready = true; lt_settings->disallow_per_lane_settings = true; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h index d26de15ce954..ea0de701d83f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.h @@ -54,7 +54,8 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( enum lttpr_mode dp_decide_8b_10b_lttpr_mode(struct dc_link *link); void decide_8b_10b_training_settings( - struct dc_link *link, + struct dc_link *link, + const struct link_resource *link_res, const struct dc_link_settings *link_setting, struct link_training_settings *lt_settings); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c index 4c6b886a9da8..f99d26290bc0 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_auxless.c @@ -39,6 +39,7 @@ bool dp_perform_link_training_skip_aux( dp_decide_training_settings( link, + link_res, link_setting, <_settings); override_training_settings( diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c index 39e4b7dc9588..603537ffd128 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c @@ -110,6 +110,7 @@ static enum link_training_result dpia_configure_link( dp_decide_training_settings( link, + link_res, link_setting, lt_settings); @@ -129,11 +130,14 @@ static enum link_training_result dpia_configure_link( if (status != DC_OK && link->is_hpd_pending) return LINK_TRAINING_ABORT; - if (link->preferred_training_settings.fec_enable != NULL) - fec_enable = *link->preferred_training_settings.fec_enable; - else - fec_enable = true; - status = dp_set_fec_ready(link, link_res, fec_enable); + if (link_dp_get_encoding_format(link_setting) == DP_8b_10b_ENCODING) { + if (link->preferred_training_settings.fec_enable != NULL) + fec_enable = *link->preferred_training_settings.fec_enable; + else + fec_enable = true; + status = dp_set_fec_ready(link, link_res, fec_enable); + } + if (status != DC_OK && link->is_hpd_pending) return LINK_TRAINING_ABORT; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c index ccf8096dde29..ce174ce5579c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c @@ -270,7 +270,8 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence( rate = get_dpcd_link_rate(<_settings->link_settings); - if (!link->dpcd_caps.lttpr_caps.main_link_channel_coding.bits.DP_128b_132b_SUPPORTED) { + // Only perform toggle if FIXED_VS LTTPR reports no IEEE OUI + if (memcmp("\x0,\x0,\x0", &link->dpcd_caps.lttpr_caps.lttpr_ieee_oui[0], 3) == 0) { /* Vendor specific: Toggle link rate */ toggle_rate = (rate == 0x6) ? 0xA : 0x6; diff --git a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h index 9267cdf88e9a..ce6fbcf14d7a 100644 --- a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h +++ b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h @@ -63,8 +63,7 @@ uint32_t MPC_MCM_SECOND_GAMUT_REMAP_C31_C32_B[MAX_MPCC]; \ uint32_t MPC_MCM_SECOND_GAMUT_REMAP_C33_C34_B[MAX_MPCC]; \ uint32_t MPCC_MCM_3DLUT_FAST_LOAD_SELECT[MAX_MPCC]; \ - uint32_t MPCC_MCM_3DLUT_FAST_LOAD_STATUS[MAX_MPCC]; \ - uint32_t MPCC_CONTROL2[MAX_MPCC] + uint32_t MPCC_MCM_3DLUT_FAST_LOAD_STATUS[MAX_MPCC]; #define MPC_COMMON_MASK_SH_LIST_DCN4_01(mask_sh) \ MPC_COMMON_MASK_SH_LIST_DCN32(mask_sh), \ @@ -184,7 +183,7 @@ struct dcn401_mpc_mask { }; struct dcn401_mpc_registers { - MPC_REG_VARIABLE_LIST_DCN4_01; + MPC_REG_VARIABLE_LIST_DCN4_01 }; struct dcn401_mpc { @@ -236,7 +235,29 @@ void mpc401_get_gamut_remap( struct mpc *mpc, int mpcc_id, struct mpc_grph_gamut_adjustment *adjust); -void mpc401_update_3dlut_fast_load_select(struct mpc *mpc, int mpcc_id, int hubp_idx); -void mpc401_get_3dlut_fast_load_status(struct mpc *mpc, int mpcc_id, uint32_t *done, uint32_t *soft_underflow, uint32_t *hard_underflow); + +void mpc401_update_3dlut_fast_load_select( + struct mpc *mpc, + int mpcc_id, + int hubp_idx); + +void mpc401_get_3dlut_fast_load_status( + struct mpc *mpc, + int mpcc_id, + uint32_t *done, + uint32_t *soft_underflow, + uint32_t *hard_underflow); + +void mpc401_update_3dlut_fast_load_select( + struct mpc *mpc, + int mpcc_id, + int hubp_idx); + +void mpc401_get_3dlut_fast_load_status( + struct mpc *mpc, + int mpcc_id, + uint32_t *done, + uint32_t *soft_underflow, + uint32_t *hard_underflow); #endif diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h index a6d4dbe82c13..8b2a8455eb56 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h @@ -104,120 +104,115 @@ SRI(OTG_MANUAL_FLOW_CONTROL, OTG, inst) +#define OPTC_REG_VARIABLE_LIST_DCN \ + uint32_t OTG_GLOBAL_CONTROL1; \ + uint32_t OTG_GLOBAL_CONTROL2; \ + uint32_t OTG_VERT_SYNC_CONTROL; \ + uint32_t OTG_MASTER_UPDATE_MODE; \ + uint32_t OTG_GSL_CONTROL; \ + uint32_t OTG_VSTARTUP_PARAM; \ + uint32_t OTG_VUPDATE_PARAM; \ + uint32_t OTG_VREADY_PARAM; \ + uint32_t OTG_BLANK_CONTROL; \ + uint32_t OTG_MASTER_UPDATE_LOCK; \ + uint32_t OTG_GLOBAL_CONTROL0; \ + uint32_t OTG_DOUBLE_BUFFER_CONTROL; \ + uint32_t OTG_H_TOTAL; \ + uint32_t OTG_H_BLANK_START_END; \ + uint32_t OTG_H_SYNC_A; \ + uint32_t OTG_H_SYNC_A_CNTL; \ + uint32_t OTG_H_TIMING_CNTL; \ + uint32_t OTG_V_TOTAL; \ + uint32_t OTG_V_BLANK_START_END; \ + uint32_t OTG_V_SYNC_A; \ + uint32_t OTG_V_SYNC_A_CNTL; \ + uint32_t OTG_INTERLACE_CONTROL; \ + uint32_t OTG_CONTROL; \ + uint32_t OTG_STEREO_CONTROL; \ + uint32_t OTG_3D_STRUCTURE_CONTROL; \ + uint32_t OTG_STEREO_STATUS; \ + uint32_t OTG_V_TOTAL_MAX; \ + uint32_t OTG_V_TOTAL_MID; \ + uint32_t OTG_V_TOTAL_MIN; \ + uint32_t OTG_V_TOTAL_CONTROL; \ + uint32_t OTG_V_COUNT_STOP_CONTROL; \ + uint32_t OTG_V_COUNT_STOP_CONTROL2; \ + uint32_t OTG_TRIGA_CNTL; \ + uint32_t OTG_TRIGA_MANUAL_TRIG; \ + uint32_t OTG_MANUAL_FLOW_CONTROL; \ + uint32_t OTG_FORCE_COUNT_NOW_CNTL; \ + uint32_t OTG_STATIC_SCREEN_CONTROL; \ + uint32_t OTG_STATUS_FRAME_COUNT; \ + uint32_t OTG_STATUS; \ + uint32_t OTG_STATUS_POSITION; \ + uint32_t OTG_NOM_VERT_POSITION; \ + uint32_t OTG_BLACK_COLOR; \ + uint32_t OTG_TEST_PATTERN_PARAMETERS; \ + uint32_t OTG_TEST_PATTERN_CONTROL; \ + uint32_t OTG_TEST_PATTERN_COLOR; \ + uint32_t OTG_CLOCK_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT0_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT0_POSITION; \ + uint32_t OTG_VERTICAL_INTERRUPT1_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT1_POSITION; \ + uint32_t OTG_VERTICAL_INTERRUPT2_CONTROL; \ + uint32_t OTG_VERTICAL_INTERRUPT2_POSITION; \ + uint32_t OPTC_INPUT_CLOCK_CONTROL; \ + uint32_t OPTC_DATA_SOURCE_SELECT; \ + uint32_t OPTC_MEMORY_CONFIG; \ + uint32_t OPTC_INPUT_GLOBAL_CONTROL; \ + uint32_t CONTROL; \ + uint32_t OTG_GSL_WINDOW_X; \ + uint32_t OTG_GSL_WINDOW_Y; \ + uint32_t OTG_VUPDATE_KEEPOUT; \ + uint32_t OTG_CRC_CNTL; \ + uint32_t OTG_CRC_CNTL2; \ + uint32_t OTG_CRC0_DATA_RG; \ + uint32_t OTG_CRC0_DATA_B; \ + uint32_t OTG_CRC1_DATA_B; \ + uint32_t OTG_CRC2_DATA_B; \ + uint32_t OTG_CRC3_DATA_B; \ + uint32_t OTG_CRC1_DATA_RG; \ + uint32_t OTG_CRC2_DATA_RG; \ + uint32_t OTG_CRC3_DATA_RG; \ + uint32_t OTG_CRC0_WINDOWA_X_CONTROL; \ + uint32_t OTG_CRC0_WINDOWA_Y_CONTROL; \ + uint32_t OTG_CRC0_WINDOWB_X_CONTROL; \ + uint32_t OTG_CRC0_WINDOWB_Y_CONTROL; \ + uint32_t OTG_CRC1_WINDOWA_X_CONTROL; \ + uint32_t OTG_CRC1_WINDOWA_Y_CONTROL; \ + uint32_t OTG_CRC1_WINDOWB_X_CONTROL; \ + uint32_t OTG_CRC1_WINDOWB_Y_CONTROL; \ + uint32_t GSL_SOURCE_SELECT; \ + uint32_t DWB_SOURCE_SELECT; \ + uint32_t OTG_DSC_START_POSITION; \ + uint32_t OPTC_DATA_FORMAT_CONTROL; \ + uint32_t OPTC_BYTES_PER_PIXEL; \ + uint32_t OPTC_WIDTH_CONTROL; \ + uint32_t OTG_DRR_CONTROL; \ + uint32_t OTG_BLANK_DATA_COLOR; \ + uint32_t OTG_BLANK_DATA_COLOR_EXT; \ + uint32_t OTG_DRR_TRIGGER_WINDOW; \ + uint32_t OTG_M_CONST_DTO0; \ + uint32_t OTG_M_CONST_DTO1; \ + uint32_t OTG_DRR_V_TOTAL_CHANGE; \ + uint32_t OTG_GLOBAL_CONTROL4; \ + uint32_t OTG_CRC0_WINDOWA_X_CONTROL_READBACK; \ + uint32_t OTG_CRC0_WINDOWA_Y_CONTROL_READBACK; \ + uint32_t OTG_CRC0_WINDOWB_X_CONTROL_READBACK; \ + uint32_t OTG_CRC0_WINDOWB_Y_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWA_X_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWA_Y_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWB_X_CONTROL_READBACK; \ + uint32_t OTG_CRC1_WINDOWB_Y_CONTROL_READBACK; \ + uint32_t OPTC_CLOCK_CONTROL; \ + uint32_t OPTC_WIDTH_CONTROL2; \ + uint32_t OTG_PSTATE_REGISTER; \ + uint32_t OTG_PIPE_UPDATE_STATUS; \ + uint32_t INTERRUPT_DEST + struct dcn_optc_registers { - uint32_t OTG_GLOBAL_CONTROL1; - uint32_t OTG_GLOBAL_CONTROL2; - uint32_t OTG_VERT_SYNC_CONTROL; - uint32_t OTG_MASTER_UPDATE_MODE; - uint32_t OTG_GSL_CONTROL; - uint32_t OTG_VSTARTUP_PARAM; - uint32_t OTG_VUPDATE_PARAM; - uint32_t OTG_VREADY_PARAM; - uint32_t OTG_BLANK_CONTROL; - uint32_t OTG_MASTER_UPDATE_LOCK; - uint32_t OTG_GLOBAL_CONTROL0; - uint32_t OTG_DOUBLE_BUFFER_CONTROL; - uint32_t OTG_H_TOTAL; - uint32_t OTG_H_BLANK_START_END; - uint32_t OTG_H_SYNC_A; - uint32_t OTG_H_SYNC_A_CNTL; - uint32_t OTG_H_TIMING_CNTL; - uint32_t OTG_V_TOTAL; - uint32_t OTG_V_BLANK_START_END; - uint32_t OTG_V_SYNC_A; - uint32_t OTG_V_SYNC_A_CNTL; - uint32_t OTG_INTERLACE_CONTROL; - uint32_t OTG_CONTROL; - uint32_t OTG_STEREO_CONTROL; - uint32_t OTG_3D_STRUCTURE_CONTROL; - uint32_t OTG_STEREO_STATUS; - uint32_t OTG_V_TOTAL_MAX; - uint32_t OTG_V_TOTAL_MID; - uint32_t OTG_V_TOTAL_MIN; - uint32_t OTG_V_TOTAL_CONTROL; - uint32_t OTG_V_COUNT_STOP_CONTROL; - uint32_t OTG_V_COUNT_STOP_CONTROL2; - uint32_t OTG_TRIGA_CNTL; - uint32_t OTG_TRIGA_MANUAL_TRIG; - uint32_t OTG_MANUAL_FLOW_CONTROL; - uint32_t OTG_FORCE_COUNT_NOW_CNTL; - uint32_t OTG_STATIC_SCREEN_CONTROL; - uint32_t OTG_STATUS_FRAME_COUNT; - uint32_t OTG_STATUS; - uint32_t OTG_STATUS_POSITION; - uint32_t OTG_NOM_VERT_POSITION; - uint32_t OTG_BLACK_COLOR; - uint32_t OTG_TEST_PATTERN_PARAMETERS; - uint32_t OTG_TEST_PATTERN_CONTROL; - uint32_t OTG_TEST_PATTERN_COLOR; - uint32_t OTG_CLOCK_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT0_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT0_POSITION; - uint32_t OTG_VERTICAL_INTERRUPT1_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT1_POSITION; - uint32_t OTG_VERTICAL_INTERRUPT2_CONTROL; - uint32_t OTG_VERTICAL_INTERRUPT2_POSITION; - uint32_t OPTC_INPUT_CLOCK_CONTROL; - uint32_t OPTC_DATA_SOURCE_SELECT; - uint32_t OPTC_MEMORY_CONFIG; - uint32_t OPTC_INPUT_GLOBAL_CONTROL; - uint32_t CONTROL; - uint32_t OTG_GSL_WINDOW_X; - uint32_t OTG_GSL_WINDOW_Y; - uint32_t OTG_VUPDATE_KEEPOUT; - uint32_t OTG_CRC_CNTL; - uint32_t OTG_CRC_CNTL2; - uint32_t OTG_CRC0_DATA_RG; - uint32_t OTG_CRC1_DATA_RG; - uint32_t OTG_CRC2_DATA_RG; - uint32_t OTG_CRC3_DATA_RG; - uint32_t OTG_CRC0_DATA_B; - uint32_t OTG_CRC1_DATA_B; - uint32_t OTG_CRC2_DATA_B; - uint32_t OTG_CRC3_DATA_B; - uint32_t OTG_CRC0_DATA_R; - uint32_t OTG_CRC1_DATA_R; - uint32_t OTG_CRC2_DATA_R; - uint32_t OTG_CRC3_DATA_R; - uint32_t OTG_CRC0_DATA_G; - uint32_t OTG_CRC1_DATA_G; - uint32_t OTG_CRC2_DATA_G; - uint32_t OTG_CRC3_DATA_G; - uint32_t OTG_CRC0_WINDOWA_X_CONTROL; - uint32_t OTG_CRC0_WINDOWA_Y_CONTROL; - uint32_t OTG_CRC0_WINDOWB_X_CONTROL; - uint32_t OTG_CRC0_WINDOWB_Y_CONTROL; - uint32_t OTG_CRC1_WINDOWA_X_CONTROL; - uint32_t OTG_CRC1_WINDOWA_Y_CONTROL; - uint32_t OTG_CRC1_WINDOWB_X_CONTROL; - uint32_t OTG_CRC1_WINDOWB_Y_CONTROL; - uint32_t GSL_SOURCE_SELECT; - uint32_t DWB_SOURCE_SELECT; - uint32_t OTG_DSC_START_POSITION; - uint32_t OPTC_DATA_FORMAT_CONTROL; - uint32_t OPTC_BYTES_PER_PIXEL; - uint32_t OPTC_WIDTH_CONTROL; - uint32_t OTG_DRR_CONTROL; - uint32_t OTG_BLANK_DATA_COLOR; - uint32_t OTG_BLANK_DATA_COLOR_EXT; - uint32_t OTG_DRR_TRIGGER_WINDOW; - uint32_t OTG_M_CONST_DTO0; - uint32_t OTG_M_CONST_DTO1; - uint32_t OTG_DRR_V_TOTAL_CHANGE; - uint32_t OTG_GLOBAL_CONTROL4; - uint32_t OTG_CRC0_WINDOWA_X_CONTROL_READBACK; - uint32_t OTG_CRC0_WINDOWA_Y_CONTROL_READBACK; - uint32_t OTG_CRC0_WINDOWB_X_CONTROL_READBACK; - uint32_t OTG_CRC0_WINDOWB_Y_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWA_X_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWA_Y_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWB_X_CONTROL_READBACK; - uint32_t OTG_CRC1_WINDOWB_Y_CONTROL_READBACK; - uint32_t OPTC_CLOCK_CONTROL; - uint32_t OPTC_WIDTH_CONTROL2; - uint32_t OTG_PSTATE_REGISTER; - uint32_t OTG_PIPE_UPDATE_STATUS; - uint32_t INTERRUPT_DEST; + OPTC_REG_VARIABLE_LIST_DCN; }; #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index 5c6dc710e96c..e4eca3e32c1b 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c @@ -1220,7 +1220,7 @@ static void get_pixel_clock_parameters( struct pipe_ctx *odm_pipe; int opp_cnt = 1; struct dc_link *link = stream->link; - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct dc *dc = pipe_ctx->stream->ctx->dc; struct dce_hwseq *hws = dc->hwseq; @@ -1229,7 +1229,8 @@ static void get_pixel_clock_parameters( pixel_clk_params->requested_pix_clk_100hz = stream->timing.pix_clk_100hz; - link_enc = link_enc_cfg_get_link_enc(link); + if (!dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc) pixel_clk_params->encoder_object_id = link_enc->id; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c index 911bd60d4fbc..3c42ba8566cf 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c @@ -890,7 +890,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = true, .enable_legacy_fast_update = true, .enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/ - .dml_hostvm_override = DML_HOSTVM_NO_OVERRIDE, + .dml_hostvm_override = DML_HOSTVM_OVERRIDE_FALSE, .using_dml2 = false, }; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c index 4e842f29d4c4..7436dfbdf927 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c @@ -1666,12 +1666,13 @@ static void dcn401_build_pipe_pix_clk_params(struct pipe_ctx *pipe_ctx) { const struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; - struct link_encoder *link_enc = NULL; + struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc; struct pixel_clk_params *pixel_clk_params = &pipe_ctx->stream_res.pix_clk_params; pixel_clk_params->requested_pix_clk_100hz = stream->timing.pix_clk_100hz; - link_enc = link_enc_cfg_get_link_enc(link); + if (!pipe_ctx->stream->ctx->dc->config.unify_link_enc_assignment) + link_enc = link_enc_cfg_get_link_enc(link); if (link_enc) pixel_clk_params->encoder_object_id = link_enc->id; diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c index 31495c9978b0..28348734d900 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c @@ -3,12 +3,11 @@ // Copyright 2024 Advanced Micro Devices, Inc. #include "dc_spl.h" -#include "dc_spl_scl_filters.h" #include "dc_spl_scl_easf_filters.h" #include "dc_spl_isharp_filters.h" #include "spl_debug.h" -#define IDENTITY_RATIO(ratio) (spl_fixpt_u2d19(ratio) == (1 << 19)) +#define IDENTITY_RATIO(ratio) (spl_fixpt_u3d19(ratio) == (1 << 19)) #define MIN_VIEWPORT_SIZE 12 static bool spl_is_yuv420(enum spl_pixel_format format) @@ -76,6 +75,21 @@ static struct spl_rect shift_rec(const struct spl_rect *rec_in, int x, int y) return rec_out; } +static void spl_opp_adjust_rect(struct spl_rect *rec, const struct spl_opp_adjust *adjust) +{ + if ((rec->x + adjust->x) >= 0) + rec->x += adjust->x; + + if ((rec->y + adjust->y) >= 0) + rec->y += adjust->y; + + if ((rec->width + adjust->width) >= 1) + rec->width += adjust->width; + + if ((rec->height + adjust->height) >= 1) + rec->height += adjust->height; +} + static struct spl_rect calculate_plane_rec_in_timing_active( struct spl_in *spl_in, const struct spl_rect *rec_in) @@ -723,13 +737,15 @@ static void spl_handle_3d_recout(struct spl_in *spl_in, struct spl_rect *recout) } } -static void spl_clamp_viewport(struct spl_rect *viewport) +static void spl_clamp_viewport(struct spl_rect *viewport, int min_viewport_size) { + if (min_viewport_size == 0) + min_viewport_size = MIN_VIEWPORT_SIZE; /* Clamp minimum viewport size */ - if (viewport->height < MIN_VIEWPORT_SIZE) - viewport->height = MIN_VIEWPORT_SIZE; - if (viewport->width < MIN_VIEWPORT_SIZE) - viewport->width = MIN_VIEWPORT_SIZE; + if (viewport->height < min_viewport_size) + viewport->height = min_viewport_size; + if (viewport->width < min_viewport_size) + viewport->width = min_viewport_size; } static enum scl_mode spl_get_dscl_mode(const struct spl_in *spl_in, @@ -870,6 +886,8 @@ static bool spl_get_isharp_en(struct spl_in *spl_in, static void spl_get_taps_non_adaptive_scaler( struct spl_scratch *spl_scratch, const struct spl_taps *in_taps) { + bool check_max_downscale = false; + if (in_taps->h_taps == 0) { if (spl_fixpt_ceil(spl_scratch->scl_data.ratios.horz) > 1) spl_scratch->scl_data.taps.h_taps = spl_min(2 * spl_fixpt_ceil( @@ -909,6 +927,23 @@ static void spl_get_taps_non_adaptive_scaler( else spl_scratch->scl_data.taps.h_taps_c = in_taps->h_taps_c; + + /* + * Max downscale supported is 6.0x. Add ASSERT to catch if go beyond that + */ + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.horz, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.vert, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.horz_c, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + check_max_downscale = spl_fixpt_le(spl_scratch->scl_data.ratios.vert_c, + spl_fixpt_from_fraction(6, 1)); + SPL_ASSERT(check_max_downscale); + if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz)) spl_scratch->scl_data.taps.h_taps = 1; if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert)) @@ -927,8 +962,8 @@ static bool spl_get_optimal_number_of_taps( bool *enable_isharp) { int num_part_y, num_part_c; - int max_taps_y, max_taps_c; - int min_taps_y, min_taps_c; + unsigned int max_taps_y, max_taps_c; + unsigned int min_taps_y, min_taps_c; enum lb_memory_config lb_config; bool skip_easf = false; bool is_subsampled = spl_is_subsampled_format(spl_in->basic_in.format); @@ -990,12 +1025,18 @@ static bool spl_get_optimal_number_of_taps( lb_config, &num_part_y, &num_part_c); /* MAX_V_TAPS = MIN (NUM_LINES - MAX(CEILING(V_RATIO,1)-2, 0), 8) */ if (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) > 2) - max_taps_y = num_part_y - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) - 2); + if ((spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) - 2) > num_part_y) + max_taps_y = 0; + else + max_taps_y = num_part_y - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert) - 2); else max_taps_y = num_part_y; if (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) > 2) - max_taps_c = num_part_c - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) - 2); + if ((spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) - 2) > num_part_c) + max_taps_c = 0; + else + max_taps_c = num_part_c - (spl_fixpt_ceil(spl_scratch->scl_data.ratios.vert_c) - 2); else max_taps_c = num_part_c; @@ -1764,6 +1805,8 @@ static bool spl_calculate_number_of_taps(struct spl_in *spl_in, struct spl_scrat spl_calculate_recout(spl_in, spl_scratch, spl_out); /* depends on pixel format */ spl_calculate_scaling_ratios(spl_in, spl_scratch, spl_out); + /* Adjust recout for opp if needed */ + spl_opp_adjust_rect(&spl_scratch->scl_data.recout, &spl_in->basic_in.opp_recout_adjust); /* depends on scaling ratios and recout, does not calculate offset yet */ spl_calculate_viewport_size(spl_in, spl_scratch); @@ -1775,7 +1818,7 @@ static bool spl_calculate_number_of_taps(struct spl_in *spl_in, struct spl_scrat } /* Calculate scaler parameters */ -bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) +bool SPL_NAMESPACE(spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)) { bool res = false; bool enable_easf_v = false; @@ -1800,7 +1843,7 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) // Handle 3d recout spl_handle_3d_recout(spl_in, &spl_scratch.scl_data.recout); // Clamp - spl_clamp_viewport(&spl_scratch.scl_data.viewport); + spl_clamp_viewport(&spl_scratch.scl_data.viewport, spl_in->min_viewport_size); // Save all calculated parameters in dscl_prog_data structure to program hw registers spl_set_dscl_prog_data(spl_in, &spl_scratch, spl_out, enable_easf_v, enable_easf_h, enable_isharp); @@ -1840,7 +1883,7 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) } /* External interface to get number of taps only */ -bool spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out) +bool SPL_NAMESPACE(spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out)) { bool res = false; bool enable_easf_v = false; diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h index 02a2d6725ed5..145961803a92 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.h @@ -9,10 +9,22 @@ #define BLACK_OFFSET_RGB_Y 0x0 #define BLACK_OFFSET_CBCR 0x8000 +#ifndef SPL_PFX_ +#define SPL_PFX_ +#endif + +#define SPL_EXPAND2(a, b) a##b +#define SPL_EXPAND(a, b) SPL_EXPAND2(a, b) +#define SPL_NAMESPACE(symbol) SPL_EXPAND(SPL_PFX_, symbol) + +#ifdef __cplusplus +extern "C" { +#endif + /* SPL interfaces */ -bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out); +bool SPL_NAMESPACE(spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)); -bool spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out); +bool SPL_NAMESPACE(spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out)); #endif /* __DC_SPL_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h index 467af9dd90de..1c3949b24611 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h +++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl_types.h @@ -427,6 +427,14 @@ struct spl_out { // SPL inputs +// opp extra adjustment for rect +struct spl_opp_adjust { + int x; + int y; + int width; + int height; +}; + // Basic input information struct basic_in { enum spl_pixel_format format; // Pixel Format @@ -444,6 +452,7 @@ struct basic_in { } num_slices_recout_width; } num_h_slices_recout_width_align; int mpc_h_slice_index; // previous mpc_combine_v - split_idx + struct spl_opp_adjust opp_recout_adjust; // Inputs for adaptive scaler - TODO enum spl_transfer_func_type tf_type; /* Transfer function type */ enum spl_transfer_func_predefined tf_predefined_type; /* Transfer function predefined type */ @@ -484,7 +493,7 @@ struct spl_sharpness_range { }; struct adaptive_sharpness { bool enable; - int sharpness_level; + unsigned int sharpness_level; struct spl_sharpness_range sharpness_range; }; enum linear_light_scaling { // convert it in translation logic @@ -535,6 +544,7 @@ struct spl_in { bool is_hdr_on; int h_active; int v_active; + int min_viewport_size; int sdr_white_level_nits; enum sharpen_policy sharpen_policy; }; diff --git a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c index 131f1e3949d3..52d97918a3bd 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c +++ b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.c @@ -346,7 +346,7 @@ struct spl_fixed31_32 spl_fixpt_exp(struct spl_fixed31_32 arg) if (m > 0) return spl_fixpt_shl( spl_fixed31_32_exp_from_taylor_series(r), - (unsigned char)m); + (unsigned int)m); else return spl_fixpt_div_int( spl_fixed31_32_exp_from_taylor_series(r), diff --git a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h index ed2647f9a099..9f349ffe9148 100644 --- a/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h +++ b/drivers/gpu/drm/amd/display/dc/sspl/spl_fixpt31_32.h @@ -189,7 +189,7 @@ static inline struct spl_fixed31_32 spl_fixpt_clamp( * @brief * result = arg << shift */ -static inline struct spl_fixed31_32 spl_fixpt_shl(struct spl_fixed31_32 arg, unsigned char shift) +static inline struct spl_fixed31_32 spl_fixpt_shl(struct spl_fixed31_32 arg, unsigned int shift) { SPL_ASSERT(((arg.value >= 0) && (arg.value <= LLONG_MAX >> shift)) || ((arg.value < 0) && (arg.value >= ~(LLONG_MAX >> shift)))); @@ -203,7 +203,7 @@ static inline struct spl_fixed31_32 spl_fixpt_shl(struct spl_fixed31_32 arg, uns * @brief * result = arg >> shift */ -static inline struct spl_fixed31_32 spl_fixpt_shr(struct spl_fixed31_32 arg, unsigned char shift) +static inline struct spl_fixed31_32 spl_fixpt_shr(struct spl_fixed31_32 arg, unsigned int shift) { bool negative = arg.value < 0; 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 8cf89aed024b..f84bbc033e64 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -161,6 +161,13 @@ #endif /** + * OS/FW agnostic memcmp + */ +#ifndef dmub_memcmp +#define dmub_memcmp(lhs, rhs, bytes) memcmp((lhs), (rhs), (bytes)) +#endif + +/** * OS/FW agnostic udelay */ #ifndef dmub_udelay @@ -1460,6 +1467,11 @@ enum dmub_cmd_type { */ DMUB_CMD__PSP = 88, + /** + * Command type used for all Fused IO commands. + */ + DMUB_CMD__FUSED_IO = 89, + DMUB_CMD__VBIOS = 128, }; @@ -1491,6 +1503,10 @@ enum dmub_out_cmd_type { * Command type used for HPD redetect notification */ DMUB_OUT_CMD__HPD_SENSE_NOTIFY = 6, + /** + * Command type used for Fused IO notification + */ + DMUB_OUT_CMD__FUSED_IO = 7, }; /* DMUB_CMD__DPIA command sub-types. */ @@ -5325,6 +5341,63 @@ struct dmub_rb_cmd_get_usbc_cable_id { } data; }; +enum dmub_cmd_fused_io_sub_type { + DMUB_CMD__FUSED_IO_EXECUTE = 0, + DMUB_CMD__FUSED_IO_ABORT = 1, +}; + +enum dmub_cmd_fused_request_type { + FUSED_REQUEST_READ, + FUSED_REQUEST_WRITE, + FUSED_REQUEST_POLL, +}; + +enum dmub_cmd_fused_request_status { + FUSED_REQUEST_STATUS_SUCCESS, + FUSED_REQUEST_STATUS_BEGIN, + FUSED_REQUEST_STATUS_SUBMIT, + FUSED_REQUEST_STATUS_REPLY, + FUSED_REQUEST_STATUS_POLL, + FUSED_REQUEST_STATUS_ABORTED, + FUSED_REQUEST_STATUS_FAILED = 0x80, + FUSED_REQUEST_STATUS_INVALID, + FUSED_REQUEST_STATUS_BUSY, + FUSED_REQUEST_STATUS_TIMEOUT, + FUSED_REQUEST_STATUS_POLL_TIMEOUT, +}; + +struct dmub_cmd_fused_request { + uint8_t status; + uint8_t type : 2; + uint8_t _reserved0 : 3; + uint8_t poll_mask_msb : 3; // Number of MSB to zero out from last byte before comparing + uint8_t identifier; + uint8_t _reserved1; + uint32_t timeout_us; + union dmub_cmd_fused_request_location { + struct dmub_cmd_fused_request_location_i2c { + uint8_t is_aux : 1; // False + uint8_t ddc_line : 3; + uint8_t _reserved0 : 4; + uint8_t address; + uint8_t offset; + uint8_t length; + } i2c; + struct dmub_cmd_fused_request_location_aux { + uint32_t is_aux : 1; // True + uint32_t ddc_line : 3; + uint32_t address : 20; + uint32_t length : 8; // Automatically split into 16B transactions + } aux; + } u; + uint8_t buffer[0x30]; // Read: out, write: in, poll: expected +}; + +struct dmub_rb_cmd_fused_io { + struct dmub_cmd_header header; + struct dmub_cmd_fused_request request; +}; + /** * Command type of a DMUB_CMD__SECURE_DISPLAY command */ @@ -5738,6 +5811,8 @@ union dmub_rb_cmd { struct dmub_rb_cmd_fams2_drr_update fams2_drr_update; struct dmub_rb_cmd_fams2_flip fams2_flip; + + struct dmub_rb_cmd_fused_io fused_io; }; /** @@ -5768,6 +5843,7 @@ union dmub_rb_out_cmd { * HPD sense notification command. */ struct dmub_rb_cmd_hpd_sense_notify hpd_sense_notify; + struct dmub_rb_cmd_fused_io fused_io; }; #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index 3d0bba602b53..9796077885c9 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -83,8 +83,8 @@ static inline void dmub_dcn31_translate_addr(const union dmub_addr *addr_in, void dmub_dcn31_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 100; - uint32_t in_reset, scratch, i, pwait_mode; + const uint32_t timeout = 100000; + uint32_t in_reset, is_enabled, scratch, i, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); @@ -108,7 +108,7 @@ void dmub_dcn31_reset(struct dmub_srv *dmub) } for (i = 0; i < timeout; ++i) { - scratch = dmub->hw_funcs.get_gpint_response(dmub); + scratch = REG_READ(DMCUB_SCRATCH7); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; @@ -125,9 +125,14 @@ void dmub_dcn31_reset(struct dmub_srv *dmub) /* Force reset in case we timed out, DMCUB is likely hung. */ } - REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); - REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); - REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enabled); + + if (is_enabled) { + REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); + } + REG_WRITE(DMCUB_INBOX1_RPTR, 0); REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c index e5e77bd3c31e..01d013a12b94 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c @@ -88,7 +88,7 @@ static inline void dmub_dcn35_translate_addr(const union dmub_addr *addr_in, void dmub_dcn35_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 100; + const uint32_t timeout = 100000; uint32_t in_reset, is_enabled, scratch, i, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); @@ -113,7 +113,7 @@ void dmub_dcn35_reset(struct dmub_srv *dmub) } for (i = 0; i < timeout; ++i) { - scratch = dmub->hw_funcs.get_gpint_response(dmub); + scratch = REG_READ(DMCUB_SCRATCH7); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c index 39a8cb6d7523..e1c4fe1c6e3e 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.c @@ -63,8 +63,10 @@ static inline void dmub_dcn401_translate_addr(const union dmub_addr *addr_in, void dmub_dcn401_reset(struct dmub_srv *dmub) { union dmub_gpint_data_register cmd; - const uint32_t timeout = 30; - uint32_t in_reset, scratch, i; + const uint32_t timeout_us = 1 * 1000 * 1000; //1s + const uint32_t poll_delay_us = 1; //1us + uint32_t i = 0; + uint32_t in_reset, scratch, pwait_mode; REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &in_reset); @@ -75,32 +77,35 @@ void dmub_dcn401_reset(struct dmub_srv *dmub) dmub->hw_funcs.set_gpint(dmub, cmd); - /** - * Timeout covers both the ACK and the wait - * for remaining work to finish. - * - * This is mostly bound by the PHY disable sequence. - * Each register check will be greater than 1us, so - * don't bother using udelay. - */ - - for (i = 0; i < timeout; ++i) { + for (i = 0; i < timeout_us; i++) { if (dmub->hw_funcs.is_gpint_acked(dmub, cmd)) break; + + udelay(poll_delay_us); } - for (i = 0; i < timeout; ++i) { + for (; i < timeout_us; i++) { scratch = dmub->hw_funcs.get_gpint_response(dmub); if (scratch == DMUB_GPINT__STOP_FW_RESPONSE) break; + + udelay(poll_delay_us); } - /* Force reset in case we timed out, DMCUB is likely hung. */ + for (; i < timeout_us; i++) { + REG_GET(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS, &pwait_mode); + if (pwait_mode & (1 << 0)) + break; + + udelay(poll_delay_us); + } + } + + if (i >= timeout_us) { + /* timeout should never occur */ + BREAK_TO_DEBUGGER(); } - REG_UPDATE(DMCUB_CNTL2, DMCUB_SOFT_RESET, 1); - REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); - REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); REG_WRITE(DMCUB_INBOX1_RPTR, 0); REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); @@ -131,7 +136,10 @@ void dmub_dcn401_backdoor_load(struct dmub_srv *dmub, dmub_dcn401_get_fb_base_offset(dmub, &fb_base, &fb_offset); + /* reset and disable DMCUB and MMHUBBUB DMUIF */ REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); dmub_dcn401_translate_addr(&cw0->offset, fb_base, fb_offset, &offset); @@ -151,6 +159,7 @@ void dmub_dcn401_backdoor_load(struct dmub_srv *dmub, DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top, DMCUB_REGION3_CW1_ENABLE, 1); + /* release DMCUB reset only to prevent premature execution */ REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID, 0x20); } @@ -161,7 +170,10 @@ void dmub_dcn401_backdoor_load_zfb_mode(struct dmub_srv *dmub, { union dmub_addr offset; + /* reset and disable DMCUB and MMHUBBUB DMUIF */ REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1); + REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1); + REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0); offset = cw0->offset; @@ -181,6 +193,7 @@ void dmub_dcn401_backdoor_load_zfb_mode(struct dmub_srv *dmub, DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top, DMCUB_REGION3_CW1_ENABLE, 1); + /* release DMCUB reset only to prevent premature execution */ REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID, 0x20); } diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h index 4c8843b79695..31f95b27e227 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn401.h @@ -169,7 +169,8 @@ struct dmub_srv; DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_INBOX0_RSP_INT_EN) \ DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_ACK) \ DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_STAT) \ - DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_EN) + DMUB_SF(HOST_INTERRUPT_CSR, HOST_REG_OUTBOX0_RDY_INT_EN) \ + DMUB_SF(DMCUB_CNTL, DMCUB_PWAIT_MODE_STATUS) struct dmub_srv_dcn401_reg_offset { #define DMUB_SR(reg) uint32_t reg; diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h index 058f882d5bdd..4c01514b926c 100644 --- a/drivers/gpu/drm/amd/display/include/logger_interface.h +++ b/drivers/gpu/drm/amd/display/include/logger_interface.h @@ -40,11 +40,6 @@ struct dc_state; * */ -void pre_surface_trace( - struct dc *dc, - const struct dc_plane_state *const *plane_states, - int surface_count); - void update_surface_trace( struct dc *dc, const struct dc_surface_update *updates, diff --git a/drivers/gpu/drm/amd/include/amd_acpi.h b/drivers/gpu/drm/amd/include/amd_acpi.h index 2d089d30518f..06badbf0c5b9 100644 --- a/drivers/gpu/drm/amd/include/amd_acpi.h +++ b/drivers/gpu/drm/amd/include/amd_acpi.h @@ -61,7 +61,7 @@ struct atif_qbtc_arguments { struct atif_qbtc_data_point { u8 luminance; /* luminance in percent */ - u8 ipnut_signal; /* input signal in range 0-255 */ + u8 input_signal; /* input signal in range 0-255 */ } __packed; struct atif_qbtc_output { @@ -75,6 +75,8 @@ struct atif_qbtc_output { u8 number_of_points; /* number of data points */ struct atif_qbtc_data_point data_points[ATIF_QBTC_MAX_DATA_POINTS]; } __packed; +static_assert(ATIF_QBTC_MAX_DATA_POINTS == MAX_LUMINANCE_DATA_POINTS); +static_assert(sizeof(struct atif_qbtc_data_point) == sizeof(struct amdgpu_dm_luminance_data)); #define ATIF_NOTIFY_MASK 0x3 #define ATIF_NOTIFY_NONE 0 diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 3e86865563dc..485b713cfad0 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -354,6 +354,10 @@ enum DC_DEBUG_MASK { * @DC_DISABLE_SUBVP: If set, disable DCN Sub-Viewport feature in amdgpu driver. */ DC_DISABLE_SUBVP = 0x20000, + /** + * @DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE: If set, disable support for custom brightness curves + */ + DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE = 0x40000, }; enum amd_dpm_forced_level; @@ -405,7 +409,7 @@ struct amd_ip_funcs { int (*prepare_suspend)(struct amdgpu_ip_block *ip_block); int (*suspend)(struct amdgpu_ip_block *ip_block); int (*resume)(struct amdgpu_ip_block *ip_block); - bool (*is_idle)(void *handle); + bool (*is_idle)(struct amdgpu_ip_block *ip_block); int (*wait_for_idle)(struct amdgpu_ip_block *ip_block); bool (*check_soft_reset)(struct amdgpu_ip_block *ip_block); int (*pre_soft_reset)(struct amdgpu_ip_block *ip_block); diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h index abdb8728156e..d6c02cf815be 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_5_0_offset.h @@ -9478,6 +9478,8 @@ #define regRLC_GFX_IMU_CMD_BASE_IDX 1 #define regGFX_IMU_RLC_STATUS 0x4054 #define regGFX_IMU_RLC_STATUS_BASE_IDX 1 +#define regGFX_IMU_STATUS 0x4055 +#define regGFX_IMU_STATUS_BASE_IDX 1 #define regGFX_IMU_SOC_DATA 0x4059 #define regGFX_IMU_SOC_DATA_BASE_IDX 1 #define regGFX_IMU_SOC_ADDR 0x405a diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h index 2bd9f3f1026f..0122a21c50cf 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_3_sh_mask.h @@ -2261,11 +2261,13 @@ #define SH_MEM_CONFIG__ADDRESS_MODE__SHIFT 0x0 #define SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT 0x3 #define SH_MEM_CONFIG__F8_MODE__SHIFT 0x8 +#define SH_MEM_CONFIG__PRECISION_MODE__SHIFT 0x9 #define SH_MEM_CONFIG__RETRY_DISABLE__SHIFT 0xc #define SH_MEM_CONFIG__PRIVATE_NV__SHIFT 0xd #define SH_MEM_CONFIG__ADDRESS_MODE_MASK 0x00000001L #define SH_MEM_CONFIG__ALIGNMENT_MODE_MASK 0x00000018L #define SH_MEM_CONFIG__F8_MODE_MASK 0x00000100L +#define SH_MEM_CONFIG__PRECISION_MODE_MASK 0x00000200L #define SH_MEM_CONFIG__RETRY_DISABLE_MASK 0x00001000L #define SH_MEM_CONFIG__PRIVATE_NV_MASK 0x00002000L //SP_MFMA_PORTD_RD_CONFIG diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index e3e635a31b8a..1e8dfa6c0dc8 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -330,6 +330,8 @@ struct kfd2kgd_calls { uint64_t (*hqd_reset)(struct amdgpu_device *adev, uint32_t pipe_id, uint32_t queue_id, uint32_t inst, unsigned int utimeout); + uint32_t (*hqd_sdma_get_doorbell)(struct amdgpu_device *adev, + int engine, int queue); }; #endif /* KGD_KFD_INTERFACE_H_INCLUDED */ diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index faae9bf48aa4..81e9b443ca0a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -716,8 +716,32 @@ int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev) ret = smu_send_rma_reason(smu); mutex_unlock(&adev->pm.mutex); - if (amdgpu_cper_generate_bp_threshold_record(adev)) - dev_warn(adev->dev, "fail to generate bad page threshold cper records\n"); + if (adev->cper.enabled) + if (amdgpu_cper_generate_bp_threshold_record(adev)) + dev_warn(adev->dev, "fail to generate bad page threshold cper records\n"); + + return ret; +} + +/** + * amdgpu_dpm_reset_sdma_is_supported - Check if SDMA reset is supported + * @adev: amdgpu_device pointer + * + * This function checks if the SMU supports resetting the SDMA engine. + * It returns false if the hardware does not support software SMU or + * if the feature is not supported. + */ +bool amdgpu_dpm_reset_sdma_is_supported(struct amdgpu_device *adev) +{ + struct smu_context *smu = adev->powerplay.pp_handle; + bool ret; + + if (!is_support_sw_smu(adev)) + return false; + + mutex_lock(&adev->pm.mutex); + ret = smu_reset_sdma_is_supported(smu); + mutex_unlock(&adev->pm.mutex); return ret; } diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h index 1f5ac7e0230d..9fb26b5c8ae7 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h @@ -603,5 +603,6 @@ int amdgpu_dpm_set_pm_policy(struct amdgpu_device *adev, int policy_type, ssize_t amdgpu_dpm_get_pm_policy_info(struct amdgpu_device *adev, enum pp_pm_policy p_type, char *buf); int amdgpu_dpm_reset_sdma(struct amdgpu_device *adev, uint32_t inst_mask); +bool amdgpu_dpm_reset_sdma_is_supported(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 67a8e22b1126..59fae668dc3f 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -3042,6 +3042,7 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block) if (!amdgpu_dpm) return 0; + mutex_lock(&adev->pm.mutex); kv_dpm_setup_asic(adev); ret = kv_dpm_enable(adev); if (ret) @@ -3049,6 +3050,8 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block) else adev->pm.dpm_enabled = true; amdgpu_legacy_dpm_compute_clocks(adev); + mutex_unlock(&adev->pm.mutex); + return ret; } @@ -3066,35 +3069,45 @@ static int kv_dpm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + cancel_work_sync(&adev->pm.dpm.thermal.work); + if (adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm_enabled = false; /* disable dpm */ kv_dpm_disable(adev); /* reset the power state */ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; + mutex_unlock(&adev->pm.mutex); } return 0; } static int kv_dpm_resume(struct amdgpu_ip_block *ip_block) { - int ret; + int ret = 0; struct amdgpu_device *adev = ip_block->adev; - if (adev->pm.dpm_enabled) { + if (!amdgpu_dpm) + return 0; + + if (!adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); /* asic init will reset to the boot state */ kv_dpm_setup_asic(adev); ret = kv_dpm_enable(adev); - if (ret) + if (ret) { adev->pm.dpm_enabled = false; - else + } else { adev->pm.dpm_enabled = true; - if (adev->pm.dpm_enabled) amdgpu_legacy_dpm_compute_clocks(adev); + } + mutex_unlock(&adev->pm.mutex); } - return 0; + return ret; } -static bool kv_dpm_is_idle(void *handle) +static bool kv_dpm_is_idle(struct amdgpu_ip_block *ip_block) { return true; } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index e861355ebd75..c7518b13e787 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work) enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL; int temp, size = sizeof(temp); - if (!adev->pm.dpm_enabled) - return; + mutex_lock(&adev->pm.mutex); + if (!adev->pm.dpm_enabled) { + mutex_unlock(&adev->pm.mutex); + return; + } if (!pp_funcs->read_sensor(adev->powerplay.pp_handle, AMDGPU_PP_SENSOR_GPU_TEMP, (void *)&temp, @@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work) adev->pm.dpm.state = dpm_state; amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle); + mutex_unlock(&adev->pm.mutex); } diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index a87dcf0974bc..1c25f3023e93 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -7786,6 +7786,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block) if (!amdgpu_dpm) return 0; + mutex_lock(&adev->pm.mutex); si_dpm_setup_asic(adev); ret = si_dpm_enable(adev); if (ret) @@ -7793,6 +7794,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block) else adev->pm.dpm_enabled = true; amdgpu_legacy_dpm_compute_clocks(adev); + mutex_unlock(&adev->pm.mutex); return ret; } @@ -7810,35 +7812,47 @@ static int si_dpm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; + cancel_work_sync(&adev->pm.dpm.thermal.work); + if (adev->pm.dpm_enabled) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm_enabled = false; /* disable dpm */ si_dpm_disable(adev); /* reset the power state */ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps; + mutex_unlock(&adev->pm.mutex); } + return 0; } static int si_dpm_resume(struct amdgpu_ip_block *ip_block) { - int ret; + int ret = 0; struct amdgpu_device *adev = ip_block->adev; - if (adev->pm.dpm_enabled) { + if (!amdgpu_dpm) + return 0; + + if (!adev->pm.dpm_enabled) { /* asic init will reset to the boot state */ + mutex_lock(&adev->pm.mutex); si_dpm_setup_asic(adev); ret = si_dpm_enable(adev); - if (ret) + if (ret) { adev->pm.dpm_enabled = false; - else + } else { adev->pm.dpm_enabled = true; - if (adev->pm.dpm_enabled) amdgpu_legacy_dpm_compute_clocks(adev); + } + mutex_unlock(&adev->pm.mutex); } - return 0; + + return ret; } -static bool si_dpm_is_idle(void *handle) +static bool si_dpm_is_idle(struct amdgpu_ip_block *ip_block) { /* XXX */ return true; diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 686345f75f26..b48a031cbba0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -51,6 +51,11 @@ static int amd_powerplay_create(struct amdgpu_device *adev) hwmgr->adev = adev; hwmgr->not_vf = !amdgpu_sriov_vf(adev); hwmgr->device = amdgpu_cgs_create_device(adev); + if (!hwmgr->device) { + kfree(hwmgr); + return -ENOMEM; + } + mutex_init(&hwmgr->msg_lock); hwmgr->chip_family = adev->family; hwmgr->chip_id = adev->asic_type; @@ -239,7 +244,7 @@ static void pp_late_fini(struct amdgpu_ip_block *ip_block) } -static bool pp_is_idle(void *handle) +static bool pp_is_idle(struct amdgpu_ip_block *ip_block) { return false; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c index 90452b66e107..a59677cf8dfc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c @@ -149,16 +149,6 @@ int phm_apply_clock_adjust_rules(struct pp_hwmgr *hwmgr) return 0; } -int phm_powerdown_uvd(struct pp_hwmgr *hwmgr) -{ - PHM_FUNC_CHECK(hwmgr); - - if (hwmgr->hwmgr_func->powerdown_uvd != NULL) - return hwmgr->hwmgr_func->powerdown_uvd(hwmgr); - return 0; -} - - int phm_disable_clock_power_gatings(struct pp_hwmgr *hwmgr) { PHM_FUNC_CHECK(hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c index 82d540334318..6120f14caab0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.c @@ -158,84 +158,6 @@ int pp_atomfwctrl_get_voltage_table_v4(struct pp_hwmgr *hwmgr, return result; } - -static struct atom_gpio_pin_lut_v2_1 *pp_atomfwctrl_get_gpio_lookup_table( - struct pp_hwmgr *hwmgr) -{ - const void *table_address; - uint16_t idx; - - idx = GetIndexIntoMasterDataTable(gpio_pin_lut); - table_address = smu_atom_get_data_table(hwmgr->adev, - idx, NULL, NULL, NULL); - PP_ASSERT_WITH_CODE(table_address, - "Error retrieving BIOS Table Address!", - return NULL); - - return (struct atom_gpio_pin_lut_v2_1 *)table_address; -} - -static bool pp_atomfwctrl_lookup_gpio_pin( - struct atom_gpio_pin_lut_v2_1 *gpio_lookup_table, - const uint32_t pin_id, - struct pp_atomfwctrl_gpio_pin_assignment *gpio_pin_assignment) -{ - unsigned int size = le16_to_cpu( - gpio_lookup_table->table_header.structuresize); - unsigned int offset = - offsetof(struct atom_gpio_pin_lut_v2_1, gpio_pin[0]); - unsigned long start = (unsigned long)gpio_lookup_table; - - while (offset < size) { - const struct atom_gpio_pin_assignment *pin_assignment = - (const struct atom_gpio_pin_assignment *)(start + offset); - - if (pin_id == pin_assignment->gpio_id) { - gpio_pin_assignment->uc_gpio_pin_bit_shift = - pin_assignment->gpio_bitshift; - gpio_pin_assignment->us_gpio_pin_aindex = - le16_to_cpu(pin_assignment->data_a_reg_index); - return true; - } - offset += offsetof(struct atom_gpio_pin_assignment, gpio_id) + 1; - } - return false; -} - -/* - * Returns TRUE if the given pin id find in lookup table. - */ -bool pp_atomfwctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, - const uint32_t pin_id, - struct pp_atomfwctrl_gpio_pin_assignment *gpio_pin_assignment) -{ - bool ret = false; - struct atom_gpio_pin_lut_v2_1 *gpio_lookup_table = - pp_atomfwctrl_get_gpio_lookup_table(hwmgr); - - /* If we cannot find the table do NOT try to control this voltage. */ - PP_ASSERT_WITH_CODE(gpio_lookup_table, - "Could not find GPIO lookup Table in BIOS.", - return false); - - ret = pp_atomfwctrl_lookup_gpio_pin(gpio_lookup_table, - pin_id, gpio_pin_assignment); - - return ret; -} - -/* - * Enter to SelfRefresh mode. - * @param hwmgr - */ -int pp_atomfwctrl_enter_self_refresh(struct pp_hwmgr *hwmgr) -{ - /* 0 - no action - * 1 - leave power to video memory always on - */ - return 0; -} - /** pp_atomfwctrl_get_gpu_pll_dividers_vega10(). * * @param hwmgr input parameter: pointer to HwMgr diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h index e86e05c786d9..0d62903d5676 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomfwctrl.h @@ -217,9 +217,6 @@ struct pp_atomfwctrl_smc_dpm_parameters { int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr, uint32_t clock_type, uint32_t clock_value, struct pp_atomfwctrl_clock_dividers_soc15 *dividers); -int pp_atomfwctrl_enter_self_refresh(struct pp_hwmgr *hwmgr); -bool pp_atomfwctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pin_id, - struct pp_atomfwctrl_gpio_pin_assignment *gpio_pin_assignment); int pp_atomfwctrl_get_voltage_table_v4(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint8_t voltage_mode, struct pp_atomfwctrl_voltage_table *voltage_table); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index a8c732e07006..9a821563bc8e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1642,7 +1642,6 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = { .apply_state_adjust_rules = smu10_apply_state_adjust_rules, .force_dpm_level = smu10_dpm_force_dpm_level, .get_power_state_size = smu10_get_power_state_size, - .powerdown_uvd = NULL, .powergate_uvd = smu10_powergate_vcn, .powergate_vce = NULL, .get_mclk = smu10_dpm_get_mclk, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c index f2bda3bcbbde..5e4c80f7b20a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.c @@ -55,7 +55,7 @@ static int smu7_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate) return smu7_enable_disable_vce_dpm(hwmgr, !bgate); } -int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr) +static int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr) { if (phm_cf_want_uvd_power_gating(hwmgr)) return smum_send_msg_to_smc(hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h index fc8f8a6acc72..e56abbadc78b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_clockpowergating.h @@ -28,7 +28,6 @@ void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate); void smu7_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate); -int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr); int smu7_powergate_acp(struct pp_hwmgr *hwmgr, bool bgate); int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr); int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 632a25957477..8da882c51856 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -5754,7 +5754,6 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = { .patch_boot_state = smu7_dpm_patch_boot_state, .get_pp_table_entry = smu7_get_pp_table_entry, .get_num_of_pp_table_entries = smu7_get_number_of_powerplay_table_entries, - .powerdown_uvd = smu7_powerdown_uvd, .powergate_uvd = smu7_powergate_uvd, .powergate_vce = smu7_powergate_vce, .disable_clock_power_gating = smu7_disable_clock_power_gating, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index 7e1197420873..9d3b33446adc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -2044,7 +2044,6 @@ static const struct pp_hwmgr_func smu8_hwmgr_funcs = { .apply_state_adjust_rules = smu8_apply_state_adjust_rules, .force_dpm_level = smu8_dpm_force_dpm_level, .get_power_state_size = smu8_get_power_state_size, - .powerdown_uvd = smu8_dpm_powerdown_uvd, .powergate_uvd = smu8_dpm_powergate_uvd, .powergate_vce = smu8_dpm_powergate_vce, .powergate_acp = smu8_dpm_powergate_acp, diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h index f4f9a104d170..915f1b8e4dba 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hardwaremanager.h @@ -396,7 +396,6 @@ struct phm_odn_clock_levels { }; extern int phm_disable_clock_power_gatings(struct pp_hwmgr *hwmgr); -extern int phm_powerdown_uvd(struct pp_hwmgr *hwmgr); extern int phm_setup_asic(struct pp_hwmgr *hwmgr); extern int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr); extern int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h index 227bf0e84a13..c661185753b4 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h @@ -257,7 +257,6 @@ struct pp_hwmgr_func { int (*get_pp_table_entry)(struct pp_hwmgr *hwmgr, unsigned long, struct pp_power_state *); int (*get_num_of_pp_table_entries)(struct pp_hwmgr *hwmgr); - int (*powerdown_uvd)(struct pp_hwmgr *hwmgr); void (*powergate_vce)(struct pp_hwmgr *hwmgr, bool bgate); void (*powergate_uvd)(struct pp_hwmgr *hwmgr, bool bgate); void (*powergate_acp)(struct pp_hwmgr *hwmgr, bool bgate); diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 0b32c6cf6924..8cfb07549f54 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -2041,15 +2041,15 @@ static int smu_hw_fini(struct amdgpu_ip_block *ip_block) if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) return 0; - for (i = 0; i < adev->vcn.num_vcn_inst; i++) + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { smu_dpm_set_vcn_enable(smu, false, i); + adev->vcn.inst[i].cur_state = AMD_PG_STATE_GATE; + } smu_dpm_set_jpeg_enable(smu, false); + adev->jpeg.cur_state = AMD_PG_STATE_GATE; smu_dpm_set_vpe_enable(smu, false); smu_dpm_set_umsch_mm_enable(smu, false); - adev->vcn.cur_state = AMD_PG_STATE_GATE; - adev->jpeg.cur_state = AMD_PG_STATE_GATE; - if (!smu->pm_enabled) return 0; @@ -2315,7 +2315,12 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, if (smu_dpm_ctx->dpm_level != level) { ret = smu_asic_set_performance_level(smu, level); if (ret) { - dev_err(smu->adev->dev, "Failed to set performance level!"); + if (ret == -EOPNOTSUPP) + dev_info(smu->adev->dev, "set performance level %d not supported", + level); + else + dev_err(smu->adev->dev, "Failed to set performance level %d", + level); return ret; } @@ -3907,6 +3912,23 @@ int smu_send_rma_reason(struct smu_context *smu) return ret; } +/** + * smu_reset_sdma_is_supported - Check if SDMA reset is supported by SMU + * @smu: smu_context pointer + * + * This function checks if the SMU supports resetting the SDMA engine. + * It returns true if supported, false otherwise. + */ +bool smu_reset_sdma_is_supported(struct smu_context *smu) +{ + bool ret = false; + + if (smu->ppt_funcs && smu->ppt_funcs->reset_sdma_is_supported) + ret = smu->ppt_funcs->reset_sdma_is_supported(smu); + + return ret; +} + int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask) { int ret = 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 3630593bce61..3ba169639f54 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1376,6 +1376,10 @@ struct pptable_funcs { * @reset_sdma: message SMU to soft reset sdma instance. */ int (*reset_sdma)(struct smu_context *smu, uint32_t inst_mask); + /** + * @reset_sdma_is_supported: Check if support resets the SDMA engine. + */ + bool (*reset_sdma_is_supported)(struct smu_context *smu); /** * @get_ecc_table: message SMU to get ECC INFO table. @@ -1637,6 +1641,7 @@ int smu_send_hbm_bad_pages_num(struct smu_context *smu, uint32_t size); int smu_send_hbm_bad_channel_flag(struct smu_context *smu, uint32_t size); int smu_send_rma_reason(struct smu_context *smu); int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask); +bool smu_reset_sdma_is_supported(struct smu_context *smu); int smu_set_pm_policy(struct smu_context *smu, enum pp_pm_policy p_type, int level); ssize_t smu_get_pm_policy_info(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h index 4a1256d29d62..d7505cfc433a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h @@ -38,6 +38,13 @@ #define NUM_SOC_P2S_TABLES 6 #define NUM_GFX_P2S_TABLES 8 #define NUM_PSM_DIDT_THRESHOLDS 3 +#define NUM_XVMIN_VMIN_THRESHOLDS 3 + +#define PRODUCT_MODEL_NUMBER_LEN 20 +#define PRODUCT_NAME_LEN 64 +#define PRODUCT_SERIAL_LEN 20 +#define PRODUCT_MANUFACTURER_NAME_LEN 32 +#define PRODUCT_FRU_ID_LEN 32 typedef enum { /*0*/ FEATURE_DATA_CALCULATION = 0, @@ -85,11 +92,11 @@ typedef enum { //enum for MPIO PCIe gen speed msgs typedef enum { + PCIE_LINK_SPEED_INDEX_TABLE_RESERVED, PCIE_LINK_SPEED_INDEX_TABLE_GEN1, PCIE_LINK_SPEED_INDEX_TABLE_GEN2, PCIE_LINK_SPEED_INDEX_TABLE_GEN3, PCIE_LINK_SPEED_INDEX_TABLE_GEN4, - PCIE_LINK_SPEED_INDEX_TABLE_GEN4_ESM, PCIE_LINK_SPEED_INDEX_TABLE_GEN5, PCIE_LINK_SPEED_INDEX_TABLE_COUNT } PCIE_LINK_SPEED_INDEX_TABLE_e; @@ -126,13 +133,149 @@ typedef enum { GFX_DVM_MARGIN_COUNT } GFX_DVM_MARGIN_e; -#define SMU_VF_METRICS_TABLE_VERSION 0x3 +#define SMU_METRICS_TABLE_VERSION 0x12 + +typedef struct __attribute__((packed, aligned(4))) { + uint64_t AccumulationCounter; + + //TEMPERATURE + uint32_t MaxSocketTemperature; + uint32_t MaxVrTemperature; + uint32_t MaxHbmTemperature; + uint64_t MaxSocketTemperatureAcc; + uint64_t MaxVrTemperatureAcc; + uint64_t MaxHbmTemperatureAcc; + + //POWER + uint32_t SocketPowerLimit; + uint32_t SocketPower; + + //ENERGY + uint64_t Timestamp; + uint64_t SocketEnergyAcc; + uint64_t XcdEnergyAcc; + uint64_t AidEnergyAcc; + uint64_t HbmEnergyAcc; + + //FREQUENCY + uint32_t GfxclkFrequencyLimit; + uint32_t FclkFrequency; + uint32_t UclkFrequency; + uint32_t SocclkFrequency[4]; + uint32_t VclkFrequency[4]; + uint32_t DclkFrequency[4]; + uint32_t LclkFrequency[4]; + uint64_t GfxclkFrequencyAcc[8]; + + //FREQUENCY RANGE + uint32_t MaxLclkDpmRange; + uint32_t MinLclkDpmRange; + + //XGMI + uint32_t XgmiWidth; + uint32_t XgmiBitrate; + uint64_t XgmiReadBandwidthAcc[8]; + uint64_t XgmiWriteBandwidthAcc[8]; + + //ACTIVITY + uint32_t SocketGfxBusy; + uint32_t DramBandwidthUtilization; + uint64_t SocketGfxBusyAcc; + uint64_t DramBandwidthAcc; + uint32_t MaxDramBandwidth; + uint64_t DramBandwidthUtilizationAcc; + uint64_t PcieBandwidthAcc[4]; + + //THROTTLERS + uint32_t ProchotResidencyAcc; + uint32_t PptResidencyAcc; + uint32_t SocketThmResidencyAcc; + uint32_t VrThmResidencyAcc; + uint32_t HbmThmResidencyAcc; + uint32_t GfxLockXCDMak; + + // New Items at end to maintain driver compatibility + uint32_t GfxclkFrequency[8]; + + //XGMI Data tranfser size + uint64_t XgmiReadDataSizeAcc[8];//in KByte + uint64_t XgmiWriteDataSizeAcc[8];//in KByte + + //PCIE BW Data and error count + uint32_t PcieBandwidth[4]; + uint32_t PCIeL0ToRecoveryCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIenReplayAAcc; // The Pcie counter itself is accumulated + uint32_t PCIenReplayARolloverCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIeNAKSentCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIeNAKReceivedCountAcc; // The Pcie counter itself is accumulated + + // VCN/JPEG ACTIVITY + uint32_t VcnBusy[4]; + uint32_t JpegBusy[40]; + + // PCIE LINK Speed and width + uint32_t PCIeLinkSpeed; + uint32_t PCIeLinkWidth; + + // PER XCD ACTIVITY + uint32_t GfxBusy[8]; + uint64_t GfxBusyAcc[8]; + + //PCIE BW Data and error count + uint32_t PCIeOtherEndRecoveryAcc; // The Pcie counter itself is accumulated + + //Total App Clock Counter + uint64_t GfxclkBelowHostLimitPptAcc[8]; + uint64_t GfxclkBelowHostLimitThmAcc[8]; + uint64_t GfxclkBelowHostLimitTotalAcc[8]; + uint64_t GfxclkLowUtilizationAcc[8]; +} MetricsTable_t; + +#define SMU_VF_METRICS_TABLE_MASK (1 << 31) +#define SMU_VF_METRICS_TABLE_VERSION (0x6 | SMU_VF_METRICS_TABLE_MASK) typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; uint32_t InstGfxclk_TargFreq; uint64_t AccGfxclk_TargFreq; uint64_t AccGfxRsmuDpm_Busy; + uint64_t AccGfxclkBelowHostLimitPpt; + uint64_t AccGfxclkBelowHostLimitThm; + uint64_t AccGfxclkBelowHostLimitTotal; + uint64_t AccGfxclkLowUtilization; } VfMetricsTable_t; +/* FRU product information */ +typedef struct __attribute__((packed, aligned(4))) { + uint8_t ModelNumber[PRODUCT_MODEL_NUMBER_LEN]; + uint8_t Name[PRODUCT_NAME_LEN]; + uint8_t Serial[PRODUCT_SERIAL_LEN]; + uint8_t ManufacturerName[PRODUCT_MANUFACTURER_NAME_LEN]; + uint8_t FruId[PRODUCT_FRU_ID_LEN]; +} FRUProductInfo_t; + +#pragma pack(push, 4) +typedef struct { + //FRU PRODUCT INFO + FRUProductInfo_t ProductInfo; + + //POWER + uint32_t MaxSocketPowerLimit; + + //FREQUENCY RANGE + uint32_t MaxGfxclkFrequency; + uint32_t MinGfxclkFrequency; + uint32_t FclkFrequencyTable[4]; + uint32_t UclkFrequencyTable[4]; + uint32_t SocclkFrequencyTable[4]; + uint32_t VclkFrequencyTable[4]; + uint32_t DclkFrequencyTable[4]; + uint32_t LclkFrequencyTable[4]; + + //PSNs + uint64_t PublicSerialNumber_AID[4]; + uint64_t PublicSerialNumber_XCD[8]; +} StaticMetricsTable_t; +#pragma pack(pop) + #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h new file mode 100644 index 000000000000..e1f490b6ce64 --- /dev/null +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h @@ -0,0 +1,143 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#ifndef SMU_13_0_12_PPSMC_H +#define SMU_13_0_12_PPSMC_H + +// SMU Response Codes: +#define PPSMC_Result_OK 0x1 +#define PPSMC_Result_Failed 0xFF +#define PPSMC_Result_UnknownCmd 0xFE +#define PPSMC_Result_CmdRejectedPrereq 0xFD +#define PPSMC_Result_CmdRejectedBusy 0xFC + +// Message Definitions: +#define PPSMC_MSG_TestMessage 0x1 +#define PPSMC_MSG_GetSmuVersion 0x2 +#define PPSMC_MSG_GfxDriverReset 0x3 +#define PPSMC_MSG_GetDriverIfVersion 0x4 +#define PPSMC_MSG_EnableAllSmuFeatures 0x5 +#define PPSMC_MSG_DisableAllSmuFeatures 0x6 +#define PPSMC_MSG_RequestI2cTransaction 0x7 +#define PPSMC_MSG_GetMetricsVersion 0x8 +#define PPSMC_MSG_GetMetricsTable 0x9 +#define PPSMC_MSG_GetEccInfoTable 0xA +#define PPSMC_MSG_GetEnabledSmuFeaturesLow 0xB +#define PPSMC_MSG_GetEnabledSmuFeaturesHigh 0xC +#define PPSMC_MSG_SetDriverDramAddrHigh 0xD +#define PPSMC_MSG_SetDriverDramAddrLow 0xE +#define PPSMC_MSG_SetToolsDramAddrHigh 0xF +#define PPSMC_MSG_SetToolsDramAddrLow 0x10 +#define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x11 +#define PPSMC_MSG_SetSystemVirtualDramAddrLow 0x12 +#define PPSMC_MSG_SetSoftMinByFreq 0x13 +#define PPSMC_MSG_SetSoftMaxByFreq 0x14 +#define PPSMC_MSG_GetMinDpmFreq 0x15 +#define PPSMC_MSG_GetMaxDpmFreq 0x16 +#define PPSMC_MSG_GetDpmFreqByIndex 0x17 +#define PPSMC_MSG_SetPptLimit 0x18 +#define PPSMC_MSG_GetPptLimit 0x19 +#define PPSMC_MSG_DramLogSetDramAddrHigh 0x1A +#define PPSMC_MSG_DramLogSetDramAddrLow 0x1B +#define PPSMC_MSG_DramLogSetDramSize 0x1C +#define PPSMC_MSG_GetDebugData 0x1D +#define PPSMC_MSG_HeavySBR 0x1E +#define PPSMC_MSG_SetNumBadHbmPagesRetired 0x1F +#define PPSMC_MSG_DFCstateControl 0x20 +#define PPSMC_MSG_GetGmiPwrDnHyst 0x21 +#define PPSMC_MSG_SetGmiPwrDnHyst 0x22 +#define PPSMC_MSG_GmiPwrDnControl 0x23 +#define PPSMC_MSG_EnterGfxoff 0x24 +#define PPSMC_MSG_ExitGfxoff 0x25 +#define PPSMC_MSG_EnableDeterminism 0x26 +#define PPSMC_MSG_DisableDeterminism 0x27 +#define PPSMC_MSG_DumpSTBtoDram 0x28 +#define PPSMC_MSG_STBtoDramLogSetDramAddrHigh 0x29 +#define PPSMC_MSG_STBtoDramLogSetDramAddrLow 0x2A +#define PPSMC_MSG_STBtoDramLogSetDramSize 0x2B +#define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrHigh 0x2C +#define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow 0x2D +#define PPSMC_MSG_GfxDriverResetRecovery 0x2E +#define PPSMC_MSG_TriggerVFFLR 0x2F +#define PPSMC_MSG_SetSoftMinGfxClk 0x30 +#define PPSMC_MSG_SetSoftMaxGfxClk 0x31 +#define PPSMC_MSG_GetMinGfxDpmFreq 0x32 +#define PPSMC_MSG_GetMaxGfxDpmFreq 0x33 +#define PPSMC_MSG_PrepareForDriverUnload 0x34 +#define PPSMC_MSG_ReadThrottlerLimit 0x35 +#define PPSMC_MSG_QueryValidMcaCount 0x36 +#define PPSMC_MSG_McaBankDumpDW 0x37 +#define PPSMC_MSG_GetCTFLimit 0x38 +#define PPSMC_MSG_ClearMcaOnRead 0x39 +#define PPSMC_MSG_QueryValidMcaCeCount 0x3A +#define PPSMC_MSG_McaBankCeDumpDW 0x3B +#define PPSMC_MSG_SelectPLPDMode 0x40 +#define PPSMC_MSG_PmLogReadSample 0x41 +#define PPSMC_MSG_PmLogGetTableVersion 0x42 +#define PPSMC_MSG_RmaDueToBadPageThreshold 0x43 +#define PPSMC_MSG_SetThrottlingPolicy 0x44 +#define PPSMC_MSG_SetPhaseDetectCSBWThreshold 0x45 +#define PPSMC_MSG_SetPhaseDetectFreqHigh 0x46 +#define PPSMC_MSG_SetPhaseDetectFreqLow 0x47 +#define PPSMC_MSG_SetPhaseDetectDownHysterisis 0x48 +#define PPSMC_MSG_SetPhaseDetectAlphaX1e6 0x49 +#define PPSMC_MSG_SetPhaseDetectOnOff 0x4A +#define PPSMC_MSG_GetPhaseDetectResidency 0x4B +#define PPSMC_MSG_UpdatePccWaitDecMaxStr 0x4C +#define PPSMC_MSG_ResetSDMA 0x4D +#define PPSMC_MSG_GetRasTableVersion 0x4E +#define PPSMC_MSG_GetRmaStatus 0x4F +#define PPSMC_MSG_GetErrorCount 0x50 +#define PPSMC_MSG_GetBadPageCount 0x51 +#define PPSMC_MSG_GetBadPageInfo 0x52 +#define PPSMC_MSG_GetBadPagePaAddrLoHi 0x53 +#define PPSMC_MSG_SetTimestampLoHi 0x54 +#define PPSMC_MSG_GetTimestampLoHi 0x55 +#define PPSMC_MSG_GetRasPolicy 0x56 +#define PPSMC_MSG_DumpErrorRecord 0x57 +#define PPSMC_MSG_EraseRasTable 0x58 +#define PPSMC_MSG_GetStaticMetricsTable 0x59 +#define PPSMC_Message_Count 0x5A + +//PPSMC Reset Types for driver msg argument +#define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET 0x1 +#define PPSMC_RESET_TYPE_DRIVER_MODE_2_RESET 0x2 +#define PPSMC_RESET_TYPE_DRIVER_MODE_3_RESET 0x3 + +//PPSMC Reset Types for driver msg argument +#define PPSMC_THROTTLING_LIMIT_TYPE_SOCKET 0x1 +#define PPSMC_THROTTLING_LIMIT_TYPE_HBM 0x2 + +//CTF/Throttle Limit types +#define PPSMC_AID_THM_TYPE 0x1 +#define PPSMC_CCD_THM_TYPE 0x2 +#define PPSMC_XCD_THM_TYPE 0x3 +#define PPSMC_HBM_THM_TYPE 0x4 + +//PLPD modes +#define PPSMC_PLPD_MODE_DEFAULT 0x1 +#define PPSMC_PLPD_MODE_OPTIMIZED 0x2 + +typedef uint32_t PPSMC_Result; +typedef uint32_t PPSMC_MSG; + +#endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index 9ccd5a1986d3..9c8468fb203a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -276,7 +276,8 @@ __SMU_DUMMY_MAP(SetThrottlingPolicy), \ __SMU_DUMMY_MAP(MALLPowerController), \ __SMU_DUMMY_MAP(MALLPowerState), \ - __SMU_DUMMY_MAP(ResetSDMA), + __SMU_DUMMY_MAP(ResetSDMA), \ + __SMU_DUMMY_MAP(GetStaticMetricsTable), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 31166974746f..cd03caffe317 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -53,6 +53,10 @@ #define SMU_13_VCLK_SHIFT 16 +#define SMUQ10_TO_UINT(x) ((x) >> 10) +#define SMUQ10_FRAC(x) ((x) & 0x3ff) +#define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) + extern const int pmfw_decoded_link_speed[5]; extern const int pmfw_decoded_link_width[7]; @@ -307,6 +311,13 @@ int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu, void smu_v13_0_interrupt_work(struct smu_context *smu); bool smu_v13_0_12_is_dpm_running(struct smu_context *smu); +int smu_v13_0_12_get_max_metrics_size(void); +int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu); +int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value); +ssize_t smu_v13_0_12_get_gpu_metrics(struct smu_context *smu, void **table); extern const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[]; +extern const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[]; #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 985355bf78b2..898487ad6cd2 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -3234,4 +3234,9 @@ void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) smu->workload_map = smu_v13_0_0_workload_map; smu->smc_driver_if_version = SMU13_0_0_DRIVER_IF_VERSION; smu_v13_0_0_set_smu_mailbox_registers(smu); + + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == + IP_VERSION(13, 0, 10) && + !amdgpu_device_has_display_hardware(smu->adev)) + smu->adev->pm.pp_feature &= ~PP_GFXOFF_MASK; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c index 86852e738837..285dbfe10303 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c @@ -28,8 +28,10 @@ #include "amdgpu_smu.h" #include "smu_v13_0_12_pmfw.h" #include "smu_v13_0_6_ppt.h" +#include "smu_v13_0_12_ppsmc.h" #include "smu_v13_0.h" #include "amdgpu_xgmi.h" +#include "amdgpu_fru_eeprom.h" #include <linux/pci.h> #include "smu_cmn.h" @@ -54,6 +56,10 @@ (FEATURE_MASK(FEATURE_DATA_CALCULATION) | \ FEATURE_MASK(FEATURE_DPM_GFXCLK) | FEATURE_MASK(FEATURE_DPM_FCLK)) +#define NUM_JPEG_RINGS_FW 10 +#define NUM_JPEG_RINGS_GPU_METRICS(gpu_metrics) \ + (ARRAY_SIZE(gpu_metrics->xcp_stats[0].jpeg_busy) / 4) + const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[SMU_FEATURE_COUNT] = { SMU_13_0_12_FEA_MAP(SMU_FEATURE_DATA_CALCULATIONS_BIT, FEATURE_DATA_CALCULATION), SMU_13_0_12_FEA_MAP(SMU_FEATURE_DPM_GFXCLK_BIT, FEATURE_DPM_GFXCLK), @@ -72,6 +78,63 @@ const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[SMU_FEATURE_COUNT] = SMU_13_0_12_FEA_MAP(SMU_FEATURE_XGMI_PER_LINK_PWR_DWN_BIT, FEATURE_XGMI_PER_LINK_PWR_DOWN), }; +// clang-format off +const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] = { + MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 0), + MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 1), + MSG_MAP(GetDriverIfVersion, PPSMC_MSG_GetDriverIfVersion, 1), + MSG_MAP(EnableAllSmuFeatures, PPSMC_MSG_EnableAllSmuFeatures, 0), + MSG_MAP(DisableAllSmuFeatures, PPSMC_MSG_DisableAllSmuFeatures, 0), + MSG_MAP(RequestI2cTransaction, PPSMC_MSG_RequestI2cTransaction, 0), + MSG_MAP(GetMetricsTable, PPSMC_MSG_GetMetricsTable, 1), + MSG_MAP(GetMetricsVersion, PPSMC_MSG_GetMetricsVersion, 1), + MSG_MAP(GetEnabledSmuFeaturesHigh, PPSMC_MSG_GetEnabledSmuFeaturesHigh, 1), + MSG_MAP(GetEnabledSmuFeaturesLow, PPSMC_MSG_GetEnabledSmuFeaturesLow, 1), + MSG_MAP(SetDriverDramAddrHigh, PPSMC_MSG_SetDriverDramAddrHigh, 1), + MSG_MAP(SetDriverDramAddrLow, PPSMC_MSG_SetDriverDramAddrLow, 1), + MSG_MAP(SetToolsDramAddrHigh, PPSMC_MSG_SetToolsDramAddrHigh, 0), + MSG_MAP(SetToolsDramAddrLow, PPSMC_MSG_SetToolsDramAddrLow, 0), + MSG_MAP(SetSoftMinByFreq, PPSMC_MSG_SetSoftMinByFreq, 0), + MSG_MAP(SetSoftMaxByFreq, PPSMC_MSG_SetSoftMaxByFreq, 1), + MSG_MAP(GetMinDpmFreq, PPSMC_MSG_GetMinDpmFreq, 1), + MSG_MAP(GetMaxDpmFreq, PPSMC_MSG_GetMaxDpmFreq, 1), + MSG_MAP(GetDpmFreqByIndex, PPSMC_MSG_GetDpmFreqByIndex, 1), + MSG_MAP(SetPptLimit, PPSMC_MSG_SetPptLimit, 0), + MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 1), + MSG_MAP(GfxDeviceDriverReset, PPSMC_MSG_GfxDriverReset, SMU_MSG_RAS_PRI), + MSG_MAP(DramLogSetDramAddrHigh, PPSMC_MSG_DramLogSetDramAddrHigh, 0), + MSG_MAP(DramLogSetDramAddrLow, PPSMC_MSG_DramLogSetDramAddrLow, 0), + MSG_MAP(DramLogSetDramSize, PPSMC_MSG_DramLogSetDramSize, 0), + MSG_MAP(GetDebugData, PPSMC_MSG_GetDebugData, 0), + MSG_MAP(SetNumBadHbmPagesRetired, PPSMC_MSG_SetNumBadHbmPagesRetired, 0), + MSG_MAP(DFCstateControl, PPSMC_MSG_DFCstateControl, 0), + MSG_MAP(GetGmiPwrDnHyst, PPSMC_MSG_GetGmiPwrDnHyst, 0), + MSG_MAP(SetGmiPwrDnHyst, PPSMC_MSG_SetGmiPwrDnHyst, 0), + MSG_MAP(GmiPwrDnControl, PPSMC_MSG_GmiPwrDnControl, 0), + MSG_MAP(EnterGfxoff, PPSMC_MSG_EnterGfxoff, 0), + MSG_MAP(ExitGfxoff, PPSMC_MSG_ExitGfxoff, 0), + MSG_MAP(EnableDeterminism, PPSMC_MSG_EnableDeterminism, 0), + MSG_MAP(DisableDeterminism, PPSMC_MSG_DisableDeterminism, 0), + MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0), + MSG_MAP(GetMinGfxclkFrequency, PPSMC_MSG_GetMinGfxDpmFreq, 1), + MSG_MAP(GetMaxGfxclkFrequency, PPSMC_MSG_GetMaxGfxDpmFreq, 1), + MSG_MAP(SetSoftMinGfxclk, PPSMC_MSG_SetSoftMinGfxClk, 1), + MSG_MAP(SetSoftMaxGfxClk, PPSMC_MSG_SetSoftMaxGfxClk, 1), + MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareForDriverUnload, 0), + MSG_MAP(GetCTFLimit, PPSMC_MSG_GetCTFLimit, 0), + MSG_MAP(GetThermalLimit, PPSMC_MSG_ReadThrottlerLimit, 0), + MSG_MAP(ClearMcaOnRead, PPSMC_MSG_ClearMcaOnRead, 0), + MSG_MAP(QueryValidMcaCount, PPSMC_MSG_QueryValidMcaCount, SMU_MSG_RAS_PRI), + MSG_MAP(QueryValidMcaCeCount, PPSMC_MSG_QueryValidMcaCeCount, SMU_MSG_RAS_PRI), + MSG_MAP(McaBankDumpDW, PPSMC_MSG_McaBankDumpDW, SMU_MSG_RAS_PRI), + MSG_MAP(McaBankCeDumpDW, PPSMC_MSG_McaBankCeDumpDW, SMU_MSG_RAS_PRI), + MSG_MAP(SelectPLPDMode, PPSMC_MSG_SelectPLPDMode, 0), + MSG_MAP(RmaDueToBadPageThreshold, PPSMC_MSG_RmaDueToBadPageThreshold, 0), + MSG_MAP(SetThrottlingPolicy, PPSMC_MSG_SetThrottlingPolicy, 0), + MSG_MAP(ResetSDMA, PPSMC_MSG_ResetSDMA, 0), + MSG_MAP(GetStaticMetricsTable, PPSMC_MSG_GetStaticMetricsTable, 1), +}; + static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu, uint64_t *feature_mask) { @@ -87,6 +150,114 @@ static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu, return ret; } +static int smu_v13_0_12_fru_get_product_info(struct smu_context *smu, + StaticMetricsTable_t *static_metrics) +{ + struct amdgpu_fru_info *fru_info; + struct amdgpu_device *adev = smu->adev; + + if (!adev->fru_info) { + adev->fru_info = kzalloc(sizeof(*adev->fru_info), GFP_KERNEL); + if (!adev->fru_info) + return -ENOMEM; + } + + fru_info = adev->fru_info; + strscpy(fru_info->product_number, static_metrics->ProductInfo.ModelNumber, + sizeof(fru_info->product_number)); + strscpy(fru_info->product_name, static_metrics->ProductInfo.Name, + sizeof(fru_info->product_name)); + strscpy(fru_info->serial, static_metrics->ProductInfo.Serial, + sizeof(fru_info->serial)); + strscpy(fru_info->manufacturer_name, static_metrics->ProductInfo.ManufacturerName, + sizeof(fru_info->manufacturer_name)); + strscpy(fru_info->fru_id, static_metrics->ProductInfo.FruId, + sizeof(fru_info->fru_id)); + + return 0; +} + +int smu_v13_0_12_get_max_metrics_size(void) +{ + return max(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t)); +} + +static int smu_v13_0_12_get_static_metrics_table(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + uint32_t table_size = smu_table->tables[SMU_TABLE_SMU_METRICS].size; + struct smu_table *table = &smu_table->driver_table; + int ret; + + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetStaticMetricsTable, NULL); + if (ret) { + dev_info(smu->adev->dev, + "Failed to export static metrics table!\n"); + return ret; + } + + amdgpu_asic_invalidate_hdp(smu->adev, NULL); + memcpy(smu_table->metrics_table, table->cpu_addr, table_size); + + return 0; +} + +int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + StaticMetricsTable_t *static_metrics = (StaticMetricsTable_t *)smu_table->metrics_table; + struct PPTable_t *pptable = + (struct PPTable_t *)smu_table->driver_pptable; + uint32_t table_version; + int ret, i; + + if (!pptable->Init) { + ret = smu_v13_0_12_get_static_metrics_table(smu); + if (ret) + return ret; + + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetMetricsVersion, + &table_version); + if (ret) + return ret; + smu_table->tables[SMU_TABLE_SMU_METRICS].version = + table_version; + + pptable->MaxSocketPowerLimit = + SMUQ10_ROUND(static_metrics->MaxSocketPowerLimit); + pptable->MaxGfxclkFrequency = + SMUQ10_ROUND(static_metrics->MaxGfxclkFrequency); + pptable->MinGfxclkFrequency = + SMUQ10_ROUND(static_metrics->MinGfxclkFrequency); + + for (i = 0; i < 4; ++i) { + pptable->FclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->FclkFrequencyTable[i]); + pptable->UclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->UclkFrequencyTable[i]); + pptable->SocclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->SocclkFrequencyTable[i]); + pptable->VclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->VclkFrequencyTable[i]); + pptable->DclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->DclkFrequencyTable[i]); + pptable->LclkFrequencyTable[i] = + SMUQ10_ROUND(static_metrics->LclkFrequencyTable[i]); + } + + /* use AID0 serial number by default */ + pptable->PublicSerialNumber_AID = + static_metrics->PublicSerialNumber_AID[0]; + ret = smu_v13_0_12_fru_get_product_info(smu, static_metrics); + if (ret) + return ret; + + pptable->Init = true; + } + + return 0; +} + bool smu_v13_0_12_is_dpm_running(struct smu_context *smu) { int ret; @@ -99,3 +270,216 @@ bool smu_v13_0_12_is_dpm_running(struct smu_context *smu) return !!(feature_enabled & SMC_DPM_FEATURE); } + +int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value) +{ + struct smu_table_context *smu_table = &smu->smu_table; + MetricsTable_t *metrics = (MetricsTable_t *)smu_table->metrics_table; + struct amdgpu_device *adev = smu->adev; + int ret = 0; + int xcc_id; + + /* For clocks with multiple instances, only report the first one */ + switch (member) { + case METRICS_CURR_GFXCLK: + case METRICS_AVERAGE_GFXCLK: + xcc_id = GET_INST(GC, 0); + *value = SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + break; + case METRICS_CURR_SOCCLK: + case METRICS_AVERAGE_SOCCLK: + *value = SMUQ10_ROUND(metrics->SocclkFrequency[0]); + break; + case METRICS_CURR_UCLK: + case METRICS_AVERAGE_UCLK: + *value = SMUQ10_ROUND(metrics->UclkFrequency); + break; + case METRICS_CURR_VCLK: + *value = SMUQ10_ROUND(metrics->VclkFrequency[0]); + break; + case METRICS_CURR_DCLK: + *value = SMUQ10_ROUND(metrics->DclkFrequency[0]); + break; + case METRICS_CURR_FCLK: + *value = SMUQ10_ROUND(metrics->FclkFrequency); + break; + case METRICS_AVERAGE_GFXACTIVITY: + *value = SMUQ10_ROUND(metrics->SocketGfxBusy); + break; + case METRICS_AVERAGE_MEMACTIVITY: + *value = SMUQ10_ROUND(metrics->DramBandwidthUtilization); + break; + case METRICS_CURR_SOCKETPOWER: + *value = SMUQ10_ROUND(metrics->SocketPower) << 8; + break; + case METRICS_TEMPERATURE_HOTSPOT: + *value = SMUQ10_ROUND(metrics->MaxSocketTemperature) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + case METRICS_TEMPERATURE_MEM: + *value = SMUQ10_ROUND(metrics->MaxHbmTemperature) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + /* This is the max of all VRs and not just SOC VR. + * No need to define another data type for the same. + */ + case METRICS_TEMPERATURE_VRSOC: + *value = SMUQ10_ROUND(metrics->MaxVrTemperature) * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + default: + *value = UINT_MAX; + break; + } + + return ret; +} + +ssize_t smu_v13_0_12_get_gpu_metrics(struct smu_context *smu, void **table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct gpu_metrics_v1_7 *gpu_metrics = + (struct gpu_metrics_v1_7 *)smu_table->gpu_metrics_table; + int ret = 0, xcc_id, inst, i, j, k, idx; + struct amdgpu_device *adev = smu->adev; + u8 num_jpeg_rings_gpu_metrics; + MetricsTable_t *metrics; + struct amdgpu_xcp *xcp; + u32 inst_mask; + + metrics = kzalloc(sizeof(MetricsTable_t), GFP_KERNEL); + memcpy(metrics, smu_table->metrics_table, sizeof(MetricsTable_t)); + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 7); + + gpu_metrics->temperature_hotspot = + SMUQ10_ROUND(metrics->MaxSocketTemperature); + /* Individual HBM stack temperature is not reported */ + gpu_metrics->temperature_mem = + SMUQ10_ROUND(metrics->MaxHbmTemperature); + /* Reports max temperature of all voltage rails */ + gpu_metrics->temperature_vrsoc = + SMUQ10_ROUND(metrics->MaxVrTemperature); + + gpu_metrics->average_gfx_activity = + SMUQ10_ROUND(metrics->SocketGfxBusy); + gpu_metrics->average_umc_activity = + SMUQ10_ROUND(metrics->DramBandwidthUtilization); + + gpu_metrics->mem_max_bandwidth = + SMUQ10_ROUND(metrics->MaxDramBandwidth); + + gpu_metrics->curr_socket_power = + SMUQ10_ROUND(metrics->SocketPower); + /* Energy counter reported in 15.259uJ (2^-16) units */ + gpu_metrics->energy_accumulator = metrics->SocketEnergyAcc; + + for (i = 0; i < MAX_GFX_CLKS; i++) { + xcc_id = GET_INST(GC, i); + if (xcc_id >= 0) + gpu_metrics->current_gfxclk[i] = + SMUQ10_ROUND(metrics->GfxclkFrequency[xcc_id]); + + if (i < MAX_CLKS) { + gpu_metrics->current_socclk[i] = + SMUQ10_ROUND(metrics->SocclkFrequency[i]); + inst = GET_INST(VCN, i); + if (inst >= 0) { + gpu_metrics->current_vclk0[i] = + SMUQ10_ROUND(metrics->VclkFrequency[inst]); + gpu_metrics->current_dclk0[i] = + SMUQ10_ROUND(metrics->DclkFrequency[inst]); + } + } + } + + gpu_metrics->current_uclk = SMUQ10_ROUND(metrics->UclkFrequency); + + /* Total accumulated cycle counter */ + gpu_metrics->accumulation_counter = metrics->AccumulationCounter; + + /* Accumulated throttler residencies */ + gpu_metrics->prochot_residency_acc = metrics->ProchotResidencyAcc; + gpu_metrics->ppt_residency_acc = metrics->PptResidencyAcc; + gpu_metrics->socket_thm_residency_acc = metrics->SocketThmResidencyAcc; + gpu_metrics->vr_thm_residency_acc = metrics->VrThmResidencyAcc; + gpu_metrics->hbm_thm_residency_acc = metrics->HbmThmResidencyAcc; + + /* Clock Lock Status. Each bit corresponds to each GFXCLK instance */ + gpu_metrics->gfxclk_lock_status = metrics->GfxLockXCDMak >> GET_INST(GC, 0); + + gpu_metrics->pcie_link_width = metrics->PCIeLinkWidth; + gpu_metrics->pcie_link_speed = + pcie_gen_to_speed(metrics->PCIeLinkSpeed); + gpu_metrics->pcie_bandwidth_acc = + SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]); + gpu_metrics->pcie_bandwidth_inst = + SMUQ10_ROUND(metrics->PcieBandwidth[0]); + gpu_metrics->pcie_l0_to_recov_count_acc = metrics->PCIeL0ToRecoveryCountAcc; + gpu_metrics->pcie_replay_count_acc = metrics->PCIenReplayAAcc; + gpu_metrics->pcie_replay_rover_count_acc = + metrics->PCIenReplayARolloverCountAcc; + gpu_metrics->pcie_nak_sent_count_acc = metrics->PCIeNAKSentCountAcc; + gpu_metrics->pcie_nak_rcvd_count_acc = metrics->PCIeNAKReceivedCountAcc; + gpu_metrics->pcie_lc_perf_other_end_recovery = metrics->PCIeOtherEndRecoveryAcc; + + gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); + + gpu_metrics->gfx_activity_acc = SMUQ10_ROUND(metrics->SocketGfxBusyAcc); + gpu_metrics->mem_activity_acc = SMUQ10_ROUND(metrics->DramBandwidthUtilizationAcc); + + for (i = 0; i < NUM_XGMI_LINKS; i++) { + gpu_metrics->xgmi_read_data_acc[i] = + SMUQ10_ROUND(metrics->XgmiReadDataSizeAcc[i]); + gpu_metrics->xgmi_write_data_acc[i] = + SMUQ10_ROUND(metrics->XgmiWriteDataSizeAcc[i]); + ret = amdgpu_get_xgmi_link_status(adev, i); + if (ret >= 0) + gpu_metrics->xgmi_link_status[i] = ret; + } + + gpu_metrics->num_partition = adev->xcp_mgr->num_xcps; + + num_jpeg_rings_gpu_metrics = NUM_JPEG_RINGS_GPU_METRICS(gpu_metrics); + for_each_xcp(adev->xcp_mgr, xcp, i) { + amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_VCN, &inst_mask); + idx = 0; + for_each_inst(k, inst_mask) { + /* Both JPEG and VCN has same instances */ + inst = GET_INST(VCN, k); + + for (j = 0; j < num_jpeg_rings_gpu_metrics; ++j) { + gpu_metrics->xcp_stats[i].jpeg_busy + [(idx * num_jpeg_rings_gpu_metrics) + j] = + SMUQ10_ROUND(metrics->JpegBusy + [(inst * NUM_JPEG_RINGS_FW) + j]); + } + gpu_metrics->xcp_stats[i].vcn_busy[idx] = + SMUQ10_ROUND(metrics->VcnBusy[inst]); + idx++; + } + + amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_GFX, &inst_mask); + idx = 0; + for_each_inst(k, inst_mask) { + inst = GET_INST(GC, k); + gpu_metrics->xcp_stats[i].gfx_busy_inst[idx] = + SMUQ10_ROUND(metrics->GfxBusy[inst]); + gpu_metrics->xcp_stats[i].gfx_busy_acc[idx] = + SMUQ10_ROUND(metrics->GfxBusyAcc[inst]); + idx++; + } + } + + gpu_metrics->xgmi_link_width = SMUQ10_ROUND(metrics->XgmiWidth); + gpu_metrics->xgmi_link_speed = SMUQ10_ROUND(metrics->XgmiBitrate); + + gpu_metrics->firmware_timestamp = metrics->Timestamp; + + *table = (void *)gpu_metrics; + kfree(metrics); + + return sizeof(*gpu_metrics); +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 9f2de69f53b2..1e1d8989c77a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -116,6 +116,7 @@ enum smu_v13_0_6_caps { SMU_CAP(RMA_MSG), SMU_CAP(ACA_SYND), SMU_CAP(SDMA_RESET), + SMU_CAP(STATIC_METRICS), SMU_CAP(ALL), }; @@ -252,25 +253,6 @@ static const uint8_t smu_v13_0_6_throttler_map[] = { [THROTTLER_PROCHOT_BIT] = (SMU_THROTTLER_PROCHOT_GFX_BIT), }; -struct PPTable_t { - uint32_t MaxSocketPowerLimit; - uint32_t MaxGfxclkFrequency; - uint32_t MinGfxclkFrequency; - uint32_t FclkFrequencyTable[4]; - uint32_t UclkFrequencyTable[4]; - uint32_t SocclkFrequencyTable[4]; - uint32_t VclkFrequencyTable[4]; - uint32_t DclkFrequencyTable[4]; - uint32_t LclkFrequencyTable[4]; - uint32_t MaxLclkDpmRange; - uint32_t MinLclkDpmRange; - uint64_t PublicSerialNumber_AID; - bool Init; -}; - -#define SMUQ10_TO_UINT(x) ((x) >> 10) -#define SMUQ10_FRAC(x) ((x) & 0x3ff) -#define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200)) #define GET_GPU_METRIC_FIELD(field, version) ((version == METRICS_VERSION_V0) ?\ (metrics_v0->field) : (metrics_v2->field)) #define GET_METRIC_FIELD(field, version) ((version == METRICS_VERSION_V1) ?\ @@ -368,6 +350,9 @@ static void smu_v13_0_12_init_caps(struct smu_context *smu) if (fw_ver >= 0x00561700) smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET)); + + if (fw_ver >= 0x00561E00) + smu_v13_0_6_cap_set(smu, SMU_CAP(STATIC_METRICS)); } static void smu_v13_0_6_init_caps(struct smu_context *smu) @@ -523,13 +508,15 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu) struct smu_table_context *smu_table = &smu->smu_table; struct smu_table *tables = smu_table->tables; struct amdgpu_device *adev = smu->adev; + int gpu_metrcs_size = METRICS_TABLE_SIZE; if (!(adev->flags & AMD_IS_APU)) SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, - METRICS_TABLE_SIZE, + max(gpu_metrcs_size, + smu_v13_0_12_get_max_metrics_size()), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); @@ -776,6 +763,9 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu) int ret, i, retry = 100; uint32_t table_version; + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) + return smu_v13_0_12_setup_driver_pptable(smu); + /* Store one-time values in driver PPTable */ if (!pptable->Init) { while (--retry) { @@ -1156,6 +1146,9 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu, if (ret) return ret; + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) + return smu_v13_0_12_get_smu_metrics_data(smu, member, value); + /* For clocks with multiple instances, only report the first one */ switch (member) { case METRICS_CURR_GFXCLK: @@ -1947,7 +1940,7 @@ static int smu_v13_0_6_set_performance_level(struct smu_context *smu, break; } - return -EINVAL; + return -EOPNOTSUPP; } static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu, @@ -2518,6 +2511,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table return ret; } + if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) + return smu_v13_0_12_get_gpu_metrics(smu, table); + metrics_v1 = (MetricsTableV1_t *)metrics_v0; metrics_v2 = (MetricsTableV2_t *)metrics_v0; @@ -2902,11 +2898,31 @@ static int smu_v13_0_6_send_rma_reason(struct smu_context *smu) return ret; } +/** + * smu_v13_0_6_reset_sdma_is_supported - Check if SDMA reset is supported + * @smu: smu_context pointer + * + * This function checks if the SMU supports resetting the SDMA engine. + * It returns false if the capability is not supported. + */ +static bool smu_v13_0_6_reset_sdma_is_supported(struct smu_context *smu) +{ + bool ret = true; + + if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SDMA_RESET))) { + dev_info(smu->adev->dev, + "SDMA reset capability is not supported\n"); + ret = false; + } + + return ret; +} + static int smu_v13_0_6_reset_sdma(struct smu_context *smu, uint32_t inst_mask) { int ret = 0; - if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SDMA_RESET))) + if (!smu_v13_0_6_reset_sdma_is_supported(smu)) return -EOPNOTSUPP; ret = smu_cmn_send_smc_msg_with_param(smu, @@ -3590,12 +3606,14 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = { .send_hbm_bad_pages_num = smu_v13_0_6_smu_send_hbm_bad_page_num, .send_rma_reason = smu_v13_0_6_send_rma_reason, .reset_sdma = smu_v13_0_6_reset_sdma, + .reset_sdma_is_supported = smu_v13_0_6_reset_sdma_is_supported, }; void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu) { smu->ppt_funcs = &smu_v13_0_6_ppt_funcs; - smu->message_map = smu_v13_0_6_message_map; + smu->message_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ? + smu_v13_0_12_message_map : smu_v13_0_6_message_map; smu->clock_map = smu_v13_0_6_clk_map; smu->feature_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ? smu_v13_0_12_feature_mask_map : smu_v13_0_6_feature_mask_map; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h index 717fe669882e..83745909e564 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h @@ -35,6 +35,22 @@ typedef enum { /*3*/ NUM_METRICS = 3 } METRICS_LIST_e; +struct PPTable_t { + uint32_t MaxSocketPowerLimit; + uint32_t MaxGfxclkFrequency; + uint32_t MinGfxclkFrequency; + uint32_t FclkFrequencyTable[4]; + uint32_t UclkFrequencyTable[4]; + uint32_t SocclkFrequencyTable[4]; + uint32_t VclkFrequencyTable[4]; + uint32_t DclkFrequencyTable[4]; + uint32_t LclkFrequencyTable[4]; + uint32_t MaxLclkDpmRange; + uint32_t MinLclkDpmRange; + uint64_t PublicSerialNumber_AID; + bool Init; +}; + extern void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu); #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index adbb6332376e..76c1adda83db 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -950,6 +950,14 @@ static int smu_v14_0_irq_process(struct amdgpu_device *adev, uint32_t client_id = entry->client_id; uint32_t src_id = entry->src_id; + /* + * ctxid is used to distinguish different + * events for SMCToHost interrupt. + */ + uint32_t ctxid = entry->src_data[0]; + uint32_t data; + uint32_t high; + if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: @@ -964,6 +972,50 @@ static int smu_v14_0_irq_process(struct amdgpu_device *adev, src_id); break; } + } else if (client_id == SOC15_IH_CLIENTID_MP1) { + if (src_id == SMU_IH_INTERRUPT_ID_TO_DRIVER) { + /* ACK SMUToHost interrupt */ + data = RREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL); + data = REG_SET_FIELD(data, MP1_SMN_IH_SW_INT_CTRL, INT_ACK, 1); + WREG32_SOC15(MP1, 0, regMP1_SMN_IH_SW_INT_CTRL, data); + + switch (ctxid) { + case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL: + high = smu->thermal_range.software_shutdown_temp + + smu->thermal_range.software_shutdown_temp_offset; + high = min_t(typeof(high), + SMU_THERMAL_MAXIMUM_ALERT_TEMP, + high); + dev_emerg(adev->dev, "Reduce soft CTF limit to %d (by an offset %d)\n", + high, + smu->thermal_range.software_shutdown_temp_offset); + + data = RREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL); + data = REG_SET_FIELD(data, THM_THERMAL_INT_CTRL, + DIG_THERM_INTH, + (high & 0xff)); + data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); + WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); + break; + case SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY: + high = min_t(typeof(high), + SMU_THERMAL_MAXIMUM_ALERT_TEMP, + smu->thermal_range.software_shutdown_temp); + dev_emerg(adev->dev, "Recover soft CTF limit to %d\n", high); + + data = RREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL); + data = REG_SET_FIELD(data, THM_THERMAL_INT_CTRL, + DIG_THERM_INTH, + (high & 0xff)); + data = data & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); + WREG32_SOC15(THM, 0, regTHM_THERMAL_INT_CTRL, data); + break; + default: + dev_dbg(adev->dev, "Unhandled context id %d from client:%d!\n", + ctxid, client_id); + break; + } + } } return 0; @@ -1897,16 +1949,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu) NULL); } -static int smu_v14_0_process_pending_interrupt(struct smu_context *smu) -{ - int ret = 0; - - if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT)) - ret = smu_v14_0_allow_ih_interrupt(smu); - - return ret; -} - int smu_v14_0_enable_thermal_alert(struct smu_context *smu) { int ret = 0; @@ -1918,7 +1960,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu) if (ret) return ret; - return smu_v14_0_process_pending_interrupt(smu); + return smu_v14_0_allow_ih_interrupt(smu); } int smu_v14_0_disable_thermal_alert(struct smu_context *smu) diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index 397e677a691c..46094cca2974 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -144,11 +144,9 @@ static int aspeed_gfx_load(struct drm_device *drm) struct aspeed_gfx *priv = to_aspeed_gfx(drm); struct device_node *np = pdev->dev.of_node; const struct aspeed_gfx_config *config; - struct resource *res; int ret; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(drm->dev, res); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 2100a687096e..914a2609a685 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -887,7 +887,7 @@ static int sii902x_audio_codec_init(struct sii902x *sii902x, lanes[0] = 0; } else if (num_lanes < 0) { dev_err(dev, - "%s: Error gettin \"sil,i2s-data-lanes\": %d\n", + "%s: Error getting \"sil,i2s-data-lanes\": %d\n", __func__, num_lanes); return num_lanes; } diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c index 1d39015f1533..6166f197e37b 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-qp.c @@ -36,6 +36,88 @@ #define SCRAMB_POLL_DELAY_MS 3000 +/* + * Unless otherwise noted, entries in this table are 100% optimization. + * Values can be obtained from dw_hdmi_qp_compute_n() but that function is + * slow so we pre-compute values we expect to see. + * + * The values for TMDS 25175, 25200, 27000, 54000, 74250 and 148500 kHz are + * the recommended N values specified in the Audio chapter of the HDMI + * specification. + */ +static const struct dw_hdmi_audio_tmds_n { + unsigned long tmds; + unsigned int n_32k; + unsigned int n_44k1; + unsigned int n_48k; +} common_tmds_n_table[] = { + { .tmds = 25175000, .n_32k = 4576, .n_44k1 = 7007, .n_48k = 6864, }, + { .tmds = 25200000, .n_32k = 4096, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 27000000, .n_32k = 4096, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 28320000, .n_32k = 4096, .n_44k1 = 5586, .n_48k = 6144, }, + { .tmds = 30240000, .n_32k = 4096, .n_44k1 = 5642, .n_48k = 6144, }, + { .tmds = 31500000, .n_32k = 4096, .n_44k1 = 5600, .n_48k = 6144, }, + { .tmds = 32000000, .n_32k = 4096, .n_44k1 = 5733, .n_48k = 6144, }, + { .tmds = 33750000, .n_32k = 4096, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 36000000, .n_32k = 4096, .n_44k1 = 5684, .n_48k = 6144, }, + { .tmds = 40000000, .n_32k = 4096, .n_44k1 = 5733, .n_48k = 6144, }, + { .tmds = 49500000, .n_32k = 4096, .n_44k1 = 5488, .n_48k = 6144, }, + { .tmds = 50000000, .n_32k = 4096, .n_44k1 = 5292, .n_48k = 6144, }, + { .tmds = 54000000, .n_32k = 4096, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 65000000, .n_32k = 4096, .n_44k1 = 7056, .n_48k = 6144, }, + { .tmds = 68250000, .n_32k = 4096, .n_44k1 = 5376, .n_48k = 6144, }, + { .tmds = 71000000, .n_32k = 4096, .n_44k1 = 7056, .n_48k = 6144, }, + { .tmds = 72000000, .n_32k = 4096, .n_44k1 = 5635, .n_48k = 6144, }, + { .tmds = 73250000, .n_32k = 11648, .n_44k1 = 14112, .n_48k = 6144, }, + { .tmds = 74250000, .n_32k = 4096, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 75000000, .n_32k = 4096, .n_44k1 = 5880, .n_48k = 6144, }, + { .tmds = 78750000, .n_32k = 4096, .n_44k1 = 5600, .n_48k = 6144, }, + { .tmds = 78800000, .n_32k = 4096, .n_44k1 = 5292, .n_48k = 6144, }, + { .tmds = 79500000, .n_32k = 4096, .n_44k1 = 4704, .n_48k = 6144, }, + { .tmds = 83500000, .n_32k = 4096, .n_44k1 = 7056, .n_48k = 6144, }, + { .tmds = 85500000, .n_32k = 4096, .n_44k1 = 5488, .n_48k = 6144, }, + { .tmds = 88750000, .n_32k = 4096, .n_44k1 = 14112, .n_48k = 6144, }, + { .tmds = 97750000, .n_32k = 4096, .n_44k1 = 14112, .n_48k = 6144, }, + { .tmds = 101000000, .n_32k = 4096, .n_44k1 = 7056, .n_48k = 6144, }, + { .tmds = 106500000, .n_32k = 4096, .n_44k1 = 4704, .n_48k = 6144, }, + { .tmds = 108000000, .n_32k = 4096, .n_44k1 = 5684, .n_48k = 6144, }, + { .tmds = 115500000, .n_32k = 4096, .n_44k1 = 5712, .n_48k = 6144, }, + { .tmds = 119000000, .n_32k = 4096, .n_44k1 = 5544, .n_48k = 6144, }, + { .tmds = 135000000, .n_32k = 4096, .n_44k1 = 5488, .n_48k = 6144, }, + { .tmds = 146250000, .n_32k = 11648, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 148500000, .n_32k = 4096, .n_44k1 = 6272, .n_48k = 6144, }, + { .tmds = 154000000, .n_32k = 4096, .n_44k1 = 5544, .n_48k = 6144, }, + { .tmds = 162000000, .n_32k = 4096, .n_44k1 = 5684, .n_48k = 6144, }, + + /* For 297 MHz+ HDMI spec have some other rule for setting N */ + { .tmds = 297000000, .n_32k = 3073, .n_44k1 = 4704, .n_48k = 5120, }, + { .tmds = 594000000, .n_32k = 3073, .n_44k1 = 9408, .n_48k = 10240,}, + + /* End of table */ + { .tmds = 0, .n_32k = 0, .n_44k1 = 0, .n_48k = 0, }, +}; + +/* + * These are the CTS values as recommended in the Audio chapter of the HDMI + * specification. + */ +static const struct dw_hdmi_audio_tmds_cts { + unsigned long tmds; + unsigned int cts_32k; + unsigned int cts_44k1; + unsigned int cts_48k; +} common_tmds_cts_table[] = { + { .tmds = 25175000, .cts_32k = 28125, .cts_44k1 = 31250, .cts_48k = 28125, }, + { .tmds = 25200000, .cts_32k = 25200, .cts_44k1 = 28000, .cts_48k = 25200, }, + { .tmds = 27000000, .cts_32k = 27000, .cts_44k1 = 30000, .cts_48k = 27000, }, + { .tmds = 54000000, .cts_32k = 54000, .cts_44k1 = 60000, .cts_48k = 54000, }, + { .tmds = 74250000, .cts_32k = 74250, .cts_44k1 = 82500, .cts_48k = 74250, }, + { .tmds = 148500000, .cts_32k = 148500, .cts_44k1 = 165000, .cts_48k = 148500, }, + + /* End of table */ + { .tmds = 0, .cts_32k = 0, .cts_44k1 = 0, .cts_48k = 0, }, +}; + struct dw_hdmi_qp_i2c { struct i2c_adapter adap; @@ -60,6 +142,8 @@ struct dw_hdmi_qp { } phy; struct regmap *regm; + + unsigned long tmds_char_rate; }; static void dw_hdmi_qp_write(struct dw_hdmi_qp *hdmi, unsigned int val, @@ -83,6 +167,346 @@ static void dw_hdmi_qp_mod(struct dw_hdmi_qp *hdmi, unsigned int data, regmap_update_bits(hdmi->regm, reg, mask, data); } +static struct dw_hdmi_qp *dw_hdmi_qp_from_bridge(struct drm_bridge *bridge) +{ + return container_of(bridge, struct dw_hdmi_qp, bridge); +} + +static void dw_hdmi_qp_set_cts_n(struct dw_hdmi_qp *hdmi, unsigned int cts, + unsigned int n) +{ + /* Set N */ + dw_hdmi_qp_mod(hdmi, n, AUDPKT_ACR_N_VALUE, AUDPKT_ACR_CONTROL0); + + /* Set CTS */ + if (cts) + dw_hdmi_qp_mod(hdmi, AUDPKT_ACR_CTS_OVR_EN, AUDPKT_ACR_CTS_OVR_EN_MSK, + AUDPKT_ACR_CONTROL1); + else + dw_hdmi_qp_mod(hdmi, 0, AUDPKT_ACR_CTS_OVR_EN_MSK, + AUDPKT_ACR_CONTROL1); + + dw_hdmi_qp_mod(hdmi, AUDPKT_ACR_CTS_OVR_VAL(cts), AUDPKT_ACR_CTS_OVR_VAL_MSK, + AUDPKT_ACR_CONTROL1); +} + +static int dw_hdmi_qp_match_tmds_n_table(struct dw_hdmi_qp *hdmi, + unsigned long pixel_clk, + unsigned long freq) +{ + const struct dw_hdmi_audio_tmds_n *tmds_n = NULL; + int i; + + for (i = 0; common_tmds_n_table[i].tmds != 0; i++) { + if (pixel_clk == common_tmds_n_table[i].tmds) { + tmds_n = &common_tmds_n_table[i]; + break; + } + } + + if (!tmds_n) + return -ENOENT; + + switch (freq) { + case 32000: + return tmds_n->n_32k; + case 44100: + case 88200: + case 176400: + return (freq / 44100) * tmds_n->n_44k1; + case 48000: + case 96000: + case 192000: + return (freq / 48000) * tmds_n->n_48k; + default: + return -ENOENT; + } +} + +static u32 dw_hdmi_qp_audio_math_diff(unsigned int freq, unsigned int n, + unsigned int pixel_clk) +{ + u64 cts = mul_u32_u32(pixel_clk, n); + + return do_div(cts, 128 * freq); +} + +static unsigned int dw_hdmi_qp_compute_n(struct dw_hdmi_qp *hdmi, + unsigned long pixel_clk, + unsigned long freq) +{ + unsigned int min_n = DIV_ROUND_UP((128 * freq), 1500); + unsigned int max_n = (128 * freq) / 300; + unsigned int ideal_n = (128 * freq) / 1000; + unsigned int best_n_distance = ideal_n; + unsigned int best_n = 0; + u64 best_diff = U64_MAX; + int n; + + /* If the ideal N could satisfy the audio math, then just take it */ + if (dw_hdmi_qp_audio_math_diff(freq, ideal_n, pixel_clk) == 0) + return ideal_n; + + for (n = min_n; n <= max_n; n++) { + u64 diff = dw_hdmi_qp_audio_math_diff(freq, n, pixel_clk); + + if (diff < best_diff || + (diff == best_diff && abs(n - ideal_n) < best_n_distance)) { + best_n = n; + best_diff = diff; + best_n_distance = abs(best_n - ideal_n); + } + + /* + * The best N already satisfy the audio math, and also be + * the closest value to ideal N, so just cut the loop. + */ + if (best_diff == 0 && (abs(n - ideal_n) > best_n_distance)) + break; + } + + return best_n; +} + +static unsigned int dw_hdmi_qp_find_n(struct dw_hdmi_qp *hdmi, unsigned long pixel_clk, + unsigned long sample_rate) +{ + int n = dw_hdmi_qp_match_tmds_n_table(hdmi, pixel_clk, sample_rate); + + if (n > 0) + return n; + + dev_warn(hdmi->dev, "Rate %lu missing; compute N dynamically\n", + pixel_clk); + + return dw_hdmi_qp_compute_n(hdmi, pixel_clk, sample_rate); +} + +static unsigned int dw_hdmi_qp_find_cts(struct dw_hdmi_qp *hdmi, unsigned long pixel_clk, + unsigned long sample_rate) +{ + const struct dw_hdmi_audio_tmds_cts *tmds_cts = NULL; + int i; + + for (i = 0; common_tmds_cts_table[i].tmds != 0; i++) { + if (pixel_clk == common_tmds_cts_table[i].tmds) { + tmds_cts = &common_tmds_cts_table[i]; + break; + } + } + + if (!tmds_cts) + return 0; + + switch (sample_rate) { + case 32000: + return tmds_cts->cts_32k; + case 44100: + case 88200: + case 176400: + return tmds_cts->cts_44k1; + case 48000: + case 96000: + case 192000: + return tmds_cts->cts_48k; + default: + return -ENOENT; + } +} + +static void dw_hdmi_qp_set_audio_interface(struct dw_hdmi_qp *hdmi, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms) +{ + u32 conf0 = 0; + + /* Reset the audio data path of the AVP */ + dw_hdmi_qp_write(hdmi, AVP_DATAPATH_PACKET_AUDIO_SWINIT_P, GLOBAL_SWRESET_REQUEST); + + /* Disable AUDS, ACR, AUDI */ + dw_hdmi_qp_mod(hdmi, 0, + PKTSCHED_ACR_TX_EN | PKTSCHED_AUDS_TX_EN | PKTSCHED_AUDI_TX_EN, + PKTSCHED_PKT_EN); + + /* Clear the audio FIFO */ + dw_hdmi_qp_write(hdmi, AUDIO_FIFO_CLR_P, AUDIO_INTERFACE_CONTROL0); + + /* Select I2S interface as the audio source */ + dw_hdmi_qp_mod(hdmi, AUD_IF_I2S, AUD_IF_SEL_MSK, AUDIO_INTERFACE_CONFIG0); + + /* Enable the active i2s lanes */ + switch (hparms->channels) { + case 7 ... 8: + conf0 |= I2S_LINES_EN(3); + fallthrough; + case 5 ... 6: + conf0 |= I2S_LINES_EN(2); + fallthrough; + case 3 ... 4: + conf0 |= I2S_LINES_EN(1); + fallthrough; + default: + conf0 |= I2S_LINES_EN(0); + break; + } + + dw_hdmi_qp_mod(hdmi, conf0, I2S_LINES_EN_MSK, AUDIO_INTERFACE_CONFIG0); + + /* + * Enable bpcuv generated internally for L-PCM, or received + * from stream for NLPCM/HBR. + */ + switch (fmt->bit_fmt) { + case SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE: + conf0 = (hparms->channels == 8) ? AUD_HBR : AUD_ASP; + conf0 |= I2S_BPCUV_RCV_EN; + break; + default: + conf0 = AUD_ASP | I2S_BPCUV_RCV_DIS; + break; + } + + dw_hdmi_qp_mod(hdmi, conf0, I2S_BPCUV_RCV_MSK | AUD_FORMAT_MSK, + AUDIO_INTERFACE_CONFIG0); + + /* Enable audio FIFO auto clear when overflow */ + dw_hdmi_qp_mod(hdmi, AUD_FIFO_INIT_ON_OVF_EN, AUD_FIFO_INIT_ON_OVF_MSK, + AUDIO_INTERFACE_CONFIG0); +} + +/* + * When transmitting IEC60958 linear PCM audio, these registers allow to + * configure the channel status information of all the channel status + * bits in the IEC60958 frame. For the moment this configuration is only + * used when the I2S audio interface, General Purpose Audio (GPA), + * or AHB audio DMA (AHBAUDDMA) interface is active + * (for S/PDIF interface this information comes from the stream). + */ +static void dw_hdmi_qp_set_channel_status(struct dw_hdmi_qp *hdmi, + u8 *channel_status, bool ref2stream) +{ + /* + * AUDPKT_CHSTATUS_OVR0: { RSV, RSV, CS1, CS0 } + * AUDPKT_CHSTATUS_OVR1: { CS6, CS5, CS4, CS3 } + * + * | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | + * CS0: | Mode | d | c | b | a | + * CS1: | Category Code | + * CS2: | Channel Number | Source Number | + * CS3: | Clock Accuracy | Sample Freq | + * CS4: | Ori Sample Freq | Word Length | + * CS5: | | CGMS-A | + * CS6~CS23: Reserved + * + * a: use of channel status block + * b: linear PCM identification: 0 for lpcm, 1 for nlpcm + * c: copyright information + * d: additional format information + */ + + if (ref2stream) + channel_status[0] |= IEC958_AES0_NONAUDIO; + + if ((dw_hdmi_qp_read(hdmi, AUDIO_INTERFACE_CONFIG0) & GENMASK(25, 24)) == AUD_HBR) { + /* fixup cs for HBR */ + channel_status[3] = (channel_status[3] & 0xf0) | IEC958_AES3_CON_FS_768000; + channel_status[4] = (channel_status[4] & 0x0f) | IEC958_AES4_CON_ORIGFS_NOTID; + } + + dw_hdmi_qp_write(hdmi, channel_status[0] | (channel_status[1] << 8), + AUDPKT_CHSTATUS_OVR0); + + regmap_bulk_write(hdmi->regm, AUDPKT_CHSTATUS_OVR1, &channel_status[3], 1); + + if (ref2stream) + dw_hdmi_qp_mod(hdmi, 0, + AUDPKT_PBIT_FORCE_EN_MASK | AUDPKT_CHSTATUS_OVR_EN_MASK, + AUDPKT_CONTROL0); + else + dw_hdmi_qp_mod(hdmi, AUDPKT_PBIT_FORCE_EN | AUDPKT_CHSTATUS_OVR_EN, + AUDPKT_PBIT_FORCE_EN_MASK | AUDPKT_CHSTATUS_OVR_EN_MASK, + AUDPKT_CONTROL0); +} + +static void dw_hdmi_qp_set_sample_rate(struct dw_hdmi_qp *hdmi, unsigned long long tmds_char_rate, + unsigned int sample_rate) +{ + unsigned int n, cts; + + n = dw_hdmi_qp_find_n(hdmi, tmds_char_rate, sample_rate); + cts = dw_hdmi_qp_find_cts(hdmi, tmds_char_rate, sample_rate); + + dw_hdmi_qp_set_cts_n(hdmi, cts, n); +} + +static int dw_hdmi_qp_audio_enable(struct drm_connector *connector, + struct drm_bridge *bridge) +{ + struct dw_hdmi_qp *hdmi = dw_hdmi_qp_from_bridge(bridge); + + if (hdmi->tmds_char_rate) + dw_hdmi_qp_mod(hdmi, 0, AVP_DATAPATH_PACKET_AUDIO_SWDISABLE, GLOBAL_SWDISABLE); + + return 0; +} + +static int dw_hdmi_qp_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms) +{ + struct dw_hdmi_qp *hdmi = dw_hdmi_qp_from_bridge(bridge); + bool ref2stream = false; + + if (!hdmi->tmds_char_rate) + return -ENODEV; + + if (fmt->bit_clk_provider | fmt->frame_clk_provider) { + dev_err(hdmi->dev, "unsupported clock settings\n"); + return -EINVAL; + } + + if (fmt->bit_fmt == SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE) + ref2stream = true; + + dw_hdmi_qp_set_audio_interface(hdmi, fmt, hparms); + dw_hdmi_qp_set_sample_rate(hdmi, hdmi->tmds_char_rate, hparms->sample_rate); + dw_hdmi_qp_set_channel_status(hdmi, hparms->iec.status, ref2stream); + drm_atomic_helper_connector_hdmi_update_audio_infoframe(connector, &hparms->cea); + + return 0; +} + +static void dw_hdmi_qp_audio_disable_regs(struct dw_hdmi_qp *hdmi) +{ + /* + * Keep ACR, AUDI, AUDS packet always on to make SINK device + * active for better compatibility and user experience. + * + * This also fix POP sound on some SINK devices which wakeup + * from suspend to active. + */ + dw_hdmi_qp_mod(hdmi, I2S_BPCUV_RCV_DIS, I2S_BPCUV_RCV_MSK, + AUDIO_INTERFACE_CONFIG0); + dw_hdmi_qp_mod(hdmi, AUDPKT_PBIT_FORCE_EN | AUDPKT_CHSTATUS_OVR_EN, + AUDPKT_PBIT_FORCE_EN_MASK | AUDPKT_CHSTATUS_OVR_EN_MASK, + AUDPKT_CONTROL0); + + dw_hdmi_qp_mod(hdmi, AVP_DATAPATH_PACKET_AUDIO_SWDISABLE, + AVP_DATAPATH_PACKET_AUDIO_SWDISABLE, GLOBAL_SWDISABLE); +} + +static void dw_hdmi_qp_audio_disable(struct drm_connector *connector, + struct drm_bridge *bridge) +{ + struct dw_hdmi_qp *hdmi = dw_hdmi_qp_from_bridge(bridge); + + drm_atomic_helper_connector_hdmi_clear_audio_infoframe(connector); + + if (hdmi->tmds_char_rate) + dw_hdmi_qp_audio_disable_regs(hdmi); +} + static int dw_hdmi_qp_i2c_read(struct dw_hdmi_qp *hdmi, unsigned char *buf, unsigned int length) { @@ -361,6 +785,51 @@ static int dw_hdmi_qp_config_drm_infoframe(struct dw_hdmi_qp *hdmi, return 0; } +/* + * Static values documented in the TRM + * Different values are only used for debug purposes + */ +#define DW_HDMI_QP_AUDIO_INFOFRAME_HB1 0x1 +#define DW_HDMI_QP_AUDIO_INFOFRAME_HB2 0xa + +static int dw_hdmi_qp_config_audio_infoframe(struct dw_hdmi_qp *hdmi, + const u8 *buffer, size_t len) +{ + /* + * AUDI_CONTENTS0: { RSV, HB2, HB1, RSV } + * AUDI_CONTENTS1: { PB3, PB2, PB1, PB0 } + * AUDI_CONTENTS2: { PB7, PB6, PB5, PB4 } + * + * PB0: CheckSum + * PB1: | CT3 | CT2 | CT1 | CT0 | F13 | CC2 | CC1 | CC0 | + * PB2: | F27 | F26 | F25 | SF2 | SF1 | SF0 | SS1 | SS0 | + * PB3: | F37 | F36 | F35 | F34 | F33 | F32 | F31 | F30 | + * PB4: | CA7 | CA6 | CA5 | CA4 | CA3 | CA2 | CA1 | CA0 | + * PB5: | DM_INH | LSV3 | LSV2 | LSV1 | LSV0 | F52 | F51 | F50 | + * PB6~PB10: Reserved + * + * AUDI_CONTENTS0 default value defined by HDMI specification, + * and shall only be changed for debug purposes. + */ + u32 header_bytes = (DW_HDMI_QP_AUDIO_INFOFRAME_HB1 << 8) | + (DW_HDMI_QP_AUDIO_INFOFRAME_HB2 << 16); + + regmap_bulk_write(hdmi->regm, PKT_AUDI_CONTENTS0, &header_bytes, 1); + regmap_bulk_write(hdmi->regm, PKT_AUDI_CONTENTS1, &buffer[3], 1); + regmap_bulk_write(hdmi->regm, PKT_AUDI_CONTENTS2, &buffer[4], 1); + + /* Enable ACR, AUDI, AMD */ + dw_hdmi_qp_mod(hdmi, + PKTSCHED_ACR_TX_EN | PKTSCHED_AUDI_TX_EN | PKTSCHED_AMD_TX_EN, + PKTSCHED_ACR_TX_EN | PKTSCHED_AUDI_TX_EN | PKTSCHED_AMD_TX_EN, + PKTSCHED_PKT_EN); + + /* Enable AUDS */ + dw_hdmi_qp_mod(hdmi, PKTSCHED_AUDS_TX_EN, PKTSCHED_AUDS_TX_EN, PKTSCHED_PKT_EN); + + return 0; +} + static void dw_hdmi_qp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_atomic_state *state) { @@ -381,6 +850,7 @@ static void dw_hdmi_qp_bridge_atomic_enable(struct drm_bridge *bridge, dev_dbg(hdmi->dev, "%s mode=HDMI rate=%llu\n", __func__, conn_state->hdmi.tmds_char_rate); op_mode = 0; + hdmi->tmds_char_rate = conn_state->hdmi.tmds_char_rate; } else { dev_dbg(hdmi->dev, "%s mode=DVI\n", __func__); op_mode = OPMODE_DVI; @@ -399,6 +869,8 @@ static void dw_hdmi_qp_bridge_atomic_disable(struct drm_bridge *bridge, { struct dw_hdmi_qp *hdmi = bridge->driver_private; + hdmi->tmds_char_rate = 0; + hdmi->phy.ops->disable(hdmi, hdmi->phy.data); } @@ -454,6 +926,13 @@ static int dw_hdmi_qp_bridge_clear_infoframe(struct drm_bridge *bridge, dw_hdmi_qp_mod(hdmi, 0, PKTSCHED_DRMI_TX_EN, PKTSCHED_PKT_EN); break; + case HDMI_INFOFRAME_TYPE_AUDIO: + dw_hdmi_qp_mod(hdmi, 0, + PKTSCHED_ACR_TX_EN | + PKTSCHED_AUDS_TX_EN | + PKTSCHED_AUDI_TX_EN, + PKTSCHED_PKT_EN); + break; default: dev_dbg(hdmi->dev, "Unsupported infoframe type %x\n", type); } @@ -476,6 +955,9 @@ static int dw_hdmi_qp_bridge_write_infoframe(struct drm_bridge *bridge, case HDMI_INFOFRAME_TYPE_DRM: return dw_hdmi_qp_config_drm_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_AUDIO: + return dw_hdmi_qp_config_audio_infoframe(hdmi, buffer, len); + default: dev_dbg(hdmi->dev, "Unsupported infoframe type %x\n", type); return 0; @@ -493,6 +975,9 @@ static const struct drm_bridge_funcs dw_hdmi_qp_bridge_funcs = { .hdmi_tmds_char_rate_valid = dw_hdmi_qp_bridge_tmds_char_rate_valid, .hdmi_clear_infoframe = dw_hdmi_qp_bridge_clear_infoframe, .hdmi_write_infoframe = dw_hdmi_qp_bridge_write_infoframe, + .hdmi_audio_startup = dw_hdmi_qp_audio_enable, + .hdmi_audio_shutdown = dw_hdmi_qp_audio_disable, + .hdmi_audio_prepare = dw_hdmi_qp_audio_prepare, }; static irqreturn_t dw_hdmi_qp_main_hardirq(int irq, void *dev_id) @@ -602,6 +1087,10 @@ struct dw_hdmi_qp *dw_hdmi_qp_bind(struct platform_device *pdev, if (IS_ERR(hdmi->bridge.ddc)) return ERR_CAST(hdmi->bridge.ddc); + hdmi->bridge.hdmi_audio_max_i2s_playback_channels = 8; + hdmi->bridge.hdmi_audio_dev = dev; + hdmi->bridge.hdmi_audio_dai_port = 1; + ret = devm_drm_bridge_add(dev, &hdmi->bridge); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 54ad462d17ef..95563aa1b450 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -561,6 +561,8 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, REG_LVDS_FMT_HS_NEG_POLARITY : 0) | (mode->flags & DRM_MODE_FLAG_NVSYNC ? REG_LVDS_FMT_VS_NEG_POLARITY : 0); + val |= bridge_state->output_bus_cfg.flags & DRM_BUS_FLAG_DE_LOW ? + REG_LVDS_FMT_DE_NEG_POLARITY : 0; /* Set up bits-per-pixel, 18bpp or 24bpp. */ if (lvds_format_24bpp) { diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index ae34585e05b3..01d456b955ab 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -195,7 +195,7 @@ struct ti_sn65dsi86 { struct gpio_chip gchip; DECLARE_BITMAP(gchip_output, SN_NUM_GPIOS); #endif -#if defined(CONFIG_PWM) +#if IS_REACHABLE(CONFIG_PWM) struct pwm_chip *pchip; bool pwm_enabled; atomic_t pwm_pin_busy; @@ -1362,7 +1362,7 @@ static struct auxiliary_driver ti_sn_bridge_driver = { /* ----------------------------------------------------------------------------- * PWM Controller */ -#if defined(CONFIG_PWM) +#if IS_REACHABLE(CONFIG_PWM) static int ti_sn_pwm_pin_request(struct ti_sn65dsi86 *pdata) { return atomic_xchg(&pdata->pwm_pin_busy, 1) ? -EBUSY : 0; @@ -1956,7 +1956,7 @@ static int ti_sn65dsi86_probe(struct i2c_client *client) return ret; } - if (IS_ENABLED(CONFIG_PWM)) { + if (IS_REACHABLE(CONFIG_PWM)) { ret = ti_sn65dsi86_add_aux_device(pdata, &pdata->pwm_aux, "pwm"); if (ret) return ret; diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index f5c596234729..dbce1c3f4969 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -2876,6 +2876,67 @@ int drm_dp_lttpr_max_link_rate(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]) EXPORT_SYMBOL(drm_dp_lttpr_max_link_rate); /** + * drm_dp_lttpr_set_transparent_mode() - set the LTTPR in transparent mode + * @aux: DisplayPort AUX channel + * @enable: Enable or disable transparent mode + * + * Returns: 0 on success or a negative error code on failure. + */ +int drm_dp_lttpr_set_transparent_mode(struct drm_dp_aux *aux, bool enable) +{ + u8 val = enable ? DP_PHY_REPEATER_MODE_TRANSPARENT : + DP_PHY_REPEATER_MODE_NON_TRANSPARENT; + int ret = drm_dp_dpcd_writeb(aux, DP_PHY_REPEATER_MODE, val); + + if (ret < 0) + return ret; + + return (ret == 1) ? 0 : -EIO; +} +EXPORT_SYMBOL(drm_dp_lttpr_set_transparent_mode); + +/** + * drm_dp_lttpr_init() - init LTTPR transparency mode according to DP standard + * @aux: DisplayPort AUX channel + * @lttpr_count: Number of LTTPRs. Between 0 and 8, according to DP standard. + * Negative error code for any non-valid number. + * See drm_dp_lttpr_count(). + * + * Returns: 0 on success or a negative error code on failure. + */ +int drm_dp_lttpr_init(struct drm_dp_aux *aux, int lttpr_count) +{ + int ret; + + if (!lttpr_count) + return 0; + + /* + * See DP Standard v2.0 3.6.6.1 about the explicit disabling of + * non-transparent mode and the disable->enable non-transparent mode + * sequence. + */ + ret = drm_dp_lttpr_set_transparent_mode(aux, true); + if (ret) + return ret; + + if (lttpr_count < 0) + return -ENODEV; + + if (drm_dp_lttpr_set_transparent_mode(aux, false)) { + /* + * Roll-back to transparent mode if setting non-transparent + * mode has failed + */ + drm_dp_lttpr_set_transparent_mode(aux, true); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(drm_dp_lttpr_init); + +/** * drm_dp_lttpr_max_lane_count - get the maximum lane count supported by all LTTPRs * @caps: LTTPR common capabilities * diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 7a25e70694ba..5302ab324898 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -3409,6 +3409,10 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_all); * This implies a reset of all active components available between the CRTC and * connectors. * + * NOTE: This relies on resetting &drm_crtc_state.connectors_changed. + * For drivers which optimize out unnecessary modesets this will result in + * a no-op commit, achieving nothing. + * * Returns: * 0 on success or a negative error code on failure. */ diff --git a/drivers/gpu/drm/drm_fb_dma_helper.c b/drivers/gpu/drm/drm_fb_dma_helper.c index e1d61a65210b..2c4dc7ebc0c3 100644 --- a/drivers/gpu/drm/drm_fb_dma_helper.c +++ b/drivers/gpu/drm/drm_fb_dma_helper.c @@ -178,7 +178,7 @@ int drm_fb_dma_get_scanout_buffer(struct drm_plane *plane, dma_obj = drm_fb_dma_get_gem_obj(fb, 0); /* Buffer should be accessible from the CPU */ - if (dma_obj->base.import_attach) + if (drm_gem_is_imported(&dma_obj->base)) return -ENODEV; /* Buffer should be already mapped to CPU */ diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index ecb278b63e8c..01d3ab307ac3 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -702,6 +702,57 @@ void drm_fb_xrgb8888_to_rgb888(struct iosys_map *dst, const unsigned int *dst_pi } EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888); +static void drm_fb_xrgb8888_to_bgr888_line(void *dbuf, const void *sbuf, unsigned int pixels) +{ + u8 *dbuf8 = dbuf; + const __le32 *sbuf32 = sbuf; + unsigned int x; + u32 pix; + + for (x = 0; x < pixels; x++) { + pix = le32_to_cpu(sbuf32[x]); + /* write red-green-blue to output in little endianness */ + *dbuf8++ = (pix & 0x00ff0000) >> 16; + *dbuf8++ = (pix & 0x0000ff00) >> 8; + *dbuf8++ = (pix & 0x000000ff) >> 0; + } +} + +/** + * drm_fb_xrgb8888_to_bgr888 - Convert XRGB8888 to BGR888 clip buffer + * @dst: Array of BGR888 destination buffers + * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines + * within @dst; can be NULL if scanlines are stored next to each other. + * @src: Array of XRGB8888 source buffers + * @fb: DRM framebuffer + * @clip: Clip rectangle area to copy + * @state: Transform and conversion state + * + * This function copies parts of a framebuffer to display memory and converts the + * color format during the process. Destination and framebuffer formats must match. The + * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at + * least as many entries as there are planes in @fb's format. Each entry stores the + * value for the format's respective color plane at the same index. + * + * This function does not apply clipping on @dst (i.e. the destination is at the + * top-left corner). + * + * Drivers can use this function for BGR888 devices that don't natively + * support XRGB8888. + */ +void drm_fb_xrgb8888_to_bgr888(struct iosys_map *dst, const unsigned int *dst_pitch, + const struct iosys_map *src, const struct drm_framebuffer *fb, + const struct drm_rect *clip, struct drm_format_conv_state *state) +{ + static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { + 3, + }; + + drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, + drm_fb_xrgb8888_to_bgr888_line); +} +EXPORT_SYMBOL(drm_fb_xrgb8888_to_bgr888); + static void drm_fb_xrgb8888_to_argb8888_line(void *dbuf, const void *sbuf, unsigned int pixels) { __le32 *dbuf32 = dbuf; @@ -1104,6 +1155,9 @@ int drm_fb_blit(struct iosys_map *dst, const unsigned int *dst_pitch, uint32_t d } else if (dst_format == DRM_FORMAT_RGB888) { drm_fb_xrgb8888_to_rgb888(dst, dst_pitch, src, fb, clip, state); return 0; + } else if (dst_format == DRM_FORMAT_BGR888) { + drm_fb_xrgb8888_to_bgr888(dst, dst_pitch, src, fb, clip, state); + return 0; } else if (dst_format == DRM_FORMAT_ARGB8888) { drm_fb_xrgb8888_to_argb8888(dst, dst_pitch, src, fb, clip, state); return 0; diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index ee811764c3df..c6240bab3fa5 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -348,7 +348,7 @@ int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, return -ENOENT; /* Don't allow imported objects to be mapped */ - if (obj->import_attach) { + if (drm_gem_is_imported(obj)) { ret = -EINVAL; goto out; } @@ -1178,7 +1178,7 @@ void drm_gem_print_info(struct drm_printer *p, unsigned int indent, drm_vma_node_start(&obj->vma_node)); drm_printf_indent(p, indent, "size=%zu\n", obj->size); drm_printf_indent(p, indent, "imported=%s\n", - str_yes_no(obj->import_attach)); + str_yes_no(drm_gem_is_imported(obj))); if (obj->funcs->print_info) obj->funcs->print_info(p, indent, obj); diff --git a/drivers/gpu/drm/drm_gem_dma_helper.c b/drivers/gpu/drm/drm_gem_dma_helper.c index 16988d316a6d..b7f033d4352a 100644 --- a/drivers/gpu/drm/drm_gem_dma_helper.c +++ b/drivers/gpu/drm/drm_gem_dma_helper.c @@ -228,9 +228,9 @@ void drm_gem_dma_free(struct drm_gem_dma_object *dma_obj) struct drm_gem_object *gem_obj = &dma_obj->base; struct iosys_map map = IOSYS_MAP_INIT_VADDR(dma_obj->vaddr); - if (gem_obj->import_attach) { + if (drm_gem_is_imported(gem_obj)) { if (dma_obj->vaddr) - dma_buf_vunmap_unlocked(gem_obj->import_attach->dmabuf, &map); + dma_buf_vunmap_unlocked(gem_obj->dma_buf, &map); drm_prime_gem_destroy(gem_obj, dma_obj->sgt); } else if (dma_obj->vaddr) { if (dma_obj->map_noncoherent) diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 185534f56bab..0fbeb686e561 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -419,7 +419,6 @@ EXPORT_SYMBOL(drm_gem_fb_vunmap); static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir, unsigned int num_planes) { - struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; int ret; @@ -428,10 +427,9 @@ static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_dat obj = drm_gem_fb_get_obj(fb, num_planes); if (!obj) continue; - import_attach = obj->import_attach; - if (!import_attach) + if (!drm_gem_is_imported(obj)) continue; - ret = dma_buf_end_cpu_access(import_attach->dmabuf, dir); + ret = dma_buf_end_cpu_access(obj->dma_buf, dir); if (ret) drm_err(fb->dev, "dma_buf_end_cpu_access(%u, %d) failed: %d\n", ret, num_planes, dir); @@ -454,7 +452,6 @@ static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_dat */ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir) { - struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; unsigned int i; int ret; @@ -465,10 +462,9 @@ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direct ret = -EINVAL; goto err___drm_gem_fb_end_cpu_access; } - import_attach = obj->import_attach; - if (!import_attach) + if (!drm_gem_is_imported(obj)) continue; - ret = dma_buf_begin_cpu_access(import_attach->dmabuf, dir); + ret = dma_buf_begin_cpu_access(obj->dma_buf, dir); if (ret) goto err___drm_gem_fb_end_cpu_access; } diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 5ab351409312..d99dee67353a 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -160,7 +160,7 @@ void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem) { struct drm_gem_object *obj = &shmem->base; - if (obj->import_attach) { + if (drm_gem_is_imported(obj)) { drm_prime_gem_destroy(obj, shmem->sgt); } else { dma_resv_lock(shmem->base.resv, NULL); @@ -255,7 +255,7 @@ int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem) dma_resv_assert_held(shmem->base.resv); - drm_WARN_ON(shmem->base.dev, shmem->base.import_attach); + drm_WARN_ON(shmem->base.dev, drm_gem_is_imported(&shmem->base)); ret = drm_gem_shmem_get_pages(shmem); @@ -286,7 +286,7 @@ int drm_gem_shmem_pin(struct drm_gem_shmem_object *shmem) struct drm_gem_object *obj = &shmem->base; int ret; - drm_WARN_ON(obj->dev, obj->import_attach); + drm_WARN_ON(obj->dev, drm_gem_is_imported(obj)); ret = dma_resv_lock_interruptible(shmem->base.resv, NULL); if (ret) @@ -309,7 +309,7 @@ void drm_gem_shmem_unpin(struct drm_gem_shmem_object *shmem) { struct drm_gem_object *obj = &shmem->base; - drm_WARN_ON(obj->dev, obj->import_attach); + drm_WARN_ON(obj->dev, drm_gem_is_imported(obj)); dma_resv_lock(shmem->base.resv, NULL); drm_gem_shmem_unpin_locked(shmem); @@ -338,11 +338,11 @@ int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct drm_gem_object *obj = &shmem->base; int ret = 0; - if (obj->import_attach) { - ret = dma_buf_vmap(obj->import_attach->dmabuf, map); + if (drm_gem_is_imported(obj)) { + ret = dma_buf_vmap(obj->dma_buf, map); if (!ret) { if (drm_WARN_ON(obj->dev, map->is_iomem)) { - dma_buf_vunmap(obj->import_attach->dmabuf, map); + dma_buf_vunmap(obj->dma_buf, map); return -EIO; } } @@ -378,7 +378,7 @@ int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, return 0; err_put_pages: - if (!obj->import_attach) + if (!drm_gem_is_imported(obj)) drm_gem_shmem_put_pages(shmem); err_zero_use: shmem->vmap_use_count = 0; @@ -404,8 +404,8 @@ void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, { struct drm_gem_object *obj = &shmem->base; - if (obj->import_attach) { - dma_buf_vunmap(obj->import_attach->dmabuf, map); + if (drm_gem_is_imported(obj)) { + dma_buf_vunmap(obj->dma_buf, map); } else { dma_resv_assert_held(shmem->base.resv); @@ -566,7 +566,7 @@ static void drm_gem_shmem_vm_open(struct vm_area_struct *vma) struct drm_gem_object *obj = vma->vm_private_data; struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - drm_WARN_ON(obj->dev, obj->import_attach); + drm_WARN_ON(obj->dev, drm_gem_is_imported(obj)); dma_resv_lock(shmem->base.resv, NULL); @@ -618,7 +618,7 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct struct drm_gem_object *obj = &shmem->base; int ret; - if (obj->import_attach) { + if (drm_gem_is_imported(obj)) { /* Reset both vm_ops and vm_private_data, so we don't end up with * vm_ops pointing to our implementation if the dma-buf backend * doesn't set those fields. @@ -663,7 +663,7 @@ EXPORT_SYMBOL_GPL(drm_gem_shmem_mmap); void drm_gem_shmem_print_info(const struct drm_gem_shmem_object *shmem, struct drm_printer *p, unsigned int indent) { - if (shmem->base.import_attach) + if (drm_gem_is_imported(&shmem->base)) return; drm_printf_indent(p, indent, "pages_use_count=%u\n", shmem->pages_use_count); @@ -690,7 +690,7 @@ struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_shmem_object *shmem) { struct drm_gem_object *obj = &shmem->base; - drm_WARN_ON(obj->dev, obj->import_attach); + drm_WARN_ON(obj->dev, drm_gem_is_imported(obj)); return drm_prime_pages_to_sg(obj->dev, shmem->pages, obj->size >> PAGE_SHIFT); } @@ -705,7 +705,7 @@ static struct sg_table *drm_gem_shmem_get_pages_sgt_locked(struct drm_gem_shmem_ if (shmem->sgt) return shmem->sgt; - drm_WARN_ON(obj->dev, obj->import_attach); + drm_WARN_ON(obj->dev, drm_gem_is_imported(obj)); ret = drm_gem_shmem_get_pages(shmem); if (ret) diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c index 34bca7567576..89e05a5bed1d 100644 --- a/drivers/gpu/drm/drm_mipi_dbi.c +++ b/drivers/gpu/drm/drm_mipi_dbi.c @@ -218,7 +218,7 @@ int mipi_dbi_buf_copy(void *dst, struct iosys_map *src, struct drm_framebuffer * switch (fb->format->format) { case DRM_FORMAT_RGB565: if (swap) - drm_fb_swab(&dst_map, NULL, src, fb, clip, !gem->import_attach, + drm_fb_swab(&dst_map, NULL, src, fb, clip, !drm_gem_is_imported(gem), fmtcnv_state); else drm_fb_memcpy(&dst_map, NULL, src, fb, clip); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 5e5c5f84daac..dfa595556320 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -162,13 +162,13 @@ of_mipi_dsi_device_add(struct mipi_dsi_host *host, struct device_node *node) u32 reg; if (of_alias_from_compatible(node, info.type, sizeof(info.type)) < 0) { - drm_err(host, "modalias failure on %pOF\n", node); + dev_err(host->dev, "modalias failure on %pOF\n", node); return ERR_PTR(-EINVAL); } ret = of_property_read_u32(node, "reg", ®); if (ret) { - drm_err(host, "device node %pOF has no valid reg property: %d\n", + dev_err(host->dev, "device node %pOF has no valid reg property: %d\n", node, ret); return ERR_PTR(-EINVAL); } @@ -206,18 +206,18 @@ mipi_dsi_device_register_full(struct mipi_dsi_host *host, int ret; if (!info) { - drm_err(host, "invalid mipi_dsi_device_info pointer\n"); + dev_err(host->dev, "invalid mipi_dsi_device_info pointer\n"); return ERR_PTR(-EINVAL); } if (info->channel > 3) { - drm_err(host, "invalid virtual channel: %u\n", info->channel); + dev_err(host->dev, "invalid virtual channel: %u\n", info->channel); return ERR_PTR(-EINVAL); } dsi = mipi_dsi_device_alloc(host); if (IS_ERR(dsi)) { - drm_err(host, "failed to allocate DSI device %ld\n", + dev_err(host->dev, "failed to allocate DSI device %ld\n", PTR_ERR(dsi)); return dsi; } @@ -228,7 +228,7 @@ mipi_dsi_device_register_full(struct mipi_dsi_host *host, ret = mipi_dsi_device_add(dsi); if (ret) { - drm_err(host, "failed to add DSI device %d\n", ret); + dev_err(host->dev, "failed to add DSI device %d\n", ret); kfree(dsi); return ERR_PTR(ret); } @@ -1266,25 +1266,6 @@ int mipi_dsi_dcs_set_page_address(struct mipi_dsi_device *dsi, u16 start, EXPORT_SYMBOL(mipi_dsi_dcs_set_page_address); /** - * mipi_dsi_dcs_set_tear_off() - turn off the display module's Tearing Effect - * output signal on the TE signal line - * @dsi: DSI peripheral device - * - * Return: 0 on success or a negative error code on failure - */ -int mipi_dsi_dcs_set_tear_off(struct mipi_dsi_device *dsi) -{ - ssize_t err; - - err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_TEAR_OFF, NULL, 0); - if (err < 0) - return err; - - return 0; -} -EXPORT_SYMBOL(mipi_dsi_dcs_set_tear_off); - -/** * mipi_dsi_dcs_set_tear_on() - turn on the display module's Tearing Effect * output signal on the TE signal line. * @dsi: DSI peripheral device @@ -1714,6 +1695,29 @@ void mipi_dsi_turn_on_peripheral_multi(struct mipi_dsi_multi_context *ctx) EXPORT_SYMBOL(mipi_dsi_turn_on_peripheral_multi); /** + * mipi_dsi_dcs_set_tear_off_multi() - turn off the display module's Tearing Effect + * output signal on the TE signal line + * @ctx: Context for multiple DSI transactions + */ +void mipi_dsi_dcs_set_tear_off_multi(struct mipi_dsi_multi_context *ctx) +{ + struct mipi_dsi_device *dsi = ctx->dsi; + struct device *dev = &dsi->dev; + ssize_t err; + + if (ctx->accum_err) + return; + + err = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_TEAR_OFF, NULL, 0); + if (err < 0) { + ctx->accum_err = err; + dev_err(dev, "Failed to set tear off: %d\n", + ctx->accum_err); + } +} +EXPORT_SYMBOL(mipi_dsi_dcs_set_tear_off_multi); + +/** * mipi_dsi_dcs_soft_reset_multi() - perform a software reset of the display module * @ctx: Context for multiple DSI transactions * diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 32a8781cfd67..bdb51c8f262e 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -453,13 +453,7 @@ struct dma_buf *drm_gem_prime_handle_to_dmabuf(struct drm_device *dev, } mutex_lock(&dev->object_name_lock); - /* re-export the original imported object */ - if (obj->import_attach) { - dmabuf = obj->import_attach->dmabuf; - get_dma_buf(dmabuf); - goto out_have_obj; - } - + /* re-export the original imported/exported object */ if (obj->dma_buf) { get_dma_buf(obj->dma_buf); dmabuf = obj->dma_buf; diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c index f139b49af4c9..edbeab88ff2b 100644 --- a/drivers/gpu/drm/drm_writeback.c +++ b/drivers/gpu/drm/drm_writeback.c @@ -213,7 +213,7 @@ static void delete_writeback_properties(struct drm_device *dev) } /** - * drm_writeback_connector_init_with_encoder - Initialize a writeback connector with + * __drm_writeback_connector_init - Initialize a writeback connector with * a custom encoder * * @dev: DRM device diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c index 3e83299113e3..718d45891fc7 100644 --- a/drivers/gpu/drm/gma500/cdv_device.c +++ b/drivers/gpu/drm/gma500/cdv_device.c @@ -215,7 +215,7 @@ static void cdv_errata(struct drm_device *dev) * Bonus Launch to work around the issue, by degrading * performance. */ - CDV_MSG_WRITE32(pci_domain_nr(pdev->bus), 3, 0x30, 0x08027108); + CDV_MSG_WRITE32(pci_domain_nr(pdev->bus), 3, 0x30, 0x08027108); } /** diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index 53990d27c39f..c85143792019 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -855,8 +855,7 @@ cdv_intel_dp_i2c_init(struct gma_connector *connector, memset(&intel_dp->adapter, '\0', sizeof (intel_dp->adapter)); intel_dp->adapter.owner = THIS_MODULE; - strncpy (intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1); - intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0'; + strscpy(intel_dp->adapter.name, name); intel_dp->adapter.algo_data = &intel_dp->algo; intel_dp->adapter.dev.parent = connector->base.kdev; diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 11953b03bb6a..66fcd90f0028 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -119,9 +119,6 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) u8 val = enable ? DP_PHY_REPEATER_MODE_TRANSPARENT : DP_PHY_REPEATER_MODE_NON_TRANSPARENT; - if (drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) != 1) - return false; - intel_dp->lttpr_common_caps[DP_PHY_REPEATER_MODE - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] = val; @@ -146,6 +143,7 @@ bool intel_dp_lttpr_transparent_mode_enabled(struct intel_dp *intel_dp) static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) { int lttpr_count; + int ret; if (!intel_dp_read_lttpr_common_caps(intel_dp, dpcd)) return 0; @@ -172,22 +170,8 @@ static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_ return lttpr_count; } - /* - * See DP Standard v2.0 3.6.6.1. about the explicit disabling of - * non-transparent mode and the disable->enable non-transparent mode - * sequence. - */ - intel_dp_set_lttpr_transparent_mode(intel_dp, true); - - /* - * In case of unsupported number of LTTPRs or failing to switch to - * non-transparent mode fall-back to transparent link training mode, - * still taking into account any LTTPR common lane- rate/count limits. - */ - if (lttpr_count < 0) - goto out_reset_lttpr_count; - - if (!intel_dp_set_lttpr_transparent_mode(intel_dp, false)) { + ret = drm_dp_lttpr_init(&intel_dp->aux, lttpr_count); + if (ret) { lt_dbg(intel_dp, DP_PHY_DPRX, "Switching to LTTPR non-transparent LT mode failed, fall-back to transparent mode\n"); @@ -196,6 +180,8 @@ static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_ goto out_reset_lttpr_count; } + intel_dp_set_lttpr_transparent_mode(intel_dp, false); + return lttpr_count; out_reset_lttpr_count: diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c index dd8433a38282..39c7de4cdcc1 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_color.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c @@ -96,7 +96,6 @@ static int mtk_disp_color_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct mtk_disp_color *priv; - struct resource *res; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -108,8 +107,7 @@ static int mtk_disp_color_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to get color clk\n"); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return dev_err_probe(dev, PTR_ERR(priv->regs), "failed to ioremap color\n"); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c index b17b11d93846..8afd15006df2 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c @@ -256,7 +256,6 @@ static int mtk_disp_gamma_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct mtk_disp_gamma *priv; - struct resource *res; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -268,8 +267,7 @@ static int mtk_disp_gamma_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to get gamma clk\n"); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return dev_err_probe(dev, PTR_ERR(priv->regs), "failed to ioremap gamma\n"); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_merge.c b/drivers/gpu/drm/mediatek/mtk_disp_merge.c index 563b1b248fbb..b174dda091d3 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_merge.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_merge.c @@ -306,7 +306,6 @@ static const struct component_ops mtk_disp_merge_component_ops = { static int mtk_disp_merge_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct mtk_disp_merge *priv; int ret; @@ -314,8 +313,7 @@ static int mtk_disp_merge_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return dev_err_probe(dev, PTR_ERR(priv->regs), "failed to ioremap merge\n"); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index df82cea4bb79..d0581c4e3c99 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -604,7 +604,6 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct mtk_disp_ovl *priv; - struct resource *res; int irq; int ret; @@ -621,8 +620,7 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to get ovl clk\n"); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return dev_err_probe(dev, PTR_ERR(priv->regs), "failed to ioremap ovl\n"); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c index bf47790e4d6b..c9d41d75e7f2 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c @@ -313,7 +313,6 @@ static int mtk_disp_rdma_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct mtk_disp_rdma *priv; - struct resource *res; int irq; int ret; @@ -330,8 +329,7 @@ static int mtk_disp_rdma_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to get rdma clk\n"); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return dev_err_probe(dev, PTR_ERR(priv->regs), "failed to ioremap rdma\n"); diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index b50dc9a013ac..0683c2b3ca5b 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1192,7 +1192,6 @@ static int mtk_dsi_probe(struct platform_device *pdev) { struct mtk_dsi *dsi; struct device *dev = &pdev->dev; - struct resource *regs; int irq_num; int ret; @@ -1217,8 +1216,7 @@ static int mtk_dsi_probe(struct platform_device *pdev) if (IS_ERR(dsi->hs_clk)) return dev_err_probe(dev, PTR_ERR(dsi->hs_clk), "Failed to get hs clock\n"); - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dsi->regs = devm_ioremap_resource(dev, regs); + dsi->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dsi->regs)) return dev_err_probe(dev, PTR_ERR(dsi->regs), "Failed to ioremap memory\n"); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index ac5e40c27617..d4ab098e1174 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1424,7 +1424,6 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, struct device_node *cec_np, *remote, *i2c_np; struct platform_device *cec_pdev; struct regmap *regmap; - struct resource *mem; int ret; ret = mtk_hdmi_get_all_clk(hdmi, np); @@ -1470,8 +1469,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, } hdmi->sys_regmap = regmap; - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdmi->regs = devm_ioremap_resource(dev, mem); + hdmi->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hdmi->regs)) { ret = PTR_ERR(hdmi->regs); goto put_device; diff --git a/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c b/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c index fc69ee38ce7d..7982788ae9df 100644 --- a/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_mdp_rdma.c @@ -291,7 +291,6 @@ static const struct component_ops mtk_mdp_rdma_component_ops = { static int mtk_mdp_rdma_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct mtk_mdp_rdma *priv; int ret = 0; @@ -299,8 +298,7 @@ static int mtk_mdp_rdma_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return dev_err_probe(dev, PTR_ERR(priv->regs), "failed to ioremap rdma\n"); diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 7ec833b6d829..974bc7c0ea76 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -170,6 +170,8 @@ config DRM_MSM_HDMI bool "Enable HDMI support in MSM DRM driver" depends on DRM_MSM default y + select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HDMI_STATE_HELPER help Compile in support for the HDMI output MSM DRM driver. It can be a primary or a secondary display on device. Note that this is used diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index edffb7737a97..53e2ff4406d8 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -880,6 +880,35 @@ static const struct adreno_info a6xx_gpus[] = { { 137, 1 }, ), }, { + .chip_ids = ADRENO_CHIP_IDS(0x06020300), + .family = ADRENO_6XX_GEN3, + .fw = { + [ADRENO_FW_SQE] = "a650_sqe.fw", + [ADRENO_FW_GMU] = "a623_gmu.bin", + }, + .gmem = SZ_512K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .init = a6xx_gpu_init, + .a6xx = &(const struct a6xx_info) { + .hwcg = a690_hwcg, + .protect = &a650_protect, + .gmu_cgc_mode = 0x00020200, + .prim_fifo_threshold = 0x00010000, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + }, + { /* sentinel */ }, + }, + }, + .address_space_size = SZ_16G, + }, { .chip_ids = ADRENO_CHIP_IDS( 0x06030001, 0x06030002 diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 699b0dd34b18..38c94915d4c9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -1169,49 +1169,50 @@ static void a6xx_gmu_shutdown(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 val; + int ret; /* - * The GMU may still be in slumber unless the GPU started so check and - * skip putting it back into slumber if so + * GMU firmware's internal power state gets messed up if we send "prepare_slumber" hfi when + * oob_gpu handshake wasn't done after the last wake up. So do a dummy handshake here when + * required */ - val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + if (adreno_gpu->base.needs_hw_init) { + if (a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET)) + goto force_off; - if (val != 0xf) { - int ret = a6xx_gmu_wait_for_idle(gmu); + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + } - /* If the GMU isn't responding assume it is hung */ - if (ret) { - a6xx_gmu_force_off(gmu); - return; - } + ret = a6xx_gmu_wait_for_idle(gmu); - a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); + /* If the GMU isn't responding assume it is hung */ + if (ret) + goto force_off; - /* tell the GMU we want to slumber */ - ret = a6xx_gmu_notify_slumber(gmu); - if (ret) { - a6xx_gmu_force_off(gmu); - return; - } + a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); - ret = gmu_poll_timeout(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, - !(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB), - 100, 10000); + /* tell the GMU we want to slumber */ + ret = a6xx_gmu_notify_slumber(gmu); + if (ret) + goto force_off; - /* - * Let the user know we failed to slumber but don't worry too - * much because we are powering down anyway - */ + ret = gmu_poll_timeout(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, + !(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB), + 100, 10000); - if (ret) - DRM_DEV_ERROR(gmu->dev, - "Unable to slumber GMU: status = 0%x/0%x\n", - gmu_read(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), - gmu_read(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2)); - } + /* + * Let the user know we failed to slumber but don't worry too + * much because we are powering down anyway + */ + + if (ret) + DRM_DEV_ERROR(gmu->dev, + "Unable to slumber GMU: status = 0%x/0%x\n", + gmu_read(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), + gmu_read(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2)); /* Turn off HFI */ a6xx_hfi_stop(gmu); @@ -1221,6 +1222,11 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) /* Tell RPMh to power off the GPU */ a6xx_rpmh_stop(gmu); + + return; + +force_off: + a6xx_gmu_force_off(gmu); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 0ae29a7c8a4d..1820c167fcee 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -616,6 +616,14 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu) gpu->ubwc_config.uavflagprd_inv = 2; } + if (adreno_is_a623(gpu)) { + gpu->ubwc_config.highest_bank_bit = 16; + gpu->ubwc_config.amsbc = 1; + gpu->ubwc_config.rgb565_predicator = 1; + gpu->ubwc_config.uavflagprd_inv = 2; + gpu->ubwc_config.macrotile_mode = 1; + } + if (adreno_is_a640_family(gpu)) gpu->ubwc_config.amsbc = 1; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 0fcae53c0b14..341a72a67401 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1214,12 +1214,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); a6xx_state->gmu_registers = state_kcalloc(a6xx_state, - 3, sizeof(*a6xx_state->gmu_registers)); + 4, sizeof(*a6xx_state->gmu_registers)); if (!a6xx_state->gmu_registers) return; - a6xx_state->nr_gmu_registers = 3; + a6xx_state->nr_gmu_registers = 4; /* Get the CX GMU registers from AHB */ _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0], @@ -1227,6 +1227,13 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1], &a6xx_state->gmu_registers[1], true); + if (adreno_is_a621(adreno_gpu) || adreno_is_a623(adreno_gpu)) + _a6xx_get_gmu_registers(gpu, a6xx_state, &a621_gpucc_reg, + &a6xx_state->gmu_registers[2], false); + else + _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gpucc_reg, + &a6xx_state->gmu_registers[2], false); + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) return; @@ -1234,7 +1241,7 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2], - &a6xx_state->gmu_registers[2], false); + &a6xx_state->gmu_registers[3], false); } static struct msm_gpu_state_bo *a6xx_snapshot_gmu_bo( @@ -1507,6 +1514,8 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu, /* Restore the size in the hardware */ gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size); + + a6xx_state->nr_indexed_regs = count; } static void a7xx_get_indexed_registers(struct msm_gpu *gpu, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index dd4c28a8d923..e545106c70be 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -363,6 +363,9 @@ static const u32 a6xx_gmu_cx_registers[] = { 0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201, /* GMU AO */ 0x9300, 0x9316, 0x9400, 0x9400, +}; + +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, @@ -373,6 +376,17 @@ static const u32 a6xx_gmu_cx_registers[] = { 0xbc00, 0xbc16, 0xbc20, 0xbc27, }; +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, +}; + static const u32 a6xx_gmu_cx_rscc_registers[] = { /* GPU RSCC */ 0x008c, 0x008c, 0x0101, 0x0102, 0x0340, 0x0342, 0x0344, 0x0347, @@ -386,6 +400,9 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = { REGS(a6xx_gmu_gx_registers, 0, 0), }; +static const struct a6xx_registers a6xx_gpucc_reg = REGS(a6xx_gmu_gpucc_registers, 0, 0); +static const struct a6xx_registers a621_gpucc_reg = REGS(a621_gmu_gpucc_registers, 0, 0); + static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu); static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 1238f3265978..7156cda07b03 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -883,6 +883,16 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, drm_printf(p, " - dir=%s\n", info->flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ"); drm_printf(p, " - type=%s\n", info->type); drm_printf(p, " - source=%s\n", info->block); + + /* Information extracted from what we think are the current + * pgtables. Hopefully the TTBR0 matches what we've extracted + * from the SMMU registers in smmu_info! + */ + drm_puts(p, "pgtable-fault-info:\n"); + drm_printf(p, " - ttbr0: %.16llx\n", (u64)info->pgtbl_ttbr0); + drm_printf(p, " - asid: %d\n", info->asid); + drm_printf(p, " - ptes: %.16llx %.16llx %.16llx %.16llx\n", + info->ptes[0], info->ptes[1], info->ptes[2], info->ptes[3]); } drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index dcf454629ce0..92caba3584da 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -442,6 +442,11 @@ static inline int adreno_is_a621(const struct adreno_gpu *gpu) return gpu->info->chip_ids[0] == 0x06020100; } +static inline int adreno_is_a623(const struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x06020300; +} + static inline int adreno_is_a630(const struct adreno_gpu *gpu) { return adreno_is_revn(gpu, 630); diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h index bcb39807fe61..6ac97c378056 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h @@ -343,8 +343,8 @@ static const struct dpu_wb_cfg sm8650_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -452,6 +452,7 @@ const struct dpu_mdss_cfg dpu_sm8650_cfg = { .mdss_ver = &sm8650_mdss_ver, .caps = &sm8650_dpu_caps, .mdp = &sm8650_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8650_ctl), .ctl = sm8650_ctl, .sspp_count = ARRAY_SIZE(sm8650_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h index ab3dfb0b374e..1f32807bb5e5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h @@ -190,6 +190,7 @@ const struct dpu_mdss_cfg dpu_msm8937_cfg = { .mdss_ver = &msm8937_mdss_ver, .caps = &msm8937_dpu_caps, .mdp = msm8937_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8937_ctl), .ctl = msm8937_ctl, .sspp_count = ARRAY_SIZE(msm8937_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h index 6bdaecca6761..42131959ff22 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h @@ -167,6 +167,7 @@ const struct dpu_mdss_cfg dpu_msm8917_cfg = { .mdss_ver = &msm8917_mdss_ver, .caps = &msm8917_dpu_caps, .mdp = msm8917_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8917_ctl), .ctl = msm8917_ctl, .sspp_count = ARRAY_SIZE(msm8917_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h index 14f36ea6ad0e..2b4723a5c676 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h @@ -198,6 +198,7 @@ const struct dpu_mdss_cfg dpu_msm8953_cfg = { .mdss_ver = &msm8953_mdss_ver, .caps = &msm8953_dpu_caps, .mdp = msm8953_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8953_ctl), .ctl = msm8953_ctl, .sspp_count = ARRAY_SIZE(msm8953_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h index 491f6f5827d1..5cf19de71f06 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h @@ -316,6 +316,7 @@ const struct dpu_mdss_cfg dpu_msm8996_cfg = { .mdss_ver = &msm8996_mdss_ver, .caps = &msm8996_dpu_caps, .mdp = msm8996_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8996_ctl), .ctl = msm8996_ctl, .sspp_count = ARRAY_SIZE(msm8996_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 64c94e919a69..746474679ef5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -302,6 +302,7 @@ const struct dpu_mdss_cfg dpu_msm8998_cfg = { .mdss_ver = &msm8998_mdss_ver, .caps = &msm8998_dpu_caps, .mdp = &msm8998_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8998_ctl), .ctl = msm8998_ctl, .sspp_count = ARRAY_SIZE(msm8998_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h index 424815e7fb7d..4f2f68b07f20 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h @@ -269,6 +269,7 @@ const struct dpu_mdss_cfg dpu_sdm660_cfg = { .mdss_ver = &sdm660_mdss_ver, .caps = &sdm660_dpu_caps, .mdp = &sdm660_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm660_ctl), .ctl = sdm660_ctl, .sspp_count = ARRAY_SIZE(sdm660_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h index df01227fc364..c70bef025ac4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h @@ -205,6 +205,7 @@ const struct dpu_mdss_cfg dpu_sdm630_cfg = { .mdss_ver = &sdm630_mdss_ver, .caps = &sdm630_dpu_caps, .mdp = &sdm630_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm630_ctl), .ctl = sdm630_ctl, .sspp_count = ARRAY_SIZE(sdm630_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h index 72bd4f7e9e50..ab7b4822ca63 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h @@ -319,6 +319,7 @@ const struct dpu_mdss_cfg dpu_sdm845_cfg = { .mdss_ver = &sdm845_mdss_ver, .caps = &sdm845_dpu_caps, .mdp = &sdm845_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm845_ctl), .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm845_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h index daef07924886..c2fde980fb52 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h @@ -132,6 +132,7 @@ const struct dpu_mdss_cfg dpu_sdm670_cfg = { .mdss_ver = &sdm670_mdss_ver, .caps = &sdm845_dpu_caps, .mdp = &sdm670_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm845_ctl), .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm670_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 36cc9dbc00b5..979527d98fbc 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -298,8 +298,8 @@ static const struct dpu_wb_cfg sm8150_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -388,6 +388,7 @@ const struct dpu_mdss_cfg dpu_sm8150_cfg = { .mdss_ver = &sm8150_mdss_ver, .caps = &sm8150_dpu_caps, .mdp = &sm8150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8150_ctl), .ctl = sm8150_ctl, .sspp_count = ARRAY_SIZE(sm8150_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index e8eacdb47967..d76b8992a6c1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -305,8 +305,8 @@ static const struct dpu_wb_cfg sc8180x_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -414,6 +414,7 @@ const struct dpu_mdss_cfg dpu_sc8180x_cfg = { .mdss_ver = &sc8180x_mdss_ver, .caps = &sc8180x_dpu_caps, .mdp = &sc8180x_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc8180x_ctl), .ctl = sc8180x_ctl, .sspp_count = ARRAY_SIZE(sc8180x_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h index 2fe674d1e059..83db11339b29 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h @@ -261,8 +261,8 @@ static const struct dpu_wb_cfg sm7150_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -309,6 +309,7 @@ const struct dpu_mdss_cfg dpu_sm7150_cfg = { .mdss_ver = &sm7150_mdss_ver, .caps = &sm7150_dpu_caps, .mdp = &sm7150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm7150_ctl), .ctl = sm7150_ctl, .sspp_count = ARRAY_SIZE(sm7150_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h index d761ed705bac..da11830d4407 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h @@ -27,6 +27,7 @@ static const struct dpu_mdp_cfg sm6150_mdp = { [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, }, }; @@ -162,6 +163,21 @@ static const struct dpu_pingpong_cfg sm6150_pp[] = { }, }; +static const struct dpu_wb_cfg sm6150_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SM8250_MASK, + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), + .clk_ctrl = DPU_CLK_CTRL_WB2, + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 2160, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + static const struct dpu_intf_cfg sm6150_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -232,6 +248,7 @@ const struct dpu_mdss_cfg dpu_sm6150_cfg = { .mdss_ver = &sm6150_mdss_ver, .caps = &sm6150_dpu_caps, .mdp = &sm6150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6150_ctl), .ctl = sm6150_ctl, .sspp_count = ARRAY_SIZE(sm6150_sspp), @@ -242,6 +259,8 @@ const struct dpu_mdss_cfg dpu_sm6150_cfg = { .dspp = sm6150_dspp, .pingpong_count = ARRAY_SIZE(sm6150_pp), .pingpong = sm6150_pp, + .wb_count = ARRAY_SIZE(sm6150_wb), + .wb = sm6150_wb, .intf_count = ARRAY_SIZE(sm6150_intf), .intf = sm6150_intf, .vbif_count = ARRAY_SIZE(sdm845_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h index 76f60a2df7a8..d3d3a34d0b45 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h @@ -145,8 +145,8 @@ static const struct dpu_wb_cfg sm6125_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -216,6 +216,7 @@ const struct dpu_mdss_cfg dpu_sm6125_cfg = { .mdss_ver = &sm6125_mdss_ver, .caps = &sm6125_dpu_caps, .mdp = &sm6125_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6125_ctl), .ctl = sm6125_ctl, .sspp_count = ARRAY_SIZE(sm6125_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index e8916ae826a6..47e01c3c242f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -386,7 +386,7 @@ const struct dpu_mdss_cfg dpu_sm8250_cfg = { .mdss_ver = &sm8250_mdss_ver, .caps = &sm8250_dpu_caps, .mdp = &sm8250_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8250_ctl), .ctl = sm8250_ctl, .sspp_count = ARRAY_SIZE(sm8250_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 7382ebb6e5b2..040c94c0bb66 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -157,8 +157,8 @@ static const struct dpu_wb_cfg sc7180_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -204,6 +204,7 @@ const struct dpu_mdss_cfg dpu_sc7180_cfg = { .mdss_ver = &sc7180_mdss_ver, .caps = &sc7180_dpu_caps, .mdp = &sc7180_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc7180_ctl), .ctl = sc7180_ctl, .sspp_count = ARRAY_SIZE(sc7180_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h index 0502cee2f116..397278ba999b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h @@ -151,8 +151,8 @@ static const struct dpu_wb_cfg sm6350_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -222,6 +222,7 @@ const struct dpu_mdss_cfg dpu_sm6350_cfg = { .mdss_ver = &sm6350_mdss_ver, .caps = &sm6350_dpu_caps, .mdp = &sm6350_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6350_ctl), .ctl = sm6350_ctl, .sspp_count = ARRAY_SIZE(sm6350_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index f7c08e89c882..0c860e804cab 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -305,8 +305,8 @@ static const struct dpu_wb_cfg sm8350_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -396,6 +396,7 @@ const struct dpu_mdss_cfg dpu_sm8350_cfg = { .mdss_ver = &sm8350_mdss_ver, .caps = &sm8350_dpu_caps, .mdp = &sm8350_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8350_ctl), .ctl = sm8350_ctl, .sspp_count = ARRAY_SIZE(sm8350_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 2f153e0b5c6a..e9625c48c567 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -248,7 +248,7 @@ const struct dpu_mdss_cfg dpu_sc7280_cfg = { .mdss_ver = &sc7280_mdss_ver, .caps = &sc7280_dpu_caps, .mdp = &sc7280_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc7280_ctl), .ctl = sc7280_ctl, .sspp_count = ARRAY_SIZE(sc7280_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 0d143e390eca..fcee1c3665f8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -435,6 +435,7 @@ const struct dpu_mdss_cfg dpu_sc8280xp_cfg = { .mdss_ver = &sc8280xp_mdss_ver, .caps = &sc8280xp_dpu_caps, .mdp = &sc8280xp_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc8280xp_ctl), .ctl = sc8280xp_ctl, .sspp_count = ARRAY_SIZE(sc8280xp_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 08742472f9cc..19b2ee8bbd5f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -321,8 +321,8 @@ static const struct dpu_wb_cfg sm8450_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -412,6 +412,7 @@ const struct dpu_mdss_cfg dpu_sm8450_cfg = { .mdss_ver = &sm8450_mdss_ver, .caps = &sm8450_dpu_caps, .mdp = &sm8450_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8450_ctl), .ctl = sm8450_ctl, .sspp_count = ARRAY_SIZE(sm8450_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h index 76ec72a32378..4d96ce71746f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h @@ -458,7 +458,7 @@ const struct dpu_mdss_cfg dpu_sa8775p_cfg = { .mdss_ver = &sa8775p_mdss_ver, .caps = &sa8775p_dpu_caps, .mdp = &sa8775p_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sa8775p_ctl), .ctl = sa8775p_ctl, .sspp_count = ARRAY_SIZE(sa8775p_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 4d3787fceb72..24f988465bf6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -317,8 +317,8 @@ static const struct dpu_wb_cfg sm8550_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -407,6 +407,7 @@ const struct dpu_mdss_cfg dpu_sm8550_cfg = { .mdss_ver = &sm8550_mdss_ver, .caps = &sm8550_dpu_caps, .mdp = &sm8550_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8550_ctl), .ctl = sm8550_ctl, .sspp_count = ARRAY_SIZE(sm8550_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index 6b112e3d17da..6417baa84f82 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -317,8 +317,8 @@ static const struct dpu_wb_cfg x1e80100_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -453,6 +453,7 @@ const struct dpu_mdss_cfg dpu_x1e80100_cfg = { .mdss_ver = &x1e80100_mdss_ver, .caps = &x1e80100_dpu_caps, .mdp = &x1e80100_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(x1e80100_ctl), .ctl = x1e80100_ctl, .sspp_count = ARRAY_SIZE(x1e80100_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index 6f0a37f954fe..0fb5789c60d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -118,26 +118,38 @@ static void _dpu_core_perf_calc_crtc(const struct dpu_core_perf *core_perf, return; } - memset(perf, 0, sizeof(struct dpu_core_perf_params)); - - if (core_perf->perf_tune.mode == DPU_PERF_MODE_MINIMUM) { - perf->bw_ctl = 0; - perf->max_per_pipe_ib = 0; - perf->core_clk_rate = 0; - } else if (core_perf->perf_tune.mode == DPU_PERF_MODE_FIXED) { - perf->bw_ctl = core_perf->fix_core_ab_vote; - perf->max_per_pipe_ib = core_perf->fix_core_ib_vote; - perf->core_clk_rate = core_perf->fix_core_clk_rate; - } else { - perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc); - perf->max_per_pipe_ib = perf_cfg->min_dram_ib; - perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state); - } - + perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc); + perf->max_per_pipe_ib = perf_cfg->min_dram_ib; + perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state); DRM_DEBUG_ATOMIC( - "crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu\n", + "crtc=%d clk_rate=%llu core_ib=%u core_ab=%u\n", crtc->base.id, perf->core_clk_rate, - perf->max_per_pipe_ib, perf->bw_ctl); + perf->max_per_pipe_ib, + (u32)DIV_ROUND_UP_ULL(perf->bw_ctl, 1000)); +} + +static void dpu_core_perf_aggregate(struct drm_device *ddev, + enum dpu_crtc_client_type curr_client_type, + struct dpu_core_perf_params *perf) +{ + struct dpu_crtc_state *dpu_cstate; + struct drm_crtc *tmp_crtc; + + drm_for_each_crtc(tmp_crtc, ddev) { + if (tmp_crtc->enabled && + curr_client_type == dpu_crtc_get_client_type(tmp_crtc)) { + dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); + + perf->max_per_pipe_ib = max(perf->max_per_pipe_ib, + dpu_cstate->new_perf.max_per_pipe_ib); + + perf->bw_ctl += dpu_cstate->new_perf.bw_ctl; + + DRM_DEBUG_ATOMIC("crtc=%d bw=%llu\n", + tmp_crtc->base.id, + dpu_cstate->new_perf.bw_ctl); + } + } } /** @@ -150,11 +162,9 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, struct drm_crtc_state *state) { u32 bw, threshold; - u64 bw_sum_of_intfs = 0; - enum dpu_crtc_client_type curr_client_type; struct dpu_crtc_state *dpu_cstate; - struct drm_crtc *tmp_crtc; struct dpu_kms *kms; + struct dpu_core_perf_params perf = { 0 }; if (!crtc || !state) { DPU_ERROR("invalid crtc\n"); @@ -172,80 +182,56 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, /* obtain new values */ _dpu_core_perf_calc_crtc(&kms->perf, crtc, state, &dpu_cstate->new_perf); - bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl; - curr_client_type = dpu_crtc_get_client_type(crtc); - - drm_for_each_crtc(tmp_crtc, crtc->dev) { - if (tmp_crtc->enabled && - dpu_crtc_get_client_type(tmp_crtc) == curr_client_type && - tmp_crtc != crtc) { - struct dpu_crtc_state *tmp_cstate = - to_dpu_crtc_state(tmp_crtc->state); - - DRM_DEBUG_ATOMIC("crtc:%d bw:%llu ctrl:%d\n", - tmp_crtc->base.id, tmp_cstate->new_perf.bw_ctl, - tmp_cstate->bw_control); + dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf); - bw_sum_of_intfs += tmp_cstate->new_perf.bw_ctl; - } - - /* convert bandwidth to kb */ - bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000); - DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw); + /* convert bandwidth to kb */ + bw = DIV_ROUND_UP_ULL(perf.bw_ctl, 1000); + DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw); - threshold = kms->perf.perf_cfg->max_bw_high; + threshold = kms->perf.perf_cfg->max_bw_high; - DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold); + DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold); - if (!threshold) { - DPU_ERROR("no bandwidth limits specified\n"); - return -E2BIG; - } else if (bw > threshold) { - DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, - threshold); - return -E2BIG; - } + if (!threshold) { + DPU_ERROR("no bandwidth limits specified\n"); + return -E2BIG; + } else if (bw > threshold) { + DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, + threshold); + return -E2BIG; } return 0; } static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms, - struct drm_crtc *crtc) + struct drm_crtc *crtc) { struct dpu_core_perf_params perf = { 0 }; - enum dpu_crtc_client_type curr_client_type - = dpu_crtc_get_client_type(crtc); - struct drm_crtc *tmp_crtc; - struct dpu_crtc_state *dpu_cstate; int i, ret = 0; - u64 avg_bw; + u32 avg_bw; + u32 peak_bw; if (!kms->num_paths) return 0; - drm_for_each_crtc(tmp_crtc, crtc->dev) { - if (tmp_crtc->enabled && - curr_client_type == - dpu_crtc_get_client_type(tmp_crtc)) { - dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); - - perf.max_per_pipe_ib = max(perf.max_per_pipe_ib, - dpu_cstate->new_perf.max_per_pipe_ib); - - perf.bw_ctl += dpu_cstate->new_perf.bw_ctl; + if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) { + avg_bw = 0; + peak_bw = 0; + } else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) { + avg_bw = kms->perf.fix_core_ab_vote; + peak_bw = kms->perf.fix_core_ib_vote; + } else { + dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf); - DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n", - tmp_crtc->base.id, - dpu_cstate->new_perf.bw_ctl, kms->num_paths); - } + avg_bw = div_u64(perf.bw_ctl, 1000); /*Bps_to_icc*/ + peak_bw = perf.max_per_pipe_ib; } - avg_bw = perf.bw_ctl; - do_div(avg_bw, (kms->num_paths * 1000)); /*Bps_to_icc*/ + avg_bw /= kms->num_paths; for (i = 0; i < kms->num_paths; i++) - icc_set_bw(kms->path[i], avg_bw, perf.max_per_pipe_ib); + icc_set_bw(kms->path[i], avg_bw, peak_bw); return ret; } @@ -476,9 +462,9 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) &perf->core_clk_rate); debugfs_create_u32("enable_bw_release", 0600, entry, (u32 *)&perf->enable_bw_release); - debugfs_create_u32("threshold_low", 0400, entry, + debugfs_create_u32("low_core_ab", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_low); - debugfs_create_u32("threshold_high", 0400, entry, + debugfs_create_u32("max_core_ab", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_high); debugfs_create_u32("min_core_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_core_ib); @@ -490,9 +476,9 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) (u32 *)perf, &dpu_core_perf_mode_fops); debugfs_create_u64("fix_core_clk_rate", 0600, entry, &perf->fix_core_clk_rate); - debugfs_create_u64("fix_core_ib_vote", 0600, entry, + debugfs_create_u32("fix_core_ib_vote", 0600, entry, &perf->fix_core_ib_vote); - debugfs_create_u64("fix_core_ab_vote", 0600, entry, + debugfs_create_u32("fix_core_ab_vote", 0600, entry, &perf->fix_core_ab_vote); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h index 451bf8021114..d2f21d34e501 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -19,7 +19,7 @@ * @core_clk_rate: core clock rate request */ struct dpu_core_perf_params { - u64 max_per_pipe_ib; + u32 max_per_pipe_ib; u64 bw_ctl; u64 core_clk_rate; }; @@ -40,8 +40,8 @@ struct dpu_core_perf_tune { * @perf_tune: debug control for performance tuning * @enable_bw_release: debug control for bandwidth release * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2 - * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2 - * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2 + * @fix_core_ib_vote: fixed core ib vote in KBps used in mode 2 + * @fix_core_ab_vote: fixed core ab vote in KBps used in mode 2 */ struct dpu_core_perf { const struct dpu_perf_cfg *perf_cfg; @@ -50,8 +50,8 @@ struct dpu_core_perf { struct dpu_core_perf_tune perf_tune; u32 enable_bw_release; u64 fix_core_clk_rate; - u64 fix_core_ib_vote; - u64 fix_core_ab_vote; + u32 fix_core_ib_vote; + u32 fix_core_ab_vote; }; int dpu_core_perf_crtc_check(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index e5dcd41a361f..0714936d8835 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -953,6 +953,45 @@ static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc) return rc; } +static int dpu_crtc_kickoff_clone_mode(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + struct drm_encoder *rt_encoder = NULL, *wb_encoder = NULL; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + + /* Find encoder for real time display */ + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) { + if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL) + wb_encoder = encoder; + else + rt_encoder = encoder; + } + + if (!rt_encoder || !wb_encoder) { + DRM_DEBUG_ATOMIC("real time or wb encoder not found\n"); + return -EINVAL; + } + + dpu_encoder_prepare_for_kickoff(wb_encoder); + dpu_encoder_prepare_for_kickoff(rt_encoder); + + dpu_vbif_clear_errors(dpu_kms); + + /* + * Kickoff real time encoder last as it's the encoder that + * will do the flush + */ + dpu_encoder_kickoff(wb_encoder); + dpu_encoder_kickoff(rt_encoder); + + /* Don't start frame done timers until the kickoffs have finished */ + dpu_encoder_start_frame_done_timer(wb_encoder); + dpu_encoder_start_frame_done_timer(rt_encoder); + + return 0; +} + /** * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc * @crtc: Pointer to drm crtc object @@ -981,13 +1020,27 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) goto end; } } - /* - * Encoder will flush/start now, unless it has a tx pending. If so, it - * may delay and flush at an irq event (e.g. ppdone) - */ - drm_for_each_encoder_mask(encoder, crtc->dev, - crtc->state->encoder_mask) - dpu_encoder_prepare_for_kickoff(encoder); + + if (drm_crtc_in_clone_mode(crtc->state)) { + if (dpu_crtc_kickoff_clone_mode(crtc)) + goto end; + } else { + /* + * Encoder will flush/start now, unless it has a tx pending. + * If so, it may delay and flush at an irq event (e.g. ppdone) + */ + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) + dpu_encoder_prepare_for_kickoff(encoder); + + dpu_vbif_clear_errors(dpu_kms); + + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) { + dpu_encoder_kickoff(encoder); + dpu_encoder_start_frame_done_timer(encoder); + } + } if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) { /* acquire bandwidth and other resources */ @@ -997,11 +1050,6 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) dpu_crtc->play_count++; - dpu_vbif_clear_errors(dpu_kms); - - drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) - dpu_encoder_kickoff(encoder); - reinit_completion(&dpu_crtc->frame_done_comp); end: @@ -1230,6 +1278,151 @@ done: return ret; } +#define MAX_CHANNELS_PER_CRTC 2 +#define MAX_HDISPLAY_SPLIT 1080 + +static struct msm_display_topology dpu_crtc_get_topology( + struct drm_crtc *crtc, + struct dpu_kms *dpu_kms, + struct drm_crtc_state *crtc_state) +{ + struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct msm_display_topology topology = {0}; + struct drm_encoder *drm_enc; + + drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) + dpu_encoder_update_topology(drm_enc, &topology, crtc_state->state, + &crtc_state->adjusted_mode); + + topology.cwb_enabled = drm_crtc_in_clone_mode(crtc_state); + + /* + * Datapath topology selection + * + * Dual display + * 2 LM, 2 INTF ( Split display using 2 interfaces) + * + * 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 + * + * Add dspps to the reservation requirements if ctm is requested + * + * Only hardcode num_lm to 2 for cases where num_intf == 2 and CWB is not + * enabled. This is because in cases where CWB is enabled, num_intf will + * count both the WB and real-time phys encoders. + * + * For non-DSC CWB usecases, have the num_lm be decided by the + * (mode->hdisplay > MAX_HDISPLAY_SPLIT) check. + */ + + if (topology.num_intf == 2 && !topology.cwb_enabled) + topology.num_lm = 2; + else if (topology.num_dsc == 2) + topology.num_lm = 2; + else if (dpu_kms->catalog->caps->has_3d_merge) + topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; + else + topology.num_lm = 1; + + if (crtc_state->ctm) + topology.num_dspp = topology.num_lm; + + return topology; +} + +static int dpu_crtc_assign_resources(struct drm_crtc *crtc, + struct drm_crtc_state *crtc_state) +{ + struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_CRTC]; + struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_CRTC]; + struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_CRTC]; + int i, num_lm, num_ctl, num_dspp; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + struct dpu_global_state *global_state; + struct dpu_crtc_state *cstate; + struct msm_display_topology topology; + int ret; + + /* + * Release and Allocate resources on every modeset + */ + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + + dpu_rm_release(global_state, crtc); + + if (!crtc_state->enable) + return 0; + + topology = dpu_crtc_get_topology(crtc, dpu_kms, crtc_state); + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + crtc_state->crtc, &topology); + if (ret) + return ret; + + cstate = to_dpu_crtc_state(crtc_state); + + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_CTL, hw_ctl, + ARRAY_SIZE(hw_ctl)); + num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_LM, hw_lm, + ARRAY_SIZE(hw_lm)); + num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_DSPP, hw_dspp, + ARRAY_SIZE(hw_dspp)); + + for (i = 0; i < num_lm; i++) { + int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); + + cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); + cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); + if (i < num_dspp) + cstate->mixers[i].hw_dspp = to_dpu_hw_dspp(hw_dspp[i]); + } + + cstate->num_mixers = num_lm; + + return 0; +} + +/** + * dpu_crtc_check_mode_changed: check if full modeset is required + * @old_crtc_state: Previous CRTC state + * @new_crtc_state: Corresponding CRTC state to be checked + * + * Check if the changes in the object properties demand full mode set. + */ +int dpu_crtc_check_mode_changed(struct drm_crtc_state *old_crtc_state, + struct drm_crtc_state *new_crtc_state) +{ + struct drm_encoder *drm_enc; + struct drm_crtc *crtc = new_crtc_state->crtc; + bool clone_mode_enabled = drm_crtc_in_clone_mode(old_crtc_state); + bool clone_mode_requested = drm_crtc_in_clone_mode(new_crtc_state); + + DRM_DEBUG_ATOMIC("%d\n", crtc->base.id); + + /* there might be cases where encoder needs a modeset too */ + drm_for_each_encoder_mask(drm_enc, crtc->dev, new_crtc_state->encoder_mask) { + if (dpu_encoder_needs_modeset(drm_enc, new_crtc_state->state)) + new_crtc_state->mode_changed = true; + } + + if ((clone_mode_requested && !clone_mode_enabled) || + (!clone_mode_requested && clone_mode_enabled)) + new_crtc_state->mode_changed = true; + + return 0; +} + static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -1245,6 +1438,13 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state); + /* don't reallocate resources if only ACTIVE has beeen changed */ + if (crtc_state->mode_changed || crtc_state->connectors_changed) { + rc = dpu_crtc_assign_resources(crtc, crtc_state); + if (rc < 0) + return rc; + } + if (dpu_use_virtual_planes && (crtc_state->planes_changed || crtc_state->zpos_changed)) { rc = dpu_crtc_reassign_planes(crtc, crtc_state); @@ -1262,10 +1462,6 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, DRM_DEBUG_ATOMIC("%s: check\n", dpu_crtc->name); - /* force a full mode set if active state changed */ - if (crtc_state->active_changed) - crtc_state->mode_changed = true; - if (cstate->num_mixers) { rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state); if (rc) @@ -1484,8 +1680,9 @@ static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v) seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc)); seq_printf(s, "core_clk_rate: %llu\n", dpu_crtc->cur_perf.core_clk_rate); - seq_printf(s, "bw_ctl: %llu\n", dpu_crtc->cur_perf.bw_ctl); - seq_printf(s, "max_per_pipe_ib: %llu\n", + seq_printf(s, "bw_ctl: %uk\n", + (u32)DIV_ROUND_UP_ULL(dpu_crtc->cur_perf.bw_ctl, 1000)); + seq_printf(s, "max_per_pipe_ib: %u\n", dpu_crtc->cur_perf.max_per_pipe_ib); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index 0b148f3ce0d7..94392b9b9245 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -239,6 +239,9 @@ static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc) return crtc ? atomic_read(&to_dpu_crtc(crtc)->frame_pending) : -EINVAL; } +int dpu_crtc_check_mode_changed(struct drm_crtc_state *old_crtc_state, + struct drm_crtc_state *new_crtc_state); + int dpu_crtc_vblank(struct drm_crtc *crtc, bool en); void dpu_crtc_vblank_callback(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 48e6e8d74c85..284e69bb47c1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -24,6 +24,7 @@ #include "dpu_hw_catalog.h" #include "dpu_hw_intf.h" #include "dpu_hw_ctl.h" +#include "dpu_hw_cwb.h" #include "dpu_hw_dspp.h" #include "dpu_hw_dsc.h" #include "dpu_hw_merge3d.h" @@ -58,8 +59,6 @@ #define IDLE_SHORT_TIMEOUT 1 -#define MAX_HDISPLAY_SPLIT 1080 - /* timeout in frames waiting for frame done */ #define DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES 5 @@ -135,8 +134,12 @@ enum dpu_enc_rc_states { * @cur_slave: As above but for the slave encoder. * @hw_pp: Handle to the pingpong blocks used for the display. No. * pingpong blocks can be different than num_phys_encs. + * @hw_cwb: Handle to the CWB muxes used for concurrent writeback + * display. Number of CWB muxes can be different than + * num_phys_encs. * @hw_dsc: Handle to the DSC blocks used for the display. * @dsc_mask: Bitmask of used DSC blocks. + * @cwb_mask: Bitmask of used CWB muxes * @intfs_swapped: Whether or not the phys_enc interfaces have been swapped * for partial update right-only cases, such as pingpong * split where virtual pingpong does not generate IRQs @@ -179,9 +182,11 @@ 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_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; unsigned int dsc_mask; + unsigned int cwb_mask; bool intfs_swapped; @@ -622,9 +627,9 @@ bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc) if (dpu_enc->phys_encs[i]) intf_count++; - /* See dpu_encoder_get_topology, we only support 2:2:1 topology */ - if (dpu_enc->dsc) - num_dsc = 2; + for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + if (dpu_enc->hw_dsc[i]) + num_dsc++; return (num_dsc > 0) && (num_dsc > intf_count); } @@ -647,130 +652,51 @@ struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc) return NULL; } -static struct msm_display_topology dpu_encoder_get_topology( - struct dpu_encoder_virt *dpu_enc, - struct dpu_kms *dpu_kms, - struct drm_display_mode *mode, - struct drm_crtc_state *crtc_state, - struct drm_dsc_config *dsc) +void dpu_encoder_update_topology(struct drm_encoder *drm_enc, + struct msm_display_topology *topology, + struct drm_atomic_state *state, + const struct drm_display_mode *adj_mode) { - struct msm_display_topology topology = {0}; - int i, intf_count = 0; + 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; + struct drm_dsc_config *dsc; + + int i; for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++) if (dpu_enc->phys_encs[i]) - intf_count++; + topology->num_intf++; - /* Datapath topology selection - * - * Dual display - * 2 LM, 2 INTF ( Split display using 2 interfaces) - * - * Single display - * 1 LM, 1 INTF - * 2 LM, 1 INTF (stream merge to support high resolution interfaces) - * - * Add dspps to the reservation requirements if ctm is requested - */ - if (intf_count == 2) - topology.num_lm = 2; - else if (!dpu_kms->catalog->caps->has_3d_merge) - topology.num_lm = 1; - else - topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; - - if (crtc_state->ctm) - topology.num_dspp = topology.num_lm; - - topology.num_intf = intf_count; + dsc = dpu_encoder_get_dsc_config(drm_enc); + /* We only support 2 DSC mode (with 2 LM and 1 INTF) */ if (dsc) { /* - * In case of Display Stream Compression (DSC), we would use - * 2 DSC encoders, 2 layer mixers and 1 interface - * this is power optimal and can drive up to (including) 4k - * screens + * 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. */ - topology.num_dsc = 2; - topology.num_lm = 2; - topology.num_intf = 1; - } - - return topology; -} - -static void dpu_encoder_assign_crtc_resources(struct dpu_kms *dpu_kms, - struct drm_encoder *drm_enc, - struct dpu_global_state *global_state, - struct drm_crtc_state *crtc_state) -{ - struct dpu_crtc_state *cstate; - struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC]; - int num_lm, num_ctl, num_dspp, i; - - cstate = to_dpu_crtc_state(crtc_state); - - memset(cstate->mixers, 0, sizeof(cstate->mixers)); - - num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); - num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); - num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp, - ARRAY_SIZE(hw_dspp)); - - for (i = 0; i < num_lm; i++) { - int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); - - cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); - cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); - cstate->mixers[i].hw_dspp = i < num_dspp ? to_dpu_hw_dspp(hw_dspp[i]) : NULL; - } - - cstate->num_mixers = num_lm; -} - -static int dpu_encoder_virt_atomic_check( - struct drm_encoder *drm_enc, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - struct dpu_encoder_virt *dpu_enc; - struct msm_drm_private *priv; - struct dpu_kms *dpu_kms; - struct drm_display_mode *adj_mode; - struct msm_display_topology topology; - struct msm_display_info *disp_info; - struct dpu_global_state *global_state; - struct drm_framebuffer *fb; - struct drm_dsc_config *dsc; - int ret = 0; - - if (!drm_enc || !crtc_state || !conn_state) { - DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n", - drm_enc != NULL, crtc_state != NULL, conn_state != NULL); - return -EINVAL; + 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; } - dpu_enc = to_dpu_encoder_virt(drm_enc); - DPU_DEBUG_ENC(dpu_enc, "\n"); - - priv = drm_enc->dev->dev_private; - disp_info = &dpu_enc->disp_info; - dpu_kms = to_dpu_kms(priv->kms); - adj_mode = &crtc_state->adjusted_mode; - global_state = dpu_kms_get_global_state(crtc_state->state); - if (IS_ERR(global_state)) - return PTR_ERR(global_state); - - trace_dpu_enc_atomic_check(DRMID(drm_enc)); - - dsc = dpu_encoder_get_dsc_config(drm_enc); - - topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode, crtc_state, dsc); + connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + if (!connector) + return; + conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return; /* * Use CDM only for writeback or DP at the moment as other interfaces cannot handle it. @@ -781,34 +707,45 @@ static int dpu_encoder_virt_atomic_check( fb = conn_state->writeback_job->fb; if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) - topology.needs_cdm = true; + topology->num_cdm++; } else if (disp_info->intf_type == INTF_DP) { if (msm_dp_is_yuv_420_enabled(priv->dp[disp_info->h_tile_instance[0]], adj_mode)) - topology.needs_cdm = true; + topology->num_cdm++; } +} - if (topology.needs_cdm && !dpu_enc->cur_master->hw_cdm) - crtc_state->mode_changed = true; - else if (!topology.needs_cdm && dpu_enc->cur_master->hw_cdm) - crtc_state->mode_changed = true; - /* - * Release and Allocate resources on every modeset - * Dont allocate when active is false. - */ - if (drm_atomic_crtc_needs_modeset(crtc_state)) { - dpu_rm_release(global_state, drm_enc); +bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state) +{ + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_framebuffer *fb; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); - if (!crtc_state->active_changed || crtc_state->enable) - ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, &topology); - if (!ret) - dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc, - global_state, crtc_state); - } + if (!drm_enc || !state) + return false; - trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags); + connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + if (!connector) + return false; - return ret; + conn_state = drm_atomic_get_new_connector_state(state, connector); + + /** + * These checks are duplicated from dpu_encoder_update_topology() since + * CRTC and encoder don't hold topology information + */ + if (dpu_enc->disp_info.intf_type == INTF_WB && conn_state->writeback_job) { + fb = conn_state->writeback_job->fb; + if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) { + if (!dpu_enc->cur_master->hw_cdm) + return true; + } else { + if (dpu_enc->cur_master->hw_cdm) + return true; + } + } + + return false; } static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc, @@ -1219,8 +1156,12 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_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_cwb = 0; + bool is_cwb_encoder; unsigned int dsc_mask = 0; + unsigned int cwb_mask = 0; int i; if (!drm_enc) { @@ -1233,6 +1174,8 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); + is_cwb_encoder = drm_crtc_in_clone_mode(crtc_state) && + dpu_enc->disp_info.intf_type == INTF_WB; global_state = dpu_kms_get_existing_global_state(dpu_kms); if (IS_ERR_OR_NULL(global_state)) { @@ -1243,18 +1186,38 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, trace_dpu_enc_mode_set(DRMID(drm_enc)); /* Query resource that have been reserved in atomic check step. */ - num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_PINGPONG, hw_pp, - ARRAY_SIZE(hw_pp)); + if (is_cwb_encoder) { + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_DCWB_PINGPONG, + hw_pp, ARRAY_SIZE(hw_pp)); + num_cwb = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_CWB, + hw_cwb, ARRAY_SIZE(hw_cwb)); + } else { + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_PINGPONG, hw_pp, + ARRAY_SIZE(hw_pp)); + } + + for (i = 0; i < num_cwb; i++) { + dpu_enc->hw_cwb[i] = to_dpu_hw_cwb(hw_cwb[i]); + cwb_mask |= BIT(dpu_enc->hw_cwb[i]->idx - CWB_0); + } + + dpu_enc->cwb_mask = cwb_mask; + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); + drm_enc->crtc, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i]) : NULL; num_dsc = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_DSC, + drm_enc->crtc, DPU_HW_BLK_DSC, hw_dsc, ARRAY_SIZE(hw_dsc)); for (i = 0; i < num_dsc; i++) { dpu_enc->hw_dsc[i] = to_dpu_hw_dsc(hw_dsc[i]); @@ -1268,7 +1231,7 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_cdm = NULL; dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CDM, + drm_enc->crtc, DPU_HW_BLK_CDM, &hw_cdm, 1); dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL; } @@ -1654,6 +1617,7 @@ static void dpu_encoder_off_work(struct work_struct *work) static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, struct dpu_encoder_phys *phys, uint32_t extra_flush_bits) { + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); struct dpu_hw_ctl *ctl; int pending_kickoff_cnt; u32 ret = UINT_MAX; @@ -1671,6 +1635,15 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys); + /* Return early if encoder is writeback and in clone mode */ + if (drm_enc->encoder_type == DRM_MODE_ENCODER_VIRTUAL && + dpu_enc->cwb_mask) { + DPU_DEBUG("encoder %d skip flush for concurrent writeback encoder\n", + DRMID(drm_enc)); + return; + } + + if (extra_flush_bits && ctl->ops.update_pending_flush) ctl->ops.update_pending_flush(ctl, extra_flush_bits); @@ -1693,6 +1666,8 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, */ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) { + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys->parent); + if (!phys) { DPU_ERROR("invalid argument(s)\n"); return; @@ -1703,6 +1678,12 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) return; } + if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL && + dpu_enc->cwb_mask) { + DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent)); + return; + } + if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED) phys->ops.trigger_start(phys); } @@ -2020,7 +2001,6 @@ static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_ctl *ctl, static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, struct drm_dsc_config *dsc) { - /* coding only for 2LM, 2enc, 1 dsc config */ struct dpu_encoder_phys *enc_master = dpu_enc->cur_master; struct dpu_hw_ctl *ctl = enc_master->hw_ctl; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; @@ -2030,22 +2010,24 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, int dsc_common_mode; int pic_width; u32 initial_lines; + int num_dsc = 0; int i; for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { hw_pp[i] = dpu_enc->hw_pp[i]; hw_dsc[i] = dpu_enc->hw_dsc[i]; - if (!hw_pp[i] || !hw_dsc[i]) { - DPU_ERROR_ENC(dpu_enc, "invalid params for DSC\n"); - return; - } + if (!hw_pp[i] || !hw_dsc[i]) + break; + + num_dsc++; } - dsc_common_mode = 0; pic_width = dsc->pic_width; - dsc_common_mode = DSC_MODE_SPLIT_PANEL; + dsc_common_mode = 0; + if (num_dsc > 1) + dsc_common_mode |= DSC_MODE_SPLIT_PANEL; if (dpu_encoder_use_dsc_merge(enc_master->parent)) dsc_common_mode |= DSC_MODE_MULTIPLEX; if (enc_master->intf_mode == INTF_MODE_VIDEO) @@ -2054,14 +2036,10 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, this_frame_slices = pic_width / dsc->slice_width; intf_ip_w = this_frame_slices * dsc->slice_width; - /* - * dsc merge case: when using 2 encoders for the same stream, - * no. of slices need to be same on both the encoders. - */ - enc_ip_w = intf_ip_w / 2; + enc_ip_w = intf_ip_w / num_dsc; initial_lines = dpu_encoder_dsc_initial_line_calc(dsc, enc_ip_w); - for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + for (i = 0; i < num_dsc; i++) dpu_encoder_dsc_pipe_cfg(ctl, hw_dsc[i], hw_pp[i], dsc, dsc_common_mode, initial_lines); } @@ -2135,6 +2113,25 @@ bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc) } /** + * dpu_encoder_start_frame_done_timer - Start the encoder frame done timer + * @drm_enc: Pointer to drm encoder structure + */ +void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + unsigned long timeout_ms; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 / + drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode); + + atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms); + mod_timer(&dpu_enc->frame_done_timer, + jiffies + msecs_to_jiffies(timeout_ms)); + +} + +/** * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path * (i.e. ctl flush and start) immediately. * @drm_enc: encoder pointer @@ -2143,7 +2140,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc; struct dpu_encoder_phys *phys; - unsigned long timeout_ms; unsigned int i; DPU_ATRACE_BEGIN("encoder_kickoff"); @@ -2151,13 +2147,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) trace_dpu_enc_kickoff(DRMID(drm_enc)); - timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 / - drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode); - - atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms); - mod_timer(&dpu_enc->frame_done_timer, - jiffies + msecs_to_jiffies(timeout_ms)); - /* All phys encs are ready to go, trigger the kickoff */ _dpu_encoder_kickoff_phys(dpu_enc); @@ -2183,22 +2172,22 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) memset(&mixer, 0, sizeof(mixer)); /* reset all mixers for this encoder */ - if (phys_enc->hw_ctl->ops.clear_all_blendstages) - phys_enc->hw_ctl->ops.clear_all_blendstages(phys_enc->hw_ctl); + if (ctl->ops.clear_all_blendstages) + ctl->ops.clear_all_blendstages(ctl); global_state = dpu_kms_get_existing_global_state(phys_enc->dpu_kms); num_lm = dpu_rm_get_assigned_resources(&phys_enc->dpu_kms->rm, global_state, - phys_enc->parent->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); + phys_enc->parent->crtc, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); for (i = 0; i < num_lm; i++) { hw_mixer[i] = to_dpu_hw_mixer(hw_lm[i]); - if (phys_enc->hw_ctl->ops.update_pending_flush_mixer) - phys_enc->hw_ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); + if (ctl->ops.update_pending_flush_mixer) + ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); /* clear all blendstages */ - if (phys_enc->hw_ctl->ops.setup_blendstage) - phys_enc->hw_ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL); + if (ctl->ops.setup_blendstage) + ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL); } } @@ -2250,7 +2239,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) dpu_enc = to_dpu_encoder_virt(phys_enc->parent); - phys_enc->hw_ctl->ops.reset(ctl); + ctl->ops.reset(ctl); dpu_encoder_helper_reset_mixers(phys_enc); @@ -2265,8 +2254,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, PINGPONG_NONE); /* mark WB flush as pending */ - if (phys_enc->hw_ctl->ops.update_pending_flush_wb) - phys_enc->hw_ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx); + if (ctl->ops.update_pending_flush_wb) + ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx); } else { for (i = 0; i < dpu_enc->num_phys_encs; i++) { if (dpu_enc->phys_encs[i] && phys_enc->hw_intf->ops.bind_pingpong_blk) @@ -2275,8 +2264,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) PINGPONG_NONE); /* mark INTF flush as pending */ - if (phys_enc->hw_ctl->ops.update_pending_flush_intf) - phys_enc->hw_ctl->ops.update_pending_flush_intf(phys_enc->hw_ctl, + if (ctl->ops.update_pending_flush_intf) + ctl->ops.update_pending_flush_intf(ctl, dpu_enc->phys_encs[i]->hw_intf->idx); } } @@ -2284,12 +2273,15 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither) phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL); + if (dpu_enc->cwb_mask) + dpu_encoder_helper_phys_setup_cwb(phys_enc, false); + /* reset the merge 3D HW block */ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); - if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) - phys_enc->hw_ctl->ops.update_pending_flush_merge_3d(ctl, + if (ctl->ops.update_pending_flush_merge_3d) + ctl->ops.update_pending_flush_merge_3d(ctl, phys_enc->hw_pp->merge_3d->idx); } @@ -2297,9 +2289,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_cdm->ops.bind_pingpong_blk && phys_enc->hw_pp) phys_enc->hw_cdm->ops.bind_pingpong_blk(phys_enc->hw_cdm, PINGPONG_NONE); - if (phys_enc->hw_ctl->ops.update_pending_flush_cdm) - phys_enc->hw_ctl->ops.update_pending_flush_cdm(phys_enc->hw_ctl, - phys_enc->hw_cdm->idx); + if (ctl->ops.update_pending_flush_cdm) + ctl->ops.update_pending_flush_cdm(ctl, + phys_enc->hw_cdm->idx); } if (dpu_enc->dsc) { @@ -2310,6 +2302,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc); + intf_cfg.cwb = dpu_enc->cwb_mask; if (phys_enc->hw_intf) intf_cfg.intf = phys_enc->hw_intf->idx; @@ -2327,6 +2320,68 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) ctl->ops.clear_pending_flush(ctl); } +void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, + bool enable) +{ + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys_enc->parent); + struct dpu_hw_cwb *hw_cwb; + struct dpu_hw_ctl *hw_ctl; + struct dpu_hw_cwb_setup_cfg cwb_cfg; + + struct dpu_kms *dpu_kms; + struct dpu_global_state *global_state; + struct dpu_hw_blk *rt_pp_list[MAX_CHANNELS_PER_ENC]; + int num_pp; + + if (!phys_enc->hw_wb) + return; + + hw_ctl = phys_enc->hw_ctl; + + if (!phys_enc->hw_ctl) { + DPU_DEBUG("[wb:%d] no ctl assigned\n", + phys_enc->hw_wb->idx - WB_0); + return; + } + + dpu_kms = phys_enc->dpu_kms; + global_state = dpu_kms_get_existing_global_state(dpu_kms); + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + phys_enc->parent->crtc, + DPU_HW_BLK_PINGPONG, rt_pp_list, + ARRAY_SIZE(rt_pp_list)); + + if (num_pp == 0 || num_pp > MAX_CHANNELS_PER_ENC) { + DPU_DEBUG_ENC(dpu_enc, "invalid num_pp %d\n", num_pp); + return; + } + + /* + * The CWB mux supports using LM or DSPP as tap points. For now, + * always use LM tap point + */ + cwb_cfg.input = INPUT_MODE_LM_OUT; + + for (int i = 0; i < MAX_CHANNELS_PER_ENC; i++) { + hw_cwb = dpu_enc->hw_cwb[i]; + if (!hw_cwb) + continue; + + if (enable) { + struct dpu_hw_pingpong *hw_pp = + to_dpu_hw_pingpong(rt_pp_list[i]); + cwb_cfg.pp_idx = hw_pp->idx; + } else { + cwb_cfg.pp_idx = PINGPONG_NONE; + } + + hw_cwb->ops.config_cwb(hw_cwb, &cwb_cfg); + + if (hw_ctl->ops.update_pending_flush_cwb) + hw_ctl->ops.update_pending_flush_cwb(hw_ctl, hw_cwb->idx); + } +} + /** * dpu_encoder_helper_phys_setup_cdm - setup chroma down sampling block * @phys_enc: Pointer to physical encoder @@ -2513,6 +2568,38 @@ static int dpu_encoder_virt_add_phys_encs( return 0; } +/** + * dpu_encoder_get_clones - Calculate the possible_clones for DPU encoder + * @drm_enc: DRM encoder pointer + * Returns: possible_clones mask + */ +uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc) +{ + struct drm_encoder *curr; + int type = drm_enc->encoder_type; + uint32_t clone_mask = drm_encoder_mask(drm_enc); + + /* + * Set writeback as possible clones of real-time DSI encoders and vice + * versa + * + * Writeback encoders can't be clones of each other and DSI + * encoders can't be clones of each other. + * + * TODO: Add DP encoders as valid possible clones for writeback encoders + * (and vice versa) once concurrent writeback has been validated for DP + */ + drm_for_each_encoder(curr, drm_enc->dev) { + if ((type == DRM_MODE_ENCODER_VIRTUAL && + curr->encoder_type == DRM_MODE_ENCODER_DSI) || + (type == DRM_MODE_ENCODER_DSI && + curr->encoder_type == DRM_MODE_ENCODER_VIRTUAL)) + clone_mask |= drm_encoder_mask(curr); + } + + return clone_mask; +} + static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, struct dpu_kms *dpu_kms, struct msm_display_info *disp_info) @@ -2630,7 +2717,6 @@ static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = { .atomic_mode_set = dpu_encoder_virt_atomic_mode_set, .atomic_disable = dpu_encoder_virt_atomic_disable, .atomic_enable = dpu_encoder_virt_atomic_enable, - .atomic_check = dpu_encoder_virt_atomic_check, }; static const struct drm_encoder_funcs dpu_encoder_funcs = { @@ -2789,6 +2875,18 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder) } /** + * dpu_encoder_helper_get_cwb_mask - get CWB blocks mask for the DPU encoder + * @phys_enc: Pointer to physical encoder structure + */ +unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc) +{ + struct drm_encoder *encoder = phys_enc->parent; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(encoder); + + return dpu_enc->cwb_mask; +} + +/** * dpu_encoder_helper_get_dsc - get DSC blocks mask for the DPU encoder * This helper function is used by physical encoder to get DSC blocks mask * used for this encoder. diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 92b5ee390788..ca1ca2e51d7e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> @@ -60,6 +60,8 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder); void dpu_encoder_virt_runtime_resume(struct drm_encoder *encoder); +uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc); + struct drm_encoder *dpu_encoder_init(struct drm_device *dev, int drm_enc_mode, struct msm_display_info *disp_info); @@ -80,6 +82,13 @@ int dpu_encoder_get_crc(const struct drm_encoder *drm_enc, u32 *crcs, int pos); bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc); +void dpu_encoder_update_topology(struct drm_encoder *drm_enc, + struct msm_display_topology *topology, + struct drm_atomic_state *state, + const struct drm_display_mode *adj_mode); + +bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state); + void dpu_encoder_prepare_wb_job(struct drm_encoder *drm_enc, struct drm_writeback_job *job); @@ -88,4 +97,5 @@ void dpu_encoder_cleanup_wb_job(struct drm_encoder *drm_enc, bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc); +void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc); #endif /* __DPU_ENCODER_H__ */ 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 63f09857025c..61b22d949454 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. */ @@ -309,6 +309,8 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode( return BLEND_3D_NONE; } +unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc); + unsigned int dpu_encoder_helper_get_dsc(struct dpu_encoder_phys *phys_enc); struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc); @@ -331,6 +333,9 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc); +void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, + bool enable); + void dpu_encoder_helper_phys_setup_cdm(struct dpu_encoder_phys *phys_enc, const struct msm_format *dpu_fmt, u32 output_type); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index e9bbccc44dad..da9994a79ca2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -5,6 +5,7 @@ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ #include <linux/delay.h> +#include <linux/string_choices.h> #include "dpu_encoder_phys.h" #include "dpu_hw_interrupts.h" #include "dpu_hw_pingpong.h" @@ -261,7 +262,7 @@ static int dpu_encoder_phys_cmd_control_vblank_irq( DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent), phys_enc->hw_pp->idx - PINGPONG_0, - enable ? "true" : "false", refcount); + str_true_false(enable), refcount); if (enable) { if (phys_enc->vblank_refcount == 0) @@ -285,7 +286,7 @@ end: DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n", DRMID(phys_enc->parent), phys_enc->hw_pp->idx - PINGPONG_0, ret, - enable ? "true" : "false", refcount); + str_true_false(enable), refcount); } return ret; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 4c006ec74575..849fea580a4c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ @@ -68,7 +68,7 @@ static void dpu_encoder_phys_wb_set_ot_limit( ot_params.num = hw_wb->idx - WB_0; ot_params.width = phys_enc->cached_mode.hdisplay; ot_params.height = phys_enc->cached_mode.vdisplay; - ot_params.is_wfd = true; + ot_params.is_wfd = !dpu_encoder_helper_get_cwb_mask(phys_enc); ot_params.frame_rate = drm_mode_vrefresh(&phys_enc->cached_mode); ot_params.vbif_idx = hw_wb->caps->vbif_idx; ot_params.rd = false; @@ -111,7 +111,7 @@ static void dpu_encoder_phys_wb_set_qos_remap( qos_params.vbif_idx = hw_wb->caps->vbif_idx; qos_params.xin_id = hw_wb->caps->xin_id; qos_params.num = hw_wb->idx - WB_0; - qos_params.is_rt = false; + qos_params.is_rt = dpu_encoder_helper_get_cwb_mask(phys_enc); DPU_DEBUG("[qos_remap] wb:%d vbif:%d xin:%d is_rt:%d\n", qos_params.num, @@ -174,6 +174,7 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc); struct dpu_hw_wb *hw_wb; struct dpu_hw_wb_cfg *wb_cfg; + u32 cdp_usage; if (!phys_enc || !phys_enc->dpu_kms || !phys_enc->dpu_kms->catalog) { DPU_ERROR("invalid encoder\n"); @@ -182,6 +183,10 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, hw_wb = phys_enc->hw_wb; wb_cfg = &wb_enc->wb_cfg; + if (dpu_encoder_helper_get_cwb_mask(phys_enc)) + cdp_usage = DPU_PERF_CDP_USAGE_RT; + else + cdp_usage = DPU_PERF_CDP_USAGE_NRT; wb_cfg->intf_mode = phys_enc->intf_mode; wb_cfg->roi.x1 = 0; @@ -199,7 +204,7 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, const struct dpu_perf_cfg *perf = phys_enc->dpu_kms->catalog->perf; hw_wb->ops.setup_cdp(hw_wb, format, - perf->cdp_cfg[DPU_PERF_CDP_USAGE_NRT].wr_enable); + perf->cdp_cfg[cdp_usage].wr_enable); } if (hw_wb->ops.setup_outaddress) @@ -236,6 +241,7 @@ static void dpu_encoder_phys_wb_setup_ctl(struct dpu_encoder_phys *phys_enc) intf_cfg.intf = DPU_NONE; intf_cfg.wb = hw_wb->idx; + intf_cfg.cwb = dpu_encoder_helper_get_cwb_mask(phys_enc); if (mode_3d && hw_pp && hw_pp->merge_3d) intf_cfg.merge_3d = hw_pp->merge_3d->idx; @@ -340,6 +346,8 @@ static void dpu_encoder_phys_wb_setup( dpu_encoder_helper_phys_setup_cdm(phys_enc, format, CDM_CDWN_OUTPUT_WB); + dpu_encoder_helper_phys_setup_cwb(phys_enc, true); + dpu_encoder_phys_wb_setup_ctl(phys_enc); } 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 0b342c043875..64265ca4656a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -232,37 +232,6 @@ static const u32 rotation_v2_formats[] = { /* TODO add formats after validation */ }; -static const u32 wb2_formats_rgb[] = { - DRM_FORMAT_RGB565, - DRM_FORMAT_BGR565, - DRM_FORMAT_RGB888, - DRM_FORMAT_ARGB8888, - DRM_FORMAT_RGBA8888, - DRM_FORMAT_ABGR8888, - DRM_FORMAT_XRGB8888, - DRM_FORMAT_RGBX8888, - DRM_FORMAT_XBGR8888, - DRM_FORMAT_ARGB1555, - DRM_FORMAT_RGBA5551, - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGBX5551, - DRM_FORMAT_ARGB4444, - DRM_FORMAT_RGBA4444, - DRM_FORMAT_RGBX4444, - DRM_FORMAT_XRGB4444, - DRM_FORMAT_BGR888, - DRM_FORMAT_BGRA8888, - DRM_FORMAT_BGRX8888, - DRM_FORMAT_ABGR1555, - DRM_FORMAT_BGRA5551, - DRM_FORMAT_XBGR1555, - DRM_FORMAT_BGRX5551, - DRM_FORMAT_ABGR4444, - DRM_FORMAT_BGRA4444, - DRM_FORMAT_BGRX4444, - DRM_FORMAT_XBGR4444, -}; - static const u32 wb2_formats_rgb_yuv[] = { DRM_FORMAT_RGB565, DRM_FORMAT_BGR565, @@ -507,7 +476,14 @@ static const struct dpu_dsc_sub_blks dsc_sblk_1 = { /************************************************************* * CDM block config *************************************************************/ -static const struct dpu_cdm_cfg sc7280_cdm = { +static const struct dpu_cdm_cfg dpu_cdm_1_x_4_x = { + .name = "cdm_0", + .id = CDM_0, + .len = 0x224, + .base = 0x79200, +}; + +static const struct dpu_cdm_cfg dpu_cdm_5_x = { .name = "cdm_0", .id = CDM_0, .len = 0x228, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c index ae1534c49ae0..3f88c3641d4a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c @@ -214,7 +214,9 @@ static void dpu_hw_cdm_bind_pingpong_blk(struct dpu_hw_cdm *ctx, const enum dpu_ mux_cfg = DPU_REG_READ(c, CDM_MUX); mux_cfg &= ~0xf; - if (pp) + if (pp >= PINGPONG_CWB_0) + mux_cfg |= 0xd; + else if (pp) mux_cfg |= (pp - PINGPONG_0) & 0x7; else mux_cfg |= 0xf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index 4893f10d6a58..411a7cf088eb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/delay.h> @@ -31,12 +31,14 @@ #define CTL_MERGE_3D_ACTIVE 0x0E4 #define CTL_DSC_ACTIVE 0x0E8 #define CTL_WB_ACTIVE 0x0EC +#define CTL_CWB_ACTIVE 0x0F0 #define CTL_INTF_ACTIVE 0x0F4 #define CTL_CDM_ACTIVE 0x0F8 #define CTL_FETCH_PIPE_ACTIVE 0x0FC #define CTL_MERGE_3D_FLUSH 0x100 #define CTL_DSC_FLUSH 0x104 #define CTL_WB_FLUSH 0x108 +#define CTL_CWB_FLUSH 0x10C #define CTL_INTF_FLUSH 0x110 #define CTL_CDM_FLUSH 0x114 #define CTL_PERIPH_FLUSH 0x128 @@ -53,6 +55,7 @@ #define PERIPH_IDX 30 #define INTF_IDX 31 #define WB_IDX 16 +#define CWB_IDX 28 #define DSPP_IDX 29 /* From DPU hw rev 7.x.x */ #define CTL_INVALID_BIT 0xffff #define CTL_DEFAULT_GROUP_ID 0xf @@ -110,6 +113,7 @@ static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx) ctx->pending_flush_mask = 0x0; ctx->pending_intf_flush_mask = 0; ctx->pending_wb_flush_mask = 0; + ctx->pending_cwb_flush_mask = 0; ctx->pending_merge_3d_flush_mask = 0; ctx->pending_dsc_flush_mask = 0; ctx->pending_cdm_flush_mask = 0; @@ -144,6 +148,9 @@ static inline void dpu_hw_ctl_trigger_flush_v1(struct dpu_hw_ctl *ctx) if (ctx->pending_flush_mask & BIT(WB_IDX)) DPU_REG_WRITE(&ctx->hw, CTL_WB_FLUSH, ctx->pending_wb_flush_mask); + if (ctx->pending_flush_mask & BIT(CWB_IDX)) + DPU_REG_WRITE(&ctx->hw, CTL_CWB_FLUSH, + ctx->pending_cwb_flush_mask); if (ctx->pending_flush_mask & BIT(DSPP_IDX)) for (dspp = DSPP_0; dspp < DSPP_MAX; dspp++) { @@ -310,6 +317,13 @@ static void dpu_hw_ctl_update_pending_flush_wb_v1(struct dpu_hw_ctl *ctx, ctx->pending_flush_mask |= BIT(WB_IDX); } +static void dpu_hw_ctl_update_pending_flush_cwb_v1(struct dpu_hw_ctl *ctx, + enum dpu_cwb cwb) +{ + ctx->pending_cwb_flush_mask |= BIT(cwb - CWB_0); + ctx->pending_flush_mask |= BIT(CWB_IDX); +} + static void dpu_hw_ctl_update_pending_flush_intf_v1(struct dpu_hw_ctl *ctx, enum dpu_intf intf) { @@ -547,6 +561,7 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, u32 intf_active = 0; u32 dsc_active = 0; u32 wb_active = 0; + u32 cwb_active = 0; u32 mode_sel = 0; /* CTL_TOP[31:28] carries group_id to collate CTL paths @@ -561,6 +576,7 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE); wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE); + cwb_active = DPU_REG_READ(c, CTL_CWB_ACTIVE); dsc_active = DPU_REG_READ(c, CTL_DSC_ACTIVE); if (cfg->intf) @@ -569,12 +585,16 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, if (cfg->wb) wb_active |= BIT(cfg->wb - WB_0); + if (cfg->cwb) + cwb_active |= cfg->cwb; + if (cfg->dsc) dsc_active |= cfg->dsc; DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); DPU_REG_WRITE(c, CTL_WB_ACTIVE, wb_active); + DPU_REG_WRITE(c, CTL_CWB_ACTIVE, cwb_active); DPU_REG_WRITE(c, CTL_DSC_ACTIVE, dsc_active); if (cfg->merge_3d) @@ -624,6 +644,7 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, struct dpu_hw_blk_reg_map *c = &ctx->hw; u32 intf_active = 0; u32 wb_active = 0; + u32 cwb_active = 0; u32 merge3d_active = 0; u32 dsc_active; u32 cdm_active; @@ -651,6 +672,12 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); } + if (cfg->cwb) { + cwb_active = DPU_REG_READ(c, CTL_CWB_ACTIVE); + cwb_active &= ~cfg->cwb; + DPU_REG_WRITE(c, CTL_CWB_ACTIVE, cwb_active); + } + if (cfg->wb) { wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE); wb_active &= ~BIT(cfg->wb - WB_0); @@ -703,6 +730,7 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->update_pending_flush_merge_3d = dpu_hw_ctl_update_pending_flush_merge_3d_v1; ops->update_pending_flush_wb = dpu_hw_ctl_update_pending_flush_wb_v1; + ops->update_pending_flush_cwb = dpu_hw_ctl_update_pending_flush_cwb_v1; ops->update_pending_flush_dsc = dpu_hw_ctl_update_pending_flush_dsc_v1; ops->update_pending_flush_cdm = dpu_hw_ctl_update_pending_flush_cdm_v1; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index 85c6c835cc87..080a9550a0cc 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #ifndef _DPU_HW_CTL_H @@ -42,6 +42,7 @@ struct dpu_hw_stage_cfg { * @cdm: CDM block used * @stream_sel: Stream selection for multi-stream interfaces * @dsc: DSC BIT masks used + * @cwb: CWB BIT masks used */ struct dpu_hw_intf_cfg { enum dpu_intf intf; @@ -51,6 +52,7 @@ struct dpu_hw_intf_cfg { enum dpu_ctl_mode_sel intf_mode_sel; enum dpu_cdm cdm; int stream_sel; + unsigned int cwb; unsigned int dsc; }; @@ -115,6 +117,15 @@ struct dpu_hw_ctl_ops { enum dpu_wb blk); /** + * OR in the given flushbits to the cached pending_(cwb_)flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @blk : concurrent writeback block index + */ + void (*update_pending_flush_cwb)(struct dpu_hw_ctl *ctx, + enum dpu_cwb blk); + + /** * OR in the given flushbits to the cached pending_(intf_)flush_mask * No effect on hardware * @ctx : ctl path ctx pointer @@ -258,6 +269,7 @@ struct dpu_hw_ctl_ops { * @pending_flush_mask: storage for pending ctl_flush managed via ops * @pending_intf_flush_mask: pending INTF flush * @pending_wb_flush_mask: pending WB flush + * @pending_cwb_flush_mask: pending CWB flush * @pending_dsc_flush_mask: pending DSC flush * @pending_cdm_flush_mask: pending CDM flush * @ops: operation list @@ -274,6 +286,7 @@ struct dpu_hw_ctl { u32 pending_flush_mask; u32 pending_intf_flush_mask; u32 pending_wb_flush_mask; + u32 pending_cwb_flush_mask; u32 pending_periph_flush_mask; u32 pending_merge_3d_flush_mask; u32 pending_dspp_flush_mask[DSPP_MAX - DSPP_0]; 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 ba7bb05efe9b..8d820cd1b554 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -77,12 +77,14 @@ enum dpu_hw_blk_type { DPU_HW_BLK_LM, DPU_HW_BLK_CTL, DPU_HW_BLK_PINGPONG, + DPU_HW_BLK_DCWB_PINGPONG, DPU_HW_BLK_INTF, DPU_HW_BLK_WB, DPU_HW_BLK_DSPP, DPU_HW_BLK_MERGE_3D, DPU_HW_BLK_DSC, DPU_HW_BLK_CDM, + DPU_HW_BLK_CWB, DPU_HW_BLK_MAX, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 97e9cb8c2b09..3305ad0623ca 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -446,6 +446,19 @@ static void dpu_kms_disable_commit(struct msm_kms *kms) pm_runtime_put_sync(&dpu_kms->pdev->dev); } +static int dpu_kms_check_mode_changed(struct msm_kms *kms, struct drm_atomic_state *state) +{ + struct drm_crtc_state *new_crtc_state; + struct drm_crtc_state *old_crtc_state; + struct drm_crtc *crtc; + int i; + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) + dpu_crtc_check_mode_changed(old_crtc_state, new_crtc_state); + + return 0; +} + static void dpu_kms_flush_commit(struct msm_kms *kms, unsigned crtc_mask) { struct dpu_kms *dpu_kms = to_dpu_kms(kms); @@ -811,8 +824,11 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) return ret; num_encoders = 0; - drm_for_each_encoder(encoder, dev) + drm_for_each_encoder(encoder, dev) { num_encoders++; + if (catalog->cwb_count > 0) + encoder->possible_clones = dpu_encoder_get_clones(encoder); + } max_crtc_count = min(catalog->mixer_count, num_encoders); @@ -1062,6 +1078,7 @@ static const struct msm_kms_funcs kms_funcs = { .irq = dpu_core_irq, .enable_commit = dpu_kms_enable_commit, .disable_commit = dpu_kms_disable_commit, + .check_mode_changed = dpu_kms_check_mode_changed, .flush_commit = dpu_kms_flush_commit, .wait_flush = dpu_kms_wait_flush, .complete_commit = dpu_kms_complete_commit, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 547cdb2c0c78..a57ec2ec1060 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -124,14 +124,15 @@ struct dpu_global_state { struct dpu_rm *rm; - uint32_t pingpong_to_enc_id[PINGPONG_MAX - PINGPONG_0]; - uint32_t mixer_to_enc_id[LM_MAX - LM_0]; - uint32_t ctl_to_enc_id[CTL_MAX - CTL_0]; - uint32_t dspp_to_enc_id[DSPP_MAX - DSPP_0]; - uint32_t dsc_to_enc_id[DSC_MAX - DSC_0]; - uint32_t cdm_to_enc_id; + uint32_t pingpong_to_crtc_id[PINGPONG_MAX - PINGPONG_0]; + uint32_t mixer_to_crtc_id[LM_MAX - LM_0]; + uint32_t ctl_to_crtc_id[CTL_MAX - CTL_0]; + uint32_t dspp_to_crtc_id[DSPP_MAX - DSPP_0]; + uint32_t dsc_to_crtc_id[DSC_MAX - DSC_0]; + uint32_t cdm_to_crtc_id; uint32_t sspp_to_crtc_id[SSPP_MAX - SSPP_NONE]; + uint32_t cwb_to_crtc_id[CWB_MAX - CWB_0]; }; struct dpu_global_state diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 5baf9df702b8..3efbba425ca6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -22,9 +22,9 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx, - uint32_t enc_id) + uint32_t crtc_id) { - return res_map[idx] && res_map[idx] != enc_id; + return res_map[idx] && res_map[idx] != crtc_id; } /** @@ -233,13 +233,66 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) return -EINVAL; } +static int _dpu_rm_reserve_cwb_mux_and_pingpongs(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t crtc_id, + struct msm_display_topology *topology) +{ + int num_cwb_mux = topology->num_lm, cwb_mux_count = 0; + int cwb_pp_start_idx = PINGPONG_CWB_0 - PINGPONG_0; + int cwb_pp_idx[MAX_BLOCKS]; + int cwb_mux_idx[MAX_BLOCKS]; + + /* + * Reserve additional dedicated CWB PINGPONG blocks and muxes for each + * mixer + * + * TODO: add support reserving resources for platforms with no + * PINGPONG_CWB + */ + for (int i = 0; i < ARRAY_SIZE(rm->mixer_blks) && + cwb_mux_count < num_cwb_mux; i++) { + for (int j = 0; j < ARRAY_SIZE(rm->cwb_blks); j++) { + /* + * Odd LMs must be assigned to odd CWB muxes and even + * LMs with even CWB muxes. + * + * Since the RM HW block array index is based on the HW + * block ids, we can also use the array index to enforce + * the odd/even rule. See dpu_rm_init() for more + * information + */ + if (reserved_by_other(global_state->cwb_to_crtc_id, j, crtc_id) || + i % 2 != j % 2) + continue; + + cwb_mux_idx[cwb_mux_count] = j; + cwb_pp_idx[cwb_mux_count] = j + cwb_pp_start_idx; + cwb_mux_count++; + break; + } + } + + if (cwb_mux_count != num_cwb_mux) { + DPU_ERROR("Unable to reserve all CWB PINGPONGs\n"); + return -ENAVAIL; + } + + for (int i = 0; i < cwb_mux_count; i++) { + global_state->pingpong_to_crtc_id[cwb_pp_idx[i]] = crtc_id; + global_state->cwb_to_crtc_id[cwb_mux_idx[i]] = crtc_id; + } + + return 0; +} + /** * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets * proposed use case requirements, incl. hardwired dependent blocks like * pingpong * @rm: dpu resource manager handle * @global_state: resources shared across multiple kms objects - * @enc_id: encoder id requesting for allocation + * @crtc_id: crtc id requesting for allocation * @lm_idx: index of proposed layer mixer in rm->mixer_blks[], function checks * if lm, and all other hardwired blocks connected to the lm (pp) is * available and appropriate @@ -252,14 +305,14 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) */ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, int lm_idx, int *pp_idx, int *dspp_idx, + uint32_t crtc_id, int lm_idx, int *pp_idx, int *dspp_idx, struct msm_display_topology *topology) { const struct dpu_lm_cfg *lm_cfg; int idx; /* Already reserved? */ - if (reserved_by_other(global_state->mixer_to_enc_id, lm_idx, enc_id)) { + if (reserved_by_other(global_state->mixer_to_crtc_id, lm_idx, crtc_id)) { DPU_DEBUG("lm %d already reserved\n", lm_idx + LM_0); return false; } @@ -271,7 +324,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return false; } - if (reserved_by_other(global_state->pingpong_to_enc_id, idx, enc_id)) { + if (reserved_by_other(global_state->pingpong_to_crtc_id, idx, crtc_id)) { DPU_DEBUG("lm %d pp %d already reserved\n", lm_cfg->id, lm_cfg->pingpong); return false; @@ -287,7 +340,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return false; } - if (reserved_by_other(global_state->dspp_to_enc_id, idx, enc_id)) { + if (reserved_by_other(global_state->dspp_to_crtc_id, idx, crtc_id)) { DPU_DEBUG("lm %d dspp %d already reserved\n", lm_cfg->id, lm_cfg->dspp); return false; @@ -299,7 +352,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, static int _dpu_rm_reserve_lms(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, struct msm_display_topology *topology) { @@ -323,7 +376,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, lm_idx[lm_count] = i; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, - enc_id, i, &pp_idx[lm_count], + crtc_id, i, &pp_idx[lm_count], &dspp_idx[lm_count], topology)) { continue; } @@ -342,7 +395,7 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, continue; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, - global_state, enc_id, j, + global_state, crtc_id, j, &pp_idx[lm_count], &dspp_idx[lm_count], topology)) { continue; @@ -359,12 +412,12 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, } for (i = 0; i < lm_count; i++) { - global_state->mixer_to_enc_id[lm_idx[i]] = enc_id; - global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id; - global_state->dspp_to_enc_id[dspp_idx[i]] = - topology->num_dspp ? enc_id : 0; + global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id; + global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id; + global_state->dspp_to_crtc_id[dspp_idx[i]] = + topology->num_dspp ? crtc_id : 0; - trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id, + trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, crtc_id, pp_idx[i] + PINGPONG_0); } @@ -374,15 +427,25 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, static int _dpu_rm_reserve_ctls( struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int ctl_idx[MAX_BLOCKS]; int i = 0, j, num_ctls; bool needs_split_display; - /* each hw_intf needs its own hw_ctrl to program its control path */ - num_ctls = top->num_intf; + /* + * For non-CWB mode, each hw_intf needs its own hw_ctl to program its + * control path. + * + * Hardcode num_ctls to 1 if CWB is enabled because in CWB, both the + * writeback and real-time encoders must be driven by the same control + * path + */ + if (top->cwb_enabled) + num_ctls = 1; + else + num_ctls = top->num_intf; needs_split_display = _dpu_rm_needs_split_display(top); @@ -393,7 +456,7 @@ static int _dpu_rm_reserve_ctls( if (!rm->ctl_blks[j]) continue; - if (reserved_by_other(global_state->ctl_to_enc_id, j, enc_id)) + if (reserved_by_other(global_state->ctl_to_crtc_id, j, crtc_id)) continue; ctl = to_dpu_hw_ctl(rm->ctl_blks[j]); @@ -417,8 +480,8 @@ static int _dpu_rm_reserve_ctls( return -ENAVAIL; for (i = 0; i < ARRAY_SIZE(ctl_idx) && i < num_ctls; i++) { - global_state->ctl_to_enc_id[ctl_idx[i]] = enc_id; - trace_dpu_rm_reserve_ctls(i + CTL_0, enc_id); + global_state->ctl_to_crtc_id[ctl_idx[i]] = crtc_id; + trace_dpu_rm_reserve_ctls(i + CTL_0, crtc_id); } return 0; @@ -426,12 +489,12 @@ static int _dpu_rm_reserve_ctls( static int _dpu_rm_pingpong_next_index(struct dpu_global_state *global_state, int start, - uint32_t enc_id) + uint32_t crtc_id) { int i; for (i = start; i < (PINGPONG_MAX - PINGPONG_0); i++) { - if (global_state->pingpong_to_enc_id[i] == enc_id) + if (global_state->pingpong_to_crtc_id[i] == crtc_id) return i; } @@ -452,7 +515,7 @@ static int _dpu_rm_pingpong_dsc_check(int dsc_idx, int pp_idx) static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int num_dsc = 0; @@ -465,10 +528,10 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, if (!rm->dsc_blks[dsc_idx]) continue; - if (reserved_by_other(global_state->dsc_to_enc_id, dsc_idx, enc_id)) + if (reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx, crtc_id)) continue; - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -476,7 +539,7 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, if (ret) return -ENAVAIL; - global_state->dsc_to_enc_id[dsc_idx] = enc_id; + global_state->dsc_to_crtc_id[dsc_idx] = crtc_id; num_dsc++; pp_idx++; } @@ -492,7 +555,7 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int num_dsc = 0; @@ -507,11 +570,11 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; /* consective dsc index to be paired */ - if (reserved_by_other(global_state->dsc_to_enc_id, dsc_idx, enc_id) || - reserved_by_other(global_state->dsc_to_enc_id, dsc_idx + 1, enc_id)) + if (reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx, crtc_id) || + reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx + 1, crtc_id)) continue; - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -521,7 +584,7 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; } - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx + 1, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx + 1, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -531,8 +594,8 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; } - global_state->dsc_to_enc_id[dsc_idx] = enc_id; - global_state->dsc_to_enc_id[dsc_idx + 1] = enc_id; + global_state->dsc_to_crtc_id[dsc_idx] = crtc_id; + global_state->dsc_to_crtc_id[dsc_idx + 1] = crtc_id; num_dsc += 2; pp_idx++; /* start for next pair */ } @@ -548,11 +611,9 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, static int _dpu_rm_reserve_dsc(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, + uint32_t crtc_id, const struct msm_display_topology *top) { - uint32_t enc_id = enc->base.id; - if (!top->num_dsc || !top->num_intf) return 0; @@ -568,16 +629,17 @@ static int _dpu_rm_reserve_dsc(struct dpu_rm *rm, /* num_dsc should be either 1, 2 or 4 */ if (top->num_dsc > top->num_intf) /* merge mode */ - return _dpu_rm_dsc_alloc_pair(rm, global_state, enc_id, top); + return _dpu_rm_dsc_alloc_pair(rm, global_state, crtc_id, top); else - return _dpu_rm_dsc_alloc(rm, global_state, enc_id, top); + return _dpu_rm_dsc_alloc(rm, global_state, crtc_id, top); return 0; } static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc) + uint32_t crtc_id, + int num_cdm) { /* try allocating only one CDM block */ if (!rm->cdm_blk) { @@ -585,12 +647,17 @@ static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, return -EIO; } - if (global_state->cdm_to_enc_id) { + if (num_cdm > 1) { + DPU_ERROR("More than 1 INTF requesting CDM\n"); + return -EINVAL; + } + + if (global_state->cdm_to_crtc_id) { DPU_ERROR("CDM_0 is already allocated\n"); return -EIO; } - global_state->cdm_to_enc_id = enc->base.id; + global_state->cdm_to_crtc_id = crtc_id; return 0; } @@ -598,30 +665,37 @@ static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, static int _dpu_rm_make_reservation( struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, + uint32_t crtc_id, struct msm_display_topology *topology) { int ret; - ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, topology); + ret = _dpu_rm_reserve_lms(rm, global_state, crtc_id, topology); if (ret) { DPU_ERROR("unable to find appropriate mixers\n"); return ret; } - ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id, + if (topology->cwb_enabled) { + ret = _dpu_rm_reserve_cwb_mux_and_pingpongs(rm, global_state, + crtc_id, topology); + if (ret) + return ret; + } + + ret = _dpu_rm_reserve_ctls(rm, global_state, crtc_id, topology); if (ret) { DPU_ERROR("unable to find appropriate CTL\n"); return ret; } - ret = _dpu_rm_reserve_dsc(rm, global_state, enc, topology); + ret = _dpu_rm_reserve_dsc(rm, global_state, crtc_id, topology); if (ret) return ret; - if (topology->needs_cdm) { - ret = _dpu_rm_reserve_cdm(rm, global_state, enc); + if (topology->num_cdm > 0) { + ret = _dpu_rm_reserve_cdm(rm, global_state, crtc_id, topology->num_cdm); if (ret) { DPU_ERROR("unable to find CDM blk\n"); return ret; @@ -632,12 +706,12 @@ static int _dpu_rm_make_reservation( } static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, - uint32_t enc_id) + uint32_t crtc_id) { int i; for (i = 0; i < cnt; i++) { - if (res_mapping[i] == enc_id) + if (res_mapping[i] == crtc_id) res_mapping[i] = 0; } } @@ -646,23 +720,27 @@ static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, * dpu_rm_release - Given the encoder for the display chain, release any * HW blocks previously reserved for that use case. * @global_state: resources shared across multiple kms objects - * @enc: DRM Encoder handle + * @crtc: DRM CRTC handle * @return: 0 on Success otherwise -ERROR */ void dpu_rm_release(struct dpu_global_state *global_state, - struct drm_encoder *enc) + struct drm_crtc *crtc) { - _dpu_rm_clear_mapping(global_state->pingpong_to_enc_id, - ARRAY_SIZE(global_state->pingpong_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->mixer_to_enc_id, - ARRAY_SIZE(global_state->mixer_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->ctl_to_enc_id, - ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->dsc_to_enc_id, - ARRAY_SIZE(global_state->dsc_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->dspp_to_enc_id, - ARRAY_SIZE(global_state->dspp_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(&global_state->cdm_to_enc_id, 1, enc->base.id); + uint32_t crtc_id = crtc->base.id; + + _dpu_rm_clear_mapping(global_state->pingpong_to_crtc_id, + ARRAY_SIZE(global_state->pingpong_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->mixer_to_crtc_id, + ARRAY_SIZE(global_state->mixer_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->ctl_to_crtc_id, + ARRAY_SIZE(global_state->ctl_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->dsc_to_crtc_id, + ARRAY_SIZE(global_state->dsc_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->dspp_to_crtc_id, + ARRAY_SIZE(global_state->dspp_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(&global_state->cdm_to_crtc_id, 1, crtc_id); + _dpu_rm_clear_mapping(global_state->cwb_to_crtc_id, + ARRAY_SIZE(global_state->cwb_to_crtc_id), crtc_id); } /** @@ -674,42 +752,33 @@ void dpu_rm_release(struct dpu_global_state *global_state, * HW Reservations should be released via dpu_rm_release_hw. * @rm: DPU Resource Manager handle * @global_state: resources shared across multiple kms objects - * @enc: DRM Encoder handle - * @crtc_state: Proposed Atomic DRM CRTC State handle + * @crtc: DRM CRTC handle * @topology: Pointer to topology info for the display * @return: 0 on Success otherwise -ERROR */ int dpu_rm_reserve( struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, - struct drm_crtc_state *crtc_state, + struct drm_crtc *crtc, struct msm_display_topology *topology) { int ret; - /* Check if this is just a page-flip */ - if (!drm_atomic_crtc_needs_modeset(crtc_state)) - return 0; - if (IS_ERR(global_state)) { DPU_ERROR("failed to global state\n"); return PTR_ERR(global_state); } - DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n", - enc->base.id, crtc_state->crtc->base.id); + DRM_DEBUG_KMS("reserving hw for crtc %d\n", crtc->base.id); DRM_DEBUG_KMS("num_lm: %d num_dsc: %d num_intf: %d\n", topology->num_lm, topology->num_dsc, topology->num_intf); - ret = _dpu_rm_make_reservation(rm, global_state, enc, topology); + ret = _dpu_rm_make_reservation(rm, global_state, crtc->base.id, topology); if (ret) DPU_ERROR("failed to reserve hw resources: %d\n", ret); - - return ret; } @@ -800,50 +869,57 @@ void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, * assigned to this encoder * @rm: DPU Resource Manager handle * @global_state: resources shared across multiple kms objects - * @enc_id: encoder id requesting for allocation + * @crtc: DRM CRTC handle * @type: resource type to return data for * @blks: pointer to the array to be filled by HW resources * @blks_size: size of the @blks array */ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, - struct dpu_global_state *global_state, uint32_t enc_id, + struct dpu_global_state *global_state, struct drm_crtc *crtc, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size) { + uint32_t crtc_id = crtc->base.id; struct dpu_hw_blk **hw_blks; - uint32_t *hw_to_enc_id; + uint32_t *hw_to_crtc_id; int i, num_blks, max_blks; switch (type) { case DPU_HW_BLK_PINGPONG: + case DPU_HW_BLK_DCWB_PINGPONG: hw_blks = rm->pingpong_blks; - hw_to_enc_id = global_state->pingpong_to_enc_id; + hw_to_crtc_id = global_state->pingpong_to_crtc_id; max_blks = ARRAY_SIZE(rm->pingpong_blks); break; case DPU_HW_BLK_LM: hw_blks = rm->mixer_blks; - hw_to_enc_id = global_state->mixer_to_enc_id; + hw_to_crtc_id = global_state->mixer_to_crtc_id; max_blks = ARRAY_SIZE(rm->mixer_blks); break; case DPU_HW_BLK_CTL: hw_blks = rm->ctl_blks; - hw_to_enc_id = global_state->ctl_to_enc_id; + hw_to_crtc_id = global_state->ctl_to_crtc_id; max_blks = ARRAY_SIZE(rm->ctl_blks); break; case DPU_HW_BLK_DSPP: hw_blks = rm->dspp_blks; - hw_to_enc_id = global_state->dspp_to_enc_id; + hw_to_crtc_id = global_state->dspp_to_crtc_id; max_blks = ARRAY_SIZE(rm->dspp_blks); break; case DPU_HW_BLK_DSC: hw_blks = rm->dsc_blks; - hw_to_enc_id = global_state->dsc_to_enc_id; + hw_to_crtc_id = global_state->dsc_to_crtc_id; max_blks = ARRAY_SIZE(rm->dsc_blks); break; case DPU_HW_BLK_CDM: hw_blks = &rm->cdm_blk; - hw_to_enc_id = &global_state->cdm_to_enc_id; + hw_to_crtc_id = &global_state->cdm_to_crtc_id; max_blks = 1; break; + case DPU_HW_BLK_CWB: + hw_blks = rm->cwb_blks; + hw_to_crtc_id = global_state->cwb_to_crtc_id; + max_blks = ARRAY_SIZE(rm->cwb_blks); + break; default: DPU_ERROR("blk type %d not managed by rm\n", type); return 0; @@ -851,17 +927,31 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, num_blks = 0; for (i = 0; i < max_blks; i++) { - if (hw_to_enc_id[i] != enc_id) + if (hw_to_crtc_id[i] != crtc_id) continue; + if (type == DPU_HW_BLK_PINGPONG) { + struct dpu_hw_pingpong *pp = to_dpu_hw_pingpong(hw_blks[i]); + + if (pp->idx >= PINGPONG_CWB_0) + continue; + } + + if (type == DPU_HW_BLK_DCWB_PINGPONG) { + struct dpu_hw_pingpong *pp = to_dpu_hw_pingpong(hw_blks[i]); + + if (pp->idx < PINGPONG_CWB_0) + continue; + } + if (num_blks == blks_size) { - DPU_ERROR("More than %d resources assigned to enc %d\n", - blks_size, enc_id); + DPU_ERROR("More than %d resources assigned to crtc %d\n", + blks_size, crtc_id); break; } if (!hw_blks[i]) { - DPU_ERROR("Allocated resource %d unavailable to assign to enc %d\n", - type, enc_id); + DPU_ERROR("Allocated resource %d unavailable to assign to crtc %d\n", + type, crtc_id); break; } blks[num_blks++] = hw_blks[i]; @@ -896,38 +986,38 @@ void dpu_rm_print_state(struct drm_printer *p, drm_puts(p, "resource mapping:\n"); drm_puts(p, "\tpingpong="); - for (i = 0; i < ARRAY_SIZE(global_state->pingpong_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->pingpong_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->pingpong_blks[i], - global_state->pingpong_to_enc_id[i]); + global_state->pingpong_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tmixer="); - for (i = 0; i < ARRAY_SIZE(global_state->mixer_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->mixer_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->mixer_blks[i], - global_state->mixer_to_enc_id[i]); + global_state->mixer_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tctl="); - for (i = 0; i < ARRAY_SIZE(global_state->ctl_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->ctl_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->ctl_blks[i], - global_state->ctl_to_enc_id[i]); + global_state->ctl_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tdspp="); - for (i = 0; i < ARRAY_SIZE(global_state->dspp_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->dspp_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->dspp_blks[i], - global_state->dspp_to_enc_id[i]); + global_state->dspp_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tdsc="); - for (i = 0; i < ARRAY_SIZE(global_state->dsc_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->dsc_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->dsc_blks[i], - global_state->dsc_to_enc_id[i]); + global_state->dsc_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tcdm="); dpu_rm_print_state_helper(p, rm->cdm_blk, - global_state->cdm_to_enc_id); + global_state->cdm_to_crtc_id); drm_puts(p, "\n"); drm_puts(p, "\tsspp="); @@ -936,4 +1026,10 @@ void dpu_rm_print_state(struct drm_printer *p, dpu_rm_print_state_helper(p, rm->hw_sspp[i] ? &rm->hw_sspp[i]->base : NULL, global_state->sspp_to_crtc_id[i]); drm_puts(p, "\n"); + + drm_puts(p, "\tcwb="); + for (i = 0; i < ARRAY_SIZE(global_state->cwb_to_crtc_id); i++) + dpu_rm_print_state_helper(p, rm->cwb_blks[i], + global_state->cwb_to_crtc_id[i]); + drm_puts(p, "\n"); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h index 99bd594ee0d1..a19dbdb1b6f4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -51,14 +51,17 @@ struct dpu_rm_sspp_requirements { * @num_intf: number of interfaces the panel is mounted on * @num_dspp: number of dspp blocks used * @num_dsc: number of Display Stream Compression (DSC) blocks used - * @needs_cdm: indicates whether cdm block is needed for this display topology + * @num_cdm: indicates how many outputs are requesting cdm block for + * this display topology + * @cwb_enabled: indicates whether CWB is enabled for this display topology */ struct msm_display_topology { u32 num_lm; u32 num_intf; u32 num_dspp; u32 num_dsc; - bool needs_cdm; + int num_cdm; + bool cwb_enabled; }; int dpu_rm_init(struct drm_device *dev, @@ -69,12 +72,11 @@ int dpu_rm_init(struct drm_device *dev, int dpu_rm_reserve(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *drm_enc, - struct drm_crtc_state *crtc_state, + struct drm_crtc *crtc, struct msm_display_topology *topology); void dpu_rm_release(struct dpu_global_state *global_state, - struct drm_encoder *enc); + struct drm_crtc *crtc); struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, struct dpu_global_state *global_state, @@ -85,7 +87,7 @@ void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, struct drm_crtc *crtc); int dpu_rm_get_assigned_resources(struct dpu_rm *rm, - struct dpu_global_state *global_state, uint32_t enc_id, + struct dpu_global_state *global_state, struct drm_crtc *crtc, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size); void dpu_rm_print_state(struct drm_printer *p, diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c index 666de99a46a5..fc183fe37f56 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c @@ -3,6 +3,7 @@ * Copyright (c) 2014-2015 The Linux Foundation. All rights reserved. */ +#include <linux/string_choices.h> #include "mdp5_kms.h" #include "mdp5_ctl.h" @@ -233,7 +234,7 @@ int mdp5_ctl_set_encoder_state(struct mdp5_ctl *ctl, return -EINVAL; ctl->encoder_enabled = enabled; - DBG("intf_%d: %s", intf->num, enabled ? "on" : "off"); + DBG("intf_%d: %s", intf->num, str_on_off(enabled)); if (start_signal_needed(ctl, pipeline)) { send_start_signal(ctl); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 9c463ae2f8fa..d8633a596f8d 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -11,6 +11,7 @@ #include <linux/phy/phy.h> #include <linux/phy/phy-dp.h> #include <linux/pm_opp.h> +#include <linux/string_choices.h> #include <drm/display/drm_dp_helper.h> #include <drm/drm_fixed.h> @@ -1366,9 +1367,9 @@ int msm_dp_ctrl_core_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "enable core clocks \n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); return 0; } @@ -1385,9 +1386,9 @@ void msm_dp_ctrl_core_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "disable core clocks \n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); } static int msm_dp_ctrl_link_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) @@ -1416,9 +1417,9 @@ static int msm_dp_ctrl_link_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "enable link clocks\n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); return 0; } @@ -1435,9 +1436,9 @@ static void msm_dp_ctrl_link_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "disabled link clocks\n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); } static int msm_dp_ctrl_enable_mainlink_clocks(struct msm_dp_ctrl_private *ctrl) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index a542d2781a09..bbc47d86ae9e 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -11,6 +11,7 @@ #include <linux/of_irq.h> #include <linux/phy/phy.h> #include <linux/delay.h> +#include <linux/string_choices.h> #include <drm/display/drm_dp_aux_bus.h> #include <drm/drm_edid.h> @@ -343,8 +344,7 @@ static int msm_dp_display_send_hpd_notification(struct msm_dp_display_private *d { if ((hpd && dp->msm_dp_display.link_ready) || (!hpd && !dp->msm_dp_display.link_ready)) { - drm_dbg_dp(dp->drm_dev, "HPD already %s\n", - (hpd ? "on" : "off")); + drm_dbg_dp(dp->drm_dev, "HPD already %s\n", str_on_off(hpd)); return 0; } @@ -367,6 +367,19 @@ static int msm_dp_display_send_hpd_notification(struct msm_dp_display_private *d return 0; } +static void msm_dp_display_lttpr_init(struct msm_dp_display_private *dp) +{ + u8 lttpr_caps[DP_LTTPR_COMMON_CAP_SIZE]; + int rc; + + if (drm_dp_read_lttpr_common_caps(dp->aux, dp->panel->dpcd, lttpr_caps)) + return; + + rc = drm_dp_lttpr_init(dp->aux, drm_dp_lttpr_count(lttpr_caps)); + if (rc) + DRM_ERROR("failed to set LTTPRs transparency mode, rc=%d\n", rc); +} + static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) { struct drm_connector *connector = dp->msm_dp_display.connector; @@ -377,6 +390,8 @@ static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) if (rc) goto end; + msm_dp_display_lttpr_init(dp); + msm_dp_link_process_request(dp->link); if (!dp->msm_dp_display.is_edp) diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index 022b3e815cf3..cca57e56c906 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -3,6 +3,7 @@ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. */ +#include <linux/string_choices.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_atomic.h> #include <drm/drm_bridge.h> @@ -25,7 +26,7 @@ static enum drm_connector_status msm_dp_bridge_detect(struct drm_bridge *bridge) dp = to_dp_bridge(bridge)->msm_dp_display; drm_dbg_dp(dp->drm_dev, "link_ready = %s\n", - (dp->link_ready) ? "true" : "false"); + str_true_false(dp->link_ready)); return (dp->link_ready) ? connector_status_connected : connector_status_disconnected; @@ -41,7 +42,7 @@ static int msm_dp_bridge_atomic_check(struct drm_bridge *bridge, dp = to_dp_bridge(bridge)->msm_dp_display; drm_dbg_dp(dp->drm_dev, "link_ready = %s\n", - (dp->link_ready) ? "true" : "false"); + str_true_false(dp->link_ready)); /* * There is no protection in the DRM framework to check if the display diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 007311c21fda..4d75529c0e85 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -179,18 +179,18 @@ struct msm_dsi_host { int irq; }; - static inline u32 dsi_read(struct msm_dsi_host *msm_host, u32 reg) { return readl(msm_host->ctrl_base + reg); } + static inline void dsi_write(struct msm_dsi_host *msm_host, u32 reg, u32 data) { writel(data, msm_host->ctrl_base + reg); } -static const struct msm_dsi_cfg_handler *dsi_get_config( - struct msm_dsi_host *msm_host) +static const struct msm_dsi_cfg_handler * +dsi_get_config(struct msm_dsi_host *msm_host) { const struct msm_dsi_cfg_handler *cfg_hnd = NULL; struct device *dev = &msm_host->pdev->dev; @@ -200,7 +200,8 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( ahb_clk = msm_clk_get(msm_host->pdev, "iface"); if (IS_ERR(ahb_clk)) { - pr_err("%s: cannot get interface clock\n", __func__); + dev_err_probe(dev, PTR_ERR(ahb_clk), "%s: cannot get interface clock\n", + __func__); goto exit; } @@ -208,13 +209,13 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( ret = clk_prepare_enable(ahb_clk); if (ret) { - pr_err("%s: unable to enable ahb_clk\n", __func__); + dev_err_probe(dev, ret, "%s: unable to enable ahb_clk\n", __func__); goto runtime_put; } ret = dsi_get_version(msm_host->ctrl_base, &major, &minor); if (ret) { - pr_err("%s: Invalid version\n", __func__); + dev_err_probe(dev, ret, "%s: Invalid version\n", __func__); goto disable_clks; } @@ -281,42 +282,31 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) msm_host->num_bus_clks = cfg->num_bus_clks; ret = devm_clk_bulk_get(&pdev->dev, msm_host->num_bus_clks, msm_host->bus_clks); - if (ret < 0) { - dev_err(&pdev->dev, "Unable to get clocks, ret = %d\n", ret); - goto exit; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Unable to get clocks\n"); /* get link and source clocks */ msm_host->byte_clk = msm_clk_get(pdev, "byte"); - if (IS_ERR(msm_host->byte_clk)) { - ret = PTR_ERR(msm_host->byte_clk); - pr_err("%s: can't find dsi_byte clock. ret=%d\n", - __func__, ret); - msm_host->byte_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->byte_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->byte_clk), + "%s: can't find dsi_byte clock\n", + __func__); msm_host->pixel_clk = msm_clk_get(pdev, "pixel"); - if (IS_ERR(msm_host->pixel_clk)) { - ret = PTR_ERR(msm_host->pixel_clk); - pr_err("%s: can't find dsi_pixel clock. ret=%d\n", - __func__, ret); - msm_host->pixel_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->pixel_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->pixel_clk), + "%s: can't find dsi_pixel clock\n", + __func__); msm_host->esc_clk = msm_clk_get(pdev, "core"); - if (IS_ERR(msm_host->esc_clk)) { - ret = PTR_ERR(msm_host->esc_clk); - pr_err("%s: can't find dsi_esc clock. ret=%d\n", - __func__, ret); - msm_host->esc_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->esc_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->esc_clk), + "%s: can't find dsi_esc clock\n", + __func__); if (cfg_hnd->ops->clk_init_ver) ret = cfg_hnd->ops->clk_init_ver(msm_host); -exit: + return ret; } @@ -380,7 +370,6 @@ int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host) return 0; } - int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) { int ret; @@ -598,7 +587,6 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi) DBG("pclk=%lu, bclk=%lu", msm_host->pixel_clk_rate, msm_host->byte_clk_rate); - } int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi) @@ -687,8 +675,8 @@ static inline enum dsi_traffic_mode dsi_get_traffic_mode(const u32 mode_flags) return NON_BURST_SYNCH_EVENT; } -static inline enum dsi_vid_dst_format dsi_get_vid_fmt( - const enum mipi_dsi_pixel_format mipi_fmt) +static inline enum dsi_vid_dst_format +dsi_get_vid_fmt(const enum mipi_dsi_pixel_format mipi_fmt) { switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return VID_DST_FORMAT_RGB888; @@ -699,8 +687,8 @@ static inline enum dsi_vid_dst_format dsi_get_vid_fmt( } } -static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt( - const enum mipi_dsi_pixel_format mipi_fmt) +static inline enum dsi_cmd_dst_format +dsi_get_cmd_fmt(const enum mipi_dsi_pixel_format mipi_fmt) { switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return CMD_DST_FORMAT_RGB888; @@ -846,7 +834,7 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host, dsi_write(msm_host, REG_DSI_CPHY_MODE_CTRL, BIT(0)); } -static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode, u32 hdisplay) +static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode) { struct drm_dsc_config *dsc = msm_host->dsc; u32 reg, reg_ctrl, reg_ctrl2; @@ -858,7 +846,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod /* first calculate dsc parameters and then program * compress mode registers */ - slice_per_intf = msm_dsc_get_slices_per_intf(dsc, hdisplay); + slice_per_intf = dsc->slice_count; total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf; bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */ @@ -991,7 +979,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) { if (msm_host->dsc) - dsi_update_dsc_timing(msm_host, false, mode->hdisplay); + dsi_update_dsc_timing(msm_host, false); dsi_write(msm_host, REG_DSI_ACTIVE_H, DSI_ACTIVE_H_START(ha_start) | @@ -1012,7 +1000,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) DSI_ACTIVE_VSYNC_VPOS_END(vs_end)); } else { /* command mode */ if (msm_host->dsc) - dsi_update_dsc_timing(msm_host, true, mode->hdisplay); + dsi_update_dsc_timing(msm_host, true); /* image data and 1 byte write_memory_start cmd */ if (!msm_host->dsc) @@ -1292,14 +1280,15 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host, static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg) { u8 *data = msg->rx_buf; + if (data && (msg->rx_len >= 1)) { *data = buf[1]; /* strip out dcs type */ return 1; - } else { - pr_err("%s: read data does not match with rx_buf len %zu\n", - __func__, msg->rx_len); - return -EINVAL; } + + pr_err("%s: read data does not match with rx_buf len %zu\n", + __func__, msg->rx_len); + return -EINVAL; } /* @@ -1308,15 +1297,16 @@ static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg) static int dsi_short_read2_resp(u8 *buf, const struct mipi_dsi_msg *msg) { u8 *data = msg->rx_buf; + if (data && (msg->rx_len >= 2)) { data[0] = buf[1]; /* strip out dcs type */ data[1] = buf[2]; return 2; - } else { - pr_err("%s: read data does not match with rx_buf len %zu\n", - __func__, msg->rx_len); - return -EINVAL; } + + pr_err("%s: read data does not match with rx_buf len %zu\n", + __func__, msg->rx_len); + return -EINVAL; } static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg) @@ -1376,8 +1366,9 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len) ret = -ETIMEDOUT; else ret = len; - } else + } else { ret = len; + } return ret; } @@ -1445,11 +1436,12 @@ static int dsi_cmds2buf_tx(struct msm_dsi_host *msm_host, return len; } - /* for video mode, do not send cmds more than - * one pixel line, since it only transmit it - * during BLLP. - */ - /* TODO: if the command is sent in LP mode, the bit rate is only + /* + * for video mode, do not send cmds more than + * one pixel line, since it only transmit it + * during BLLP. + * + * TODO: if the command is sent in LP mode, the bit rate is only * half of esc clk rate. In this case, if the video is already * actively streaming, we need to check more carefully if the * command can be fit into one BLLP. @@ -1767,8 +1759,20 @@ static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc return -EINVAL; } - if (dsc->bits_per_component != 8) { - DRM_DEV_ERROR(&msm_host->pdev->dev, "DSI does not support bits_per_component != 8 yet\n"); + switch (dsc->bits_per_component) { + case 8: + case 10: + case 12: + /* + * Only 8, 10, and 12 bpc are supported for DSC 1.1 block. + * If additional bpc values need to be supported, update + * this quard with the appropriate DSC version verification. + */ + break; + default: + DRM_DEV_ERROR(&msm_host->pdev->dev, + "Unsupported bits_per_component value: %d\n", + dsc->bits_per_component); return -EOPNOTSUPP; } @@ -1779,7 +1783,7 @@ static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc drm_dsc_set_const_params(dsc); drm_dsc_set_rc_buf_thresh(dsc); - /* handle only bpp = bpc = 8, pre-SCR panels */ + /* DPU supports only pre-SCR panels */ ret = drm_dsc_setup_rc_params(dsc, DRM_DSC_1_1_PRE_SCR); if (ret) { DRM_DEV_ERROR(&msm_host->pdev->dev, "could not find DSC RC parameters\n"); @@ -1827,8 +1831,15 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) __func__, ret); goto err; } - if (!ret) + if (!ret) { msm_dsi->te_source = devm_kstrdup(dev, te_source, GFP_KERNEL); + if (!msm_dsi->te_source) { + DRM_DEV_ERROR(dev, "%s: failed to allocate te_source\n", + __func__); + ret = -ENOMEM; + goto err; + } + } ret = 0; if (of_property_present(np, "syscon-sfpb")) { @@ -1874,39 +1885,35 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) int ret; msm_host = devm_kzalloc(&pdev->dev, sizeof(*msm_host), GFP_KERNEL); - if (!msm_host) { + if (!msm_host) return -ENOMEM; - } msm_host->pdev = pdev; msm_dsi->host = &msm_host->base; ret = dsi_host_parse_dt(msm_host); - if (ret) { - pr_err("%s: failed to parse dt\n", __func__); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "%s: failed to parse dt\n", + __func__); msm_host->ctrl_base = msm_ioremap_size(pdev, "dsi_ctrl", &msm_host->ctrl_size); - if (IS_ERR(msm_host->ctrl_base)) { - pr_err("%s: unable to map Dsi ctrl base\n", __func__); - return PTR_ERR(msm_host->ctrl_base); - } + if (IS_ERR(msm_host->ctrl_base)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->ctrl_base), + "%s: unable to map Dsi ctrl base\n", __func__); pm_runtime_enable(&pdev->dev); msm_host->cfg_hnd = dsi_get_config(msm_host); - if (!msm_host->cfg_hnd) { - pr_err("%s: get config failed\n", __func__); - return -EINVAL; - } + if (!msm_host->cfg_hnd) + return dev_err_probe(&pdev->dev, -EINVAL, + "%s: get config failed\n", __func__); cfg = msm_host->cfg_hnd->cfg; msm_host->id = dsi_host_get_id(msm_host); - if (msm_host->id < 0) { - pr_err("%s: unable to identify DSI host index\n", __func__); - return msm_host->id; - } + if (msm_host->id < 0) + return dev_err_probe(&pdev->dev, msm_host->id, + "%s: unable to identify DSI host index\n", + __func__); /* fixup base address by io offset */ msm_host->ctrl_base += cfg->io_offset; @@ -1918,42 +1925,32 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) return ret; ret = dsi_clk_init(msm_host); - if (ret) { - pr_err("%s: unable to initialize dsi clks\n", __func__); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "%s: unable to initialize dsi clks\n", __func__); msm_host->rx_buf = devm_kzalloc(&pdev->dev, SZ_4K, GFP_KERNEL); - if (!msm_host->rx_buf) { - pr_err("%s: alloc rx temp buf failed\n", __func__); + if (!msm_host->rx_buf) return -ENOMEM; - } ret = devm_pm_opp_set_clkname(&pdev->dev, "byte"); if (ret) return ret; /* OPP table is optional */ ret = devm_pm_opp_of_add_table(&pdev->dev); - if (ret && ret != -ENODEV) { - dev_err(&pdev->dev, "invalid OPP table in device tree\n"); - return ret; - } + if (ret && ret != -ENODEV) + return dev_err_probe(&pdev->dev, ret, "invalid OPP table in device tree\n"); msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (!msm_host->irq) { - dev_err(&pdev->dev, "failed to get irq\n"); - return -EINVAL; - } + if (!msm_host->irq) + return dev_err_probe(&pdev->dev, -EINVAL, "failed to get irq\n"); /* do not autoenable, will be enabled later */ ret = devm_request_irq(&pdev->dev, msm_host->irq, dsi_host_irq, IRQF_TRIGGER_HIGH | IRQF_NO_AUTOEN, "dsi_isr", msm_host); - if (ret < 0) { - dev_err(&pdev->dev, "failed to request IRQ%u: %d\n", - msm_host->irq, ret); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "failed to request IRQ%u\n", + msm_host->irq); init_completion(&msm_host->dma_comp); init_completion(&msm_host->video_comp); diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index a210b7c9e5ca..4fabb01345aa 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -74,17 +74,35 @@ static int dsi_mgr_setup_components(int id) int ret; if (!IS_BONDED_DSI()) { + /* + * Set the usecase before calling msm_dsi_host_register(), which would + * already program the PLL source mux based on a default usecase. + */ + msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); + msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); + ret = msm_dsi_host_register(msm_dsi->host); if (ret) return ret; - - msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); - msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); } else if (other_dsi) { struct msm_dsi *master_link_dsi = IS_MASTER_DSI_LINK(id) ? msm_dsi : other_dsi; struct msm_dsi *slave_link_dsi = IS_MASTER_DSI_LINK(id) ? other_dsi : msm_dsi; + + /* + * PLL0 is to drive both DSI link clocks in bonded DSI mode. + * + * Set the usecase before calling msm_dsi_host_register(), which would + * already program the PLL source mux based on a default usecase. + */ + msm_dsi_phy_set_usecase(clk_master_dsi->phy, + MSM_DSI_PHY_MASTER); + msm_dsi_phy_set_usecase(clk_slave_dsi->phy, + MSM_DSI_PHY_SLAVE); + msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); + msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy); + /* Register slave host first, so that slave DSI device * has a chance to probe, and do not block the master * DSI device's probe. @@ -98,14 +116,6 @@ static int dsi_mgr_setup_components(int id) ret = msm_dsi_host_register(master_link_dsi->host); if (ret) return ret; - - /* PLL0 is to drive both 2 DSI link clocks in bonded DSI mode. */ - msm_dsi_phy_set_usecase(clk_master_dsi->phy, - MSM_DSI_PHY_MASTER); - msm_dsi_phy_set_usecase(clk_slave_dsi->phy, - MSM_DSI_PHY_SLAVE); - msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); - msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy); } return 0; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 8985818bb2e0..1925418d9999 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -6,6 +6,7 @@ #ifndef __DSI_PHY_H__ #define __DSI_PHY_H__ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk-provider.h> #include <linux/delay.h> #include <linux/regulator/consumer.h> @@ -84,9 +85,7 @@ struct msm_dsi_dphy_timing { u8 hs_halfbyte_en_ckln; }; -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 -#define NUM_PROVIDED_CLKS 2 +#define NUM_PROVIDED_CLKS (DSI_PIXEL_PLL_CLK + 1) #define DSI_LANE_MAX 5 diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 677c62571811..9812b4d69197 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 2c3cbe0f2870..3a1c8ece6657 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2016, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/delay.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index 1383e3a4e050..90348a2af3e9 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2015, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index 5311ab7f3c70..f3643320ff2f 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -3,6 +3,7 @@ * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk-provider.h> #include <linux/delay.h> 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 798168180c1a..a92decbee5b5 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -3,6 +3,8 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> @@ -305,7 +307,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *confi writel(pll->phy->cphy_mode ? 0x00 : 0x10, base + REG_DSI_7nm_PHY_PLL_CMODE_1); writel(config->pll_clock_inverters, - base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS); + base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS_1); } static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, @@ -572,11 +574,11 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) cached->pll_out_div &= 0x3; cmn_clk_cfg0 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); - cached->bit_clk_div = cmn_clk_cfg0 & 0xf; - cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; + cached->bit_clk_div = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0__MASK, cmn_clk_cfg0); + cached->pix_clk_div = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4__MASK, cmn_clk_cfg0); cmn_clk_cfg1 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - cached->pll_mux = cmn_clk_cfg1 & 0x3; + cached->pll_mux = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, cmn_clk_cfg1); DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", pll_7nm->phy->id, cached->pll_out_div, cached->bit_clk_div, @@ -598,7 +600,8 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) dsi_pll_cmn_clk_cfg0_write(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) | DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div)); - dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux); + dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, + cached->pll_mux); ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw, pll_7nm->vco_current_rate, @@ -736,11 +739,9 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide * don't register a pclk_mux clock and just use post_out_div instead */ if (pll_7nm->phy->cphy_mode) { - u32 data; - - data = readl(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - writel(data | 3, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - + dsi_pll_cmn_clk_cfg1_update(pll_7nm, + DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, + DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL(3)); phy_pll_out_dsi_parent = pll_post_out_div; } else { snprintf(clk_name, sizeof(clk_name), "dsi%d_pclk_mux", pll_7nm->phy->id); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 37b3809c6bdd..248541ff4492 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -12,8 +12,8 @@ #include <drm/drm_bridge_connector.h> #include <drm/drm_of.h> +#include <drm/display/drm_hdmi_state_helper.h> -#include <sound/hdmi-codec.h> #include "hdmi.h" void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on) @@ -24,7 +24,7 @@ void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on) spin_lock_irqsave(&hdmi->reg_lock, flags); if (power_on) { ctrl |= HDMI_CTRL_ENABLE; - if (!hdmi->hdmi_mode) { + if (!hdmi->connector->display_info.is_hdmi) { ctrl |= HDMI_CTRL_HDMI; hdmi_write(hdmi, REG_HDMI_CTRL, ctrl); ctrl &= ~HDMI_CTRL_HDMI; @@ -165,8 +165,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, hdmi->dev = dev; hdmi->encoder = encoder; - hdmi_audio_infoframe_init(&hdmi->audio.infoframe); - ret = msm_hdmi_bridge_init(hdmi); if (ret) { DRM_DEV_ERROR(dev->dev, "failed to create HDMI bridge: %d\n", ret); @@ -246,111 +244,6 @@ static const struct hdmi_platform_config hdmi_tx_8974_config = { .hpd_freq = hpd_clk_freq_8x74, }; -/* - * HDMI audio codec callbacks - */ -static int msm_hdmi_audio_hw_params(struct device *dev, void *data, - struct hdmi_codec_daifmt *daifmt, - struct hdmi_codec_params *params) -{ - struct hdmi *hdmi = dev_get_drvdata(dev); - unsigned int chan; - unsigned int channel_allocation = 0; - unsigned int rate; - unsigned int level_shift = 0; /* 0dB */ - bool down_mix = false; - - DRM_DEV_DEBUG(dev, "%u Hz, %d bit, %d channels\n", params->sample_rate, - params->sample_width, params->cea.channels); - - switch (params->cea.channels) { - case 2: - /* FR and FL speakers */ - channel_allocation = 0; - chan = MSM_HDMI_AUDIO_CHANNEL_2; - break; - case 4: - /* FC, LFE, FR and FL speakers */ - channel_allocation = 0x3; - chan = MSM_HDMI_AUDIO_CHANNEL_4; - break; - case 6: - /* RR, RL, FC, LFE, FR and FL speakers */ - channel_allocation = 0x0B; - chan = MSM_HDMI_AUDIO_CHANNEL_6; - break; - case 8: - /* FRC, FLC, RR, RL, FC, LFE, FR and FL speakers */ - channel_allocation = 0x1F; - chan = MSM_HDMI_AUDIO_CHANNEL_8; - break; - default: - return -EINVAL; - } - - switch (params->sample_rate) { - case 32000: - rate = HDMI_SAMPLE_RATE_32KHZ; - break; - case 44100: - rate = HDMI_SAMPLE_RATE_44_1KHZ; - break; - case 48000: - rate = HDMI_SAMPLE_RATE_48KHZ; - break; - case 88200: - rate = HDMI_SAMPLE_RATE_88_2KHZ; - break; - case 96000: - rate = HDMI_SAMPLE_RATE_96KHZ; - break; - case 176400: - rate = HDMI_SAMPLE_RATE_176_4KHZ; - break; - case 192000: - rate = HDMI_SAMPLE_RATE_192KHZ; - break; - default: - DRM_DEV_ERROR(dev, "rate[%d] not supported!\n", - params->sample_rate); - return -EINVAL; - } - - msm_hdmi_audio_set_sample_rate(hdmi, rate); - msm_hdmi_audio_info_setup(hdmi, 1, chan, channel_allocation, - level_shift, down_mix); - - return 0; -} - -static void msm_hdmi_audio_shutdown(struct device *dev, void *data) -{ - struct hdmi *hdmi = dev_get_drvdata(dev); - - msm_hdmi_audio_info_setup(hdmi, 0, 0, 0, 0, 0); -} - -static const struct hdmi_codec_ops msm_hdmi_audio_codec_ops = { - .hw_params = msm_hdmi_audio_hw_params, - .audio_shutdown = msm_hdmi_audio_shutdown, -}; - -static struct hdmi_codec_pdata codec_data = { - .ops = &msm_hdmi_audio_codec_ops, - .max_i2s_channels = 8, - .i2s = 1, -}; - -static int msm_hdmi_register_audio_driver(struct hdmi *hdmi, struct device *dev) -{ - hdmi->audio_pdev = platform_device_register_data(dev, - HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &codec_data, - sizeof(codec_data)); - return PTR_ERR_OR_ZERO(hdmi->audio_pdev); -} - static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) { struct msm_drm_private *priv = dev_get_drvdata(master); @@ -362,12 +255,6 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) return err; priv->hdmi = hdmi; - err = msm_hdmi_register_audio_driver(hdmi, dev); - if (err) { - DRM_ERROR("Failed to attach an audio codec %d\n", err); - hdmi->audio_pdev = NULL; - } - return 0; } @@ -377,9 +264,6 @@ static void msm_hdmi_unbind(struct device *dev, struct device *master, struct msm_drm_private *priv = dev_get_drvdata(master); if (priv->hdmi) { - if (priv->hdmi->audio_pdev) - platform_device_unregister(priv->hdmi->audio_pdev); - if (priv->hdmi->bridge) msm_hdmi_hpd_disable(priv->hdmi); diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index a62d2aedfbb7..a5f481c39277 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -24,8 +24,8 @@ struct hdmi_platform_config; struct hdmi_audio { bool enabled; - struct hdmi_audio_infoframe infoframe; int rate; + int channels; }; struct hdmi_hdcp_ctrl; @@ -33,7 +33,6 @@ struct hdmi_hdcp_ctrl; struct hdmi { struct drm_device *dev; struct platform_device *pdev; - struct platform_device *audio_pdev; const struct hdmi_platform_config *config; @@ -67,8 +66,6 @@ struct hdmi { /* the encoder we are hooked to (outside of hdmi block) */ struct drm_encoder *encoder; - bool hdmi_mode; /* are we in hdmi mode? */ - int irq; struct workqueue_struct *workq; @@ -207,26 +204,16 @@ static inline int msm_hdmi_pll_8998_init(struct platform_device *pdev) /* * audio: */ -/* Supported HDMI Audio channels and rates */ -#define MSM_HDMI_AUDIO_CHANNEL_2 0 -#define MSM_HDMI_AUDIO_CHANNEL_4 1 -#define MSM_HDMI_AUDIO_CHANNEL_6 2 -#define MSM_HDMI_AUDIO_CHANNEL_8 3 - -#define HDMI_SAMPLE_RATE_32KHZ 0 -#define HDMI_SAMPLE_RATE_44_1KHZ 1 -#define HDMI_SAMPLE_RATE_48KHZ 2 -#define HDMI_SAMPLE_RATE_88_2KHZ 3 -#define HDMI_SAMPLE_RATE_96KHZ 4 -#define HDMI_SAMPLE_RATE_176_4KHZ 5 -#define HDMI_SAMPLE_RATE_192KHZ 6 +struct hdmi_codec_daifmt; +struct hdmi_codec_params; int msm_hdmi_audio_update(struct hdmi *hdmi); -int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled, - uint32_t num_of_channels, uint32_t channel_allocation, - uint32_t level_shift, bool down_mix); -void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate); - +int msm_hdmi_bridge_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params); +void msm_hdmi_bridge_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge); /* * hdmi bridge: diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c index 4c2058c4adc1..8bb975e82c17 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c @@ -4,11 +4,13 @@ * Author: Rob Clark <robdclark@gmail.com> */ +#include <drm/display/drm_hdmi_state_helper.h> + #include <linux/hdmi.h> -#include "hdmi.h" -/* maps MSM_HDMI_AUDIO_CHANNEL_n consts used by audio driver to # of channels: */ -static int nchannels[] = { 2, 4, 6, 8 }; +#include <sound/hdmi-codec.h> + +#include "hdmi.h" /* Supported HDMI Audio sample rates */ #define MSM_HDMI_SAMPLE_RATE_32KHZ 0 @@ -74,16 +76,17 @@ static const struct hdmi_msm_audio_arcs *get_arcs(unsigned long int pixclock) int msm_hdmi_audio_update(struct hdmi *hdmi) { struct hdmi_audio *audio = &hdmi->audio; - struct hdmi_audio_infoframe *info = &audio->infoframe; const struct hdmi_msm_audio_arcs *arcs = NULL; bool enabled = audio->enabled; uint32_t acr_pkt_ctrl, vbi_pkt_ctrl, aud_pkt_ctrl; - uint32_t infofrm_ctrl, audio_config; + uint32_t audio_config; + + if (!hdmi->connector->display_info.is_hdmi) + return -EINVAL; + + DBG("audio: enabled=%d, channels=%d, rate=%d", + audio->enabled, audio->channels, audio->rate); - DBG("audio: enabled=%d, channels=%d, channel_allocation=0x%x, " - "level_shift_value=%d, downmix_inhibit=%d, rate=%d", - audio->enabled, info->channels, info->channel_allocation, - info->level_shift_value, info->downmix_inhibit, audio->rate); DBG("video: power_on=%d, pixclock=%lu", hdmi->power_on, hdmi->pixclock); if (enabled && !(hdmi->power_on && hdmi->pixclock)) { @@ -104,7 +107,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) acr_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_ACR_PKT_CTRL); vbi_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_VBI_PKT_CTRL); aud_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_AUDIO_PKT_CTRL1); - infofrm_ctrl = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); audio_config = hdmi_read(hdmi, REG_HDMI_AUDIO_CFG); /* Clear N/CTS selection bits */ @@ -113,7 +115,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) if (enabled) { uint32_t n, cts, multiplier; enum hdmi_acr_cts select; - uint8_t buf[14]; n = arcs->lut[audio->rate].n; cts = arcs->lut[audio->rate].cts; @@ -155,20 +156,12 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) HDMI_ACR_1_N(n)); hdmi_write(hdmi, REG_HDMI_AUDIO_PKT_CTRL2, - COND(info->channels != 2, HDMI_AUDIO_PKT_CTRL2_LAYOUT) | + COND(audio->channels != 2, HDMI_AUDIO_PKT_CTRL2_LAYOUT) | HDMI_AUDIO_PKT_CTRL2_OVERRIDE); acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_CONT; acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_SEND; - /* configure infoframe: */ - hdmi_audio_infoframe_pack(info, buf, sizeof(buf)); - hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0, - (buf[3] << 0) | (buf[4] << 8) | - (buf[5] << 16) | (buf[6] << 24)); - hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1, - (buf[7] << 0) | (buf[8] << 8)); - hdmi_write(hdmi, REG_HDMI_GC, 0); vbi_pkt_ctrl |= HDMI_VBI_PKT_CTRL_GC_ENABLE; @@ -176,11 +169,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) aud_pkt_ctrl |= HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; - audio_config &= ~HDMI_AUDIO_CFG_FIFO_WATERMARK__MASK; audio_config |= HDMI_AUDIO_CFG_FIFO_WATERMARK(4); audio_config |= HDMI_AUDIO_CFG_ENGINE_ENABLE; @@ -190,17 +178,12 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) vbi_pkt_ctrl &= ~HDMI_VBI_PKT_CTRL_GC_ENABLE; vbi_pkt_ctrl &= ~HDMI_VBI_PKT_CTRL_GC_EVERY_FRAME; aud_pkt_ctrl &= ~HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; audio_config &= ~HDMI_AUDIO_CFG_ENGINE_ENABLE; } hdmi_write(hdmi, REG_HDMI_ACR_PKT_CTRL, acr_pkt_ctrl); hdmi_write(hdmi, REG_HDMI_VBI_PKT_CTRL, vbi_pkt_ctrl); hdmi_write(hdmi, REG_HDMI_AUDIO_PKT_CTRL1, aud_pkt_ctrl); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, infofrm_ctrl); hdmi_write(hdmi, REG_HDMI_AUD_INT, COND(enabled, HDMI_AUD_INT_AUD_FIFO_URUN_INT) | @@ -214,41 +197,72 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) return 0; } -int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled, - uint32_t num_of_channels, uint32_t channel_allocation, - uint32_t level_shift, bool down_mix) +int msm_hdmi_bridge_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) { - struct hdmi_audio *audio; - - if (!hdmi) - return -ENXIO; - - audio = &hdmi->audio; - - if (num_of_channels >= ARRAY_SIZE(nchannels)) + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + unsigned int rate; + int ret; + + drm_dbg_driver(bridge->dev, "%u Hz, %d bit, %d channels\n", + params->sample_rate, + params->sample_width, + params->cea.channels); + + switch (params->sample_rate) { + case 32000: + rate = MSM_HDMI_SAMPLE_RATE_32KHZ; + break; + case 44100: + rate = MSM_HDMI_SAMPLE_RATE_44_1KHZ; + break; + case 48000: + rate = MSM_HDMI_SAMPLE_RATE_48KHZ; + break; + case 88200: + rate = MSM_HDMI_SAMPLE_RATE_88_2KHZ; + break; + case 96000: + rate = MSM_HDMI_SAMPLE_RATE_96KHZ; + break; + case 176400: + rate = MSM_HDMI_SAMPLE_RATE_176_4KHZ; + break; + case 192000: + rate = MSM_HDMI_SAMPLE_RATE_192KHZ; + break; + default: + drm_err(bridge->dev, "rate[%d] not supported!\n", + params->sample_rate); return -EINVAL; + } + + ret = drm_atomic_helper_connector_hdmi_update_audio_infoframe(connector, + ¶ms->cea); + if (ret) + return ret; - audio->enabled = enabled; - audio->infoframe.channels = nchannels[num_of_channels]; - audio->infoframe.channel_allocation = channel_allocation; - audio->infoframe.level_shift_value = level_shift; - audio->infoframe.downmix_inhibit = down_mix; + hdmi->audio.rate = rate; + hdmi->audio.channels = params->cea.channels; + hdmi->audio.enabled = true; return msm_hdmi_audio_update(hdmi); } -void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate) +void msm_hdmi_bridge_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge) { - struct hdmi_audio *audio; - - if (!hdmi) - return; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; - audio = &hdmi->audio; + drm_atomic_helper_connector_hdmi_clear_audio_infoframe(connector); - if ((rate < 0) || (rate >= MSM_HDMI_SAMPLE_RATE_MAX)) - return; + hdmi->audio.rate = 0; + hdmi->audio.channels = 2; + hdmi->audio.enabled = false; - audio->rate = rate; msm_hdmi_audio_update(hdmi); } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 4a5b5112227f..1456354c8af4 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -7,6 +7,8 @@ #include <linux/delay.h> #include <drm/drm_bridge_connector.h> #include <drm/drm_edid.h> +#include <drm/display/drm_hdmi_helper.h> +#include <drm/display/drm_hdmi_state_helper.h> #include "msm_kms.h" #include "hdmi.h" @@ -67,24 +69,20 @@ static void power_off(struct drm_bridge *bridge) } #define AVI_IFRAME_LINE_NUMBER 1 +#define SPD_IFRAME_LINE_NUMBER 1 +#define VENSPEC_IFRAME_LINE_NUMBER 3 -static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi) +static int msm_hdmi_config_avi_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) { - struct drm_crtc *crtc = hdmi->encoder->crtc; - const struct drm_display_mode *mode = &crtc->state->adjusted_mode; - union hdmi_infoframe frame; - u8 buffer[HDMI_INFOFRAME_SIZE(AVI)]; + u32 buf[4] = {}; u32 val; - int len; + int i; - drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, - hdmi->connector, mode); - - len = hdmi_infoframe_pack(&frame, buffer, sizeof(buffer)); - if (len < 0) { + if (len != HDMI_INFOFRAME_SIZE(AVI) || len - 3 > sizeof(buf)) { DRM_DEV_ERROR(&hdmi->pdev->dev, "failed to configure avi infoframe\n"); - return; + return -EINVAL; } /* @@ -93,57 +91,245 @@ static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi) * written to the LSB byte of AVI_INFO0 and the version is written to * the third byte from the LSB of AVI_INFO3 */ - hdmi_write(hdmi, REG_HDMI_AVI_INFO(0), + memcpy(buf, &buffer[3], len - 3); + + buf[3] |= buffer[1] << 24; + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_AVI_INFO(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val |= HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; + val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + return 0; +} + +static int msm_hdmi_config_audio_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 val; + + if (len != HDMI_INFOFRAME_SIZE(AUDIO)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure audio infoframe\n"); + return -EINVAL; + } + + hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0, buffer[3] | buffer[4] << 8 | buffer[5] << 16 | buffer[6] << 24); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(1), + hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1, buffer[7] | buffer[8] << 8 | buffer[9] << 16 | buffer[10] << 24); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(2), - buffer[11] | - buffer[12] << 8 | - buffer[13] << 16 | - buffer[14] << 24); + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(3), - buffer[15] | - buffer[16] << 8 | - buffer[1] << 24); + return 0; +} - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, - HDMI_INFOFRAME_CTRL0_AVI_SEND | - HDMI_INFOFRAME_CTRL0_AVI_CONT); +static int msm_hdmi_config_spd_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 buf[7] = {}; + u32 val; + int i; - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); - val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; - val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + if (len != HDMI_INFOFRAME_SIZE(SPD) || len - 3 > sizeof(buf)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure SPD infoframe\n"); + return -EINVAL; + } + + /* checksum gets written together with the body of the frame */ + hdmi_write(hdmi, REG_HDMI_GENERIC1_HDR, + buffer[0] | + buffer[1] << 8 | + buffer[2] << 16); + + memcpy(buf, &buffer[3], len - 3); + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_GENERIC1(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val |= HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE(SPD_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + return 0; } -static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge) +static int msm_hdmi_config_hdmi_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 buf[7] = {}; + u32 val; + int i; + + if (len < HDMI_INFOFRAME_HEADER_SIZE + HDMI_VENDOR_INFOFRAME_SIZE || + len - 3 > sizeof(buf)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure HDMI infoframe\n"); + return -EINVAL; + } + + /* checksum gets written together with the body of the frame */ + hdmi_write(hdmi, REG_HDMI_GENERIC0_HDR, + buffer[0] | + buffer[1] << 8 | + buffer[2] << 16); + + memcpy(buf, &buffer[3], len - 3); + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_GENERIC0(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val |= HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE(VENSPEC_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + return 0; +} + +static int msm_hdmi_bridge_clear_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + u32 val; + + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); + val &= ~(HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + break; + + case HDMI_INFOFRAME_TYPE_AUDIO: + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); + val &= ~(HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + break; + + case HDMI_INFOFRAME_TYPE_SPD: + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val &= ~(HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + break; + + case HDMI_INFOFRAME_TYPE_VENDOR: + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val &= ~(HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + break; + + default: + drm_dbg_driver(hdmi_bridge->base.dev, "Unsupported infoframe type %x\n", type); + } + + return 0; +} + +static int msm_hdmi_bridge_write_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type, + const u8 *buffer, size_t len) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + + msm_hdmi_bridge_clear_infoframe(bridge, type); + + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + return msm_hdmi_config_avi_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_AUDIO: + return msm_hdmi_config_audio_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_SPD: + return msm_hdmi_config_spd_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_VENDOR: + return msm_hdmi_config_hdmi_infoframe(hdmi, buffer, len); + default: + drm_dbg_driver(hdmi_bridge->base.dev, "Unsupported infoframe type %x\n", type); + return 0; + } +} + +static void msm_hdmi_set_timings(struct hdmi *hdmi, + const struct drm_display_mode *mode); + +static void msm_hdmi_bridge_atomic_pre_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; struct hdmi_phy *phy = hdmi->phy; + struct drm_encoder *encoder = bridge->encoder; + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_crtc_state *crtc_state; DBG("power up"); + connector = drm_atomic_get_new_connector_for_encoder(state, encoder); + conn_state = drm_atomic_get_new_connector_state(state, connector); + crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); + + hdmi->pixclock = conn_state->hdmi.tmds_char_rate; + + msm_hdmi_set_timings(hdmi, &crtc_state->adjusted_mode); + if (!hdmi->power_on) { msm_hdmi_phy_resource_enable(phy); msm_hdmi_power_on(bridge); hdmi->power_on = true; - if (hdmi->hdmi_mode) { - msm_hdmi_config_avi_infoframe(hdmi); + if (connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); - } } + drm_atomic_helper_connector_hdmi_update_infoframes(connector, state); + msm_hdmi_phy_powerup(phy, hdmi->pixclock); msm_hdmi_set_mode(hdmi, true); @@ -152,7 +338,8 @@ static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge) msm_hdmi_hdcp_on(hdmi->hdcp_ctrl); } -static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge) +static void msm_hdmi_bridge_atomic_post_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; @@ -169,25 +356,18 @@ static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge) if (hdmi->power_on) { power_off(bridge); hdmi->power_on = false; - if (hdmi->hdmi_mode) + if (hdmi->connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); msm_hdmi_phy_resource_disable(phy); } } -static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adjusted_mode) +static void msm_hdmi_set_timings(struct hdmi *hdmi, + const struct drm_display_mode *mode) { - struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); - struct hdmi *hdmi = hdmi_bridge->hdmi; int hstart, hend, vstart, vend; uint32_t frame_ctrl; - mode = adjusted_mode; - - hdmi->pixclock = mode->clock * 1000; - hstart = mode->htotal - mode->hsync_start; hend = mode->htotal - mode->hsync_start + mode->hdisplay; @@ -232,7 +412,7 @@ static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, DBG("frame_ctrl=%08x", frame_ctrl); hdmi_write(hdmi, REG_HDMI_FRAME_CTRL, frame_ctrl); - if (hdmi->hdmi_mode) + if (hdmi->connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); } @@ -251,32 +431,19 @@ static const struct drm_edid *msm_hdmi_bridge_edid_read(struct drm_bridge *bridg hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl); - if (drm_edid) { - /* - * FIXME: This should use connector->display_info.is_hdmi from a - * path that has read the EDID and called - * drm_edid_connector_update(). - */ - const struct edid *edid = drm_edid_raw(drm_edid); - - hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid); - } - return drm_edid; } -static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +static enum drm_mode_status msm_hdmi_bridge_tmds_char_rate_valid(const struct drm_bridge *bridge, + const struct drm_display_mode *mode, + unsigned long long tmds_rate) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; const struct hdmi_platform_config *config = hdmi->config; struct msm_drm_private *priv = bridge->dev->dev_private; struct msm_kms *kms = priv->kms; - long actual, requested; - - requested = 1000 * mode->clock; + long actual; /* for mdp5/apq8074, we manage our own pixel clk (as opposed to * mdp4/dtv stuff where pixel clk is assigned to mdp/encoder @@ -284,27 +451,34 @@ static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge */ if (kms->funcs->round_pixclk) actual = kms->funcs->round_pixclk(kms, - requested, hdmi_bridge->hdmi->encoder); + tmds_rate, + hdmi_bridge->hdmi->encoder); else if (config->pwr_clk_cnt > 0) - actual = clk_round_rate(hdmi->pwr_clks[0], requested); + actual = clk_round_rate(hdmi->pwr_clks[0], tmds_rate); else - actual = requested; + actual = tmds_rate; - DBG("requested=%ld, actual=%ld", requested, actual); + DBG("requested=%lld, actual=%ld", tmds_rate, actual); - if (actual != requested) + if (actual != tmds_rate) return MODE_CLOCK_RANGE; return 0; } static const struct drm_bridge_funcs msm_hdmi_bridge_funcs = { - .pre_enable = msm_hdmi_bridge_pre_enable, - .post_disable = msm_hdmi_bridge_post_disable, - .mode_set = msm_hdmi_bridge_mode_set, - .mode_valid = msm_hdmi_bridge_mode_valid, + .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, + .atomic_pre_enable = msm_hdmi_bridge_atomic_pre_enable, + .atomic_post_disable = msm_hdmi_bridge_atomic_post_disable, .edid_read = msm_hdmi_bridge_edid_read, .detect = msm_hdmi_bridge_detect, + .hdmi_tmds_char_rate_valid = msm_hdmi_bridge_tmds_char_rate_valid, + .hdmi_clear_infoframe = msm_hdmi_bridge_clear_infoframe, + .hdmi_write_infoframe = msm_hdmi_bridge_write_infoframe, + .hdmi_audio_prepare = msm_hdmi_bridge_audio_prepare, + .hdmi_audio_shutdown = msm_hdmi_bridge_audio_shutdown, }; static void @@ -336,9 +510,15 @@ int msm_hdmi_bridge_init(struct hdmi *hdmi) bridge->funcs = &msm_hdmi_bridge_funcs; bridge->ddc = hdmi->i2c; bridge->type = DRM_MODE_CONNECTOR_HDMIA; + bridge->vendor = "Qualcomm"; + bridge->product = "Snapdragon"; bridge->ops = DRM_BRIDGE_OP_HPD | DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_HDMI | DRM_BRIDGE_OP_EDID; + bridge->hdmi_audio_max_i2s_playback_channels = 8; + bridge->hdmi_audio_dev = &hdmi->pdev->dev; + bridge->hdmi_audio_dai_port = -1; ret = devm_drm_bridge_add(hdmi->dev->dev, bridge); if (ret) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index a7a2384044ff..87a91148a731 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -183,10 +183,16 @@ static unsigned get_crtc_mask(struct drm_atomic_state *state) int msm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { + struct msm_drm_private *priv = dev->dev_private; + struct msm_kms *kms = priv->kms; struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; - int i; + int i, ret = 0; + /* + * FIXME: stop setting allow_modeset and move this check to the DPU + * driver. + */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if ((old_crtc_state->ctm && !new_crtc_state->ctm) || @@ -196,6 +202,11 @@ int msm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) } } + if (kms && kms->funcs && kms->funcs->check_mode_changed) + ret = kms->funcs->check_mode_changed(kms, state); + if (ret) + return ret; + return drm_atomic_helper_check(dev, state); } @@ -221,6 +232,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + atomic_set(&kms->fault_snapshot_capture, 0); + /* * Now that there is no in-progress flush, prepare the * current update: diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ff7a7a9f7b0d..c3588dc9e537 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -894,6 +894,7 @@ static const struct drm_driver msm_driver = { DRIVER_RENDER | DRIVER_ATOMIC | DRIVER_MODESET | + DRIVER_SYNCOBJ_TIMELINE | DRIVER_SYNCOBJ, .open = msm_open, .postclose = msm_postclose, diff --git a/drivers/gpu/drm/msm/msm_dsc_helper.h b/drivers/gpu/drm/msm/msm_dsc_helper.h index b9049fe1e279..63f95523b2cb 100644 --- a/drivers/gpu/drm/msm/msm_dsc_helper.h +++ b/drivers/gpu/drm/msm/msm_dsc_helper.h @@ -13,17 +13,6 @@ #include <drm/display/drm_dsc_helper.h> /** - * msm_dsc_get_slices_per_intf() - calculate number of slices per interface - * @dsc: Pointer to drm dsc config struct - * @intf_width: interface width in pixels - * Returns: Integer representing the number of slices for the given interface - */ -static inline u32 msm_dsc_get_slices_per_intf(const struct drm_dsc_config *dsc, u32 intf_width) -{ - return DIV_ROUND_UP(intf_width, dsc->slice_width); -} - -/** * msm_dsc_get_bytes_per_line() - calculate bytes per line * @dsc: Pointer to drm dsc config struct * Returns: Integer value representing bytes per line. DSI and DP need diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index dee470403036..3e9aa2cc38ef 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -509,7 +509,7 @@ static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, } if (syncobj_desc.flags & ~MSM_SUBMIT_SYNCOBJ_FLAGS) { - ret = -SUBMIT_ERROR(EINVAL, submit, "invalid syncobj flags: %x", syncobj_desc.flags); + ret = SUBMIT_ERROR(EINVAL, submit, "invalid syncobj flags: %x", syncobj_desc.flags); break; } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 8557998e0c92..c380d9d9f5af 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -281,6 +281,15 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, if (submit) { int i; + if (state->fault_info.ttbr0) { + struct msm_gpu_fault_info *info = &state->fault_info; + struct msm_mmu *mmu = submit->aspace->mmu; + + msm_iommu_pagetable_params(mmu, &info->pgtbl_ttbr0, + &info->asid); + msm_iommu_pagetable_walk(mmu, info->iova, info->ptes); + } + state->bos = kcalloc(submit->nr_bos, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 7cabc8480d7c..e25009150579 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -101,6 +101,14 @@ struct msm_gpu_fault_info { int flags; const char *type; const char *block; + + /* Information about what we think/expect is the current SMMU state, + * for example expected_ttbr0 should match smmu_info.ttbr0 which + * was read back from SMMU registers. + */ + phys_addr_t pgtbl_ttbr0; + u64 ptes[4]; + int asid; }; /** diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 2a94e82316f9..fd73dcd3f30e 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -195,6 +195,28 @@ struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu) return &iommu->domain->geometry; } +int +msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]) +{ + struct msm_iommu_pagetable *pagetable; + struct arm_lpae_io_pgtable_walk_data wd = {}; + + if (mmu->type != MSM_MMU_IOMMU_PAGETABLE) + return -EINVAL; + + pagetable = to_pagetable(mmu); + + if (!pagetable->pgtbl_ops->pgtable_walk) + return -EINVAL; + + pagetable->pgtbl_ops->pgtable_walk(pagetable->pgtbl_ops, iova, &wd); + + for (int i = 0; i < ARRAY_SIZE(wd.ptes); i++) + ptes[i] = wd.ptes[i]; + + return 0; +} + static const struct msm_mmu_funcs pagetable_funcs = { .map = msm_iommu_pagetable_map, .unmap = msm_iommu_pagetable_unmap, @@ -243,7 +265,7 @@ static const struct iommu_flush_ops tlb_ops = { .tlb_add_page = msm_iommu_tlb_add_page, }; -static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, +static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg); struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) @@ -319,7 +341,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) return &pagetable->base; } -static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, +static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg) { struct msm_iommu *iommu = arg; @@ -343,6 +365,17 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, return 0; } +static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg) +{ + struct msm_iommu *iommu = arg; + + if (iommu->base.handler) + return iommu->base.handler(iommu->base.arg, iova, flags, NULL); + + return -ENOSYS; +} + static void msm_iommu_resume_translation(struct msm_mmu *mmu) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev); @@ -437,6 +470,21 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) return &iommu->base; } +struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks) +{ + struct msm_iommu *iommu; + struct msm_mmu *mmu; + + mmu = msm_iommu_new(dev, quirks); + if (IS_ERR_OR_NULL(mmu)) + return mmu; + + iommu = to_msm_iommu(mmu); + iommu_set_fault_handler(iommu->domain, msm_disp_fault_handler, iommu); + + return mmu; +} + struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev); @@ -448,7 +496,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig return mmu; iommu = to_msm_iommu(mmu); - iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu); + iommu_set_fault_handler(iommu->domain, msm_gpu_fault_handler, iommu); /* Enable stall on iommu fault: */ if (adreno_smmu->set_stall) diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 38965e12a6bf..35d5397e73b4 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -164,12 +164,26 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc) vblank_ctrl_queue_work(priv, crtc, false); } +static int msm_kms_fault_handler(void *arg, unsigned long iova, int flags, void *data) +{ + struct msm_kms *kms = arg; + + if (atomic_read(&kms->fault_snapshot_capture) == 0) { + msm_disp_snapshot_state(kms->dev); + atomic_inc(&kms->fault_snapshot_capture); + } + + return -ENOSYS; +} + struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) { struct msm_gem_address_space *aspace; struct msm_mmu *mmu; struct device *mdp_dev = dev->dev; struct device *mdss_dev = mdp_dev->parent; + struct msm_drm_private *priv = dev->dev_private; + struct msm_kms *kms = priv->kms; struct device *iommu_dev; /* @@ -181,7 +195,7 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) else iommu_dev = mdss_dev; - mmu = msm_iommu_new(iommu_dev, 0); + mmu = msm_iommu_disp_new(iommu_dev, 0); if (IS_ERR(mmu)) return ERR_CAST(mmu); @@ -195,8 +209,11 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) if (IS_ERR(aspace)) { dev_err(mdp_dev, "aspace create, error %pe\n", aspace); mmu->funcs->destroy(mmu); + return aspace; } + msm_mmu_set_fault_handler(aspace->mmu, kms, msm_kms_fault_handler); + return aspace; } diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index e60162744c66..43b58d052ee6 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -60,6 +60,13 @@ struct msm_kms_funcs { void (*disable_commit)(struct msm_kms *kms); /** + * @check_mode_changed: + * + * Verify if the commit requires a full modeset on one of CRTCs. + */ + int (*check_mode_changed)(struct msm_kms *kms, struct drm_atomic_state *state); + + /** * Prepare for atomic commit. This is called after any previous * (async or otherwise) commit has completed. */ @@ -128,6 +135,9 @@ struct msm_kms { int irq; bool irq_requested; + /* rate limit the snapshot capture to once per attach */ + atomic_t fault_snapshot_capture; + /* mapper-id used to request GEM buffer mapped for scanout: */ struct msm_gem_address_space *aspace; diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index 88af4f490881..daf91529e02b 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -42,6 +42,7 @@ static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev, struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks); struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks); +struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks); static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, int (*handler)(void *arg, unsigned long iova, int flags, void *data)) @@ -53,7 +54,8 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent); int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr, - int *asid); + int *asid); +int msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]); struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu); #endif /* __MSM_MMU_H__ */ diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml index 35f7f40e405b..d2c8c46bb041 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml @@ -17,6 +17,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="CLK_EN" pos="5" type="boolean"/> <bitfield name="CLK_EN_SEL" pos="4" type="boolean"/> <bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/> + <bitfield name="DSICLK_SEL" low="0" high="1" type="uint"/> </reg32> <reg32 offset="0x00018" name="GLBL_CTRL"/> <reg32 offset="0x0001c" name="RBUF_CTRL"/> diff --git a/drivers/gpu/drm/msm/registers/display/hdmi.xml b/drivers/gpu/drm/msm/registers/display/hdmi.xml index 1cf1b14fbd91..0ebb96297dae 100644 --- a/drivers/gpu/drm/msm/registers/display/hdmi.xml +++ b/drivers/gpu/drm/msm/registers/display/hdmi.xml @@ -131,7 +131,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> --> <bitfield name="GENERIC0_SEND" pos="0" type="boolean"/> <bitfield name="GENERIC0_CONT" pos="1" type="boolean"/> - <bitfield name="GENERIC0_UPDATE" low="2" high="3" type="uint"/> <!-- ??? --> + <bitfield name="GENERIC0_UPDATE" pos="2" type="boolean"/> <bitfield name="GENERIC1_SEND" pos="4" type="boolean"/> <bitfield name="GENERIC1_CONT" pos="5" type="boolean"/> <bitfield name="GENERIC0_LINE" low="16" high="21" type="uint"/> diff --git a/drivers/gpu/drm/nouveau/include/nvif/ioctl.h b/drivers/gpu/drm/nouveau/include/nvif/ioctl.h index e825c8a1d9ca..00015412cb3e 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/ioctl.h +++ b/drivers/gpu/drm/nouveau/include/nvif/ioctl.h @@ -3,25 +3,30 @@ #define __NVIF_IOCTL_H__ struct nvif_ioctl_v0 { - __u8 version; + /* New members MUST be added within the struct_group() macro below. */ + struct_group_tagged(nvif_ioctl_v0_hdr, __hdr, + __u8 version; #define NVIF_IOCTL_V0_SCLASS 0x01 #define NVIF_IOCTL_V0_NEW 0x02 #define NVIF_IOCTL_V0_DEL 0x03 #define NVIF_IOCTL_V0_MTHD 0x04 #define NVIF_IOCTL_V0_MAP 0x07 #define NVIF_IOCTL_V0_UNMAP 0x08 - __u8 type; - __u8 pad02[4]; + __u8 type; + __u8 pad02[4]; #define NVIF_IOCTL_V0_OWNER_NVIF 0x00 #define NVIF_IOCTL_V0_OWNER_ANY 0xff - __u8 owner; + __u8 owner; #define NVIF_IOCTL_V0_ROUTE_NVIF 0x00 #define NVIF_IOCTL_V0_ROUTE_HIDDEN 0xff - __u8 route; - __u64 token; - __u64 object; + __u8 route; + __u64 token; + __u64 object; + ); __u8 data[]; /* ioctl data (below) */ }; +static_assert(offsetof(struct nvif_ioctl_v0, data) == sizeof(struct nvif_ioctl_v0_hdr), + "struct member likely outside of struct_group()"); struct nvif_ioctl_sclass_v0 { /* nvif_ioctl ... */ @@ -51,12 +56,17 @@ struct nvif_ioctl_del { }; struct nvif_ioctl_mthd_v0 { - /* nvif_ioctl ... */ - __u8 version; - __u8 method; - __u8 pad02[6]; + /* New members MUST be added within the struct_group() macro below. */ + struct_group_tagged(nvif_ioctl_mthd_v0_hdr, __hdr, + /* nvif_ioctl ... */ + __u8 version; + __u8 method; + __u8 pad02[6]; + ); __u8 data[]; /* method data (class.h) */ }; +static_assert(offsetof(struct nvif_ioctl_mthd_v0, data) == sizeof(struct nvif_ioctl_mthd_v0_hdr), + "struct member likely outside of struct_group()"); struct nvif_ioctl_map_v0 { /* nvif_ioctl ... */ diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index bcda0105160f..55691ec44aba 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -79,21 +79,8 @@ nouveau_dp_probe_dpcd(struct nouveau_connector *nv_connector, !drm_dp_read_lttpr_common_caps(aux, dpcd, outp->dp.lttpr.caps)) { int nr = drm_dp_lttpr_count(outp->dp.lttpr.caps); - if (nr) { - drm_dp_dpcd_writeb(aux, DP_PHY_REPEATER_MODE, - DP_PHY_REPEATER_MODE_TRANSPARENT); - - if (nr > 0) { - ret = drm_dp_dpcd_writeb(aux, DP_PHY_REPEATER_MODE, - DP_PHY_REPEATER_MODE_NON_TRANSPARENT); - if (ret != 1) { - drm_dp_dpcd_writeb(aux, DP_PHY_REPEATER_MODE, - DP_PHY_REPEATER_MODE_TRANSPARENT); - } else { - outp->dp.lttpr.nr = nr; - } - } - } + if (!drm_dp_lttpr_init(aux, nr)) + outp->dp.lttpr.nr = nr; } ret = drm_dp_read_dpcd_caps(aux, dpcd); diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 8ea98f06d39a..825c867eba7c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -79,8 +79,8 @@ struct nouveau_svm { #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) struct nouveau_pfnmap_args { - struct nvif_ioctl_v0 i; - struct nvif_ioctl_mthd_v0 m; + struct nvif_ioctl_v0_hdr i; + struct nvif_ioctl_mthd_v0_hdr m; struct nvif_vmm_pfnmap_v0 p; }; diff --git a/drivers/gpu/drm/nouveau/nvif/object.c b/drivers/gpu/drm/nouveau/nvif/object.c index 0b87278ac0f8..70af63d70976 100644 --- a/drivers/gpu/drm/nouveau/nvif/object.c +++ b/drivers/gpu/drm/nouveau/nvif/object.c @@ -57,7 +57,7 @@ int nvif_object_sclass_get(struct nvif_object *object, struct nvif_sclass **psclass) { struct { - struct nvif_ioctl_v0 ioctl; + struct nvif_ioctl_v0_hdr ioctl; struct nvif_ioctl_sclass_v0 sclass; } *args = NULL; int ret, cnt = 0, i; @@ -101,7 +101,7 @@ int nvif_object_mthd(struct nvif_object *object, u32 mthd, void *data, u32 size) { struct { - struct nvif_ioctl_v0 ioctl; + struct nvif_ioctl_v0_hdr ioctl; struct nvif_ioctl_mthd_v0 mthd; } *args; u32 args_size; @@ -135,7 +135,7 @@ void nvif_object_unmap_handle(struct nvif_object *object) { struct { - struct nvif_ioctl_v0 ioctl; + struct nvif_ioctl_v0_hdr ioctl; struct nvif_ioctl_unmap unmap; } args = { .ioctl.type = NVIF_IOCTL_V0_UNMAP, @@ -149,7 +149,7 @@ nvif_object_map_handle(struct nvif_object *object, void *argv, u32 argc, u64 *handle, u64 *length) { struct { - struct nvif_ioctl_v0 ioctl; + struct nvif_ioctl_v0_hdr ioctl; struct nvif_ioctl_map_v0 map; } *args; u32 argn = sizeof(*args) + argc; @@ -211,7 +211,7 @@ void nvif_object_dtor(struct nvif_object *object) { struct { - struct nvif_ioctl_v0 ioctl; + struct nvif_ioctl_v0_hdr ioctl; struct nvif_ioctl_del del; } args = { .ioctl.type = NVIF_IOCTL_V0_DEL, @@ -230,7 +230,7 @@ nvif_object_ctor(struct nvif_object *parent, const char *name, u32 handle, s32 oclass, void *data, u32 size, struct nvif_object *object) { struct { - struct nvif_ioctl_v0 ioctl; + struct nvif_ioctl_v0_hdr ioctl; struct nvif_ioctl_new_v0 new; } *args; int ret = 0; diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index d7469c565d1d..e059b06e0239 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -573,6 +573,16 @@ config DRM_PANEL_RAYDIUM_RM67191 Say Y here if you want to enable support for Raydium RM67191 FHD (1080x1920) DSI panel. +config DRM_PANEL_RAYDIUM_RM67200 + tristate "Raydium RM67200-based DSI panel" + depends on OF + depends on DRM_MIPI_DSI + help + Say Y here if you want to enable support for Raydium RM67200-based + DSI video mode panels. This panel controller can be found in the + Wanchanglong W552793BAA panel found on the Rockchip RK3588 EVB1 + evaluation boards. + config DRM_PANEL_RAYDIUM_RM68200 tristate "Raydium RM68200 720x1280 DSI video mode panel" depends on OF @@ -925,6 +935,15 @@ config DRM_PANEL_SIMPLE that it can be automatically turned off when the panel goes into a low power state. +config DRM_PANEL_SUMMIT + tristate "Apple Summit display panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + help + Say Y if you want to enable support for the "Summit" display panel + used as a touchbar on certain Apple laptops. + config DRM_PANEL_SYNAPTICS_R63353 tristate "Synaptics R63353-based panels" depends on OF @@ -996,6 +1015,18 @@ config DRM_PANEL_VISIONOX_RM69299 Say Y here if you want to enable support for Visionox RM69299 DSI Video Mode panel. +config DRM_PANEL_VISIONOX_RM692E5 + tristate "Visionox RM692E5" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + select DRM_DISPLAY_DSC_HELPER + select DRM_DISPLAY_HELPER + help + Say Y here if you want to enable support for Visionox RM692E5 amoled + display panels, such as the one found in the Nothing Phone (1) + smartphone. + config DRM_PANEL_VISIONOX_VTDR6130 tristate "Visionox VTDR6130" depends on OF diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index 7dcf72646cac..1bb8ae46b59b 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -58,6 +58,7 @@ obj-$(CONFIG_DRM_PANEL_OSD_OSD101T2587_53TS) += panel-osd-osd101t2587-53ts.o obj-$(CONFIG_DRM_PANEL_PANASONIC_VVX10F034N00) += panel-panasonic-vvx10f034n00.o obj-$(CONFIG_DRM_PANEL_RASPBERRYPI_TOUCHSCREEN) += panel-raspberrypi-touchscreen.o obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM67191) += panel-raydium-rm67191.o +obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM67200) += panel-raydium-rm67200.o obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM68200) += panel-raydium-rm68200.o obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM692E5) += panel-raydium-rm692e5.o obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM69380) += panel-raydium-rm69380.o @@ -89,6 +90,7 @@ obj-$(CONFIG_DRM_PANEL_SHARP_LS060T1SX01) += panel-sharp-ls060t1sx01.o obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7701) += panel-sitronix-st7701.o obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7703) += panel-sitronix-st7703.o obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7789V) += panel-sitronix-st7789v.o +obj-$(CONFIG_DRM_PANEL_SUMMIT) += panel-summit.o obj-$(CONFIG_DRM_PANEL_SYNAPTICS_R63353) += panel-synaptics-r63353.o obj-$(CONFIG_DRM_PANEL_SONY_ACX565AKM) += panel-sony-acx565akm.o obj-$(CONFIG_DRM_PANEL_SONY_TD4353_JDI) += panel-sony-td4353-jdi.o @@ -100,6 +102,7 @@ obj-$(CONFIG_DRM_PANEL_TPO_TD043MTEA1) += panel-tpo-td043mtea1.o obj-$(CONFIG_DRM_PANEL_TPO_TPG110) += panel-tpo-tpg110.o obj-$(CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA) += panel-truly-nt35597.o obj-$(CONFIG_DRM_PANEL_VISIONOX_RM69299) += panel-visionox-rm69299.o +obj-$(CONFIG_DRM_PANEL_VISIONOX_RM692E5) += panel-visionox-rm692e5.o obj-$(CONFIG_DRM_PANEL_VISIONOX_VTDR6130) += panel-visionox-vtdr6130.o obj-$(CONFIG_DRM_PANEL_VISIONOX_R66451) += panel-visionox-r66451.o obj-$(CONFIG_DRM_PANEL_WIDECHIPS_WS2401) += panel-widechips-ws2401.o diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c b/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c index 266a087fe14c..3c24a63b6be8 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c @@ -607,7 +607,7 @@ static int ili9882t_add(struct ili9882t *ili) ili->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW); if (IS_ERR(ili->enable_gpio)) { - dev_err(dev, "cannot get reset-gpios %ld\n", + dev_err(dev, "cannot get enable-gpios %ld\n", PTR_ERR(ili->enable_gpio)); return PTR_ERR(ili->enable_gpio); } diff --git a/drivers/gpu/drm/panel/panel-raydium-rm67200.c b/drivers/gpu/drm/panel/panel-raydium-rm67200.c new file mode 100644 index 000000000000..64b685dc11f6 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-raydium-rm67200.c @@ -0,0 +1,499 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2024 Collabora + +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/property.h> +#include <linux/regulator/consumer.h> + +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> + +struct raydium_rm67200_panel_info { + struct drm_display_mode mode; + const struct regulator_bulk_data *regulators; + int num_regulators; + void (*panel_setup)(struct mipi_dsi_multi_context *ctx); +}; + +struct raydium_rm67200 { + struct drm_panel panel; + const struct raydium_rm67200_panel_info *panel_info; + struct mipi_dsi_device *dsi; + struct gpio_desc *reset_gpio; + struct regulator_bulk_data *supplies; + int num_supplies; +}; + +static inline struct raydium_rm67200 *to_raydium_rm67200(struct drm_panel *panel) +{ + return container_of(panel, struct raydium_rm67200, panel); +} + +static void raydium_rm67200_reset(struct raydium_rm67200 *ctx) +{ + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + msleep(60); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + msleep(60); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + msleep(60); +} + +static void raydium_rm67200_write(struct mipi_dsi_multi_context *ctx, + u8 arg1, u8 arg2) +{ + u8 d[] = { arg1, arg2 }; + + mipi_dsi_generic_write_multi(ctx, d, ARRAY_SIZE(d)); +} + +static void w552793baa_setup(struct mipi_dsi_multi_context *ctx) +{ + raydium_rm67200_write(ctx, 0xfe, 0x21); + raydium_rm67200_write(ctx, 0x04, 0x00); + raydium_rm67200_write(ctx, 0x00, 0x64); + raydium_rm67200_write(ctx, 0x2a, 0x00); + raydium_rm67200_write(ctx, 0x26, 0x64); + raydium_rm67200_write(ctx, 0x54, 0x00); + raydium_rm67200_write(ctx, 0x50, 0x64); + raydium_rm67200_write(ctx, 0x7b, 0x00); + raydium_rm67200_write(ctx, 0x77, 0x64); + raydium_rm67200_write(ctx, 0xa2, 0x00); + raydium_rm67200_write(ctx, 0x9d, 0x64); + raydium_rm67200_write(ctx, 0xc9, 0x00); + raydium_rm67200_write(ctx, 0xc5, 0x64); + raydium_rm67200_write(ctx, 0x01, 0x71); + raydium_rm67200_write(ctx, 0x27, 0x71); + raydium_rm67200_write(ctx, 0x51, 0x71); + raydium_rm67200_write(ctx, 0x78, 0x71); + raydium_rm67200_write(ctx, 0x9e, 0x71); + raydium_rm67200_write(ctx, 0xc6, 0x71); + raydium_rm67200_write(ctx, 0x02, 0x89); + raydium_rm67200_write(ctx, 0x28, 0x89); + raydium_rm67200_write(ctx, 0x52, 0x89); + raydium_rm67200_write(ctx, 0x79, 0x89); + raydium_rm67200_write(ctx, 0x9f, 0x89); + raydium_rm67200_write(ctx, 0xc7, 0x89); + raydium_rm67200_write(ctx, 0x03, 0x9e); + raydium_rm67200_write(ctx, 0x29, 0x9e); + raydium_rm67200_write(ctx, 0x53, 0x9e); + raydium_rm67200_write(ctx, 0x7a, 0x9e); + raydium_rm67200_write(ctx, 0xa0, 0x9e); + raydium_rm67200_write(ctx, 0xc8, 0x9e); + raydium_rm67200_write(ctx, 0x09, 0x00); + raydium_rm67200_write(ctx, 0x05, 0xb0); + raydium_rm67200_write(ctx, 0x31, 0x00); + raydium_rm67200_write(ctx, 0x2b, 0xb0); + raydium_rm67200_write(ctx, 0x5a, 0x00); + raydium_rm67200_write(ctx, 0x55, 0xb0); + raydium_rm67200_write(ctx, 0x80, 0x00); + raydium_rm67200_write(ctx, 0x7c, 0xb0); + raydium_rm67200_write(ctx, 0xa7, 0x00); + raydium_rm67200_write(ctx, 0xa3, 0xb0); + raydium_rm67200_write(ctx, 0xce, 0x00); + raydium_rm67200_write(ctx, 0xca, 0xb0); + raydium_rm67200_write(ctx, 0x06, 0xc0); + raydium_rm67200_write(ctx, 0x2d, 0xc0); + raydium_rm67200_write(ctx, 0x56, 0xc0); + raydium_rm67200_write(ctx, 0x7d, 0xc0); + raydium_rm67200_write(ctx, 0xa4, 0xc0); + raydium_rm67200_write(ctx, 0xcb, 0xc0); + raydium_rm67200_write(ctx, 0x07, 0xcf); + raydium_rm67200_write(ctx, 0x2f, 0xcf); + raydium_rm67200_write(ctx, 0x58, 0xcf); + raydium_rm67200_write(ctx, 0x7e, 0xcf); + raydium_rm67200_write(ctx, 0xa5, 0xcf); + raydium_rm67200_write(ctx, 0xcc, 0xcf); + raydium_rm67200_write(ctx, 0x08, 0xdd); + raydium_rm67200_write(ctx, 0x30, 0xdd); + raydium_rm67200_write(ctx, 0x59, 0xdd); + raydium_rm67200_write(ctx, 0x7f, 0xdd); + raydium_rm67200_write(ctx, 0xa6, 0xdd); + raydium_rm67200_write(ctx, 0xcd, 0xdd); + raydium_rm67200_write(ctx, 0x0e, 0x15); + raydium_rm67200_write(ctx, 0x0a, 0xe9); + raydium_rm67200_write(ctx, 0x36, 0x15); + raydium_rm67200_write(ctx, 0x32, 0xe9); + raydium_rm67200_write(ctx, 0x5f, 0x15); + raydium_rm67200_write(ctx, 0x5b, 0xe9); + raydium_rm67200_write(ctx, 0x85, 0x15); + raydium_rm67200_write(ctx, 0x81, 0xe9); + raydium_rm67200_write(ctx, 0xad, 0x15); + raydium_rm67200_write(ctx, 0xa9, 0xe9); + raydium_rm67200_write(ctx, 0xd3, 0x15); + raydium_rm67200_write(ctx, 0xcf, 0xe9); + raydium_rm67200_write(ctx, 0x0b, 0x14); + raydium_rm67200_write(ctx, 0x33, 0x14); + raydium_rm67200_write(ctx, 0x5c, 0x14); + raydium_rm67200_write(ctx, 0x82, 0x14); + raydium_rm67200_write(ctx, 0xaa, 0x14); + raydium_rm67200_write(ctx, 0xd0, 0x14); + raydium_rm67200_write(ctx, 0x0c, 0x36); + raydium_rm67200_write(ctx, 0x34, 0x36); + raydium_rm67200_write(ctx, 0x5d, 0x36); + raydium_rm67200_write(ctx, 0x83, 0x36); + raydium_rm67200_write(ctx, 0xab, 0x36); + raydium_rm67200_write(ctx, 0xd1, 0x36); + raydium_rm67200_write(ctx, 0x0d, 0x6b); + raydium_rm67200_write(ctx, 0x35, 0x6b); + raydium_rm67200_write(ctx, 0x5e, 0x6b); + raydium_rm67200_write(ctx, 0x84, 0x6b); + raydium_rm67200_write(ctx, 0xac, 0x6b); + raydium_rm67200_write(ctx, 0xd2, 0x6b); + raydium_rm67200_write(ctx, 0x13, 0x5a); + raydium_rm67200_write(ctx, 0x0f, 0x94); + raydium_rm67200_write(ctx, 0x3b, 0x5a); + raydium_rm67200_write(ctx, 0x37, 0x94); + raydium_rm67200_write(ctx, 0x64, 0x5a); + raydium_rm67200_write(ctx, 0x60, 0x94); + raydium_rm67200_write(ctx, 0x8a, 0x5a); + raydium_rm67200_write(ctx, 0x86, 0x94); + raydium_rm67200_write(ctx, 0xb2, 0x5a); + raydium_rm67200_write(ctx, 0xae, 0x94); + raydium_rm67200_write(ctx, 0xd8, 0x5a); + raydium_rm67200_write(ctx, 0xd4, 0x94); + raydium_rm67200_write(ctx, 0x10, 0xd1); + raydium_rm67200_write(ctx, 0x38, 0xd1); + raydium_rm67200_write(ctx, 0x61, 0xd1); + raydium_rm67200_write(ctx, 0x87, 0xd1); + raydium_rm67200_write(ctx, 0xaf, 0xd1); + raydium_rm67200_write(ctx, 0xd5, 0xd1); + raydium_rm67200_write(ctx, 0x11, 0x04); + raydium_rm67200_write(ctx, 0x39, 0x04); + raydium_rm67200_write(ctx, 0x62, 0x04); + raydium_rm67200_write(ctx, 0x88, 0x04); + raydium_rm67200_write(ctx, 0xb0, 0x04); + raydium_rm67200_write(ctx, 0xd6, 0x04); + raydium_rm67200_write(ctx, 0x12, 0x05); + raydium_rm67200_write(ctx, 0x3a, 0x05); + raydium_rm67200_write(ctx, 0x63, 0x05); + raydium_rm67200_write(ctx, 0x89, 0x05); + raydium_rm67200_write(ctx, 0xb1, 0x05); + raydium_rm67200_write(ctx, 0xd7, 0x05); + raydium_rm67200_write(ctx, 0x18, 0xaa); + raydium_rm67200_write(ctx, 0x14, 0x36); + raydium_rm67200_write(ctx, 0x42, 0xaa); + raydium_rm67200_write(ctx, 0x3d, 0x36); + raydium_rm67200_write(ctx, 0x69, 0xaa); + raydium_rm67200_write(ctx, 0x65, 0x36); + raydium_rm67200_write(ctx, 0x8f, 0xaa); + raydium_rm67200_write(ctx, 0x8b, 0x36); + raydium_rm67200_write(ctx, 0xb7, 0xaa); + raydium_rm67200_write(ctx, 0xb3, 0x36); + raydium_rm67200_write(ctx, 0xdd, 0xaa); + raydium_rm67200_write(ctx, 0xd9, 0x36); + raydium_rm67200_write(ctx, 0x15, 0x74); + raydium_rm67200_write(ctx, 0x3f, 0x74); + raydium_rm67200_write(ctx, 0x66, 0x74); + raydium_rm67200_write(ctx, 0x8c, 0x74); + raydium_rm67200_write(ctx, 0xb4, 0x74); + raydium_rm67200_write(ctx, 0xda, 0x74); + raydium_rm67200_write(ctx, 0x16, 0x9f); + raydium_rm67200_write(ctx, 0x40, 0x9f); + raydium_rm67200_write(ctx, 0x67, 0x9f); + raydium_rm67200_write(ctx, 0x8d, 0x9f); + raydium_rm67200_write(ctx, 0xb5, 0x9f); + raydium_rm67200_write(ctx, 0xdb, 0x9f); + raydium_rm67200_write(ctx, 0x17, 0xdc); + raydium_rm67200_write(ctx, 0x41, 0xdc); + raydium_rm67200_write(ctx, 0x68, 0xdc); + raydium_rm67200_write(ctx, 0x8e, 0xdc); + raydium_rm67200_write(ctx, 0xb6, 0xdc); + raydium_rm67200_write(ctx, 0xdc, 0xdc); + raydium_rm67200_write(ctx, 0x1d, 0xff); + raydium_rm67200_write(ctx, 0x19, 0x03); + raydium_rm67200_write(ctx, 0x47, 0xff); + raydium_rm67200_write(ctx, 0x43, 0x03); + raydium_rm67200_write(ctx, 0x6e, 0xff); + raydium_rm67200_write(ctx, 0x6a, 0x03); + raydium_rm67200_write(ctx, 0x94, 0xff); + raydium_rm67200_write(ctx, 0x90, 0x03); + raydium_rm67200_write(ctx, 0xbc, 0xff); + raydium_rm67200_write(ctx, 0xb8, 0x03); + raydium_rm67200_write(ctx, 0xe2, 0xff); + raydium_rm67200_write(ctx, 0xde, 0x03); + raydium_rm67200_write(ctx, 0x1a, 0x35); + raydium_rm67200_write(ctx, 0x44, 0x35); + raydium_rm67200_write(ctx, 0x6b, 0x35); + raydium_rm67200_write(ctx, 0x91, 0x35); + raydium_rm67200_write(ctx, 0xb9, 0x35); + raydium_rm67200_write(ctx, 0xdf, 0x35); + raydium_rm67200_write(ctx, 0x1b, 0x45); + raydium_rm67200_write(ctx, 0x45, 0x45); + raydium_rm67200_write(ctx, 0x6c, 0x45); + raydium_rm67200_write(ctx, 0x92, 0x45); + raydium_rm67200_write(ctx, 0xba, 0x45); + raydium_rm67200_write(ctx, 0xe0, 0x45); + raydium_rm67200_write(ctx, 0x1c, 0x55); + raydium_rm67200_write(ctx, 0x46, 0x55); + raydium_rm67200_write(ctx, 0x6d, 0x55); + raydium_rm67200_write(ctx, 0x93, 0x55); + raydium_rm67200_write(ctx, 0xbb, 0x55); + raydium_rm67200_write(ctx, 0xe1, 0x55); + raydium_rm67200_write(ctx, 0x22, 0xff); + raydium_rm67200_write(ctx, 0x1e, 0x68); + raydium_rm67200_write(ctx, 0x4c, 0xff); + raydium_rm67200_write(ctx, 0x48, 0x68); + raydium_rm67200_write(ctx, 0x73, 0xff); + raydium_rm67200_write(ctx, 0x6f, 0x68); + raydium_rm67200_write(ctx, 0x99, 0xff); + raydium_rm67200_write(ctx, 0x95, 0x68); + raydium_rm67200_write(ctx, 0xc1, 0xff); + raydium_rm67200_write(ctx, 0xbd, 0x68); + raydium_rm67200_write(ctx, 0xe7, 0xff); + raydium_rm67200_write(ctx, 0xe3, 0x68); + raydium_rm67200_write(ctx, 0x1f, 0x7e); + raydium_rm67200_write(ctx, 0x49, 0x7e); + raydium_rm67200_write(ctx, 0x70, 0x7e); + raydium_rm67200_write(ctx, 0x96, 0x7e); + raydium_rm67200_write(ctx, 0xbe, 0x7e); + raydium_rm67200_write(ctx, 0xe4, 0x7e); + raydium_rm67200_write(ctx, 0x20, 0x97); + raydium_rm67200_write(ctx, 0x4a, 0x97); + raydium_rm67200_write(ctx, 0x71, 0x97); + raydium_rm67200_write(ctx, 0x97, 0x97); + raydium_rm67200_write(ctx, 0xbf, 0x97); + raydium_rm67200_write(ctx, 0xe5, 0x97); + raydium_rm67200_write(ctx, 0x21, 0xb5); + raydium_rm67200_write(ctx, 0x4b, 0xb5); + raydium_rm67200_write(ctx, 0x72, 0xb5); + raydium_rm67200_write(ctx, 0x98, 0xb5); + raydium_rm67200_write(ctx, 0xc0, 0xb5); + raydium_rm67200_write(ctx, 0xe6, 0xb5); + raydium_rm67200_write(ctx, 0x25, 0xf0); + raydium_rm67200_write(ctx, 0x23, 0xe8); + raydium_rm67200_write(ctx, 0x4f, 0xf0); + raydium_rm67200_write(ctx, 0x4d, 0xe8); + raydium_rm67200_write(ctx, 0x76, 0xf0); + raydium_rm67200_write(ctx, 0x74, 0xe8); + raydium_rm67200_write(ctx, 0x9c, 0xf0); + raydium_rm67200_write(ctx, 0x9a, 0xe8); + raydium_rm67200_write(ctx, 0xc4, 0xf0); + raydium_rm67200_write(ctx, 0xc2, 0xe8); + raydium_rm67200_write(ctx, 0xea, 0xf0); + raydium_rm67200_write(ctx, 0xe8, 0xe8); + raydium_rm67200_write(ctx, 0x24, 0xff); + raydium_rm67200_write(ctx, 0x4e, 0xff); + raydium_rm67200_write(ctx, 0x75, 0xff); + raydium_rm67200_write(ctx, 0x9b, 0xff); + raydium_rm67200_write(ctx, 0xc3, 0xff); + raydium_rm67200_write(ctx, 0xe9, 0xff); + raydium_rm67200_write(ctx, 0xfe, 0x3d); + raydium_rm67200_write(ctx, 0x00, 0x04); + raydium_rm67200_write(ctx, 0xfe, 0x23); + raydium_rm67200_write(ctx, 0x08, 0x82); + raydium_rm67200_write(ctx, 0x0a, 0x00); + raydium_rm67200_write(ctx, 0x0b, 0x00); + raydium_rm67200_write(ctx, 0x0c, 0x01); + raydium_rm67200_write(ctx, 0x16, 0x00); + raydium_rm67200_write(ctx, 0x18, 0x02); + raydium_rm67200_write(ctx, 0x1b, 0x04); + raydium_rm67200_write(ctx, 0x19, 0x04); + raydium_rm67200_write(ctx, 0x1c, 0x81); + raydium_rm67200_write(ctx, 0x1f, 0x00); + raydium_rm67200_write(ctx, 0x20, 0x03); + raydium_rm67200_write(ctx, 0x23, 0x04); + raydium_rm67200_write(ctx, 0x21, 0x01); + raydium_rm67200_write(ctx, 0x54, 0x63); + raydium_rm67200_write(ctx, 0x55, 0x54); + raydium_rm67200_write(ctx, 0x6e, 0x45); + raydium_rm67200_write(ctx, 0x6d, 0x36); + raydium_rm67200_write(ctx, 0xfe, 0x3d); + raydium_rm67200_write(ctx, 0x55, 0x78); + raydium_rm67200_write(ctx, 0xfe, 0x20); + raydium_rm67200_write(ctx, 0x26, 0x30); + raydium_rm67200_write(ctx, 0xfe, 0x3d); + raydium_rm67200_write(ctx, 0x20, 0x71); + raydium_rm67200_write(ctx, 0x50, 0x8f); + raydium_rm67200_write(ctx, 0x51, 0x8f); + raydium_rm67200_write(ctx, 0xfe, 0x00); + raydium_rm67200_write(ctx, 0x35, 0x00); +} + +static int raydium_rm67200_prepare(struct drm_panel *panel) +{ + struct raydium_rm67200 *ctx = to_raydium_rm67200(panel); + int ret; + + ret = regulator_bulk_enable(ctx->num_supplies, ctx->supplies); + if (ret < 0) + return ret; + + raydium_rm67200_reset(ctx); + + msleep(60); + + return 0; +} + +static int raydium_rm67200_unprepare(struct drm_panel *panel) +{ + struct raydium_rm67200 *ctx = to_raydium_rm67200(panel); + + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + regulator_bulk_disable(ctx->num_supplies, ctx->supplies); + + msleep(60); + + return 0; +} + +static int raydium_rm67200_enable(struct drm_panel *panel) +{ + struct raydium_rm67200 *rm67200 = to_raydium_rm67200(panel); + struct mipi_dsi_multi_context ctx = { .dsi = rm67200->dsi }; + + rm67200->panel_info->panel_setup(&ctx); + mipi_dsi_dcs_exit_sleep_mode_multi(&ctx); + mipi_dsi_msleep(&ctx, 120); + mipi_dsi_dcs_set_display_on_multi(&ctx); + mipi_dsi_msleep(&ctx, 30); + + return ctx.accum_err; +} + +static int raydium_rm67200_disable(struct drm_panel *panel) +{ + struct raydium_rm67200 *rm67200 = to_raydium_rm67200(panel); + struct mipi_dsi_multi_context ctx = { .dsi = rm67200->dsi }; + + mipi_dsi_dcs_set_display_off_multi(&ctx); + mipi_dsi_dcs_enter_sleep_mode_multi(&ctx); + mipi_dsi_msleep(&ctx, 60); + + return ctx.accum_err; +} + +static int raydium_rm67200_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct raydium_rm67200 *ctx = to_raydium_rm67200(panel); + + return drm_connector_helper_get_modes_fixed(connector, &ctx->panel_info->mode); +} + +static const struct drm_panel_funcs raydium_rm67200_funcs = { + .prepare = raydium_rm67200_prepare, + .unprepare = raydium_rm67200_unprepare, + .get_modes = raydium_rm67200_get_modes, + .enable = raydium_rm67200_enable, + .disable = raydium_rm67200_disable, +}; + +static int raydium_rm67200_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + struct raydium_rm67200 *ctx; + int ret = 0; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->panel_info = device_get_match_data(dev); + if (!ctx->panel_info) + return -EINVAL; + + ctx->num_supplies = ctx->panel_info->num_regulators; + ret = devm_regulator_bulk_get_const(&dsi->dev, + ctx->panel_info->num_regulators, + ctx->panel_info->regulators, + &ctx->supplies); + if (ret < 0) + return ret; + + ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(ctx->reset_gpio)) + return dev_err_probe(dev, PTR_ERR(ctx->reset_gpio), + "Failed to get reset-gpios\n"); + + ctx->dsi = dsi; + mipi_dsi_set_drvdata(dsi, ctx); + + 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; + ctx->panel.prepare_prev_first = true; + + drm_panel_init(&ctx->panel, dev, &raydium_rm67200_funcs, + DRM_MODE_CONNECTOR_DSI); + + ret = drm_panel_of_backlight(&ctx->panel); + if (ret) + return ret; + + drm_panel_add(&ctx->panel); + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "Failed to attach to DSI host: %d\n", ret); + drm_panel_remove(&ctx->panel); + } + + return ret; +} + +static void raydium_rm67200_remove(struct mipi_dsi_device *dsi) +{ + struct raydium_rm67200 *ctx = mipi_dsi_get_drvdata(dsi); + int ret; + + ret = mipi_dsi_detach(dsi); + if (ret < 0) + dev_err(&dsi->dev, "Failed to detach DSI host: %d\n", ret); + + drm_panel_remove(&ctx->panel); +} + +static const struct regulator_bulk_data w552793baa_regulators[] = { + { .supply = "vdd", }, /* 2.8V */ + { .supply = "iovcc", }, /* 1.8V */ + { .supply = "vsp", }, /* +5.5V */ + { .supply = "vsn", }, /* -5.5V */ +}; + +static const struct raydium_rm67200_panel_info w552793baa_info = { + .mode = { + .clock = 132000, + .hdisplay = 1080, + .hsync_start = 1095, + .hsync_end = 1125, + .htotal = 1129, + .vdisplay = 1920, + .vsync_start = 1935, + .vsync_end = 1950, + .vtotal = 1952, + .width_mm = 68, /* 68.04mm */ + .height_mm = 121, /* 120.96mm */ + .type = DRM_MODE_TYPE_DRIVER, + }, + .regulators = w552793baa_regulators, + .num_regulators = ARRAY_SIZE(w552793baa_regulators), + .panel_setup = w552793baa_setup, +}; + +static const struct of_device_id raydium_rm67200_of_match[] = { + { .compatible = "wanchanglong,w552793baa", .data = &w552793baa_info }, + { /*sentinel*/ } +}; +MODULE_DEVICE_TABLE(of, raydium_rm67200_of_match); + +static struct mipi_dsi_driver raydium_rm67200_driver = { + .probe = raydium_rm67200_probe, + .remove = raydium_rm67200_remove, + .driver = { + .name = "panel-raydium-rm67200", + .of_match_table = raydium_rm67200_of_match, + }, +}; +module_mipi_dsi_driver(raydium_rm67200_driver); + +MODULE_AUTHOR("Sebastian Reichel <sebastian.reichel@collabora.com>"); +MODULE_DESCRIPTION("DRM driver for RM67200-equipped DSI panels"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 9b2f128fd309..232b03c1a259 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1374,6 +1374,64 @@ static const struct panel_desc bananapi_s070wv20_ct16 = { }, }; +static const struct display_timing boe_av101hdt_a10_timing = { + .pixelclock = { 74210000, 75330000, 76780000, }, + .hactive = { 1280, 1280, 1280, }, + .hfront_porch = { 10, 42, 33, }, + .hback_porch = { 10, 18, 33, }, + .hsync_len = { 30, 10, 30, }, + .vactive = { 720, 720, 720, }, + .vfront_porch = { 200, 183, 200, }, + .vback_porch = { 8, 8, 8, }, + .vsync_len = { 2, 19, 2, }, + .flags = DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW, +}; + +static const struct panel_desc boe_av101hdt_a10 = { + .timings = &boe_av101hdt_a10_timing, + .num_timings = 1, + .bpc = 8, + .size = { + .width = 224, + .height = 126, + }, + .delay = { + .enable = 50, + .disable = 50, + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .connector_type = DRM_MODE_CONNECTOR_LVDS, +}; + +static const struct display_timing boe_av123z7m_n17_timing = { + .pixelclock = { 86600000, 88000000, 90800000, }, + .hactive = { 1920, 1920, 1920, }, + .hfront_porch = { 10, 10, 10, }, + .hback_porch = { 10, 10, 10, }, + .hsync_len = { 9, 12, 25, }, + .vactive = { 720, 720, 720, }, + .vfront_porch = { 7, 10, 13, }, + .vback_porch = { 7, 10, 13, }, + .vsync_len = { 7, 11, 14, }, + .flags = DISPLAY_FLAGS_DE_HIGH | DISPLAY_FLAGS_HSYNC_LOW | DISPLAY_FLAGS_VSYNC_LOW, +}; + +static const struct panel_desc boe_av123z7m_n17 = { + .timings = &boe_av123z7m_n17_timing, + .bpc = 8, + .num_timings = 1, + .size = { + .width = 292, + .height = 110, + }, + .delay = { + .prepare = 50, + .disable = 50, + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .connector_type = DRM_MODE_CONNECTOR_LVDS, +}; + static const struct drm_display_mode boe_bp101wx1_100_mode = { .clock = 78945, .hdisplay = 1280, @@ -4814,6 +4872,12 @@ static const struct of_device_id platform_of_match[] = { .compatible = "bananapi,s070wv20-ct16", .data = &bananapi_s070wv20_ct16, }, { + .compatible = "boe,av101hdt-a10", + .data = &boe_av101hdt_a10, + }, { + .compatible = "boe,av123z7m-n17", + .data = &boe_av123z7m_n17, + }, { .compatible = "boe,bp082wx1-100", .data = &boe_bp082wx1_100, }, { diff --git a/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c b/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c index 472195d4bbbe..97f4bb4e1029 100644 --- a/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c +++ b/drivers/gpu/drm/panel/panel-sony-td4353-jdi.c @@ -47,93 +47,40 @@ static inline struct sony_td4353_jdi *to_sony_td4353_jdi(struct drm_panel *panel static int sony_td4353_jdi_on(struct sony_td4353_jdi *ctx) { struct mipi_dsi_device *dsi = ctx->dsi; - struct device *dev = &dsi->dev; - int ret; + struct mipi_dsi_multi_context dsi_ctx = { .dsi = dsi }; dsi->mode_flags |= MIPI_DSI_MODE_LPM; - ret = mipi_dsi_dcs_set_column_address(dsi, 0x0000, 1080 - 1); - if (ret < 0) { - dev_err(dev, "Failed to set column address: %d\n", ret); - return ret; - } - - ret = mipi_dsi_dcs_set_page_address(dsi, 0x0000, 2160 - 1); - if (ret < 0) { - dev_err(dev, "Failed to set page address: %d\n", ret); - return ret; - } - - ret = mipi_dsi_dcs_set_tear_scanline(dsi, 0); - if (ret < 0) { - dev_err(dev, "Failed to set tear scanline: %d\n", ret); - return ret; - } - - ret = mipi_dsi_dcs_set_tear_on(dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); - if (ret < 0) { - dev_err(dev, "Failed to set tear on: %d\n", ret); - return ret; - } + mipi_dsi_dcs_set_column_address_multi(&dsi_ctx, 0x0000, 1080 - 1); + mipi_dsi_dcs_set_page_address_multi(&dsi_ctx, 0x0000, 2160 - 1); + mipi_dsi_dcs_set_tear_scanline_multi(&dsi_ctx, 0); + mipi_dsi_dcs_set_tear_on_multi(&dsi_ctx, MIPI_DSI_DCS_TEAR_MODE_VBLANK); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_SET_ADDRESS_MODE, 0x00); - mipi_dsi_dcs_write_seq(dsi, MIPI_DCS_SET_ADDRESS_MODE, 0x00); - - ret = mipi_dsi_dcs_set_pixel_format(dsi, 0x77); - if (ret < 0) { - dev_err(dev, "Failed to set pixel format: %d\n", ret); - return ret; - } - - mipi_dsi_dcs_write_seq(dsi, MIPI_DCS_SET_PARTIAL_ROWS, - 0x00, 0x00, 0x08, 0x6f); - - ret = mipi_dsi_dcs_exit_sleep_mode(dsi); - if (ret < 0) { - dev_err(dev, "Failed to exit sleep mode: %d\n", ret); - return ret; - } - msleep(70); + mipi_dsi_dcs_set_pixel_format_multi(&dsi_ctx, 0x77); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_SET_PARTIAL_ROWS, + 0x00, 0x00, 0x08, 0x6f); - mipi_dsi_dcs_write_seq(dsi, MIPI_DCS_WRITE_MEMORY_START); + mipi_dsi_dcs_exit_sleep_mode_multi(&dsi_ctx); + mipi_dsi_msleep(&dsi_ctx, 70); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_WRITE_MEMORY_START); + mipi_dsi_dcs_set_display_on_multi(&dsi_ctx); - ret = mipi_dsi_dcs_set_display_on(dsi); - if (ret < 0) { - dev_err(dev, "Failed to turn display on: %d\n", ret); - return ret; - } - - return 0; + return dsi_ctx.accum_err; } -static int sony_td4353_jdi_off(struct sony_td4353_jdi *ctx) +static void sony_td4353_jdi_off(struct sony_td4353_jdi *ctx) { struct mipi_dsi_device *dsi = ctx->dsi; - struct device *dev = &dsi->dev; - int ret; + struct mipi_dsi_multi_context dsi_ctx = { .dsi = dsi }; dsi->mode_flags &= ~MIPI_DSI_MODE_LPM; - ret = mipi_dsi_dcs_set_display_off(dsi); - if (ret < 0) { - dev_err(dev, "Failed to set display off: %d\n", ret); - return ret; - } - msleep(22); - - ret = mipi_dsi_dcs_set_tear_off(dsi); - if (ret < 0) { - dev_err(dev, "Failed to set tear off: %d\n", ret); - return ret; - } - - ret = mipi_dsi_dcs_enter_sleep_mode(dsi); - if (ret < 0) { - dev_err(dev, "Failed to enter sleep mode: %d\n", ret); - return ret; - } - msleep(80); - - return 0; + mipi_dsi_dcs_set_display_off_multi(&dsi_ctx); + mipi_dsi_msleep(&dsi_ctx, 22); + mipi_dsi_dcs_set_tear_off_multi(&dsi_ctx); + mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx); + mipi_dsi_msleep(&dsi_ctx, 80); } static void sony_td4353_assert_reset_gpios(struct sony_td4353_jdi *ctx, int mode) @@ -146,14 +93,11 @@ static void sony_td4353_assert_reset_gpios(struct sony_td4353_jdi *ctx, int mode static int sony_td4353_jdi_prepare(struct drm_panel *panel) { struct sony_td4353_jdi *ctx = to_sony_td4353_jdi(panel); - struct device *dev = &ctx->dsi->dev; int ret; ret = regulator_bulk_enable(ARRAY_SIZE(ctx->supplies), ctx->supplies); - if (ret < 0) { - dev_err(dev, "Failed to enable regulators: %d\n", ret); + if (ret < 0) return ret; - } msleep(100); @@ -161,7 +105,6 @@ static int sony_td4353_jdi_prepare(struct drm_panel *panel) ret = sony_td4353_jdi_on(ctx); if (ret < 0) { - dev_err(dev, "Failed to power on panel: %d\n", ret); sony_td4353_assert_reset_gpios(ctx, 0); regulator_bulk_disable(ARRAY_SIZE(ctx->supplies), ctx->supplies); return ret; @@ -173,12 +116,8 @@ static int sony_td4353_jdi_prepare(struct drm_panel *panel) static int sony_td4353_jdi_unprepare(struct drm_panel *panel) { struct sony_td4353_jdi *ctx = to_sony_td4353_jdi(panel); - struct device *dev = &ctx->dsi->dev; - int ret; - ret = sony_td4353_jdi_off(ctx); - if (ret < 0) - dev_err(dev, "Failed to power off panel: %d\n", ret); + sony_td4353_jdi_off(ctx); sony_td4353_assert_reset_gpios(ctx, 0); regulator_bulk_disable(ARRAY_SIZE(ctx->supplies), ctx->supplies); diff --git a/drivers/gpu/drm/panel/panel-summit.c b/drivers/gpu/drm/panel/panel-summit.c new file mode 100644 index 000000000000..e780faee1857 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-summit.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/backlight.h> +#include <drm/drm_device.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_mode.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> +#include <drm/drm_probe_helper.h> +#include <video/mipi_display.h> + +struct summit_data { + struct mipi_dsi_device *dsi; + struct backlight_device *bl; + struct drm_panel panel; +}; + +static int summit_set_brightness(struct device *dev) +{ + struct summit_data *s_data = dev_get_drvdata(dev); + int level = backlight_get_brightness(s_data->bl); + + return mipi_dsi_dcs_set_display_brightness(s_data->dsi, level); +} + +static int summit_bl_update_status(struct backlight_device *dev) +{ + return summit_set_brightness(&dev->dev); +} + +static const struct backlight_ops summit_bl_ops = { + .update_status = summit_bl_update_status, +}; + +static struct drm_display_mode summit_mode = { + .vdisplay = 2008, + .hdisplay = 60, + .hsync_start = 60 + 8, + .hsync_end = 60 + 8 + 80, + .htotal = 60 + 8 + 80 + 40, + .vsync_start = 2008 + 1, + .vsync_end = 2008 + 1 + 15, + .vtotal = 2008 + 1 + 15 + 6, + .clock = ((60 + 8 + 80 + 40) * (2008 + 1 + 15 + 6) * 60) / 1000, + .type = DRM_MODE_TYPE_DRIVER, + .flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC, +}; + +static int summit_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + connector->display_info.non_desktop = true; + drm_object_property_set_value(&connector->base, + connector->dev->mode_config.non_desktop_property, + connector->display_info.non_desktop); + + return drm_connector_helper_get_modes_fixed(connector, &summit_mode); +} + +static const struct drm_panel_funcs summit_panel_funcs = { + .get_modes = summit_get_modes, +}; + +static int summit_probe(struct mipi_dsi_device *dsi) +{ + struct backlight_properties props = { 0 }; + struct device *dev = &dsi->dev; + struct summit_data *s_data; + int ret; + + s_data = devm_kzalloc(dev, sizeof(*s_data), GFP_KERNEL); + if (!s_data) + return -ENOMEM; + + mipi_dsi_set_drvdata(dsi, s_data); + s_data->dsi = dsi; + + ret = device_property_read_u32(dev, "max-brightness", &props.max_brightness); + if (ret) + return ret; + props.type = BACKLIGHT_RAW; + + s_data->bl = devm_backlight_device_register(dev, dev_name(dev), + dev, s_data, &summit_bl_ops, &props); + if (IS_ERR(s_data->bl)) + return PTR_ERR(s_data->bl); + + drm_panel_init(&s_data->panel, dev, &summit_panel_funcs, + DRM_MODE_CONNECTOR_DSI); + drm_panel_add(&s_data->panel); + + return mipi_dsi_attach(dsi); +} + +static void summit_remove(struct mipi_dsi_device *dsi) +{ + struct summit_data *s_data = mipi_dsi_get_drvdata(dsi); + + mipi_dsi_detach(dsi); + drm_panel_remove(&s_data->panel); +} + +static int summit_suspend(struct device *dev) +{ + struct summit_data *s_data = dev_get_drvdata(dev); + + return mipi_dsi_dcs_set_display_brightness(s_data->dsi, 0); +} + +static DEFINE_SIMPLE_DEV_PM_OPS(summit_pm_ops, summit_suspend, + summit_set_brightness); + +static const struct of_device_id summit_of_match[] = { + { .compatible = "apple,summit" }, + {}, +}; + +MODULE_DEVICE_TABLE(of, summit_of_match); + +static struct mipi_dsi_driver summit_driver = { + .probe = summit_probe, + .remove = summit_remove, + .driver = { + .name = "panel-summit", + .of_match_table = summit_of_match, + .pm = pm_sleep_ptr(&summit_pm_ops), + }, +}; +module_mipi_dsi_driver(summit_driver); + +MODULE_DESCRIPTION("Summit Display Panel Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-visionox-rm692e5.c b/drivers/gpu/drm/panel/panel-visionox-rm692e5.c new file mode 100644 index 000000000000..4db7fa8d74c4 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-visionox-rm692e5.c @@ -0,0 +1,442 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Generated with linux-mdss-dsi-panel-driver-generator from vendor device tree: + * Copyright (c) 2013, The Linux Foundation. All rights reserved. + * Copyright (c) 2025, Eugene Lepshy <fekz115@gmail.com> + * Copyright (c) 2025, Danila Tikhonov <danila@jiaxyga.com> + */ + +#include <linux/backlight.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/regulator/consumer.h> + +#include <video/mipi_display.h> + +#include <drm/display/drm_dsc.h> +#include <drm/display/drm_dsc_helper.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> +#include <drm/drm_probe_helper.h> + +struct visionox_rm692e5 { + struct drm_panel panel; + struct mipi_dsi_device *dsi; + struct drm_dsc_config dsc; + struct gpio_desc *reset_gpio; + struct regulator_bulk_data *supplies; +}; + +static const struct regulator_bulk_data visionox_rm692e5_supplies[] = { + { .supply = "vddio" }, /* 1p8 */ + { .supply = "vdd" }, /* 3p3 */ +}; + +static inline +struct visionox_rm692e5 *to_visionox_rm692e5(struct drm_panel *panel) +{ + return container_of(panel, struct visionox_rm692e5, panel); +} + +static void visionox_rm692e5_reset(struct visionox_rm692e5 *ctx) +{ + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + usleep_range(1000, 2000); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + msleep(32); +} + +static int visionox_rm692e5_on(struct visionox_rm692e5 *ctx) +{ + struct mipi_dsi_device *dsi = ctx->dsi; + struct mipi_dsi_multi_context dsi_ctx = { .dsi = dsi }; + + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfe, 0x40); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xbd, 0x07); + mipi_dsi_usleep_range(&dsi_ctx, 17000, 18000); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfe, 0xd2); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x50, 0x11); + mipi_dsi_dcs_set_display_brightness_multi(&dsi_ctx, 0x00ab); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x52, 0x30); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_WRITE_CONTROL_DISPLAY, 0x09); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x54, 0x60); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_WRITE_POWER_SAVE, 0x04); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x56, 0x38); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x58, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x59, 0x14); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x5a, 0x02); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x5b, 0x1c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x5c, 0x02); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x5d, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_SET_CABC_MIN_BRIGHTNESS, 0x20); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x5f, 0x01); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x60, 0xe8); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x61, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x62, 0x07); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x63, 0x0c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x64, 0x05); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x65, 0x0e); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x66, 0x05); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x67, 0x16); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x68, 0x18); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x69, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x6a, 0x10); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x6b, 0xf0); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x6c, 0x07); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x6d, 0x10); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x6e, 0x20); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x6f, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x70, 0x06); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x71, 0x0f); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x72, 0x0f); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x73, 0x33); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x74, 0x0e); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x75, 0x1c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x76, 0x2a); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x77, 0x38); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x78, 0x46); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x79, 0x54); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x7a, 0x62); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x7b, 0x69); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x7c, 0x70); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x7d, 0x77); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x7e, 0x79); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x7f, 0x7b); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x80, 0x7d); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x81, 0x7e); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x82, 0x01); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x83, 0x02); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x84, 0x22); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x85, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x86, 0x2a); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x87, 0x40); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x88, 0x2a); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x89, 0xbe); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x8a, 0x3a); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x8b, 0xfc); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x8c, 0x3a); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x8d, 0xfa); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x8e, 0x3a); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x8f, 0xf8); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x90, 0x3b); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x91, 0x38); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x92, 0x3b); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x93, 0x78); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x94, 0x3b); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x95, 0xb6); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x96, 0x4b); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x97, 0xf6); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x98, 0x4c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x99, 0x34); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x9a, 0x4c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x9b, 0x74); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x9c, 0x5c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x9d, 0x74); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x9e, 0x8c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x9f, 0xf4); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_READ_PPS_START, 0x02); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xa3, 0x1c); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xa4, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xa5, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xa6, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xa7, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, MIPI_DCS_READ_PPS_CONTINUE, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xaa, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xa0, 0x80); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfe, 0xa1); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xcd, 0x6b); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xce, 0xbb); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfe, 0xd1); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xb4, 0x01); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfe, 0x38); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x17, 0x0f); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0x18, 0x0f); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfe, 0x00); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xfa, 0x01); + mipi_dsi_dcs_write_seq_multi(&dsi_ctx, 0xc2, 0x08); + mipi_dsi_dcs_set_tear_on_multi(&dsi_ctx, MIPI_DSI_DCS_TEAR_MODE_VBLANK); + mipi_dsi_dcs_set_display_brightness_multi(&dsi_ctx, 0x000d); + mipi_dsi_dcs_exit_sleep_mode_multi(&dsi_ctx); + mipi_dsi_msleep(&dsi_ctx, 50); + mipi_dsi_dcs_set_display_on_multi(&dsi_ctx); + mipi_dsi_usleep_range(&dsi_ctx, 1000, 2000); + + return dsi_ctx.accum_err; +} + +static int visionox_rm692e5_disable(struct drm_panel *panel) +{ + struct visionox_rm692e5 *ctx = to_visionox_rm692e5(panel); + struct mipi_dsi_device *dsi = ctx->dsi; + struct mipi_dsi_multi_context dsi_ctx = { .dsi = dsi }; + + dsi->mode_flags &= ~MIPI_DSI_MODE_LPM; + + mipi_dsi_dcs_set_display_off_multi(&dsi_ctx); + mipi_dsi_usleep_range(&dsi_ctx, 1000, 2000); + mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx); + mipi_dsi_usleep_range(&dsi_ctx, 1000, 2000); + + return dsi_ctx.accum_err; +} + +static int visionox_rm692e5_prepare(struct drm_panel *panel) +{ + struct visionox_rm692e5 *ctx = to_visionox_rm692e5(panel); + struct drm_dsc_picture_parameter_set pps; + struct mipi_dsi_multi_context dsi_ctx = { .dsi = ctx->dsi }; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(visionox_rm692e5_supplies), + ctx->supplies); + if (ret < 0) + return ret; + + visionox_rm692e5_reset(ctx); + + ret = visionox_rm692e5_on(ctx); + if (ret < 0) { + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + goto err; + } + + drm_dsc_pps_payload_pack(&pps, &ctx->dsc); + mipi_dsi_picture_parameter_set_multi(&dsi_ctx, &pps); + mipi_dsi_compression_mode_ext_multi(&dsi_ctx, true, MIPI_DSI_COMPRESSION_DSC, 0); + + mipi_dsi_msleep(&dsi_ctx, 28); + + if (dsi_ctx.accum_err < 0) { + ret = dsi_ctx.accum_err; + goto err; + } + + return dsi_ctx.accum_err; +err: + regulator_bulk_disable(ARRAY_SIZE(visionox_rm692e5_supplies), + ctx->supplies); + return ret; +} + +static int visionox_rm692e5_unprepare(struct drm_panel *panel) +{ + struct visionox_rm692e5 *ctx = to_visionox_rm692e5(panel); + + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + regulator_bulk_disable(ARRAY_SIZE(visionox_rm692e5_supplies), + ctx->supplies); + + return 0; +} + +static const struct drm_display_mode visionox_rm692e5_modes[] = { + /* Let's initialize the highest frequency first */ + { /* 120Hz mode */ + .clock = (1080 + 26 + 39 + 36) * (2400 + 16 + 21 + 16) * 120 / 1000, + .hdisplay = 1080, + .hsync_start = 1080 + 26, + .hsync_end = 1080 + 26 + 39, + .htotal = 1080 + 26 + 39 + 36, + .vdisplay = 2400, + .vsync_start = 2400 + 16, + .vsync_end = 2400 + 16 + 21, + .vtotal = 2400 + 16 + 21 + 16, + .width_mm = 68, + .height_mm = 152, + .type = DRM_MODE_TYPE_DRIVER, + }, + { /* 90Hz mode */ + .clock = (1080 + 26 + 39 + 36) * (2400 + 16 + 21 + 16) * 90 / 1000, + .hdisplay = 1080, + .hsync_start = 1080 + 26, + .hsync_end = 1080 + 26 + 39, + .htotal = 1080 + 26 + 39 + 36, + .vdisplay = 2400, + .vsync_start = 2400 + 16, + .vsync_end = 2400 + 16 + 21, + .vtotal = 2400 + 16 + 21 + 16, + .width_mm = 68, + .height_mm = 152, + .type = DRM_MODE_TYPE_DRIVER, + }, + { /* 60Hz mode */ + .clock = (1080 + 26 + 39 + 36) * (2400 + 16 + 21 + 16) * 60 / 1000, + .hdisplay = 1080, + .hsync_start = 1080 + 26, + .hsync_end = 1080 + 26 + 39, + .htotal = 1080 + 26 + 39 + 36, + .vdisplay = 2400, + .vsync_start = 2400 + 16, + .vsync_end = 2400 + 16 + 21, + .vtotal = 2400 + 16 + 21 + 16, + .width_mm = 68, + .height_mm = 152, + .type = DRM_MODE_TYPE_DRIVER, + }, +}; + +static int visionox_rm692e5_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + int count = 0; + + for (int i = 0; i < ARRAY_SIZE(visionox_rm692e5_modes); i++) + count += drm_connector_helper_get_modes_fixed(connector, + &visionox_rm692e5_modes[i]); + + return count; +} + +static const struct drm_panel_funcs visionox_rm692e5_panel_funcs = { + .prepare = visionox_rm692e5_prepare, + .unprepare = visionox_rm692e5_unprepare, + .disable = visionox_rm692e5_disable, + .get_modes = visionox_rm692e5_get_modes, +}; + +static int visionox_rm692e5_bl_update_status(struct backlight_device *bl) +{ + struct mipi_dsi_device *dsi = bl_get_data(bl); + u16 brightness = backlight_get_brightness(bl); + int ret; + + dsi->mode_flags &= ~MIPI_DSI_MODE_LPM; + + ret = mipi_dsi_dcs_set_display_brightness_large(dsi, brightness); + if (ret < 0) + return ret; + + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + + return 0; +} + +static int visionox_rm692e5_bl_get_brightness(struct backlight_device *bl) +{ + struct mipi_dsi_device *dsi = bl_get_data(bl); + u16 brightness; + int ret; + + dsi->mode_flags &= ~MIPI_DSI_MODE_LPM; + + ret = mipi_dsi_dcs_get_display_brightness_large(dsi, &brightness); + if (ret < 0) + return ret; + + dsi->mode_flags |= MIPI_DSI_MODE_LPM; + + return brightness; +} + +static const struct backlight_ops visionox_rm692e5_bl_ops = { + .update_status = visionox_rm692e5_bl_update_status, + .get_brightness = visionox_rm692e5_bl_get_brightness, +}; + +static struct backlight_device * +visionox_rm692e5_create_backlight(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + const struct backlight_properties props = { + .type = BACKLIGHT_RAW, + .brightness = 2047, + .max_brightness = 4095, + }; + + return devm_backlight_device_register(dev, dev_name(dev), dev, dsi, + &visionox_rm692e5_bl_ops, &props); +} + +static int visionox_rm692e5_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + struct visionox_rm692e5 *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ret = devm_regulator_bulk_get_const(&dsi->dev, + ARRAY_SIZE(visionox_rm692e5_supplies), + visionox_rm692e5_supplies, + &ctx->supplies); + if (ret < 0) + return dev_err_probe(dev, ret, "Failed to get regulators\n"); + + ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(ctx->reset_gpio)) + return dev_err_probe(dev, PTR_ERR(ctx->reset_gpio), + "Failed to get reset-gpios\n"); + + ctx->dsi = dsi; + mipi_dsi_set_drvdata(dsi, ctx); + + dsi->lanes = 4; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_CLOCK_NON_CONTINUOUS; + + drm_panel_init(&ctx->panel, dev, &visionox_rm692e5_panel_funcs, + DRM_MODE_CONNECTOR_DSI); + ctx->panel.prepare_prev_first = true; + + ctx->panel.backlight = visionox_rm692e5_create_backlight(dsi); + if (IS_ERR(ctx->panel.backlight)) + return dev_err_probe(dev, PTR_ERR(ctx->panel.backlight), + "Failed to create backlight\n"); + + drm_panel_add(&ctx->panel); + + dsi->dsc = &ctx->dsc; + ctx->dsc.dsc_version_major = 1; + ctx->dsc.dsc_version_minor = 1; + ctx->dsc.slice_height = 20; + ctx->dsc.slice_width = 540; + ctx->dsc.slice_count = 1080 / ctx->dsc.slice_width; + ctx->dsc.bits_per_component = 10; + ctx->dsc.bits_per_pixel = 8 << 4; + ctx->dsc.block_pred_enable = true; + + ret = devm_mipi_dsi_attach(dev, dsi); + if (ret < 0) { + drm_panel_remove(&ctx->panel); + return dev_err_probe(dev, ret, "Failed to attach to DSI host\n"); + } + + return 0; +} + +static void visionox_rm692e5_remove(struct mipi_dsi_device *dsi) +{ + struct visionox_rm692e5 *ctx = mipi_dsi_get_drvdata(dsi); + + drm_panel_remove(&ctx->panel); +} + +static const struct of_device_id visionox_rm692e5_of_match[] = { + { .compatible = "visionox,rm692e5" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, visionox_rm692e5_of_match); + +static struct mipi_dsi_driver visionox_rm692e5_driver = { + .probe = visionox_rm692e5_probe, + .remove = visionox_rm692e5_remove, + .driver = { + .name = "panel-visionox-rm692e5", + .of_match_table = visionox_rm692e5_of_match, + }, +}; +module_mipi_dsi_driver(visionox_rm692e5_driver); + +MODULE_AUTHOR("Eugene Lepshy <fekz115@gmail.com>"); +MODULE_AUTHOR("Danila Tikhonov <danila@jiaxyga.com>"); +MODULE_DESCRIPTION("DRM driver for Visionox RM692E5 cmd mode dsi panel"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index 4a9c4afa9ad7..0f52766a3120 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -636,8 +636,8 @@ static int panthor_fw_read_build_info(struct panthor_device *ptdev, u32 ehdr) { struct panthor_fw_build_info_hdr hdr; - char header[9]; - const char git_sha_header[sizeof(header)] = "git_sha: "; + static const char git_sha_header[] = "git_sha: "; + const int header_len = sizeof(git_sha_header) - 1; int ret; ret = panthor_fw_binary_iter_read(ptdev, iter, &hdr, sizeof(hdr)); @@ -651,8 +651,7 @@ static int panthor_fw_read_build_info(struct panthor_device *ptdev, return 0; } - if (memcmp(git_sha_header, fw->data + hdr.meta_start, - sizeof(git_sha_header))) { + if (memcmp(git_sha_header, fw->data + hdr.meta_start, header_len)) { /* Not the expected header, this isn't metadata we understand */ return 0; } @@ -665,7 +664,7 @@ static int panthor_fw_read_build_info(struct panthor_device *ptdev, } drm_info(&ptdev->base, "Firmware git sha: %s\n", - fw->data + hdr.meta_start + sizeof(git_sha_header)); + fw->data + hdr.meta_start + header_len); return 0; } diff --git a/drivers/gpu/drm/panthor/panthor_fw.h b/drivers/gpu/drm/panthor/panthor_fw.h index 22448abde992..6598d96c6d2a 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.h +++ b/drivers/gpu/drm/panthor/panthor_fw.h @@ -102,9 +102,9 @@ struct panthor_fw_cs_output_iface { #define CS_STATUS_BLOCKED_REASON_SB_WAIT 1 #define CS_STATUS_BLOCKED_REASON_PROGRESS_WAIT 2 #define CS_STATUS_BLOCKED_REASON_SYNC_WAIT 3 -#define CS_STATUS_BLOCKED_REASON_DEFERRED 5 -#define CS_STATUS_BLOCKED_REASON_RES 6 -#define CS_STATUS_BLOCKED_REASON_FLUSH 7 +#define CS_STATUS_BLOCKED_REASON_DEFERRED 4 +#define CS_STATUS_BLOCKED_REASON_RESOURCE 5 +#define CS_STATUS_BLOCKED_REASON_FLUSH 6 #define CS_STATUS_BLOCKED_REASON_MASK GENMASK(3, 0) u32 status_blocked_reason; u32 status_wait_sync_value_hi; diff --git a/drivers/gpu/drm/panthor/panthor_heap.c b/drivers/gpu/drm/panthor/panthor_heap.c index db0285ce5812..3bdf61c14264 100644 --- a/drivers/gpu/drm/panthor/panthor_heap.c +++ b/drivers/gpu/drm/panthor/panthor_heap.c @@ -97,6 +97,9 @@ struct panthor_heap_pool { /** @gpu_contexts: Buffer object containing the GPU heap contexts. */ struct panthor_kernel_bo *gpu_contexts; + + /** @size: Size of all chunks across all heaps in the pool. */ + atomic_t size; }; static int panthor_heap_ctx_stride(struct panthor_device *ptdev) @@ -118,7 +121,7 @@ static void *panthor_get_heap_ctx(struct panthor_heap_pool *pool, int id) panthor_get_heap_ctx_offset(pool, id); } -static void panthor_free_heap_chunk(struct panthor_vm *vm, +static void panthor_free_heap_chunk(struct panthor_heap_pool *pool, struct panthor_heap *heap, struct panthor_heap_chunk *chunk) { @@ -127,12 +130,13 @@ static void panthor_free_heap_chunk(struct panthor_vm *vm, heap->chunk_count--; mutex_unlock(&heap->lock); + atomic_sub(heap->chunk_size, &pool->size); + panthor_kernel_bo_destroy(chunk->bo); kfree(chunk); } -static int panthor_alloc_heap_chunk(struct panthor_device *ptdev, - struct panthor_vm *vm, +static int panthor_alloc_heap_chunk(struct panthor_heap_pool *pool, struct panthor_heap *heap, bool initial_chunk) { @@ -144,7 +148,7 @@ static int panthor_alloc_heap_chunk(struct panthor_device *ptdev, if (!chunk) return -ENOMEM; - chunk->bo = panthor_kernel_bo_create(ptdev, vm, heap->chunk_size, + chunk->bo = panthor_kernel_bo_create(pool->ptdev, pool->vm, heap->chunk_size, DRM_PANTHOR_BO_NO_MMAP, DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC, PANTHOR_VM_KERNEL_AUTO_VA); @@ -180,6 +184,8 @@ static int panthor_alloc_heap_chunk(struct panthor_device *ptdev, heap->chunk_count++; mutex_unlock(&heap->lock); + atomic_add(heap->chunk_size, &pool->size); + return 0; err_destroy_bo: @@ -191,17 +197,16 @@ err_free_chunk: return ret; } -static void panthor_free_heap_chunks(struct panthor_vm *vm, +static void panthor_free_heap_chunks(struct panthor_heap_pool *pool, struct panthor_heap *heap) { struct panthor_heap_chunk *chunk, *tmp; list_for_each_entry_safe(chunk, tmp, &heap->chunks, node) - panthor_free_heap_chunk(vm, heap, chunk); + panthor_free_heap_chunk(pool, heap, chunk); } -static int panthor_alloc_heap_chunks(struct panthor_device *ptdev, - struct panthor_vm *vm, +static int panthor_alloc_heap_chunks(struct panthor_heap_pool *pool, struct panthor_heap *heap, u32 chunk_count) { @@ -209,7 +214,7 @@ static int panthor_alloc_heap_chunks(struct panthor_device *ptdev, u32 i; for (i = 0; i < chunk_count; i++) { - ret = panthor_alloc_heap_chunk(ptdev, vm, heap, true); + ret = panthor_alloc_heap_chunk(pool, heap, true); if (ret) return ret; } @@ -226,7 +231,7 @@ panthor_heap_destroy_locked(struct panthor_heap_pool *pool, u32 handle) if (!heap) return -EINVAL; - panthor_free_heap_chunks(pool->vm, heap); + panthor_free_heap_chunks(pool, heap); mutex_destroy(&heap->lock); kfree(heap); return 0; @@ -308,8 +313,7 @@ int panthor_heap_create(struct panthor_heap_pool *pool, heap->max_chunks = max_chunks; heap->target_in_flight = target_in_flight; - ret = panthor_alloc_heap_chunks(pool->ptdev, vm, heap, - initial_chunk_count); + ret = panthor_alloc_heap_chunks(pool, heap, initial_chunk_count); if (ret) goto err_free_heap; @@ -342,7 +346,7 @@ int panthor_heap_create(struct panthor_heap_pool *pool, return id; err_free_heap: - panthor_free_heap_chunks(pool->vm, heap); + panthor_free_heap_chunks(pool, heap); mutex_destroy(&heap->lock); kfree(heap); @@ -389,6 +393,7 @@ int panthor_heap_return_chunk(struct panthor_heap_pool *pool, removed = chunk; list_del(&chunk->node); heap->chunk_count--; + atomic_sub(heap->chunk_size, &pool->size); break; } } @@ -466,7 +471,7 @@ int panthor_heap_grow(struct panthor_heap_pool *pool, * further jobs in this queue fail immediately instead of having to * wait for the job timeout. */ - ret = panthor_alloc_heap_chunk(pool->ptdev, pool->vm, heap, false); + ret = panthor_alloc_heap_chunk(pool, heap, false); if (ret) goto out_unlock; @@ -560,6 +565,8 @@ panthor_heap_pool_create(struct panthor_device *ptdev, struct panthor_vm *vm) if (ret) goto err_destroy_pool; + atomic_add(pool->gpu_contexts->obj->size, &pool->size); + return pool; err_destroy_pool: @@ -594,8 +601,10 @@ void panthor_heap_pool_destroy(struct panthor_heap_pool *pool) xa_for_each(&pool->xa, i, heap) drm_WARN_ON(&pool->ptdev->base, panthor_heap_destroy_locked(pool, i)); - if (!IS_ERR_OR_NULL(pool->gpu_contexts)) + if (!IS_ERR_OR_NULL(pool->gpu_contexts)) { + atomic_sub(pool->gpu_contexts->obj->size, &pool->size); panthor_kernel_bo_destroy(pool->gpu_contexts); + } /* Reflects the fact the pool has been destroyed. */ pool->vm = NULL; @@ -605,27 +614,16 @@ void panthor_heap_pool_destroy(struct panthor_heap_pool *pool) } /** - * panthor_heap_pool_size() - Calculate size of all chunks across all heaps in a pool - * @pool: Pool whose total chunk size to calculate. + * panthor_heap_pool_size() - Get a heap pool's total size + * @pool: Pool whose total chunks size to return * - * This function adds the size of all heap chunks across all heaps in the - * argument pool. It also adds the size of the gpu contexts kernel bo. - * It is meant to be used by fdinfo for displaying the size of internal - * driver BO's that aren't exposed to userspace through a GEM handle. + * Returns the aggregated size of all chunks for all heaps in the pool * */ size_t panthor_heap_pool_size(struct panthor_heap_pool *pool) { - struct panthor_heap *heap; - unsigned long i; - size_t size = 0; - - down_read(&pool->lock); - xa_for_each(&pool->xa, i, heap) - size += heap->chunk_size * heap->chunk_count; - up_read(&pool->lock); - - size += pool->gpu_contexts->obj->size; + if (!pool) + return 0; - return size; + return atomic_read(&pool->size); } diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 8c6fc587ddc3..12a02e28f50f 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -1963,13 +1963,7 @@ void panthor_vm_heaps_sizes(struct panthor_file *pfile, struct drm_memory_stats xa_lock(&pfile->vms->xa); xa_for_each(&pfile->vms->xa, i, vm) { - size_t size = 0; - - mutex_lock(&vm->heaps.lock); - if (vm->heaps.pool) - size = panthor_heap_pool_size(vm->heaps.pool); - mutex_unlock(&vm->heaps.lock); - + size_t size = panthor_heap_pool_size(vm->heaps.pool); stats->resident += size; if (vm->as.id >= 0) stats->active += size; diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index 1a276db095ff..4d31d1967716 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -9,6 +9,7 @@ #include <drm/panthor_drm.h> #include <linux/build_bug.h> +#include <linux/cleanup.h> #include <linux/clk.h> #include <linux/delay.h> #include <linux/dma-mapping.h> @@ -631,10 +632,10 @@ struct panthor_group { struct panthor_gpu_usage data; /** - * @lock: Mutex to govern concurrent access from drm file's fdinfo callback - * and job post-completion processing function + * @fdinfo.lock: Spinlock to govern concurrent access from drm file's fdinfo + * callback and job post-completion processing function */ - struct mutex lock; + spinlock_t lock; /** @fdinfo.kbo_sizes: Aggregate size of private kernel BO's held by the group. */ size_t kbo_sizes; @@ -910,8 +911,6 @@ static void group_release_work(struct work_struct *work) release_work); u32 i; - mutex_destroy(&group->fdinfo.lock); - for (i = 0; i < group->queue_count; i++) group_free_queue(group, group->queues[i]); @@ -2861,12 +2860,12 @@ static void update_fdinfo_stats(struct panthor_job *job) struct panthor_job_profiling_data *slots = queue->profiling.slots->kmap; struct panthor_job_profiling_data *data = &slots[job->profiling.slot]; - mutex_lock(&group->fdinfo.lock); - if (job->profiling.mask & PANTHOR_DEVICE_PROFILING_CYCLES) - fdinfo->cycles += data->cycles.after - data->cycles.before; - if (job->profiling.mask & PANTHOR_DEVICE_PROFILING_TIMESTAMP) - fdinfo->time += data->time.after - data->time.before; - mutex_unlock(&group->fdinfo.lock); + scoped_guard(spinlock, &group->fdinfo.lock) { + if (job->profiling.mask & PANTHOR_DEVICE_PROFILING_CYCLES) + fdinfo->cycles += data->cycles.after - data->cycles.before; + if (job->profiling.mask & PANTHOR_DEVICE_PROFILING_TIMESTAMP) + fdinfo->time += data->time.after - data->time.before; + } } void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile) @@ -2880,12 +2879,11 @@ void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile) xa_lock(&gpool->xa); xa_for_each(&gpool->xa, i, group) { - mutex_lock(&group->fdinfo.lock); + guard(spinlock)(&group->fdinfo.lock); pfile->stats.cycles += group->fdinfo.data.cycles; pfile->stats.time += group->fdinfo.data.time; group->fdinfo.data.cycles = 0; group->fdinfo.data.time = 0; - mutex_unlock(&group->fdinfo.lock); } xa_unlock(&gpool->xa); } @@ -3537,7 +3535,7 @@ int panthor_group_create(struct panthor_file *pfile, mutex_unlock(&sched->reset.lock); add_group_kbo_sizes(group->ptdev, group); - mutex_init(&group->fdinfo.lock); + spin_lock_init(&group->fdinfo.lock); return gid; diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 05c13102a8cb..d22889fbfa9c 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -359,7 +359,8 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev) return -1; } -static void r300_gpu_init(struct radeon_device *rdev) +/* rs400_gpu_init also calls this! */ +void r300_gpu_init(struct radeon_device *rdev) { uint32_t gb_tile_config, tmp; diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index 1e00f6b99f94..8f5e07834fcc 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -165,6 +165,7 @@ void r200_set_safe_registers(struct radeon_device *rdev); */ extern int r300_init(struct radeon_device *rdev); extern void r300_fini(struct radeon_device *rdev); +extern void r300_gpu_init(struct radeon_device *rdev); extern int r300_suspend(struct radeon_device *rdev); extern int r300_resume(struct radeon_device *rdev); extern int r300_asic_reset(struct radeon_device *rdev, bool hard); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 6f071e61f764..bbd39348a7ab 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -530,7 +530,7 @@ int radeon_wb_init(struct radeon_device *rdev) * @mc: memory controller structure holding memory informations * @base: base address at which to put VRAM * - * Function will place try to place VRAM at base address provided + * Function will try to place VRAM at base address provided * as parameter (which is so far either PCI aperture address or * for IGP TOM base address). * @@ -557,7 +557,7 @@ int radeon_wb_init(struct radeon_device *rdev) * * Note 3: when limiting vram it's safe to overwritte real_vram_size because * we are not in case where real_vram_size is inferior to mc_vram_size (ie - * note afected by bogus hw of Novell bug 204882 + along with lots of ubuntu + * not affected by bogus hw of Novell bug 204882 + along with lots of ubuntu * ones) * * Note 4: IGP TOM addr should be the same as the aperture addr, we don't @@ -594,7 +594,7 @@ void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 * @rdev: radeon device structure holding all necessary informations * @mc: memory controller structure holding memory informations * - * Function will place try to place GTT before or after VRAM. + * Function will try to place GTT before or after VRAM. * * If GTT size is bigger than space left then we ajust GTT size. * Thus function will never fails. diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index daff61586be5..8ff4f18b51a9 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -840,7 +840,7 @@ int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring) } radeon_fence_write(rdev, atomic64_read(&rdev->fence_drv[ring].last_seq), ring); rdev->fence_drv[ring].initialized = true; - dev_info(rdev->dev, "fence driver on ring %d use gpu addr 0x%016llx\n", + dev_info(rdev->dev, "fence driver on ring %d uses gpu addr 0x%016llx\n", ring, rdev->fence_drv[ring].gpu_addr); return 0; } diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c index d6c18fd740ec..13cd0a688a65 100644 --- a/drivers/gpu/drm/radeon/rs400.c +++ b/drivers/gpu/drm/radeon/rs400.c @@ -256,8 +256,22 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev) static void rs400_gpu_init(struct radeon_device *rdev) { - /* FIXME: is this correct ? */ - r420_pipes_init(rdev); + /* Earlier code was calling r420_pipes_init and then + * rs400_mc_wait_for_idle(rdev). The problem is that + * at least on my Mobility Radeon Xpress 200M RC410 card + * that ends up in this code path ends up num_gb_pipes == 3 + * while the card seems to have only one pipe. With the + * r420 pipe initialization method. + * + * Problems shown up as HyperZ glitches, see: + * https://bugs.freedesktop.org/show_bug.cgi?id=110897 + * + * Delegating initialization to r300 code seems to work + * and results in proper pipe numbers. The rs400 cards + * are said to be not r400, but r300 kind of cards. + */ + r300_gpu_init(rdev); + if (rs400_mc_wait_for_idle(rdev)) { pr_warn("rs400: Failed to wait MC idle while programming pipes. Bad things might happen. %08x\n", RREG32(RADEON_MC_STATUS)); diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 6c95575ce109..26197aceb001 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -6198,7 +6198,7 @@ static inline u32 si_get_ih_wptr(struct radeon_device *rdev) if (wptr & RB_OVERFLOW) { wptr &= ~RB_OVERFLOW; - /* When a ring buffer overflow happen start parsing interrupt + /* When a ring buffer overflow happens, start parsing interrupts * from the last not overwritten vector (wptr + 16). Hopefully * this should allow us to catchup. */ diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c index 0844175c37c5..a8265a1bf9ff 100644 --- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c +++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c @@ -32,27 +32,32 @@ #include "rockchip_drm_drv.h" -#define RK3288_GRF_SOC_CON6 0x25c -#define RK3288_EDP_LCDC_SEL BIT(5) -#define RK3399_GRF_SOC_CON20 0x6250 -#define RK3399_EDP_LCDC_SEL BIT(5) - -#define HIWORD_UPDATE(val, mask) (val | (mask) << 16) - #define PSR_WAIT_LINE_FLAG_TIMEOUT_MS 100 +#define GRF_REG_FIELD(_reg, _lsb, _msb) { \ + .reg = _reg, \ + .lsb = _lsb, \ + .msb = _msb, \ + .valid = true, \ + } + +struct rockchip_grf_reg_field { + u32 reg; + u32 lsb; + u32 msb; + bool valid; +}; + /** * struct rockchip_dp_chip_data - splite the grf setting of kind of chips - * @lcdsel_grf_reg: grf register offset of lcdc select - * @lcdsel_big: reg value of selecting vop big for eDP - * @lcdsel_lit: reg value of selecting vop little for eDP + * @lcdc_sel: grf register field of lcdc_sel * @chip_type: specific chip type + * @reg: register base address */ struct rockchip_dp_chip_data { - u32 lcdsel_grf_reg; - u32 lcdsel_big; - u32 lcdsel_lit; + const struct rockchip_grf_reg_field lcdc_sel; u32 chip_type; + u32 reg; }; struct rockchip_dp_device { @@ -84,6 +89,26 @@ static struct rockchip_dp_device *pdata_encoder_to_dp(struct analogix_dp_plat_da return container_of(plat_data, struct rockchip_dp_device, plat_data); } +static int rockchip_grf_write(struct regmap *grf, u32 reg, u32 mask, u32 val) +{ + return regmap_write(grf, reg, (mask << 16) | (val & mask)); +} + +static int rockchip_grf_field_write(struct regmap *grf, + const struct rockchip_grf_reg_field *field, + u32 val) +{ + u32 mask; + + if (!field->valid) + return 0; + + mask = GENMASK(field->msb, field->lsb); + val <<= field->lsb; + + return rockchip_grf_write(grf, field->reg, mask, val); +} + static int rockchip_dp_pre_init(struct rockchip_dp_device *dp) { reset_control_assert(dp->rst); @@ -181,7 +206,6 @@ static void rockchip_dp_drm_encoder_enable(struct drm_encoder *encoder, struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state; int ret; - u32 val; crtc = rockchip_dp_drm_get_new_crtc(encoder, state); if (!crtc) @@ -192,24 +216,19 @@ static void rockchip_dp_drm_encoder_enable(struct drm_encoder *encoder, if (old_crtc_state && old_crtc_state->self_refresh_active) return; - ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, encoder); - if (ret < 0) - return; - - if (ret) - val = dp->data->lcdsel_lit; - else - val = dp->data->lcdsel_big; - - DRM_DEV_DEBUG(dp->dev, "vop %s output to dp\n", (ret) ? "LIT" : "BIG"); - ret = clk_prepare_enable(dp->grfclk); if (ret < 0) { DRM_DEV_ERROR(dp->dev, "failed to enable grfclk %d\n", ret); return; } - ret = regmap_write(dp->grf, dp->data->lcdsel_grf_reg, val); + ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, encoder); + if (ret < 0) + return; + + DRM_DEV_DEBUG(dp->dev, "vop %s output to dp\n", (ret) ? "LIT" : "BIG"); + + ret = rockchip_grf_field_write(dp->grf, &dp->data->lcdc_sel, ret); if (ret != 0) DRM_DEV_ERROR(dp->dev, "Could not write to GRF: %d\n", ret); @@ -379,6 +398,8 @@ static int rockchip_dp_probe(struct platform_device *pdev) const struct rockchip_dp_chip_data *dp_data; struct drm_panel *panel = NULL; struct rockchip_dp_device *dp; + struct resource *res; + int i; int ret; dp_data = of_device_get_match_data(dev); @@ -393,9 +414,24 @@ static int rockchip_dp_probe(struct platform_device *pdev) if (!dp) return -ENOMEM; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + i = 0; + while (dp_data[i].reg) { + if (dp_data[i].reg == res->start) { + dp->data = &dp_data[i]; + break; + } + + i++; + } + + if (!dp->data) + return dev_err_probe(dev, -EINVAL, "no chip-data for %s node\n", + dev->of_node->name); + dp->dev = dev; dp->adp = ERR_PTR(-ENODEV); - dp->data = dp_data; dp->plat_data.panel = panel; dp->plat_data.dev_type = dp->data->chip_type; dp->plat_data.power_on = rockchip_dp_poweron; @@ -447,18 +483,22 @@ static int rockchip_dp_resume(struct device *dev) static DEFINE_RUNTIME_DEV_PM_OPS(rockchip_dp_pm_ops, rockchip_dp_suspend, rockchip_dp_resume, NULL); -static const struct rockchip_dp_chip_data rk3399_edp = { - .lcdsel_grf_reg = RK3399_GRF_SOC_CON20, - .lcdsel_big = HIWORD_UPDATE(0, RK3399_EDP_LCDC_SEL), - .lcdsel_lit = HIWORD_UPDATE(RK3399_EDP_LCDC_SEL, RK3399_EDP_LCDC_SEL), - .chip_type = RK3399_EDP, +static const struct rockchip_dp_chip_data rk3399_edp[] = { + { + .lcdc_sel = GRF_REG_FIELD(0x6250, 5, 5), + .chip_type = RK3399_EDP, + .reg = 0xff970000, + }, + { /* sentinel */ } }; -static const struct rockchip_dp_chip_data rk3288_dp = { - .lcdsel_grf_reg = RK3288_GRF_SOC_CON6, - .lcdsel_big = HIWORD_UPDATE(0, RK3288_EDP_LCDC_SEL), - .lcdsel_lit = HIWORD_UPDATE(RK3288_EDP_LCDC_SEL, RK3288_EDP_LCDC_SEL), - .chip_type = RK3288_DP, +static const struct rockchip_dp_chip_data rk3288_dp[] = { + { + .lcdc_sel = GRF_REG_FIELD(0x025c, 5, 5), + .chip_type = RK3288_DP, + .reg = 0xff970000, + }, + { /* sentinel */ } }; static const struct of_device_id rockchip_dp_dt_ids[] = { diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index e7a6669c46b0..f737e7d46e66 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -203,7 +203,7 @@ static int rockchip_hdmi_parse_dt(struct rockchip_hdmi *hdmi) hdmi->regmap = syscon_regmap_lookup_by_phandle(np, "rockchip,grf"); if (IS_ERR(hdmi->regmap)) { - drm_err(hdmi, "Unable to get rockchip,grf\n"); + dev_err(hdmi->dev, "Unable to get rockchip,grf\n"); return PTR_ERR(hdmi->regmap); } @@ -214,7 +214,7 @@ static int rockchip_hdmi_parse_dt(struct rockchip_hdmi *hdmi) if (IS_ERR(hdmi->ref_clk)) { ret = PTR_ERR(hdmi->ref_clk); if (ret != -EPROBE_DEFER) - drm_err(hdmi, "failed to get reference clock\n"); + dev_err(hdmi->dev, "failed to get reference clock\n"); return ret; } @@ -222,7 +222,7 @@ static int rockchip_hdmi_parse_dt(struct rockchip_hdmi *hdmi) if (IS_ERR(hdmi->grf_clk)) { ret = PTR_ERR(hdmi->grf_clk); if (ret != -EPROBE_DEFER) - drm_err(hdmi, "failed to get grf clock\n"); + dev_err(hdmi->dev, "failed to get grf clock\n"); return ret; } @@ -302,16 +302,16 @@ static void dw_hdmi_rockchip_encoder_enable(struct drm_encoder *encoder) ret = clk_prepare_enable(hdmi->grf_clk); if (ret < 0) { - drm_err(hdmi, "failed to enable grfclk %d\n", ret); + dev_err(hdmi->dev, "failed to enable grfclk %d\n", ret); return; } ret = regmap_write(hdmi->regmap, hdmi->chip_data->lcdsel_grf_reg, val); if (ret != 0) - drm_err(hdmi, "Could not write to GRF: %d\n", ret); + dev_err(hdmi->dev, "Could not write to GRF: %d\n", ret); clk_disable_unprepare(hdmi->grf_clk); - drm_dbg(hdmi, "vop %s output to hdmi\n", ret ? "LIT" : "BIG"); + dev_dbg(hdmi->dev, "vop %s output to hdmi\n", ret ? "LIT" : "BIG"); } static int @@ -574,7 +574,7 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master, ret = rockchip_hdmi_parse_dt(hdmi); if (ret) { if (ret != -EPROBE_DEFER) - drm_err(hdmi, "Unable to parse OF data\n"); + dev_err(hdmi->dev, "Unable to parse OF data\n"); return ret; } @@ -582,7 +582,7 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master, if (IS_ERR(hdmi->phy)) { ret = PTR_ERR(hdmi->phy); if (ret != -EPROBE_DEFER) - drm_err(hdmi, "failed to get phy\n"); + dev_err(hdmi->dev, "failed to get phy\n"); return ret; } diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c index f41151d49fca..3d1dddb34603 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c @@ -242,7 +242,7 @@ static void dw_hdmi_qp_rk3588_hpd_work(struct work_struct *work) if (drm) { changed = drm_helper_hpd_irq_event(drm); if (changed) - drm_dbg(hdmi, "connector status changed\n"); + dev_dbg(hdmi->dev, "connector status changed\n"); } } @@ -472,7 +472,7 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master, } } if (hdmi->port_id < 0) { - drm_err(hdmi, "Failed to match HDMI port ID\n"); + dev_err(hdmi->dev, "Failed to match HDMI port ID\n"); return hdmi->port_id; } @@ -496,20 +496,20 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master, hdmi->regmap = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,grf"); if (IS_ERR(hdmi->regmap)) { - drm_err(hdmi, "Unable to get rockchip,grf\n"); + dev_err(hdmi->dev, "Unable to get rockchip,grf\n"); return PTR_ERR(hdmi->regmap); } hdmi->vo_regmap = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,vo-grf"); if (IS_ERR(hdmi->vo_regmap)) { - drm_err(hdmi, "Unable to get rockchip,vo-grf\n"); + dev_err(hdmi->dev, "Unable to get rockchip,vo-grf\n"); return PTR_ERR(hdmi->vo_regmap); } ret = devm_clk_bulk_get_all_enabled(hdmi->dev, &clks); if (ret < 0) { - drm_err(hdmi, "Failed to get clocks: %d\n", ret); + dev_err(hdmi->dev, "Failed to get clocks: %d\n", ret); return ret; } @@ -517,7 +517,7 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master, GPIOD_OUT_HIGH); if (IS_ERR(hdmi->enable_gpio)) { ret = PTR_ERR(hdmi->enable_gpio); - drm_err(hdmi, "Failed to request enable GPIO: %d\n", ret); + dev_err(hdmi->dev, "Failed to request enable GPIO: %d\n", ret); return ret; } @@ -525,7 +525,7 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master, if (IS_ERR(hdmi->phy)) { ret = PTR_ERR(hdmi->phy); if (ret != -EPROBE_DEFER) - drm_err(hdmi, "failed to get phy: %d\n", ret); + dev_err(hdmi->dev, "failed to get phy: %d\n", ret); return ret; } @@ -564,7 +564,7 @@ static int dw_hdmi_qp_rockchip_bind(struct device *dev, struct device *master, connector = drm_bridge_connector_init(drm, encoder); if (IS_ERR(connector)) { ret = PTR_ERR(connector); - drm_err(hdmi, "failed to init bridge connector: %d\n", ret); + dev_err(hdmi->dev, "failed to init bridge connector: %d\n", ret); return ret; } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 439edc165ff6..180fad5d49ad 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -484,9 +484,11 @@ static void rockchip_drm_platform_remove(struct platform_device *pdev) static void rockchip_drm_platform_shutdown(struct platform_device *pdev) { - struct drm_device *drm = platform_get_drvdata(pdev); + if (component_master_is_bound(&pdev->dev, &rockchip_drm_ops)) { + struct drm_device *drm = platform_get_drvdata(pdev); - drm_atomic_helper_shutdown(drm); + drm_atomic_helper_shutdown(drm); + } } static const struct of_device_id rockchip_drm_dt_ids[] = { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index afc946ead870..d0f5fea15e21 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -33,7 +33,6 @@ #include <drm/drm_vblank.h> #include <uapi/linux/videodev2.h> -#include <dt-bindings/soc/rockchip,vop2.h> #include "rockchip_drm_gem.h" #include "rockchip_drm_vop2.h" @@ -102,147 +101,8 @@ enum vop2_afbc_format { VOP2_AFBC_FMT_INVALID = -1, }; -union vop2_alpha_ctrl { - u32 val; - struct { - /* [0:1] */ - u32 color_mode:1; - u32 alpha_mode:1; - /* [2:3] */ - u32 blend_mode:2; - u32 alpha_cal_mode:1; - /* [5:7] */ - u32 factor_mode:3; - /* [8:9] */ - u32 alpha_en:1; - u32 src_dst_swap:1; - u32 reserved:6; - /* [16:23] */ - u32 glb_alpha:8; - } bits; -}; - -struct vop2_alpha { - union vop2_alpha_ctrl src_color_ctrl; - union vop2_alpha_ctrl dst_color_ctrl; - union vop2_alpha_ctrl src_alpha_ctrl; - union vop2_alpha_ctrl dst_alpha_ctrl; -}; - -struct vop2_alpha_config { - bool src_premulti_en; - bool dst_premulti_en; - bool src_pixel_alpha_en; - bool dst_pixel_alpha_en; - u16 src_glb_alpha_value; - u16 dst_glb_alpha_value; -}; - -struct vop2_win { - struct vop2 *vop2; - struct drm_plane base; - const struct vop2_win_data *data; - struct regmap_field *reg[VOP2_WIN_MAX_REG]; - - /** - * @win_id: graphic window id, a cluster may be split into two - * graphics windows. - */ - u8 win_id; - u8 delay; - u32 offset; - - enum drm_plane_type type; -}; - -struct vop2_video_port { - struct drm_crtc crtc; - struct vop2 *vop2; - struct clk *dclk; - struct clk *dclk_src; - unsigned int id; - const struct vop2_video_port_data *data; - - struct completion dsp_hold_completion; - - /** - * @win_mask: Bitmask of windows attached to the video port; - */ - u32 win_mask; - - struct vop2_win *primary_plane; - struct drm_pending_vblank_event *event; - - unsigned int nlayers; -}; - -struct vop2 { - struct device *dev; - struct drm_device *drm; - struct vop2_video_port vps[ROCKCHIP_MAX_CRTC]; - - const struct vop2_data *data; - /* - * Number of windows that are registered as plane, may be less than the - * total number of hardware windows. - */ - u32 registered_num_wins; - - struct resource *res; - void __iomem *regs; - struct regmap *map; - - struct regmap *sys_grf; - struct regmap *vop_grf; - struct regmap *vo1_grf; - struct regmap *sys_pmu; - - /* physical map length of vop2 register */ - u32 len; - - void __iomem *lut_regs; - - /* protects crtc enable/disable */ - struct mutex vop2_lock; - - int irq; - - /* - * Some global resources are shared between all video ports(crtcs), so - * we need a ref counter here. - */ - unsigned int enable_count; - struct clk *hclk; - struct clk *aclk; - struct clk *pclk; - struct clk *pll_hdmiphy0; - - /* optional internal rgb encoder */ - struct rockchip_rgb *rgb; - - /* must be put at the end of the struct */ - struct vop2_win win[]; -}; - #define VOP2_MAX_DCLK_RATE 600000000 -#define vop2_output_if_is_hdmi(x) ((x) == ROCKCHIP_VOP2_EP_HDMI0 || \ - (x) == ROCKCHIP_VOP2_EP_HDMI1) - -#define vop2_output_if_is_dp(x) ((x) == ROCKCHIP_VOP2_EP_DP0 || \ - (x) == ROCKCHIP_VOP2_EP_DP1) - -#define vop2_output_if_is_edp(x) ((x) == ROCKCHIP_VOP2_EP_EDP0 || \ - (x) == ROCKCHIP_VOP2_EP_EDP1) - -#define vop2_output_if_is_mipi(x) ((x) == ROCKCHIP_VOP2_EP_MIPI0 || \ - (x) == ROCKCHIP_VOP2_EP_MIPI1) - -#define vop2_output_if_is_lvds(x) ((x) == ROCKCHIP_VOP2_EP_LVDS0 || \ - (x) == ROCKCHIP_VOP2_EP_LVDS1) - -#define vop2_output_if_is_dpi(x) ((x) == ROCKCHIP_VOP2_EP_RGB0) - /* * bus-format types. */ @@ -276,16 +136,6 @@ static DRM_ENUM_NAME_FN(drm_get_bus_format_name, drm_bus_format_enum_list) static const struct regmap_config vop2_regmap_config; -static struct vop2_video_port *to_vop2_video_port(struct drm_crtc *crtc) -{ - return container_of(crtc, struct vop2_video_port, crtc); -} - -static struct vop2_win *to_vop2_win(struct drm_plane *p) -{ - return container_of(p, struct vop2_win, base); -} - static void vop2_lock(struct vop2 *vop2) { mutex_lock(&vop2->vop2_lock); @@ -296,44 +146,6 @@ static void vop2_unlock(struct vop2 *vop2) mutex_unlock(&vop2->vop2_lock); } -static void vop2_writel(struct vop2 *vop2, u32 offset, u32 v) -{ - regmap_write(vop2->map, offset, v); -} - -static void vop2_vp_write(struct vop2_video_port *vp, u32 offset, u32 v) -{ - regmap_write(vp->vop2->map, vp->data->offset + offset, v); -} - -static u32 vop2_readl(struct vop2 *vop2, u32 offset) -{ - u32 val; - - regmap_read(vop2->map, offset, &val); - - return val; -} - -static u32 vop2_vp_read(struct vop2_video_port *vp, u32 offset) -{ - u32 val; - - regmap_read(vp->vop2->map, vp->data->offset + offset, &val); - - return val; -} - -static void vop2_win_write(const struct vop2_win *win, unsigned int reg, u32 v) -{ - regmap_field_write(win->reg[reg], v); -} - -static bool vop2_cluster_window(const struct vop2_win *win) -{ - return win->data->feature & WIN_FEATURE_CLUSTER; -} - /* * Note: * The write mask function is documented but missing on rk3566/8, writes @@ -543,7 +355,7 @@ static bool vop2_output_uv_swap(u32 bus_format, u32 output_mode) static bool vop2_output_rg_swap(struct vop2 *vop2, u32 bus_format) { - if (vop2->data->soc_id == 3588) { + if (vop2->version == VOP_VERSION_RK3588) { if (bus_format == MEDIA_BUS_FMT_YUV8_1X24 || bus_format == MEDIA_BUS_FMT_YUV10_1X30) return true; @@ -596,7 +408,7 @@ static bool rockchip_vop2_mod_supported(struct drm_plane *plane, u32 format, if (modifier == DRM_FORMAT_MOD_INVALID) return false; - if (vop2->data->soc_id == 3568 || vop2->data->soc_id == 3566) { + if (vop2->version == VOP_VERSION_RK3568) { if (vop2_cluster_window(win)) { if (modifier == DRM_FORMAT_MOD_LINEAR) { drm_dbg_kms(vop2->drm, @@ -607,7 +419,7 @@ static bool rockchip_vop2_mod_supported(struct drm_plane *plane, u32 format, } if (format == DRM_FORMAT_XRGB2101010 || format == DRM_FORMAT_XBGR2101010) { - if (vop2->data->soc_id == 3588) { + if (vop2->version == VOP_VERSION_RK3588) { if (!rockchip_afbc(plane, modifier)) { drm_dbg_kms(vop2->drm, "Only support 32 bpp format with afbc\n"); return false; @@ -1006,6 +818,7 @@ static void rk3588_vop2_power_domain_enable_all(struct vop2 *vop2) static void vop2_enable(struct vop2 *vop2) { int ret; + u32 version; ret = pm_runtime_resume_and_get(vop2->dev); if (ret < 0) { @@ -1025,10 +838,20 @@ static void vop2_enable(struct vop2 *vop2) return; } + version = vop2_readl(vop2, RK3568_VERSION_INFO); + if (version != vop2->version) { + drm_err(vop2->drm, "Hardware version(0x%08x) mismatch\n", version); + return; + } + + /* + * rk3566 share the same vop version with rk3568, so + * we need to use soc_id for identification here. + */ if (vop2->data->soc_id == 3566) vop2_writel(vop2, RK3568_OTP_WIN_EN, 1); - if (vop2->data->soc_id == 3588) + if (vop2->version == VOP_VERSION_RK3588) rk3588_vop2_power_domain_enable_all(vop2); vop2_writel(vop2, RK3568_REG_CFG_DONE, RK3568_REG_CFG_DONE__GLB_CFG_DONE_EN); @@ -1109,7 +932,7 @@ static void vop2_vp_dsp_lut_update_enable(struct vop2_video_port *vp) static inline bool vop2_supports_seamless_gamma_lut_update(struct vop2 *vop2) { - return (vop2->data->soc_id != 3566 && vop2->data->soc_id != 3568); + return vop2->version != VOP_VERSION_RK3568; } static bool vop2_gamma_lut_in_use(struct vop2 *vop2, struct vop2_video_port *vp) @@ -1451,12 +1274,15 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, &fb->format->format, afbc_en ? "AFBC" : "", &yrgb_mst); - if (vop2->data->soc_id > 3568) { + if (vop2->version > VOP_VERSION_RK3568) { vop2_win_write(win, VOP2_WIN_AXI_BUS_ID, win->data->axi_bus_id); vop2_win_write(win, VOP2_WIN_AXI_YRGB_R_ID, win->data->axi_yrgb_r_id); vop2_win_write(win, VOP2_WIN_AXI_UV_R_ID, win->data->axi_uv_r_id); } + if (vop2->version >= VOP_VERSION_RK3576) + vop2_win_write(win, VOP2_WIN_VP_SEL, vp->id); + if (vop2_cluster_window(win)) vop2_win_write(win, VOP2_WIN_AFBC_HALF_BLOCK_EN, half_block_en); @@ -1511,7 +1337,7 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, * this bit is gating disable, we should write 1 to * disable gating when enable afbc. */ - if (vop2->data->soc_id == 3566 || vop2->data->soc_id == 3568) + if (vop2->version == VOP_VERSION_RK3568) vop2_win_write(win, VOP2_WIN_AFBC_AUTO_GATING_EN, 0); else vop2_win_write(win, VOP2_WIN_AFBC_AUTO_GATING_EN, 1); @@ -1521,10 +1347,15 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, else vop2_win_write(win, VOP2_WIN_AFBC_BLOCK_SPLIT_EN, 0); + if (vop2->version >= VOP_VERSION_RK3576) { + vop2_win_write(win, VOP2_WIN_AFBC_PLD_OFFSET_EN, 1); + vop2_win_write(win, VOP2_WIN_AFBC_PLD_OFFSET, yrgb_mst); + } + transform_offset = vop2_afbc_transform_offset(pstate, half_block_en); vop2_win_write(win, VOP2_WIN_AFBC_HDR_PTR, yrgb_mst); vop2_win_write(win, VOP2_WIN_AFBC_PIC_SIZE, act_info); - vop2_win_write(win, VOP2_WIN_AFBC_TRANSFORM_OFFSET, transform_offset); + vop2_win_write(win, VOP2_WIN_TRANSFORM_OFFSET, transform_offset); vop2_win_write(win, VOP2_WIN_AFBC_PIC_OFFSET, ((src->x1 >> 16) | src->y1)); vop2_win_write(win, VOP2_WIN_AFBC_DSP_OFFSET, (dest->x1 | (dest->y1 << 16))); vop2_win_write(win, VOP2_WIN_AFBC_PIC_VIR_WIDTH, stride); @@ -1535,7 +1366,7 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, } else { if (vop2_cluster_window(win)) { vop2_win_write(win, VOP2_WIN_AFBC_ENABLE, 0); - vop2_win_write(win, VOP2_WIN_AFBC_TRANSFORM_OFFSET, 0); + vop2_win_write(win, VOP2_WIN_TRANSFORM_OFFSET, 0); } vop2_win_write(win, VOP2_WIN_YRGB_VIR, DIV_ROUND_UP(fb->pitches[0], 4)); @@ -1554,10 +1385,8 @@ static void vop2_plane_atomic_update(struct drm_plane *plane, rb_swap = vop2_win_rb_swap(fb->format->format); vop2_win_write(win, VOP2_WIN_RB_SWAP, rb_swap); - if (!vop2_cluster_window(win)) { - uv_swap = vop2_win_uv_swap(fb->format->format); - vop2_win_write(win, VOP2_WIN_UV_SWAP, uv_swap); - } + uv_swap = vop2_win_uv_swap(fb->format->format); + vop2_win_write(win, VOP2_WIN_UV_SWAP, uv_swap); if (fb->format->is_yuv) { vop2_win_write(win, VOP2_WIN_UV_VIR, DIV_ROUND_UP(fb->pitches[1], 4)); @@ -1731,6 +1560,7 @@ static void vop2_dither_setup(struct drm_crtc *crtc, u32 *dsp_ctrl) static void vop2_post_config(struct drm_crtc *crtc) { struct vop2_video_port *vp = to_vop2_video_port(crtc); + struct vop2 *vop2 = vp->vop2; struct drm_display_mode *mode = &crtc->state->adjusted_mode; u16 vtotal = mode->crtc_vtotal; u16 hdisplay = mode->crtc_hdisplay; @@ -1741,18 +1571,10 @@ static void vop2_post_config(struct drm_crtc *crtc) u32 top_margin = 100, bottom_margin = 100; u16 hsize = hdisplay * (left_margin + right_margin) / 200; u16 vsize = vdisplay * (top_margin + bottom_margin) / 200; - u16 hsync_len = mode->crtc_hsync_end - mode->crtc_hsync_start; u16 hact_end, vact_end; u32 val; - u32 bg_dly; - u32 pre_scan_dly; - bg_dly = vp->data->pre_scan_max_dly[3]; - vop2_writel(vp->vop2, RK3568_VP_BG_MIX_CTRL(vp->id), - FIELD_PREP(RK3568_VP_BG_MIX_CTRL__BG_DLY, bg_dly)); - - pre_scan_dly = ((bg_dly + (hdisplay >> 1) - 1) << 16) | hsync_len; - vop2_vp_write(vp, RK3568_VP_PRE_SCAN_HTIMING, pre_scan_dly); + vop2->ops->setup_bg_dly(vp); vsize = rounddown(vsize, 2); hsize = rounddown(hsize, 2); @@ -1788,347 +1610,6 @@ static void vop2_post_config(struct drm_crtc *crtc) vop2_vp_write(vp, RK3568_VP_DSP_BG, 0); } -static unsigned long rk3568_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags) -{ - struct vop2 *vop2 = vp->vop2; - struct drm_crtc *crtc = &vp->crtc; - u32 die, dip; - - die = vop2_readl(vop2, RK3568_DSP_IF_EN); - dip = vop2_readl(vop2, RK3568_DSP_IF_POL); - - switch (id) { - case ROCKCHIP_VOP2_EP_RGB0: - die &= ~RK3568_SYS_DSP_INFACE_EN_RGB_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_RGB | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_RGB_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL, polflags); - if (polflags & POLFLAG_DCLK_INV) - regmap_write(vop2->sys_grf, RK3568_GRF_VO_CON1, BIT(3 + 16) | BIT(3)); - else - regmap_write(vop2->sys_grf, RK3568_GRF_VO_CON1, BIT(3 + 16)); - break; - case ROCKCHIP_VOP2_EP_HDMI0: - die &= ~RK3568_SYS_DSP_INFACE_EN_HDMI_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_HDMI | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_HDMI_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__HDMI_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__HDMI_PIN_POL, polflags); - break; - case ROCKCHIP_VOP2_EP_EDP0: - die &= ~RK3568_SYS_DSP_INFACE_EN_EDP_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_EDP | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_EDP_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__EDP_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__EDP_PIN_POL, polflags); - break; - case ROCKCHIP_VOP2_EP_MIPI0: - die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_MIPI0 | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__MIPI_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__MIPI_PIN_POL, polflags); - break; - case ROCKCHIP_VOP2_EP_MIPI1: - die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI1_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_MIPI1 | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_MIPI1_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__MIPI_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__MIPI_PIN_POL, polflags); - break; - case ROCKCHIP_VOP2_EP_LVDS0: - die &= ~RK3568_SYS_DSP_INFACE_EN_LVDS0_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_LVDS0 | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_LVDS0_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL, polflags); - break; - case ROCKCHIP_VOP2_EP_LVDS1: - die &= ~RK3568_SYS_DSP_INFACE_EN_LVDS1_MUX; - die |= RK3568_SYS_DSP_INFACE_EN_LVDS1 | - FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_LVDS1_MUX, vp->id); - dip &= ~RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL; - dip |= FIELD_PREP(RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL, polflags); - break; - default: - drm_err(vop2->drm, "Invalid interface id %d on vp%d\n", id, vp->id); - return 0; - } - - dip |= RK3568_DSP_IF_POL__CFG_DONE_IMD; - - vop2_writel(vop2, RK3568_DSP_IF_EN, die); - vop2_writel(vop2, RK3568_DSP_IF_POL, dip); - - return crtc->state->adjusted_mode.crtc_clock * 1000LL; -} - -/* - * calc the dclk on rk3588 - * the available div of dclk is 1, 2, 4 - */ -static unsigned long rk3588_calc_dclk(unsigned long child_clk, unsigned long max_dclk) -{ - if (child_clk * 4 <= max_dclk) - return child_clk * 4; - else if (child_clk * 2 <= max_dclk) - return child_clk * 2; - else if (child_clk <= max_dclk) - return child_clk; - else - return 0; -} - -/* - * 4 pixclk/cycle on rk3588 - * RGB/eDP/HDMI: if_pixclk >= dclk_core - * DP: dp_pixclk = dclk_out <= dclk_core - * DSI: mipi_pixclk <= dclk_out <= dclk_core - */ -static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id, - int *dclk_core_div, int *dclk_out_div, - int *if_pixclk_div, int *if_dclk_div) -{ - struct vop2 *vop2 = vp->vop2; - struct drm_crtc *crtc = &vp->crtc; - struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode; - struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(crtc->state); - int output_mode = vcstate->output_mode; - unsigned long v_pixclk = adjusted_mode->crtc_clock * 1000LL; /* video timing pixclk */ - unsigned long dclk_core_rate = v_pixclk >> 2; - unsigned long dclk_rate = v_pixclk; - unsigned long dclk_out_rate; - unsigned long if_pixclk_rate; - int K = 1; - - if (vop2_output_if_is_hdmi(id)) { - /* - * K = 2: dclk_core = if_pixclk_rate > if_dclk_rate - * K = 1: dclk_core = hdmie_edp_dclk > if_pixclk_rate - */ - if (output_mode == ROCKCHIP_OUT_MODE_YUV420) { - dclk_rate = dclk_rate >> 1; - K = 2; - } - - /* - * if_pixclk_rate = (dclk_core_rate << 1) / K; - * if_dclk_rate = dclk_core_rate / K; - * *if_pixclk_div = dclk_rate / if_pixclk_rate; - * *if_dclk_div = dclk_rate / if_dclk_rate; - */ - *if_pixclk_div = 2; - *if_dclk_div = 4; - } else if (vop2_output_if_is_edp(id)) { - /* - * edp_pixclk = edp_dclk > dclk_core - */ - if_pixclk_rate = v_pixclk / K; - dclk_rate = if_pixclk_rate * K; - /* - * *if_pixclk_div = dclk_rate / if_pixclk_rate; - * *if_dclk_div = *if_pixclk_div; - */ - *if_pixclk_div = K; - *if_dclk_div = K; - } else if (vop2_output_if_is_dp(id)) { - if (output_mode == ROCKCHIP_OUT_MODE_YUV420) - dclk_out_rate = v_pixclk >> 3; - else - dclk_out_rate = v_pixclk >> 2; - - dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000000); - if (!dclk_rate) { - drm_err(vop2->drm, "DP dclk_out_rate out of range, dclk_out_rate: %ld Hz\n", - dclk_out_rate); - return 0; - } - *dclk_out_div = dclk_rate / dclk_out_rate; - } else if (vop2_output_if_is_mipi(id)) { - if_pixclk_rate = dclk_core_rate / K; - /* - * dclk_core = dclk_out * K = if_pixclk * K = v_pixclk / 4 - */ - dclk_out_rate = if_pixclk_rate; - /* - * dclk_rate = N * dclk_core_rate N = (1,2,4 ), - * we get a little factor here - */ - dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000000); - if (!dclk_rate) { - drm_err(vop2->drm, "MIPI dclk out of range, dclk_out_rate: %ld Hz\n", - dclk_out_rate); - return 0; - } - *dclk_out_div = dclk_rate / dclk_out_rate; - /* - * mipi pixclk == dclk_out - */ - *if_pixclk_div = 1; - } else if (vop2_output_if_is_dpi(id)) { - dclk_rate = v_pixclk; - } - - *dclk_core_div = dclk_rate / dclk_core_rate; - *if_pixclk_div = ilog2(*if_pixclk_div); - *if_dclk_div = ilog2(*if_dclk_div); - *dclk_core_div = ilog2(*dclk_core_div); - *dclk_out_div = ilog2(*dclk_out_div); - - drm_dbg(vop2->drm, "dclk: %ld, pixclk_div: %d, dclk_div: %d\n", - dclk_rate, *if_pixclk_div, *if_dclk_div); - - return dclk_rate; -} - -/* - * MIPI port mux on rk3588: - * 0: Video Port2 - * 1: Video Port3 - * 3: Video Port 1(MIPI1 only) - */ -static u32 rk3588_get_mipi_port_mux(int vp_id) -{ - if (vp_id == 1) - return 3; - else if (vp_id == 3) - return 1; - else - return 0; -} - -static u32 rk3588_get_hdmi_pol(u32 flags) -{ - u32 val; - - val = (flags & DRM_MODE_FLAG_NHSYNC) ? BIT(HSYNC_POSITIVE) : 0; - val |= (flags & DRM_MODE_FLAG_NVSYNC) ? BIT(VSYNC_POSITIVE) : 0; - - return val; -} - -static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags) -{ - struct vop2 *vop2 = vp->vop2; - int dclk_core_div, dclk_out_div, if_pixclk_div, if_dclk_div; - unsigned long clock; - u32 die, dip, div, vp_clk_div, val; - - clock = rk3588_calc_cru_cfg(vp, id, &dclk_core_div, &dclk_out_div, - &if_pixclk_div, &if_dclk_div); - if (!clock) - return 0; - - vp_clk_div = FIELD_PREP(RK3588_VP_CLK_CTRL__DCLK_CORE_DIV, dclk_core_div); - vp_clk_div |= FIELD_PREP(RK3588_VP_CLK_CTRL__DCLK_OUT_DIV, dclk_out_div); - - die = vop2_readl(vop2, RK3568_DSP_IF_EN); - dip = vop2_readl(vop2, RK3568_DSP_IF_POL); - div = vop2_readl(vop2, RK3568_DSP_IF_CTRL); - - switch (id) { - case ROCKCHIP_VOP2_EP_HDMI0: - div &= ~RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV; - div &= ~RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV; - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV, if_dclk_div); - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV, if_pixclk_div); - die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX; - die |= RK3588_SYS_DSP_INFACE_EN_HDMI0 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX, vp->id); - val = rk3588_get_hdmi_pol(polflags); - regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 1, 1)); - regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0, HIWORD_UPDATE(val, 6, 5)); - break; - case ROCKCHIP_VOP2_EP_HDMI1: - div &= ~RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV; - div &= ~RK3588_DSP_IF_EDP_HDMI1_PCLK_DIV; - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV, if_dclk_div); - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI1_PCLK_DIV, if_pixclk_div); - die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX; - die |= RK3588_SYS_DSP_INFACE_EN_HDMI1 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX, vp->id); - val = rk3588_get_hdmi_pol(polflags); - regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 4, 4)); - regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0, HIWORD_UPDATE(val, 8, 7)); - break; - case ROCKCHIP_VOP2_EP_EDP0: - div &= ~RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV; - div &= ~RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV; - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV, if_dclk_div); - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV, if_pixclk_div); - die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX; - die |= RK3588_SYS_DSP_INFACE_EN_EDP0 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX, vp->id); - regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 0, 0)); - break; - case ROCKCHIP_VOP2_EP_EDP1: - div &= ~RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV; - div &= ~RK3588_DSP_IF_EDP_HDMI1_PCLK_DIV; - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV, if_dclk_div); - div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV, if_pixclk_div); - die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX; - die |= RK3588_SYS_DSP_INFACE_EN_EDP1 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX, vp->id); - regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 3, 3)); - break; - case ROCKCHIP_VOP2_EP_MIPI0: - div &= ~RK3588_DSP_IF_MIPI0_PCLK_DIV; - div |= FIELD_PREP(RK3588_DSP_IF_MIPI0_PCLK_DIV, if_pixclk_div); - die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI0_MUX; - val = rk3588_get_mipi_port_mux(vp->id); - die |= RK3588_SYS_DSP_INFACE_EN_MIPI0 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI0_MUX, !!val); - break; - case ROCKCHIP_VOP2_EP_MIPI1: - div &= ~RK3588_DSP_IF_MIPI1_PCLK_DIV; - div |= FIELD_PREP(RK3588_DSP_IF_MIPI1_PCLK_DIV, if_pixclk_div); - die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX; - val = rk3588_get_mipi_port_mux(vp->id); - die |= RK3588_SYS_DSP_INFACE_EN_MIPI1 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX, val); - break; - case ROCKCHIP_VOP2_EP_DP0: - die &= ~RK3588_SYS_DSP_INFACE_EN_DP0_MUX; - die |= RK3588_SYS_DSP_INFACE_EN_DP0 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_DP0_MUX, vp->id); - dip &= ~RK3588_DSP_IF_POL__DP0_PIN_POL; - dip |= FIELD_PREP(RK3588_DSP_IF_POL__DP0_PIN_POL, polflags); - break; - case ROCKCHIP_VOP2_EP_DP1: - die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX; - die |= RK3588_SYS_DSP_INFACE_EN_MIPI1 | - FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX, vp->id); - dip &= ~RK3588_DSP_IF_POL__DP1_PIN_POL; - dip |= FIELD_PREP(RK3588_DSP_IF_POL__DP1_PIN_POL, polflags); - break; - default: - drm_err(vop2->drm, "Invalid interface id %d on vp%d\n", id, vp->id); - return 0; - } - - dip |= RK3568_DSP_IF_POL__CFG_DONE_IMD; - - vop2_vp_write(vp, RK3588_VP_CLK_CTRL, vp_clk_div); - vop2_writel(vop2, RK3568_DSP_IF_EN, die); - vop2_writel(vop2, RK3568_DSP_IF_CTRL, div); - vop2_writel(vop2, RK3568_DSP_IF_POL, dip); - - return clock; -} - -static unsigned long vop2_set_intf_mux(struct vop2_video_port *vp, int ep_id, u32 polflags) -{ - struct vop2 *vop2 = vp->vop2; - - if (vop2->data->soc_id == 3566 || vop2->data->soc_id == 3568) - return rk3568_set_intf_mux(vp, ep_id, polflags); - else if (vop2->data->soc_id == 3588) - return rk3588_set_intf_mux(vp, ep_id, polflags); - else - return 0; -} - static int us_to_vertical_line(struct drm_display_mode *mode, int us) { return us * mode->clock / mode->htotal / 1000; @@ -2201,7 +1682,7 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc, * process multi(1/2/4/8) pixels per cycle, so the dclk feed by the * system cru may be the 1/2 or 1/4 of mode->clock. */ - clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags); + clock = vop2->ops->setup_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags); } if (!clock) { @@ -2270,11 +1751,14 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc, * Switch to HDMI PHY PLL as DCLK source for display modes up * to 4K@60Hz, if available, otherwise keep using the system CRU. */ - if (vop2->pll_hdmiphy0 && clock <= VOP2_MAX_DCLK_RATE) { + if ((vop2->pll_hdmiphy0 || vop2->pll_hdmiphy1) && clock <= VOP2_MAX_DCLK_RATE) { drm_for_each_encoder_mask(encoder, crtc->dev, crtc_state->encoder_mask) { struct rockchip_encoder *rkencoder = to_rockchip_encoder(encoder); if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI0) { + if (!vop2->pll_hdmiphy0) + break; + if (!vp->dclk_src) vp->dclk_src = clk_get_parent(vp->dclk); @@ -2284,6 +1768,20 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc, "Could not switch to HDMI0 PHY PLL: %d\n", ret); break; } + + if (rkencoder->crtc_endpoint_id == ROCKCHIP_VOP2_EP_HDMI1) { + if (!vop2->pll_hdmiphy1) + break; + + if (!vp->dclk_src) + vp->dclk_src = clk_get_parent(vp->dclk); + + ret = clk_set_parent(vp->dclk, vop2->pll_hdmiphy1); + if (ret < 0) + drm_warn(vop2->drm, + "Could not switch to HDMI1 PHY PLL: %d\n", ret); + break; + } } } @@ -2351,454 +1849,13 @@ static int vop2_crtc_atomic_check(struct drm_crtc *crtc, return 0; } -static bool is_opaque(u16 alpha) -{ - return (alpha >> 8) == 0xff; -} - -static void vop2_parse_alpha(struct vop2_alpha_config *alpha_config, - struct vop2_alpha *alpha) -{ - int src_glb_alpha_en = is_opaque(alpha_config->src_glb_alpha_value) ? 0 : 1; - int dst_glb_alpha_en = is_opaque(alpha_config->dst_glb_alpha_value) ? 0 : 1; - int src_color_mode = alpha_config->src_premulti_en ? - ALPHA_SRC_PRE_MUL : ALPHA_SRC_NO_PRE_MUL; - int dst_color_mode = alpha_config->dst_premulti_en ? - ALPHA_SRC_PRE_MUL : ALPHA_SRC_NO_PRE_MUL; - - alpha->src_color_ctrl.val = 0; - alpha->dst_color_ctrl.val = 0; - alpha->src_alpha_ctrl.val = 0; - alpha->dst_alpha_ctrl.val = 0; - - if (!alpha_config->src_pixel_alpha_en) - alpha->src_color_ctrl.bits.blend_mode = ALPHA_GLOBAL; - else if (alpha_config->src_pixel_alpha_en && !src_glb_alpha_en) - alpha->src_color_ctrl.bits.blend_mode = ALPHA_PER_PIX; - else - alpha->src_color_ctrl.bits.blend_mode = ALPHA_PER_PIX_GLOBAL; - - alpha->src_color_ctrl.bits.alpha_en = 1; - - if (alpha->src_color_ctrl.bits.blend_mode == ALPHA_GLOBAL) { - alpha->src_color_ctrl.bits.color_mode = src_color_mode; - alpha->src_color_ctrl.bits.factor_mode = SRC_FAC_ALPHA_SRC_GLOBAL; - } else if (alpha->src_color_ctrl.bits.blend_mode == ALPHA_PER_PIX) { - alpha->src_color_ctrl.bits.color_mode = src_color_mode; - alpha->src_color_ctrl.bits.factor_mode = SRC_FAC_ALPHA_ONE; - } else { - alpha->src_color_ctrl.bits.color_mode = ALPHA_SRC_PRE_MUL; - alpha->src_color_ctrl.bits.factor_mode = SRC_FAC_ALPHA_SRC_GLOBAL; - } - alpha->src_color_ctrl.bits.glb_alpha = alpha_config->src_glb_alpha_value >> 8; - alpha->src_color_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; - alpha->src_color_ctrl.bits.alpha_cal_mode = ALPHA_SATURATION; - - alpha->dst_color_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; - alpha->dst_color_ctrl.bits.alpha_cal_mode = ALPHA_SATURATION; - alpha->dst_color_ctrl.bits.blend_mode = ALPHA_GLOBAL; - alpha->dst_color_ctrl.bits.glb_alpha = alpha_config->dst_glb_alpha_value >> 8; - alpha->dst_color_ctrl.bits.color_mode = dst_color_mode; - alpha->dst_color_ctrl.bits.factor_mode = ALPHA_SRC_INVERSE; - - alpha->src_alpha_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; - alpha->src_alpha_ctrl.bits.blend_mode = alpha->src_color_ctrl.bits.blend_mode; - alpha->src_alpha_ctrl.bits.alpha_cal_mode = ALPHA_SATURATION; - alpha->src_alpha_ctrl.bits.factor_mode = ALPHA_ONE; - - alpha->dst_alpha_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; - if (alpha_config->dst_pixel_alpha_en && !dst_glb_alpha_en) - alpha->dst_alpha_ctrl.bits.blend_mode = ALPHA_PER_PIX; - else - alpha->dst_alpha_ctrl.bits.blend_mode = ALPHA_PER_PIX_GLOBAL; - alpha->dst_alpha_ctrl.bits.alpha_cal_mode = ALPHA_NO_SATURATION; - alpha->dst_alpha_ctrl.bits.factor_mode = ALPHA_SRC_INVERSE; -} - -static int vop2_find_start_mixer_id_for_vp(struct vop2 *vop2, u8 port_id) -{ - struct vop2_video_port *vp; - int used_layer = 0; - int i; - - for (i = 0; i < port_id; i++) { - vp = &vop2->vps[i]; - used_layer += hweight32(vp->win_mask); - } - - return used_layer; -} - -static void vop2_setup_cluster_alpha(struct vop2 *vop2, struct vop2_win *main_win) -{ - struct vop2_alpha_config alpha_config; - struct vop2_alpha alpha; - struct drm_plane_state *bottom_win_pstate; - bool src_pixel_alpha_en = false; - u16 src_glb_alpha_val, dst_glb_alpha_val; - bool premulti_en = false; - bool swap = false; - u32 offset = 0; - - /* At one win mode, win0 is dst/bottom win, and win1 is a all zero src/top win */ - bottom_win_pstate = main_win->base.state; - src_glb_alpha_val = 0; - dst_glb_alpha_val = main_win->base.state->alpha; - - if (!bottom_win_pstate->fb) - return; - - alpha_config.src_premulti_en = premulti_en; - alpha_config.dst_premulti_en = false; - alpha_config.src_pixel_alpha_en = src_pixel_alpha_en; - alpha_config.dst_pixel_alpha_en = true; /* alpha value need transfer to next mix */ - alpha_config.src_glb_alpha_value = src_glb_alpha_val; - alpha_config.dst_glb_alpha_value = dst_glb_alpha_val; - vop2_parse_alpha(&alpha_config, &alpha); - - alpha.src_color_ctrl.bits.src_dst_swap = swap; - - switch (main_win->data->phys_id) { - case ROCKCHIP_VOP2_CLUSTER0: - offset = 0x0; - break; - case ROCKCHIP_VOP2_CLUSTER1: - offset = 0x10; - break; - case ROCKCHIP_VOP2_CLUSTER2: - offset = 0x20; - break; - case ROCKCHIP_VOP2_CLUSTER3: - offset = 0x30; - break; - } - - vop2_writel(vop2, RK3568_CLUSTER0_MIX_SRC_COLOR_CTRL + offset, - alpha.src_color_ctrl.val); - vop2_writel(vop2, RK3568_CLUSTER0_MIX_DST_COLOR_CTRL + offset, - alpha.dst_color_ctrl.val); - vop2_writel(vop2, RK3568_CLUSTER0_MIX_SRC_ALPHA_CTRL + offset, - alpha.src_alpha_ctrl.val); - vop2_writel(vop2, RK3568_CLUSTER0_MIX_DST_ALPHA_CTRL + offset, - alpha.dst_alpha_ctrl.val); -} - -static void vop2_setup_alpha(struct vop2_video_port *vp) -{ - struct vop2 *vop2 = vp->vop2; - struct drm_framebuffer *fb; - struct vop2_alpha_config alpha_config; - struct vop2_alpha alpha; - struct drm_plane *plane; - int pixel_alpha_en; - int premulti_en, gpremulti_en = 0; - int mixer_id; - u32 offset; - bool bottom_layer_alpha_en = false; - u32 dst_global_alpha = DRM_BLEND_ALPHA_OPAQUE; - - mixer_id = vop2_find_start_mixer_id_for_vp(vop2, vp->id); - alpha_config.dst_pixel_alpha_en = true; /* alpha value need transfer to next mix */ - - drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { - struct vop2_win *win = to_vop2_win(plane); - - if (plane->state->normalized_zpos == 0 && - !is_opaque(plane->state->alpha) && - !vop2_cluster_window(win)) { - /* - * If bottom layer have global alpha effect [except cluster layer, - * because cluster have deal with bottom layer global alpha value - * at cluster mix], bottom layer mix need deal with global alpha. - */ - bottom_layer_alpha_en = true; - dst_global_alpha = plane->state->alpha; - } - } - - drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { - struct vop2_win *win = to_vop2_win(plane); - int zpos = plane->state->normalized_zpos; - - /* - * Need to configure alpha from second layer. - */ - if (zpos == 0) - continue; - - if (plane->state->pixel_blend_mode == DRM_MODE_BLEND_PREMULTI) - premulti_en = 1; - else - premulti_en = 0; - - plane = &win->base; - fb = plane->state->fb; - - pixel_alpha_en = fb->format->has_alpha; - - alpha_config.src_premulti_en = premulti_en; - - if (bottom_layer_alpha_en && zpos == 1) { - gpremulti_en = premulti_en; - /* Cd = Cs + (1 - As) * Cd * Agd */ - alpha_config.dst_premulti_en = false; - alpha_config.src_pixel_alpha_en = pixel_alpha_en; - alpha_config.src_glb_alpha_value = plane->state->alpha; - alpha_config.dst_glb_alpha_value = dst_global_alpha; - } else if (vop2_cluster_window(win)) { - /* Mix output data only have pixel alpha */ - alpha_config.dst_premulti_en = true; - alpha_config.src_pixel_alpha_en = true; - alpha_config.src_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; - alpha_config.dst_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; - } else { - /* Cd = Cs + (1 - As) * Cd */ - alpha_config.dst_premulti_en = true; - alpha_config.src_pixel_alpha_en = pixel_alpha_en; - alpha_config.src_glb_alpha_value = plane->state->alpha; - alpha_config.dst_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; - } - - vop2_parse_alpha(&alpha_config, &alpha); - - offset = (mixer_id + zpos - 1) * 0x10; - vop2_writel(vop2, RK3568_MIX0_SRC_COLOR_CTRL + offset, - alpha.src_color_ctrl.val); - vop2_writel(vop2, RK3568_MIX0_DST_COLOR_CTRL + offset, - alpha.dst_color_ctrl.val); - vop2_writel(vop2, RK3568_MIX0_SRC_ALPHA_CTRL + offset, - alpha.src_alpha_ctrl.val); - vop2_writel(vop2, RK3568_MIX0_DST_ALPHA_CTRL + offset, - alpha.dst_alpha_ctrl.val); - } - - if (vp->id == 0) { - if (bottom_layer_alpha_en) { - /* Transfer pixel alpha to hdr mix */ - alpha_config.src_premulti_en = gpremulti_en; - alpha_config.dst_premulti_en = true; - alpha_config.src_pixel_alpha_en = true; - alpha_config.src_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; - alpha_config.dst_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; - vop2_parse_alpha(&alpha_config, &alpha); - - vop2_writel(vop2, RK3568_HDR0_SRC_COLOR_CTRL, - alpha.src_color_ctrl.val); - vop2_writel(vop2, RK3568_HDR0_DST_COLOR_CTRL, - alpha.dst_color_ctrl.val); - vop2_writel(vop2, RK3568_HDR0_SRC_ALPHA_CTRL, - alpha.src_alpha_ctrl.val); - vop2_writel(vop2, RK3568_HDR0_DST_ALPHA_CTRL, - alpha.dst_alpha_ctrl.val); - } else { - vop2_writel(vop2, RK3568_HDR0_SRC_COLOR_CTRL, 0); - } - } -} - -static void vop2_setup_layer_mixer(struct vop2_video_port *vp) -{ - struct vop2 *vop2 = vp->vop2; - struct drm_plane *plane; - u32 layer_sel = 0; - u32 port_sel; - u8 layer_id; - u8 old_layer_id; - u8 layer_sel_id; - unsigned int ofs; - u32 ovl_ctrl; - int i; - struct vop2_video_port *vp0 = &vop2->vps[0]; - struct vop2_video_port *vp1 = &vop2->vps[1]; - struct vop2_video_port *vp2 = &vop2->vps[2]; - struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(vp->crtc.state); - - ovl_ctrl = vop2_readl(vop2, RK3568_OVL_CTRL); - ovl_ctrl |= RK3568_OVL_CTRL__LAYERSEL_REGDONE_IMD; - if (vcstate->yuv_overlay) - ovl_ctrl |= RK3568_OVL_CTRL__YUV_MODE(vp->id); - else - ovl_ctrl &= ~RK3568_OVL_CTRL__YUV_MODE(vp->id); - - vop2_writel(vop2, RK3568_OVL_CTRL, ovl_ctrl); - - port_sel = vop2_readl(vop2, RK3568_OVL_PORT_SEL); - port_sel &= RK3568_OVL_PORT_SEL__SEL_PORT; - - if (vp0->nlayers) - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT0_MUX, - vp0->nlayers - 1); - else - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT0_MUX, 8); - - if (vp1->nlayers) - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT1_MUX, - (vp0->nlayers + vp1->nlayers - 1)); - else - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT1_MUX, 8); - - if (vp2->nlayers) - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, - (vp2->nlayers + vp1->nlayers + vp0->nlayers - 1)); - else - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, 8); - - layer_sel = vop2_readl(vop2, RK3568_OVL_LAYER_SEL); - - ofs = 0; - for (i = 0; i < vp->id; i++) - ofs += vop2->vps[i].nlayers; - - drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { - struct vop2_win *win = to_vop2_win(plane); - struct vop2_win *old_win; - - layer_id = (u8)(plane->state->normalized_zpos + ofs); - - /* - * Find the layer this win bind in old state. - */ - for (old_layer_id = 0; old_layer_id < vop2->data->win_size; old_layer_id++) { - layer_sel_id = (layer_sel >> (4 * old_layer_id)) & 0xf; - if (layer_sel_id == win->data->layer_sel_id) - break; - } - - /* - * Find the win bind to this layer in old state - */ - for (i = 0; i < vop2->data->win_size; i++) { - old_win = &vop2->win[i]; - layer_sel_id = (layer_sel >> (4 * layer_id)) & 0xf; - if (layer_sel_id == old_win->data->layer_sel_id) - break; - } - - switch (win->data->phys_id) { - case ROCKCHIP_VOP2_CLUSTER0: - port_sel &= ~RK3568_OVL_PORT_SEL__CLUSTER0; - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__CLUSTER0, vp->id); - break; - case ROCKCHIP_VOP2_CLUSTER1: - port_sel &= ~RK3568_OVL_PORT_SEL__CLUSTER1; - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__CLUSTER1, vp->id); - break; - case ROCKCHIP_VOP2_CLUSTER2: - port_sel &= ~RK3588_OVL_PORT_SEL__CLUSTER2; - port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__CLUSTER2, vp->id); - break; - case ROCKCHIP_VOP2_CLUSTER3: - port_sel &= ~RK3588_OVL_PORT_SEL__CLUSTER3; - port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__CLUSTER3, vp->id); - break; - case ROCKCHIP_VOP2_ESMART0: - port_sel &= ~RK3568_OVL_PORT_SEL__ESMART0; - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__ESMART0, vp->id); - break; - case ROCKCHIP_VOP2_ESMART1: - port_sel &= ~RK3568_OVL_PORT_SEL__ESMART1; - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__ESMART1, vp->id); - break; - case ROCKCHIP_VOP2_ESMART2: - port_sel &= ~RK3588_OVL_PORT_SEL__ESMART2; - port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__ESMART2, vp->id); - break; - case ROCKCHIP_VOP2_ESMART3: - port_sel &= ~RK3588_OVL_PORT_SEL__ESMART3; - port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__ESMART3, vp->id); - break; - case ROCKCHIP_VOP2_SMART0: - port_sel &= ~RK3568_OVL_PORT_SEL__SMART0; - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__SMART0, vp->id); - break; - case ROCKCHIP_VOP2_SMART1: - port_sel &= ~RK3568_OVL_PORT_SEL__SMART1; - port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__SMART1, vp->id); - break; - } - - layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(layer_id, 0x7); - layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(layer_id, win->data->layer_sel_id); - /* - * When we bind a window from layerM to layerN, we also need to move the old - * window on layerN to layerM to avoid one window selected by two or more layers. - */ - layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(old_layer_id, 0x7); - layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(old_layer_id, old_win->data->layer_sel_id); - } - - vop2_writel(vop2, RK3568_OVL_LAYER_SEL, layer_sel); - vop2_writel(vop2, RK3568_OVL_PORT_SEL, port_sel); -} - -static void vop2_setup_dly_for_windows(struct vop2 *vop2) -{ - struct vop2_win *win; - int i = 0; - u32 cdly = 0, sdly = 0; - - for (i = 0; i < vop2->data->win_size; i++) { - u32 dly; - - win = &vop2->win[i]; - dly = win->delay; - - switch (win->data->phys_id) { - case ROCKCHIP_VOP2_CLUSTER0: - cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER0_0, dly); - cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER0_1, dly); - break; - case ROCKCHIP_VOP2_CLUSTER1: - cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER1_0, dly); - cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER1_1, dly); - break; - case ROCKCHIP_VOP2_ESMART0: - sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__ESMART0, dly); - break; - case ROCKCHIP_VOP2_ESMART1: - sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__ESMART1, dly); - break; - case ROCKCHIP_VOP2_SMART0: - case ROCKCHIP_VOP2_ESMART2: - sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__SMART0, dly); - break; - case ROCKCHIP_VOP2_SMART1: - case ROCKCHIP_VOP2_ESMART3: - sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__SMART1, dly); - break; - } - } - - vop2_writel(vop2, RK3568_CLUSTER_DLY_NUM, cdly); - vop2_writel(vop2, RK3568_SMART_DLY_NUM, sdly); -} - static void vop2_crtc_atomic_begin(struct drm_crtc *crtc, struct drm_atomic_state *state) { struct vop2_video_port *vp = to_vop2_video_port(crtc); struct vop2 *vop2 = vp->vop2; - struct drm_plane *plane; - - vp->win_mask = 0; - - drm_atomic_crtc_for_each_plane(plane, crtc) { - struct vop2_win *win = to_vop2_win(plane); - - win->delay = win->data->dly[VOP2_DLY_MODE_DEFAULT]; - vp->win_mask |= BIT(win->data->phys_id); - - if (vop2_cluster_window(win)) - vop2_setup_cluster_alpha(vop2, win); - } - - if (!vp->win_mask) - return; - - vop2_setup_layer_mixer(vp); - vop2_setup_alpha(vp); - vop2_setup_dly_for_windows(vop2); + vop2->ops->setup_overlay(vp); } static void vop2_crtc_atomic_flush(struct drm_crtc *crtc, @@ -3110,6 +2167,52 @@ static const struct drm_crtc_funcs vop2_crtc_funcs = { .late_register = vop2_crtc_late_register, }; +static irqreturn_t rk3576_vp_isr(int irq, void *data) +{ + struct vop2_video_port *vp = data; + struct vop2 *vop2 = vp->vop2; + struct drm_crtc *crtc = &vp->crtc; + uint32_t irqs; + int ret = IRQ_NONE; + + if (!pm_runtime_get_if_in_use(vop2->dev)) + return IRQ_NONE; + + irqs = vop2_readl(vop2, RK3568_VP_INT_STATUS(vp->id)); + vop2_writel(vop2, RK3568_VP_INT_CLR(vp->id), irqs << 16 | irqs); + + if (irqs & VP_INT_DSP_HOLD_VALID) { + complete(&vp->dsp_hold_completion); + ret = IRQ_HANDLED; + } + + if (irqs & VP_INT_FS_FIELD) { + drm_crtc_handle_vblank(crtc); + spin_lock(&crtc->dev->event_lock); + if (vp->event) { + u32 val = vop2_readl(vop2, RK3568_REG_CFG_DONE); + + if (!(val & BIT(vp->id))) { + drm_crtc_send_vblank_event(crtc, vp->event); + vp->event = NULL; + drm_crtc_vblank_put(crtc); + } + } + spin_unlock(&crtc->dev->event_lock); + + ret = IRQ_HANDLED; + } + + if (irqs & VP_INT_POST_BUF_EMPTY) { + drm_err_ratelimited(vop2->drm, "POST_BUF_EMPTY irq err at vp%d\n", vp->id); + ret = IRQ_HANDLED; + } + + pm_runtime_put(vop2->dev); + + return ret; +} + static irqreturn_t vop2_isr(int irq, void *data) { struct vop2 *vop2 = data; @@ -3125,41 +2228,43 @@ static irqreturn_t vop2_isr(int irq, void *data) if (!pm_runtime_get_if_in_use(vop2->dev)) return IRQ_NONE; - for (i = 0; i < vop2_data->nr_vps; i++) { - struct vop2_video_port *vp = &vop2->vps[i]; - struct drm_crtc *crtc = &vp->crtc; - u32 irqs; + if (vop2->version < VOP_VERSION_RK3576) { + for (i = 0; i < vop2_data->nr_vps; i++) { + struct vop2_video_port *vp = &vop2->vps[i]; + struct drm_crtc *crtc = &vp->crtc; + u32 irqs; - irqs = vop2_readl(vop2, RK3568_VP_INT_STATUS(vp->id)); - vop2_writel(vop2, RK3568_VP_INT_CLR(vp->id), irqs << 16 | irqs); + irqs = vop2_readl(vop2, RK3568_VP_INT_STATUS(vp->id)); + vop2_writel(vop2, RK3568_VP_INT_CLR(vp->id), irqs << 16 | irqs); - if (irqs & VP_INT_DSP_HOLD_VALID) { - complete(&vp->dsp_hold_completion); - ret = IRQ_HANDLED; - } - - if (irqs & VP_INT_FS_FIELD) { - drm_crtc_handle_vblank(crtc); - spin_lock(&crtc->dev->event_lock); - if (vp->event) { - u32 val = vop2_readl(vop2, RK3568_REG_CFG_DONE); + if (irqs & VP_INT_DSP_HOLD_VALID) { + complete(&vp->dsp_hold_completion); + ret = IRQ_HANDLED; + } - if (!(val & BIT(vp->id))) { - drm_crtc_send_vblank_event(crtc, vp->event); - vp->event = NULL; - drm_crtc_vblank_put(crtc); + if (irqs & VP_INT_FS_FIELD) { + drm_crtc_handle_vblank(crtc); + spin_lock(&crtc->dev->event_lock); + if (vp->event) { + u32 val = vop2_readl(vop2, RK3568_REG_CFG_DONE); + + if (!(val & BIT(vp->id))) { + drm_crtc_send_vblank_event(crtc, vp->event); + vp->event = NULL; + drm_crtc_vblank_put(crtc); + } } - } - spin_unlock(&crtc->dev->event_lock); + spin_unlock(&crtc->dev->event_lock); - ret = IRQ_HANDLED; - } + ret = IRQ_HANDLED; + } - if (irqs & VP_INT_POST_BUF_EMPTY) { - drm_err_ratelimited(vop2->drm, - "POST_BUF_EMPTY irq err at vp%d\n", - vp->id); - ret = IRQ_HANDLED; + if (irqs & VP_INT_POST_BUF_EMPTY) { + drm_err_ratelimited(vop2->drm, + "POST_BUF_EMPTY irq err at vp%d\n", + vp->id); + ret = IRQ_HANDLED; + } } } @@ -3213,22 +2318,29 @@ static int vop2_plane_init(struct vop2 *vop2, struct vop2_win *win, return 0; } -static struct vop2_video_port *find_vp_without_primary(struct vop2 *vop2) +/* + * On RK3566 these windows don't have an independent + * framebuffer. They can only share/mirror the framebuffer + * with smart0, esmart0 and cluster0 respectively. + * And RK3566 share the same vop version with Rk3568, so we + * need to use soc_id for identification here. + */ +static bool vop2_is_mirror_win(struct vop2_win *win) { - int i; - - for (i = 0; i < vop2->data->nr_vps; i++) { - struct vop2_video_port *vp = &vop2->vps[i]; - - if (!vp->crtc.port) - continue; - if (vp->primary_plane) - continue; + struct vop2 *vop2 = win->vop2; - return vp; + if (vop2->data->soc_id == 3566) { + switch (win->data->phys_id) { + case ROCKCHIP_VOP2_SMART1: + case ROCKCHIP_VOP2_ESMART1: + case ROCKCHIP_VOP2_CLUSTER1: + return true; + default: + return false; + } + } else { + return false; } - - return NULL; } static int vop2_create_crtcs(struct vop2 *vop2) @@ -3239,7 +2351,9 @@ static int vop2_create_crtcs(struct vop2 *vop2) struct drm_plane *plane; struct device_node *port; struct vop2_video_port *vp; - int i, nvp, nvps = 0; + struct vop2_win *win; + u32 possible_crtcs; + int i, j, nvp, nvps = 0; int ret; for (i = 0; i < vop2_data->nr_vps; i++) { @@ -3255,10 +2369,9 @@ static int vop2_create_crtcs(struct vop2 *vop2) snprintf(dclk_name, sizeof(dclk_name), "dclk_vp%d", vp->id); vp->dclk = devm_clk_get(vop2->dev, dclk_name); - if (IS_ERR(vp->dclk)) { - drm_err(vop2->drm, "failed to get %s\n", dclk_name); - return PTR_ERR(vp->dclk); - } + if (IS_ERR(vp->dclk)) + return dev_err_probe(drm->dev, PTR_ERR(vp->dclk), + "failed to get %s\n", dclk_name); np = of_graph_get_remote_node(dev->of_node, i, -1); if (!np) { @@ -3268,55 +2381,79 @@ static int vop2_create_crtcs(struct vop2 *vop2) of_node_put(np); port = of_graph_get_port_by_id(dev->of_node, i); - if (!port) { - drm_err(vop2->drm, "no port node found for video_port%d\n", i); - return -ENOENT; - } - + if (!port) + return dev_err_probe(drm->dev, -ENOENT, + "no port node found for video_port%d\n", i); vp->crtc.port = port; nvps++; } nvp = 0; - for (i = 0; i < vop2->registered_num_wins; i++) { - struct vop2_win *win = &vop2->win[i]; - u32 possible_crtcs = 0; - - if (vop2->data->soc_id == 3566) { - /* - * On RK3566 these windows don't have an independent - * framebuffer. They share the framebuffer with smart0, - * esmart0 and cluster0 respectively. - */ - switch (win->data->phys_id) { - case ROCKCHIP_VOP2_SMART1: - case ROCKCHIP_VOP2_ESMART1: - case ROCKCHIP_VOP2_CLUSTER1: + /* Register a primary plane for every crtc */ + for (i = 0; i < vop2_data->nr_vps; i++) { + vp = &vop2->vps[i]; + + if (!vp->crtc.port) + continue; + + for (j = 0; j < vop2->registered_num_wins; j++) { + win = &vop2->win[j]; + + /* Aready registered as primary plane */ + if (win->base.type == DRM_PLANE_TYPE_PRIMARY) + continue; + + /* If this win can not attached to this VP */ + if (!(win->data->possible_vp_mask & BIT(vp->id))) + continue; + + if (vop2_is_mirror_win(win)) continue; - } - } - if (win->type == DRM_PLANE_TYPE_PRIMARY) { - vp = find_vp_without_primary(vop2); - if (vp) { + if (win->type == DRM_PLANE_TYPE_PRIMARY) { possible_crtcs = BIT(nvp); vp->primary_plane = win; + ret = vop2_plane_init(vop2, win, possible_crtcs); + if (ret) + return dev_err_probe(drm->dev, ret, + "failed to init primary plane %s\n", + win->data->name); nvp++; - } else { - /* change the unused primary window to overlay window */ - win->type = DRM_PLANE_TYPE_OVERLAY; + break; } } + } - if (win->type == DRM_PLANE_TYPE_OVERLAY) - possible_crtcs = (1 << nvps) - 1; + /* Register all unused window as overlay plane */ + for (i = 0; i < vop2->registered_num_wins; i++) { + win = &vop2->win[i]; - ret = vop2_plane_init(vop2, win, possible_crtcs); - if (ret) { - drm_err(vop2->drm, "failed to init plane %s: %d\n", - win->data->name, ret); - return ret; + /* Aready registered as primary plane */ + if (win->base.type == DRM_PLANE_TYPE_PRIMARY) + continue; + + if (vop2_is_mirror_win(win)) + continue; + + win->type = DRM_PLANE_TYPE_OVERLAY; + + possible_crtcs = 0; + nvp = 0; + for (j = 0; j < vop2_data->nr_vps; j++) { + vp = &vop2->vps[j]; + + if (!vp->crtc.port) + continue; + + if (win->data->possible_vp_mask & BIT(vp->id)) + possible_crtcs |= BIT(nvp); + nvp++; } + + ret = vop2_plane_init(vop2, win, possible_crtcs); + if (ret) + return dev_err_probe(drm->dev, ret, "failed to init overlay plane %s\n", + win->data->name); } for (i = 0; i < vop2_data->nr_vps; i++) { @@ -3330,10 +2467,9 @@ static int vop2_create_crtcs(struct vop2 *vop2) ret = drm_crtc_init_with_planes(drm, &vp->crtc, plane, NULL, &vop2_crtc_funcs, "video_port%d", vp->id); - if (ret) { - drm_err(vop2->drm, "crtc init for video_port%d failed\n", i); - return ret; - } + if (ret) + return dev_err_probe(drm->dev, ret, + "crtc init for video_port%d failed\n", i); drm_crtc_helper_add(&vp->crtc, &vop2_crtc_helper_funcs); if (vop2->lut_regs) { @@ -3400,184 +2536,26 @@ static int vop2_find_rgb_encoder(struct vop2 *vop2) return -ENOENT; } -static struct reg_field vop2_cluster_regs[VOP2_WIN_MAX_REG] = { - [VOP2_WIN_ENABLE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 0, 0), - [VOP2_WIN_FORMAT] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 1, 5), - [VOP2_WIN_RB_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 14, 14), - [VOP2_WIN_DITHER_UP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 18, 18), - [VOP2_WIN_ACT_INFO] = REG_FIELD(RK3568_CLUSTER_WIN_ACT_INFO, 0, 31), - [VOP2_WIN_DSP_INFO] = REG_FIELD(RK3568_CLUSTER_WIN_DSP_INFO, 0, 31), - [VOP2_WIN_DSP_ST] = REG_FIELD(RK3568_CLUSTER_WIN_DSP_ST, 0, 31), - [VOP2_WIN_YRGB_MST] = REG_FIELD(RK3568_CLUSTER_WIN_YRGB_MST, 0, 31), - [VOP2_WIN_UV_MST] = REG_FIELD(RK3568_CLUSTER_WIN_CBR_MST, 0, 31), - [VOP2_WIN_YUV_CLIP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 19, 19), - [VOP2_WIN_YRGB_VIR] = REG_FIELD(RK3568_CLUSTER_WIN_VIR, 0, 15), - [VOP2_WIN_UV_VIR] = REG_FIELD(RK3568_CLUSTER_WIN_VIR, 16, 31), - [VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 8, 8), - [VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 9, 9), - [VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 10, 11), - [VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 0, 3), - [VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 5, 8), - /* RK3588 only, reserved bit on rk3568*/ - [VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3568_CLUSTER_CTRL, 13, 13), - - /* Scale */ - [VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 0, 15), - [VOP2_WIN_SCALE_YRGB_Y] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 16, 31), - [VOP2_WIN_YRGB_VER_SCL_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 14, 15), - [VOP2_WIN_YRGB_HOR_SCL_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 12, 13), - [VOP2_WIN_BIC_COE_SEL] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 2, 3), - [VOP2_WIN_VSD_YRGB_GT2] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 28, 28), - [VOP2_WIN_VSD_YRGB_GT4] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 29, 29), - - /* cluster regs */ - [VOP2_WIN_AFBC_ENABLE] = REG_FIELD(RK3568_CLUSTER_CTRL, 1, 1), - [VOP2_WIN_CLUSTER_ENABLE] = REG_FIELD(RK3568_CLUSTER_CTRL, 0, 0), - [VOP2_WIN_CLUSTER_LB_MODE] = REG_FIELD(RK3568_CLUSTER_CTRL, 4, 7), - - /* afbc regs */ - [VOP2_WIN_AFBC_FORMAT] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 2, 6), - [VOP2_WIN_AFBC_RB_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 9, 9), - [VOP2_WIN_AFBC_UV_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 10, 10), - [VOP2_WIN_AFBC_AUTO_GATING_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_OUTPUT_CTRL, 4, 4), - [VOP2_WIN_AFBC_HALF_BLOCK_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 7, 7), - [VOP2_WIN_AFBC_BLOCK_SPLIT_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 8, 8), - [VOP2_WIN_AFBC_HDR_PTR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_HDR_PTR, 0, 31), - [VOP2_WIN_AFBC_PIC_SIZE] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_PIC_SIZE, 0, 31), - [VOP2_WIN_AFBC_PIC_VIR_WIDTH] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_VIR_WIDTH, 0, 15), - [VOP2_WIN_AFBC_TILE_NUM] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_VIR_WIDTH, 16, 31), - [VOP2_WIN_AFBC_PIC_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_PIC_OFFSET, 0, 31), - [VOP2_WIN_AFBC_DSP_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_DSP_OFFSET, 0, 31), - [VOP2_WIN_AFBC_TRANSFORM_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_TRANSFORM_OFFSET, 0, 31), - [VOP2_WIN_AFBC_ROTATE_90] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 0, 0), - [VOP2_WIN_AFBC_ROTATE_270] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 1, 1), - [VOP2_WIN_XMIRROR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 2, 2), - [VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 3, 3), - [VOP2_WIN_UV_SWAP] = { .reg = 0xffffffff }, - [VOP2_WIN_COLOR_KEY] = { .reg = 0xffffffff }, - [VOP2_WIN_COLOR_KEY_EN] = { .reg = 0xffffffff }, - [VOP2_WIN_SCALE_CBCR_X] = { .reg = 0xffffffff }, - [VOP2_WIN_SCALE_CBCR_Y] = { .reg = 0xffffffff }, - [VOP2_WIN_YRGB_HSCL_FILTER_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_YRGB_VSCL_FILTER_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_CBCR_VER_SCL_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_CBCR_HSCL_FILTER_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_CBCR_HOR_SCL_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_CBCR_VSCL_FILTER_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_VSD_CBCR_GT2] = { .reg = 0xffffffff }, - [VOP2_WIN_VSD_CBCR_GT4] = { .reg = 0xffffffff }, -}; - -static int vop2_cluster_init(struct vop2_win *win) -{ - struct vop2 *vop2 = win->vop2; - struct reg_field *cluster_regs; - int ret, i; - - cluster_regs = kmemdup(vop2_cluster_regs, sizeof(vop2_cluster_regs), - GFP_KERNEL); - if (!cluster_regs) - return -ENOMEM; - - for (i = 0; i < ARRAY_SIZE(vop2_cluster_regs); i++) - if (cluster_regs[i].reg != 0xffffffff) - cluster_regs[i].reg += win->offset; - - ret = devm_regmap_field_bulk_alloc(vop2->dev, vop2->map, win->reg, - cluster_regs, - ARRAY_SIZE(vop2_cluster_regs)); - - kfree(cluster_regs); - - return ret; -}; - -static struct reg_field vop2_esmart_regs[VOP2_WIN_MAX_REG] = { - [VOP2_WIN_ENABLE] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 0, 0), - [VOP2_WIN_FORMAT] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 1, 5), - [VOP2_WIN_DITHER_UP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 12, 12), - [VOP2_WIN_RB_SWAP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 14, 14), - [VOP2_WIN_UV_SWAP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 16, 16), - [VOP2_WIN_ACT_INFO] = REG_FIELD(RK3568_SMART_REGION0_ACT_INFO, 0, 31), - [VOP2_WIN_DSP_INFO] = REG_FIELD(RK3568_SMART_REGION0_DSP_INFO, 0, 31), - [VOP2_WIN_DSP_ST] = REG_FIELD(RK3568_SMART_REGION0_DSP_ST, 0, 28), - [VOP2_WIN_YRGB_MST] = REG_FIELD(RK3568_SMART_REGION0_YRGB_MST, 0, 31), - [VOP2_WIN_UV_MST] = REG_FIELD(RK3568_SMART_REGION0_CBR_MST, 0, 31), - [VOP2_WIN_YUV_CLIP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 17, 17), - [VOP2_WIN_YRGB_VIR] = REG_FIELD(RK3568_SMART_REGION0_VIR, 0, 15), - [VOP2_WIN_UV_VIR] = REG_FIELD(RK3568_SMART_REGION0_VIR, 16, 31), - [VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_SMART_CTRL0, 0, 0), - [VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_SMART_CTRL0, 1, 1), - [VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_SMART_CTRL0, 2, 3), - [VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_SMART_CTRL1, 31, 31), - [VOP2_WIN_COLOR_KEY] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 0, 29), - [VOP2_WIN_COLOR_KEY_EN] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 31, 31), - [VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 4, 8), - [VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 12, 16), - /* RK3588 only, reserved register on rk3568 */ - [VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3588_SMART_AXI_CTRL, 1, 1), - - /* Scale */ - [VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 0, 15), - [VOP2_WIN_SCALE_YRGB_Y] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 16, 31), - [VOP2_WIN_SCALE_CBCR_X] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_CBR, 0, 15), - [VOP2_WIN_SCALE_CBCR_Y] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_CBR, 16, 31), - [VOP2_WIN_YRGB_HOR_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 0, 1), - [VOP2_WIN_YRGB_HSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 2, 3), - [VOP2_WIN_YRGB_VER_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 4, 5), - [VOP2_WIN_YRGB_VSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 6, 7), - [VOP2_WIN_CBCR_HOR_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 8, 9), - [VOP2_WIN_CBCR_HSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 10, 11), - [VOP2_WIN_CBCR_VER_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 12, 13), - [VOP2_WIN_CBCR_VSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 14, 15), - [VOP2_WIN_BIC_COE_SEL] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 16, 17), - [VOP2_WIN_VSD_YRGB_GT2] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 8, 8), - [VOP2_WIN_VSD_YRGB_GT4] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 9, 9), - [VOP2_WIN_VSD_CBCR_GT2] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 10, 10), - [VOP2_WIN_VSD_CBCR_GT4] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 11, 11), - [VOP2_WIN_XMIRROR] = { .reg = 0xffffffff }, - [VOP2_WIN_CLUSTER_ENABLE] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_ENABLE] = { .reg = 0xffffffff }, - [VOP2_WIN_CLUSTER_LB_MODE] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_FORMAT] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_RB_SWAP] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_UV_SWAP] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_AUTO_GATING_EN] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_BLOCK_SPLIT_EN] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_PIC_VIR_WIDTH] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_TILE_NUM] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_PIC_OFFSET] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_PIC_SIZE] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_DSP_OFFSET] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_TRANSFORM_OFFSET] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_HDR_PTR] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_HALF_BLOCK_EN] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_ROTATE_270] = { .reg = 0xffffffff }, - [VOP2_WIN_AFBC_ROTATE_90] = { .reg = 0xffffffff }, -}; - -static int vop2_esmart_init(struct vop2_win *win) +static int vop2_regmap_init(struct vop2_win *win, const struct reg_field *regs, + int nr_regs) { struct vop2 *vop2 = win->vop2; - struct reg_field *esmart_regs; - int ret, i; - - esmart_regs = kmemdup(vop2_esmart_regs, sizeof(vop2_esmart_regs), - GFP_KERNEL); - if (!esmart_regs) - return -ENOMEM; - - for (i = 0; i < ARRAY_SIZE(vop2_esmart_regs); i++) - if (esmart_regs[i].reg != 0xffffffff) - esmart_regs[i].reg += win->offset; + int i; - ret = devm_regmap_field_bulk_alloc(vop2->dev, vop2->map, win->reg, - esmart_regs, - ARRAY_SIZE(vop2_esmart_regs)); + for (i = 0; i < nr_regs; i++) { + const struct reg_field field = { + .reg = (regs[i].reg != 0xffffffff) ? + regs[i].reg + win->offset : regs[i].reg, + .lsb = regs[i].lsb, + .msb = regs[i].msb + }; - kfree(esmart_regs); + win->reg[i] = devm_regmap_field_alloc(vop2->dev, vop2->map, field); + if (IS_ERR(win->reg[i])) + return PTR_ERR(win->reg[i]); + } - return ret; + return 0; }; static int vop2_win_init(struct vop2 *vop2) @@ -3596,9 +2574,11 @@ static int vop2_win_init(struct vop2 *vop2) win->win_id = i; win->vop2 = vop2; if (vop2_cluster_window(win)) - ret = vop2_cluster_init(win); + ret = vop2_regmap_init(win, vop2->data->cluster_reg, + vop2->data->nr_cluster_regs); else - ret = vop2_esmart_init(win); + ret = vop2_regmap_init(win, vop2->data->smart_reg, + vop2->data->nr_smart_regs); if (ret) return ret; } @@ -3655,15 +2635,16 @@ static int vop2_bind(struct device *dev, struct device *master, void *data) vop2->dev = dev; vop2->data = vop2_data; + vop2->ops = vop2_data->ops; + vop2->version = vop2_data->version; vop2->drm = drm; dev_set_drvdata(dev, vop2); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vop"); - if (!res) { - drm_err(vop2->drm, "failed to get vop2 register byname\n"); - return -EINVAL; - } + if (!res) + return dev_err_probe(drm->dev, -EINVAL, + "failed to get vop2 register byname\n"); vop2->res = res; vop2->regs = devm_ioremap_resource(dev, res); @@ -3688,56 +2669,59 @@ static int vop2_bind(struct device *dev, struct device *master, void *data) if (vop2_data->feature & VOP2_FEATURE_HAS_SYS_GRF) { vop2->sys_grf = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,grf"); if (IS_ERR(vop2->sys_grf)) - return dev_err_probe(dev, PTR_ERR(vop2->sys_grf), "cannot get sys_grf"); + return dev_err_probe(drm->dev, PTR_ERR(vop2->sys_grf), + "cannot get sys_grf\n"); } if (vop2_data->feature & VOP2_FEATURE_HAS_VOP_GRF) { vop2->vop_grf = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,vop-grf"); if (IS_ERR(vop2->vop_grf)) - return dev_err_probe(dev, PTR_ERR(vop2->vop_grf), "cannot get vop_grf"); + return dev_err_probe(drm->dev, PTR_ERR(vop2->vop_grf), + "cannot get vop_grf\n"); } if (vop2_data->feature & VOP2_FEATURE_HAS_VO1_GRF) { vop2->vo1_grf = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,vo1-grf"); if (IS_ERR(vop2->vo1_grf)) - return dev_err_probe(dev, PTR_ERR(vop2->vo1_grf), "cannot get vo1_grf"); + return dev_err_probe(drm->dev, PTR_ERR(vop2->vo1_grf), + "cannot get vo1_grf\n"); } if (vop2_data->feature & VOP2_FEATURE_HAS_SYS_PMU) { vop2->sys_pmu = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,pmu"); if (IS_ERR(vop2->sys_pmu)) - return dev_err_probe(dev, PTR_ERR(vop2->sys_pmu), "cannot get sys_pmu"); + return dev_err_probe(drm->dev, PTR_ERR(vop2->sys_pmu), + "cannot get sys_pmu\n"); } vop2->hclk = devm_clk_get(vop2->dev, "hclk"); - if (IS_ERR(vop2->hclk)) { - drm_err(vop2->drm, "failed to get hclk source\n"); - return PTR_ERR(vop2->hclk); - } + if (IS_ERR(vop2->hclk)) + return dev_err_probe(drm->dev, PTR_ERR(vop2->hclk), + "failed to get hclk source\n"); vop2->aclk = devm_clk_get(vop2->dev, "aclk"); - if (IS_ERR(vop2->aclk)) { - drm_err(vop2->drm, "failed to get aclk source\n"); - return PTR_ERR(vop2->aclk); - } + if (IS_ERR(vop2->aclk)) + return dev_err_probe(drm->dev, PTR_ERR(vop2->aclk), + "failed to get aclk source\n"); vop2->pclk = devm_clk_get_optional(vop2->dev, "pclk_vop"); - if (IS_ERR(vop2->pclk)) { - drm_err(vop2->drm, "failed to get pclk source\n"); - return PTR_ERR(vop2->pclk); - } + if (IS_ERR(vop2->pclk)) + return dev_err_probe(drm->dev, PTR_ERR(vop2->pclk), + "failed to get pclk source\n"); vop2->pll_hdmiphy0 = devm_clk_get_optional(vop2->dev, "pll_hdmiphy0"); - if (IS_ERR(vop2->pll_hdmiphy0)) { - drm_err(vop2->drm, "failed to get pll_hdmiphy0\n"); - return PTR_ERR(vop2->pll_hdmiphy0); - } + if (IS_ERR(vop2->pll_hdmiphy0)) + return dev_err_probe(drm->dev, PTR_ERR(vop2->pll_hdmiphy0), + "failed to get pll_hdmiphy0\n"); + + vop2->pll_hdmiphy1 = devm_clk_get_optional(vop2->dev, "pll_hdmiphy1"); + if (IS_ERR(vop2->pll_hdmiphy1)) + return dev_err_probe(drm->dev, PTR_ERR(vop2->pll_hdmiphy1), + "failed to get pll_hdmiphy1\n"); vop2->irq = platform_get_irq(pdev, 0); - if (vop2->irq < 0) { - drm_err(vop2->drm, "cannot find irq for vop2\n"); - return vop2->irq; - } + if (vop2->irq < 0) + return dev_err_probe(drm->dev, vop2->irq, "cannot find irq for vop2\n"); mutex_init(&vop2->vop2_lock); @@ -3749,6 +2733,30 @@ static int vop2_bind(struct device *dev, struct device *master, void *data) if (ret) return ret; + if (vop2->version >= VOP_VERSION_RK3576) { + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, drm) { + struct vop2_video_port *vp = to_vop2_video_port(crtc); + int vp_irq; + const char *irq_name = devm_kasprintf(dev, GFP_KERNEL, "vp%d", vp->id); + + if (!irq_name) + return -ENOMEM; + + vp_irq = platform_get_irq_byname(pdev, irq_name); + if (vp_irq < 0) + return dev_err_probe(drm->dev, vp_irq, + "cannot find irq for vop2 vp%d\n", vp->id); + + ret = devm_request_irq(dev, vp_irq, rk3576_vp_isr, IRQF_SHARED, irq_name, + vp); + if (ret) + dev_err_probe(drm->dev, ret, + "request irq for vop2 vp%d failed\n", vp->id); + } + } + ret = vop2_find_rgb_encoder(vop2); if (ret >= 0) { vop2->rgb = rockchip_rgb_init(dev, &vop2->vps[ret].crtc, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h index 29cc7fb8f6d8..680bedbb770e 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h @@ -9,9 +9,19 @@ #include <linux/regmap.h> #include <drm/drm_modes.h> +#include <dt-bindings/soc/rockchip,vop2.h> #include "rockchip_drm_drv.h" #include "rockchip_drm_vop.h" +#define VOP2_VERSION(major, minor, build) ((major) << 24 | (minor) << 16 | (build)) + +/* The VOP version of new SoC is bigger than the old */ +#define VOP_VERSION_RK3568 VOP2_VERSION(0x40, 0x15, 0x8023) +#define VOP_VERSION_RK3588 VOP2_VERSION(0x40, 0x17, 0x6786) +#define VOP_VERSION_RK3528 VOP2_VERSION(0x50, 0x17, 0x1263) +#define VOP_VERSION_RK3562 VOP2_VERSION(0x50, 0x17, 0x4350) +#define VOP_VERSION_RK3576 VOP2_VERSION(0x50, 0x19, 0x9765) + #define VOP2_VP_FEATURE_OUTPUT_10BIT BIT(0) #define VOP2_FEATURE_HAS_SYS_GRF BIT(0) @@ -34,6 +44,13 @@ enum win_dly_mode { VOP2_DLY_MODE_MAX, }; +enum vop2_dly_module { + VOP2_DLY_WIN, /** Win delay cycle for this VP */ + VOP2_DLY_LAYER_MIX, /** Layer Mix delay cycle for this VP */ + VOP2_DLY_HDR_MIX, /** HDR delay cycle for this VP */ + VOP2_DLY_MAX, +}; + enum vop2_scale_up_mode { VOP2_SCALE_UP_NRST_NBOR, VOP2_SCALE_UP_BIL, @@ -58,6 +75,23 @@ enum vop2_scale_down_mode { #define VOP2_PD_DSC_4K BIT(6) #define VOP2_PD_ESMART BIT(7) +#define vop2_output_if_is_hdmi(x) ((x) == ROCKCHIP_VOP2_EP_HDMI0 || \ + (x) == ROCKCHIP_VOP2_EP_HDMI1) + +#define vop2_output_if_is_dp(x) ((x) == ROCKCHIP_VOP2_EP_DP0 || \ + (x) == ROCKCHIP_VOP2_EP_DP1) + +#define vop2_output_if_is_edp(x) ((x) == ROCKCHIP_VOP2_EP_EDP0 || \ + (x) == ROCKCHIP_VOP2_EP_EDP1) + +#define vop2_output_if_is_mipi(x) ((x) == ROCKCHIP_VOP2_EP_MIPI0 || \ + (x) == ROCKCHIP_VOP2_EP_MIPI1) + +#define vop2_output_if_is_lvds(x) ((x) == ROCKCHIP_VOP2_EP_LVDS0 || \ + (x) == ROCKCHIP_VOP2_EP_LVDS1) + +#define vop2_output_if_is_dpi(x) ((x) == ROCKCHIP_VOP2_EP_RGB0) + enum vop2_win_regs { VOP2_WIN_ENABLE, VOP2_WIN_FORMAT, @@ -113,16 +147,22 @@ enum vop2_win_regs { VOP2_WIN_AFBC_UV_SWAP, VOP2_WIN_AFBC_AUTO_GATING_EN, VOP2_WIN_AFBC_BLOCK_SPLIT_EN, + VOP2_WIN_AFBC_PLD_OFFSET_EN, VOP2_WIN_AFBC_PIC_VIR_WIDTH, VOP2_WIN_AFBC_TILE_NUM, VOP2_WIN_AFBC_PIC_OFFSET, VOP2_WIN_AFBC_PIC_SIZE, VOP2_WIN_AFBC_DSP_OFFSET, - VOP2_WIN_AFBC_TRANSFORM_OFFSET, + VOP2_WIN_AFBC_PLD_OFFSET, + VOP2_WIN_TRANSFORM_OFFSET, VOP2_WIN_AFBC_HDR_PTR, VOP2_WIN_AFBC_HALF_BLOCK_EN, VOP2_WIN_AFBC_ROTATE_270, VOP2_WIN_AFBC_ROTATE_90, + + VOP2_WIN_VP_SEL, + VOP2_WIN_DLY_NUM, + VOP2_WIN_MAX_REG, }; @@ -140,6 +180,7 @@ struct vop2_win_data { unsigned int phys_id; u32 base; + u32 possible_vp_mask; enum drm_plane_type type; u32 nformats; @@ -148,9 +189,9 @@ struct vop2_win_data { const unsigned int supported_rotations; /** - * @layer_sel_id: defined by register OVERLAY_LAYER_SEL of VOP2 + * @layer_sel_id: defined by register OVERLAY_LAYER_SEL or PORTn_LAYER_SEL */ - unsigned int layer_sel_id; + unsigned int layer_sel_id[ROCKCHIP_MAX_CRTC]; uint64_t feature; uint8_t axi_bus_id; @@ -162,6 +203,23 @@ struct vop2_win_data { const u8 dly[VOP2_DLY_MODE_MAX]; }; +struct vop2_win { + struct vop2 *vop2; + struct drm_plane base; + const struct vop2_win_data *data; + struct regmap_field *reg[VOP2_WIN_MAX_REG]; + + /** + * @win_id: graphic window id, a cluster may be split into two + * graphics windows. + */ + u8 win_id; + u8 delay; + u32 offset; + + enum drm_plane_type type; +}; + struct vop2_video_port_data { unsigned int id; u32 feature; @@ -170,22 +228,116 @@ struct vop2_video_port_data { struct vop_rect max_output; const u8 pre_scan_max_dly[4]; unsigned int offset; + /** + * @pixel_rate: pixel per cycle + */ + u8 pixel_rate; +}; + +struct vop2_video_port { + struct drm_crtc crtc; + struct vop2 *vop2; + struct clk *dclk; + struct clk *dclk_src; + unsigned int id; + const struct vop2_video_port_data *data; + + struct completion dsp_hold_completion; + + /** + * @win_mask: Bitmask of windows attached to the video port; + */ + u32 win_mask; + + struct vop2_win *primary_plane; + struct drm_pending_vblank_event *event; + + unsigned int nlayers; +}; + +/** + * struct vop2_ops - helper operations for vop2 hardware + * + * These hooks are used by the common part of the vop2 driver to + * implement the proper behaviour of different variants. + */ +struct vop2_ops { + unsigned long (*setup_intf_mux)(struct vop2_video_port *vp, int ep_id, u32 polflags); + void (*setup_bg_dly)(struct vop2_video_port *vp); + void (*setup_overlay)(struct vop2_video_port *vp); }; struct vop2_data { u8 nr_vps; u64 feature; + u32 version; + const struct vop2_ops *ops; const struct vop2_win_data *win; const struct vop2_video_port_data *vp; + const struct reg_field *cluster_reg; + const struct reg_field *smart_reg; const struct vop2_regs_dump *regs_dump; struct vop_rect max_input; struct vop_rect max_output; + unsigned int nr_cluster_regs; + unsigned int nr_smart_regs; unsigned int win_size; unsigned int regs_dump_size; unsigned int soc_id; }; +struct vop2 { + u32 version; + struct device *dev; + struct drm_device *drm; + struct vop2_video_port vps[ROCKCHIP_MAX_CRTC]; + + const struct vop2_data *data; + const struct vop2_ops *ops; + /* + * Number of windows that are registered as plane, may be less than the + * total number of hardware windows. + */ + u32 registered_num_wins; + + struct resource *res; + void __iomem *regs; + struct regmap *map; + + struct regmap *sys_grf; + struct regmap *vop_grf; + struct regmap *vo1_grf; + struct regmap *sys_pmu; + + /* physical map length of vop2 register */ + u32 len; + + void __iomem *lut_regs; + + /* protects crtc enable/disable */ + struct mutex vop2_lock; + + int irq; + + /* + * Some global resources are shared between all video ports(crtcs), so + * we need a ref counter here. + */ + unsigned int enable_count; + struct clk *hclk; + struct clk *aclk; + struct clk *pclk; + struct clk *pll_hdmiphy0; + struct clk *pll_hdmiphy1; + + /* optional internal rgb encoder */ + struct rockchip_rgb *rgb; + + /* must be put at the end of the struct */ + struct vop2_win win[]; +}; + /* interrupt define */ #define FS_NEW_INTR BIT(4) #define ADDR_SAME_INTR BIT(5) @@ -240,10 +392,13 @@ enum dst_factor_mode { #define RK3568_REG_CFG_DONE 0x000 #define RK3568_VERSION_INFO 0x004 #define RK3568_SYS_AUTO_GATING_CTRL 0x008 +#define RK3576_SYS_MMU_CTRL_IMD 0x020 #define RK3568_SYS_AXI_LUT_CTRL 0x024 #define RK3568_DSP_IF_EN 0x028 +#define RK3576_SYS_PORT_CTRL_IMD 0x028 #define RK3568_DSP_IF_CTRL 0x02c #define RK3568_DSP_IF_POL 0x030 +#define RK3576_SYS_CLUSTER_PD_CTRL_IMD 0x030 #define RK3588_SYS_PD_CTRL 0x034 #define RK3568_WB_CTRL 0x40 #define RK3568_WB_XSCAL_FACTOR 0x44 @@ -263,6 +418,55 @@ enum dst_factor_mode { #define RK3568_VP_INT_CLR(vp) (0xA4 + (vp) * 0x10) #define RK3568_VP_INT_STATUS(vp) (0xA8 + (vp) * 0x10) #define RK3568_VP_INT_RAW_STATUS(vp) (0xAC + (vp) * 0x10) +#define RK3576_WB_CTRL 0x100 +#define RK3576_WB_XSCAL_FACTOR 0x104 +#define RK3576_WB_YRGB_MST 0x108 +#define RK3576_WB_CBR_MST 0x10C +#define RK3576_WB_VIR_STRIDE 0x110 +#define RK3576_WB_TIMEOUT_CTRL 0x114 +#define RK3576_MIPI0_IF_CTRL 0x180 +#define RK3576_HDMI0_IF_CTRL 0x184 +#define RK3576_EDP0_IF_CTRL 0x188 +#define RK3576_DP0_IF_CTRL 0x18C +#define RK3576_RGB_IF_CTRL 0x194 +#define RK3576_DP1_IF_CTRL 0x1A4 +#define RK3576_DP2_IF_CTRL 0x1B0 + +/* Extra OVL register definition */ +#define RK3576_SYS_EXTRA_ALPHA_CTRL 0x500 +#define RK3576_CLUSTER0_MIX_SRC_COLOR_CTRL 0x530 +#define RK3576_CLUSTER0_MIX_DST_COLOR_CTRL 0x534 +#define RK3576_CLUSTER0_MIX_SRC_ALPHA_CTRL 0x538 +#define RK3576_CLUSTER0_MIX_DST_ALPHA_CTRL 0x53c +#define RK3576_CLUSTER1_MIX_SRC_COLOR_CTRL 0x540 +#define RK3576_CLUSTER1_MIX_DST_COLOR_CTRL 0x544 +#define RK3576_CLUSTER1_MIX_SRC_ALPHA_CTRL 0x548 +#define RK3576_CLUSTER1_MIX_DST_ALPHA_CTRL 0x54c + +/* OVL registers for Video Port definition */ +#define RK3576_OVL_CTRL(vp) (0x600 + (vp) * 0x100) +#define RK3576_OVL_LAYER_SEL(vp) (0x604 + (vp) * 0x100) +#define RK3576_OVL_MIX0_SRC_COLOR_CTRL(vp) (0x620 + (vp) * 0x100) +#define RK3576_OVL_MIX0_DST_COLOR_CTRL(vp) (0x624 + (vp) * 0x100) +#define RK3576_OVL_MIX0_SRC_ALPHA_CTRL(vp) (0x628 + (vp) * 0x100) +#define RK3576_OVL_MIX0_DST_ALPHA_CTRL(vp) (0x62C + (vp) * 0x100) +#define RK3576_OVL_MIX1_SRC_COLOR_CTRL(vp) (0x630 + (vp) * 0x100) +#define RK3576_OVL_MIX1_DST_COLOR_CTRL(vp) (0x634 + (vp) * 0x100) +#define RK3576_OVL_MIX1_SRC_ALPHA_CTRL(vp) (0x638 + (vp) * 0x100) +#define RK3576_OVL_MIX1_DST_ALPHA_CTRL(vp) (0x63C + (vp) * 0x100) +#define RK3576_OVL_MIX2_SRC_COLOR_CTRL(vp) (0x640 + (vp) * 0x100) +#define RK3576_OVL_MIX2_DST_COLOR_CTRL(vp) (0x644 + (vp) * 0x100) +#define RK3576_OVL_MIX2_SRC_ALPHA_CTRL(vp) (0x648 + (vp) * 0x100) +#define RK3576_OVL_MIX2_DST_ALPHA_CTRL(vp) (0x64C + (vp) * 0x100) +#define RK3576_EXTRA_OVL_SRC_COLOR_CTRL(vp) (0x650 + (vp) * 0x100) +#define RK3576_EXTRA_OVL_DST_COLOR_CTRL(vp) (0x654 + (vp) * 0x100) +#define RK3576_EXTRA_OVL_SRC_ALPHA_CTRL(vp) (0x658 + (vp) * 0x100) +#define RK3576_EXTRA_OVL_DST_ALPHA_CTRL(vp) (0x65C + (vp) * 0x100) +#define RK3576_OVL_HDR_SRC_COLOR_CTRL(vp) (0x660 + (vp) * 0x100) +#define RK3576_OVL_HDR_DST_COLOR_CTRL(vp) (0x664 + (vp) * 0x100) +#define RK3576_OVL_HDR_SRC_ALPHA_CTRL(vp) (0x668 + (vp) * 0x100) +#define RK3576_OVL_HDR_DST_ALPHA_CTRL(vp) (0x66C + (vp) * 0x100) +#define RK3576_OVL_BG_MIX_CTRL(vp) (0x670 + (vp) * 0x100) /* Video Port registers definition */ #define RK3568_VP0_CTRL_BASE 0x0C00 @@ -335,7 +539,7 @@ enum dst_factor_mode { #define RK3568_CLUSTER_WIN_DSP_INFO 0x24 #define RK3568_CLUSTER_WIN_DSP_ST 0x28 #define RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB 0x30 -#define RK3568_CLUSTER_WIN_AFBCD_TRANSFORM_OFFSET 0x3C +#define RK3568_CLUSTER_WIN_TRANSFORM_OFFSET 0x3C #define RK3568_CLUSTER_WIN_AFBCD_OUTPUT_CTRL 0x50 #define RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE 0x54 #define RK3568_CLUSTER_WIN_AFBCD_HDR_PTR 0x58 @@ -345,7 +549,11 @@ enum dst_factor_mode { #define RK3568_CLUSTER_WIN_AFBCD_DSP_OFFSET 0x68 #define RK3568_CLUSTER_WIN_AFBCD_CTRL 0x6C +#define RK3576_CLUSTER_WIN_AFBCD_PLD_PTR_OFFSET 0x78 + #define RK3568_CLUSTER_CTRL 0x100 +#define RK3576_CLUSTER_PORT_SEL_IMD 0x1F4 +#define RK3576_CLUSTER_DLY_NUM 0x1F8 /* (E)smart register definition, offset relative to window base */ #define RK3568_SMART_CTRL0 0x00 @@ -396,6 +604,9 @@ enum dst_factor_mode { #define RK3568_SMART_REGION3_SCL_FACTOR_CBR 0xC8 #define RK3568_SMART_REGION3_SCL_OFFSET 0xCC #define RK3568_SMART_COLOR_KEY_CTRL 0xD0 +#define RK3576_SMART_ALPHA_MAP 0xD8 +#define RK3576_SMART_PORT_SEL_IMD 0xF4 +#define RK3576_SMART_DLY_NUM 0xF8 /* HDR register definition */ #define RK3568_HDR_LUT_CTRL 0x2000 @@ -544,6 +755,17 @@ enum dst_factor_mode { #define POLFLAG_DCLK_INV BIT(3) +#define RK3576_OVL_CTRL__YUV_MODE BIT(0) +#define RK3576_OVL_BG_MIX_CTRL__BG_DLY GENMASK(31, 24) + +#define RK3576_DSP_IF_CFG_DONE_IMD BIT(31) +#define RK3576_DSP_IF_DCLK_SEL_OUT BIT(21) +#define RK3576_DSP_IF_PCLK_DIV BIT(20) +#define RK3576_DSP_IF_PIN_POL GENMASK(5, 4) +#define RK3576_DSP_IF_MUX GENMASK(3, 2) +#define RK3576_DSP_IF_CLK_OUT_EN BIT(1) +#define RK3576_DSP_IF_EN BIT(0) + enum vop2_layer_phy_id { ROCKCHIP_VOP2_CLUSTER0 = 0, ROCKCHIP_VOP2_CLUSTER1, @@ -560,4 +782,52 @@ enum vop2_layer_phy_id { extern const struct component_ops vop2_component_ops; +static inline void vop2_writel(struct vop2 *vop2, u32 offset, u32 v) +{ + regmap_write(vop2->map, offset, v); +} + +static inline void vop2_vp_write(struct vop2_video_port *vp, u32 offset, u32 v) +{ + regmap_write(vp->vop2->map, vp->data->offset + offset, v); +} + +static inline u32 vop2_readl(struct vop2 *vop2, u32 offset) +{ + u32 val; + + regmap_read(vop2->map, offset, &val); + + return val; +} + +static inline u32 vop2_vp_read(struct vop2_video_port *vp, u32 offset) +{ + u32 val; + + regmap_read(vp->vop2->map, vp->data->offset + offset, &val); + + return val; +} + +static inline void vop2_win_write(const struct vop2_win *win, unsigned int reg, u32 v) +{ + regmap_field_write(win->reg[reg], v); +} + +static inline bool vop2_cluster_window(const struct vop2_win *win) +{ + return win->data->feature & WIN_FEATURE_CLUSTER; +} + +static inline struct vop2_video_port *to_vop2_video_port(struct drm_crtc *crtc) +{ + return container_of(crtc, struct vop2_video_port, crtc); +} + +static inline struct vop2_win *to_vop2_win(struct drm_plane *p) +{ + return container_of(p, struct vop2_win, base); +} + #endif /* _ROCKCHIP_DRM_VOP2_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index 385cf6881504..a673779de3d2 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -448,17 +448,14 @@ struct drm_encoder_helper_funcs px30_lvds_encoder_helper_funcs = { static int rk3288_lvds_probe(struct platform_device *pdev, struct rockchip_lvds *lvds) { - int ret; - lvds->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(lvds->regs)) return PTR_ERR(lvds->regs); - lvds->pclk = devm_clk_get(lvds->dev, "pclk_lvds"); - if (IS_ERR(lvds->pclk)) { - DRM_DEV_ERROR(lvds->dev, "could not get pclk_lvds\n"); - return PTR_ERR(lvds->pclk); - } + lvds->pclk = devm_clk_get_prepared(lvds->dev, "pclk_lvds"); + if (IS_ERR(lvds->pclk)) + return dev_err_probe(lvds->dev, PTR_ERR(lvds->pclk), + "could not get or prepare pclk_lvds\n"); lvds->pins = devm_kzalloc(lvds->dev, sizeof(*lvds->pins), GFP_KERNEL); @@ -467,25 +464,19 @@ static int rk3288_lvds_probe(struct platform_device *pdev, lvds->pins->p = devm_pinctrl_get(lvds->dev); if (IS_ERR(lvds->pins->p)) { - DRM_DEV_ERROR(lvds->dev, "no pinctrl handle\n"); + dev_warn(lvds->dev, "no pinctrl handle\n"); devm_kfree(lvds->dev, lvds->pins); lvds->pins = NULL; } else { lvds->pins->default_state = pinctrl_lookup_state(lvds->pins->p, "lcdc"); if (IS_ERR(lvds->pins->default_state)) { - DRM_DEV_ERROR(lvds->dev, "no default pinctrl state\n"); + dev_warn(lvds->dev, "no default pinctrl state\n"); devm_kfree(lvds->dev, lvds->pins); lvds->pins = NULL; } } - ret = clk_prepare(lvds->pclk); - if (ret < 0) { - DRM_DEV_ERROR(lvds->dev, "failed to prepare pclk_lvds\n"); - return ret; - } - return 0; } @@ -555,11 +546,10 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, lvds->drm_dev = drm_dev; port = of_graph_get_port_by_id(dev->of_node, 1); - if (!port) { - DRM_DEV_ERROR(dev, - "can't found port point, please init lvds panel port!\n"); - return -EINVAL; - } + if (!port) + return dev_err_probe(dev, -EINVAL, + "can't found port point, please init lvds panel port!\n"); + for_each_child_of_node(port, endpoint) { child_count++; of_property_read_u32(endpoint, "reg", &endpoint_id); @@ -571,8 +561,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, } } if (!child_count) { - DRM_DEV_ERROR(dev, "lvds port does not have any children\n"); - ret = -EINVAL; + ret = dev_err_probe(dev, -EINVAL, "lvds port does not have any children\n"); goto err_put_port; } else if (ret) { dev_err_probe(dev, ret, "failed to find panel and bridge node\n"); @@ -589,8 +578,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, lvds->output = rockchip_lvds_name_to_output(name); if (lvds->output < 0) { - DRM_DEV_ERROR(dev, "invalid output type [%s]\n", name); - ret = lvds->output; + ret = dev_err_probe(dev, lvds->output, "invalid output type [%s]\n", name); goto err_put_remote; } @@ -601,8 +589,8 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, lvds->format = rockchip_lvds_name_to_format(name); if (lvds->format < 0) { - DRM_DEV_ERROR(dev, "invalid data-mapping format [%s]\n", name); - ret = lvds->format; + ret = dev_err_probe(dev, lvds->format, + "invalid data-mapping format [%s]\n", name); goto err_put_remote; } @@ -612,8 +600,8 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, ret = drm_simple_encoder_init(drm_dev, encoder, DRM_MODE_ENCODER_LVDS); if (ret < 0) { - DRM_DEV_ERROR(drm_dev->dev, - "failed to initialize encoder: %d\n", ret); + drm_err(drm_dev, + "failed to initialize encoder: %d\n", ret); goto err_put_remote; } @@ -626,8 +614,8 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, &rockchip_lvds_connector_funcs, DRM_MODE_CONNECTOR_LVDS); if (ret < 0) { - DRM_DEV_ERROR(drm_dev->dev, - "failed to initialize connector: %d\n", ret); + drm_err(drm_dev, + "failed to initialize connector: %d\n", ret); goto err_free_encoder; } @@ -641,9 +629,9 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, connector = drm_bridge_connector_init(lvds->drm_dev, encoder); if (IS_ERR(connector)) { - DRM_DEV_ERROR(drm_dev->dev, - "failed to initialize bridge connector: %pe\n", - connector); + drm_err(drm_dev, + "failed to initialize bridge connector: %pe\n", + connector); ret = PTR_ERR(connector); goto err_free_encoder; } @@ -651,8 +639,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, ret = drm_connector_attach_encoder(connector, encoder); if (ret < 0) { - DRM_DEV_ERROR(drm_dev->dev, - "failed to attach encoder: %d\n", ret); + drm_err(drm_dev, "failed to attach encoder: %d\n", ret); goto err_free_connector; } @@ -714,34 +701,25 @@ static int rockchip_lvds_probe(struct platform_device *pdev) lvds->grf = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,grf"); - if (IS_ERR(lvds->grf)) { - DRM_DEV_ERROR(dev, "missing rockchip,grf property\n"); - return PTR_ERR(lvds->grf); - } + if (IS_ERR(lvds->grf)) + return dev_err_probe(dev, PTR_ERR(lvds->grf), "missing rockchip,grf property\n"); ret = lvds->soc_data->probe(pdev, lvds); - if (ret) { - DRM_DEV_ERROR(dev, "Platform initialization failed\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Platform initialization failed\n"); dev_set_drvdata(dev, lvds); ret = component_add(&pdev->dev, &rockchip_lvds_component_ops); - if (ret < 0) { - DRM_DEV_ERROR(dev, "failed to add component\n"); - clk_unprepare(lvds->pclk); - } + if (ret < 0) + return dev_err_probe(dev, ret, "failed to add component\n"); - return ret; + return 0; } static void rockchip_lvds_remove(struct platform_device *pdev) { - struct rockchip_lvds *lvds = platform_get_drvdata(pdev); - component_del(&pdev->dev, &rockchip_lvds_component_ops); - clk_unprepare(lvds->pclk); } struct platform_driver rockchip_lvds_driver = { diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c index 65a88f489693..14958d6b3d2e 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c @@ -4,17 +4,56 @@ * Author: Andy Yan <andy.yan@rock-chips.com> */ +#include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/component.h> #include <linux/mod_devicetable.h> #include <linux/platform_device.h> #include <linux/of.h> +#include <drm/drm_blend.h> #include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> #include <drm/drm_plane.h> #include <drm/drm_print.h> #include "rockchip_drm_vop2.h" +union vop2_alpha_ctrl { + u32 val; + struct { + /* [0:1] */ + u32 color_mode:1; + u32 alpha_mode:1; + /* [2:3] */ + u32 blend_mode:2; + u32 alpha_cal_mode:1; + /* [5:7] */ + u32 factor_mode:3; + /* [8:9] */ + u32 alpha_en:1; + u32 src_dst_swap:1; + u32 reserved:6; + /* [16:23] */ + u32 glb_alpha:8; + } bits; +}; + +struct vop2_alpha { + union vop2_alpha_ctrl src_color_ctrl; + union vop2_alpha_ctrl dst_color_ctrl; + union vop2_alpha_ctrl src_alpha_ctrl; + union vop2_alpha_ctrl dst_alpha_ctrl; +}; + +struct vop2_alpha_config { + bool src_premulti_en; + bool dst_premulti_en; + bool src_pixel_alpha_en; + bool dst_pixel_alpha_en; + u16 src_glb_alpha_value; + u16 dst_glb_alpha_value; +}; + static const uint32_t formats_cluster[] = { DRM_FORMAT_XRGB2101010, DRM_FORMAT_XBGR2101010, @@ -32,6 +71,37 @@ static const uint32_t formats_cluster[] = { DRM_FORMAT_Y210, /* yuv422_10bit non-Linear mode only */ }; +/* + * The cluster windows on rk3576 support: + * RGB: linear mode and afbc + * YUV: linear mode and rfbc + * rfbc is a rockchip defined non-linear mode, produced by + * Video decoder + */ +static const uint32_t formats_rk3576_cluster[] = { + DRM_FORMAT_XRGB2101010, + DRM_FORMAT_XBGR2101010, + DRM_FORMAT_ARGB2101010, + DRM_FORMAT_ABGR2101010, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_BGR888, + DRM_FORMAT_RGB565, + DRM_FORMAT_BGR565, + DRM_FORMAT_NV12, /* yuv420_8bit linear mode, 2 plane */ + DRM_FORMAT_NV21, /* yvu420_8bit linear mode, 2 plane */ + DRM_FORMAT_NV16, /* yuv422_8bit linear mode, 2 plane */ + DRM_FORMAT_NV61, /* yvu422_8bit linear mode, 2 plane */ + DRM_FORMAT_NV24, /* yuv444_8bit linear mode, 2 plane */ + DRM_FORMAT_NV42, /* yvu444_8bit linear mode, 2 plane */ + DRM_FORMAT_NV15, /* yuv420_10bit linear mode, 2 plane, no padding */ + DRM_FORMAT_NV20, /* yuv422_10bit linear mode, 2 plane, no padding */ + DRM_FORMAT_NV30, /* yuv444_10bit linear mode, 2 plane, no padding */ +}; + static const uint32_t formats_esmart[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, @@ -78,6 +148,41 @@ static const uint32_t formats_rk356x_esmart[] = { DRM_FORMAT_VYUY, /* yuv422_8bit[VYUY] linear mode */ }; +/* + * Add XRGB2101010/ARGB2101010ARGB1555/XRGB1555 + */ +static const uint32_t formats_rk3576_esmart[] = { + DRM_FORMAT_XRGB2101010, + DRM_FORMAT_XBGR2101010, + DRM_FORMAT_ARGB2101010, + DRM_FORMAT_ABGR2101010, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_BGR888, + DRM_FORMAT_RGB565, + DRM_FORMAT_BGR565, + DRM_FORMAT_ARGB1555, + DRM_FORMAT_ABGR1555, + DRM_FORMAT_XRGB1555, + DRM_FORMAT_XBGR1555, + DRM_FORMAT_NV12, /* yuv420_8bit linear mode, 2 plane */ + DRM_FORMAT_NV21, /* yvu420_8bit linear mode, 2 plane */ + DRM_FORMAT_NV16, /* yuv422_8bit linear mode, 2 plane */ + DRM_FORMAT_NV61, /* yvu422_8bit linear mode, 2 plane */ + DRM_FORMAT_NV20, /* yuv422_10bit linear mode, 2 plane, no padding */ + DRM_FORMAT_NV24, /* yuv444_8bit linear mode, 2 plane */ + DRM_FORMAT_NV42, /* yvu444_8bit linear mode, 2 plane */ + DRM_FORMAT_NV30, /* yuv444_10bit linear mode, 2 plane, no padding */ + DRM_FORMAT_NV15, /* yuv420_10bit linear mode, 2 plane, no padding */ + DRM_FORMAT_YVYU, /* yuv422_8bit[YVYU] linear mode */ + DRM_FORMAT_VYUY, /* yuv422_8bit[VYUY] linear mode */ + DRM_FORMAT_YUYV, /* yuv422_8bit[YUYV] linear mode */ + DRM_FORMAT_UYVY, /* yuv422_8bit[UYVY] linear mode */ +}; + static const uint32_t formats_smart[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, @@ -131,6 +236,321 @@ static const uint64_t format_modifiers_afbc[] = { DRM_FORMAT_MOD_INVALID, }; +/* used from rk3576, afbc 32*8 half mode */ +static const uint64_t format_modifiers_rk3576_afbc[] = { + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_SPLIT), + + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_SPARSE | + AFBC_FORMAT_MOD_SPLIT), + + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_YTR | + AFBC_FORMAT_MOD_SPLIT), + + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_CBR | + AFBC_FORMAT_MOD_SPLIT), + + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_CBR | + AFBC_FORMAT_MOD_SPARSE | + AFBC_FORMAT_MOD_SPLIT), + + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_YTR | + AFBC_FORMAT_MOD_CBR | + AFBC_FORMAT_MOD_SPLIT), + + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_YTR | + AFBC_FORMAT_MOD_CBR | + AFBC_FORMAT_MOD_SPARSE | + AFBC_FORMAT_MOD_SPLIT), + + /* SPLIT mandates SPARSE, RGB modes mandates YTR */ + DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 | + AFBC_FORMAT_MOD_YTR | + AFBC_FORMAT_MOD_SPARSE | + AFBC_FORMAT_MOD_SPLIT), + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID, +}; + +static const struct reg_field rk3568_vop_cluster_regs[VOP2_WIN_MAX_REG] = { + [VOP2_WIN_ENABLE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 0, 0), + [VOP2_WIN_FORMAT] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 1, 5), + [VOP2_WIN_RB_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 14, 14), + [VOP2_WIN_DITHER_UP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 18, 18), + [VOP2_WIN_ACT_INFO] = REG_FIELD(RK3568_CLUSTER_WIN_ACT_INFO, 0, 31), + [VOP2_WIN_DSP_INFO] = REG_FIELD(RK3568_CLUSTER_WIN_DSP_INFO, 0, 31), + [VOP2_WIN_DSP_ST] = REG_FIELD(RK3568_CLUSTER_WIN_DSP_ST, 0, 31), + [VOP2_WIN_YRGB_MST] = REG_FIELD(RK3568_CLUSTER_WIN_YRGB_MST, 0, 31), + [VOP2_WIN_UV_MST] = REG_FIELD(RK3568_CLUSTER_WIN_CBR_MST, 0, 31), + [VOP2_WIN_YUV_CLIP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 19, 19), + [VOP2_WIN_YRGB_VIR] = REG_FIELD(RK3568_CLUSTER_WIN_VIR, 0, 15), + [VOP2_WIN_UV_VIR] = REG_FIELD(RK3568_CLUSTER_WIN_VIR, 16, 31), + [VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 8, 8), + [VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 9, 9), + [VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 10, 11), + [VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 0, 3), + [VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 5, 8), + /* RK3588 only, reserved bit on rk3568*/ + [VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3568_CLUSTER_CTRL, 13, 13), + + /* Scale */ + [VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 0, 15), + [VOP2_WIN_SCALE_YRGB_Y] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 16, 31), + [VOP2_WIN_YRGB_VER_SCL_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 14, 15), + [VOP2_WIN_YRGB_HOR_SCL_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 12, 13), + [VOP2_WIN_BIC_COE_SEL] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 2, 3), + [VOP2_WIN_VSD_YRGB_GT2] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 28, 28), + [VOP2_WIN_VSD_YRGB_GT4] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 29, 29), + + /* cluster regs */ + [VOP2_WIN_AFBC_ENABLE] = REG_FIELD(RK3568_CLUSTER_CTRL, 1, 1), + [VOP2_WIN_CLUSTER_ENABLE] = REG_FIELD(RK3568_CLUSTER_CTRL, 0, 0), + [VOP2_WIN_CLUSTER_LB_MODE] = REG_FIELD(RK3568_CLUSTER_CTRL, 4, 7), + + /* afbc regs */ + [VOP2_WIN_AFBC_FORMAT] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 2, 6), + [VOP2_WIN_AFBC_RB_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 9, 9), + [VOP2_WIN_AFBC_UV_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 10, 10), + [VOP2_WIN_AFBC_AUTO_GATING_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_OUTPUT_CTRL, 4, 4), + [VOP2_WIN_AFBC_HALF_BLOCK_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 7, 7), + [VOP2_WIN_AFBC_BLOCK_SPLIT_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 8, 8), + [VOP2_WIN_AFBC_HDR_PTR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_HDR_PTR, 0, 31), + [VOP2_WIN_AFBC_PIC_SIZE] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_PIC_SIZE, 0, 31), + [VOP2_WIN_AFBC_PIC_VIR_WIDTH] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_VIR_WIDTH, 0, 15), + [VOP2_WIN_AFBC_TILE_NUM] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_VIR_WIDTH, 16, 31), + [VOP2_WIN_AFBC_PIC_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_PIC_OFFSET, 0, 31), + [VOP2_WIN_AFBC_DSP_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_DSP_OFFSET, 0, 31), + [VOP2_WIN_TRANSFORM_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_TRANSFORM_OFFSET, 0, 31), + [VOP2_WIN_AFBC_ROTATE_90] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 0, 0), + [VOP2_WIN_AFBC_ROTATE_270] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 1, 1), + [VOP2_WIN_XMIRROR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 2, 2), + [VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 3, 3), + [VOP2_WIN_UV_SWAP] = { .reg = 0xffffffff }, + [VOP2_WIN_COLOR_KEY] = { .reg = 0xffffffff }, + [VOP2_WIN_COLOR_KEY_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_SCALE_CBCR_X] = { .reg = 0xffffffff }, + [VOP2_WIN_SCALE_CBCR_Y] = { .reg = 0xffffffff }, + [VOP2_WIN_YRGB_HSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_YRGB_VSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_VER_SCL_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_HSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_HOR_SCL_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_VSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_VSD_CBCR_GT2] = { .reg = 0xffffffff }, + [VOP2_WIN_VSD_CBCR_GT4] = { .reg = 0xffffffff }, +}; + +static const struct reg_field rk3568_vop_smart_regs[VOP2_WIN_MAX_REG] = { + [VOP2_WIN_ENABLE] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 0, 0), + [VOP2_WIN_FORMAT] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 1, 5), + [VOP2_WIN_DITHER_UP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 12, 12), + [VOP2_WIN_RB_SWAP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 14, 14), + [VOP2_WIN_UV_SWAP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 16, 16), + [VOP2_WIN_ACT_INFO] = REG_FIELD(RK3568_SMART_REGION0_ACT_INFO, 0, 31), + [VOP2_WIN_DSP_INFO] = REG_FIELD(RK3568_SMART_REGION0_DSP_INFO, 0, 31), + [VOP2_WIN_DSP_ST] = REG_FIELD(RK3568_SMART_REGION0_DSP_ST, 0, 28), + [VOP2_WIN_YRGB_MST] = REG_FIELD(RK3568_SMART_REGION0_YRGB_MST, 0, 31), + [VOP2_WIN_UV_MST] = REG_FIELD(RK3568_SMART_REGION0_CBR_MST, 0, 31), + [VOP2_WIN_YUV_CLIP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 17, 17), + [VOP2_WIN_YRGB_VIR] = REG_FIELD(RK3568_SMART_REGION0_VIR, 0, 15), + [VOP2_WIN_UV_VIR] = REG_FIELD(RK3568_SMART_REGION0_VIR, 16, 31), + [VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_SMART_CTRL0, 0, 0), + [VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_SMART_CTRL0, 1, 1), + [VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_SMART_CTRL0, 2, 3), + [VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_SMART_CTRL1, 31, 31), + [VOP2_WIN_COLOR_KEY] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 0, 29), + [VOP2_WIN_COLOR_KEY_EN] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 31, 31), + [VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 4, 8), + [VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 12, 16), + /* RK3588 only, reserved register on rk3568 */ + [VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3588_SMART_AXI_CTRL, 1, 1), + + /* Scale */ + [VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 0, 15), + [VOP2_WIN_SCALE_YRGB_Y] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 16, 31), + [VOP2_WIN_SCALE_CBCR_X] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_CBR, 0, 15), + [VOP2_WIN_SCALE_CBCR_Y] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_CBR, 16, 31), + [VOP2_WIN_YRGB_HOR_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 0, 1), + [VOP2_WIN_YRGB_HSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 2, 3), + [VOP2_WIN_YRGB_VER_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 4, 5), + [VOP2_WIN_YRGB_VSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 6, 7), + [VOP2_WIN_CBCR_HOR_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 8, 9), + [VOP2_WIN_CBCR_HSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 10, 11), + [VOP2_WIN_CBCR_VER_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 12, 13), + [VOP2_WIN_CBCR_VSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 14, 15), + [VOP2_WIN_BIC_COE_SEL] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 16, 17), + [VOP2_WIN_VSD_YRGB_GT2] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 8, 8), + [VOP2_WIN_VSD_YRGB_GT4] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 9, 9), + [VOP2_WIN_VSD_CBCR_GT2] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 10, 10), + [VOP2_WIN_VSD_CBCR_GT4] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 11, 11), + [VOP2_WIN_XMIRROR] = { .reg = 0xffffffff }, + [VOP2_WIN_CLUSTER_ENABLE] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_ENABLE] = { .reg = 0xffffffff }, + [VOP2_WIN_CLUSTER_LB_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_FORMAT] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_RB_SWAP] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_UV_SWAP] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_AUTO_GATING_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_BLOCK_SPLIT_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_PIC_VIR_WIDTH] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_TILE_NUM] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_PIC_OFFSET] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_PIC_SIZE] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_DSP_OFFSET] = { .reg = 0xffffffff }, + [VOP2_WIN_TRANSFORM_OFFSET] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_HDR_PTR] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_HALF_BLOCK_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_ROTATE_270] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_ROTATE_90] = { .reg = 0xffffffff }, +}; + +static const struct reg_field rk3576_vop_cluster_regs[VOP2_WIN_MAX_REG] = { + [VOP2_WIN_ENABLE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 0, 0), + [VOP2_WIN_FORMAT] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 1, 5), + [VOP2_WIN_RB_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 14, 14), + [VOP2_WIN_UV_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 17, 17), + [VOP2_WIN_DITHER_UP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 18, 18), + [VOP2_WIN_ACT_INFO] = REG_FIELD(RK3568_CLUSTER_WIN_ACT_INFO, 0, 31), + [VOP2_WIN_DSP_INFO] = REG_FIELD(RK3568_CLUSTER_WIN_DSP_INFO, 0, 31), + [VOP2_WIN_DSP_ST] = REG_FIELD(RK3568_CLUSTER_WIN_DSP_ST, 0, 31), + [VOP2_WIN_YRGB_MST] = REG_FIELD(RK3568_CLUSTER_WIN_YRGB_MST, 0, 31), + [VOP2_WIN_UV_MST] = REG_FIELD(RK3568_CLUSTER_WIN_CBR_MST, 0, 31), + [VOP2_WIN_YUV_CLIP] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 19, 19), + [VOP2_WIN_YRGB_VIR] = REG_FIELD(RK3568_CLUSTER_WIN_VIR, 0, 15), + [VOP2_WIN_UV_VIR] = REG_FIELD(RK3568_CLUSTER_WIN_VIR, 16, 31), + [VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 8, 8), + [VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 9, 9), + [VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL0, 10, 11), + [VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 0, 4), + [VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL2, 5, 9), + /* Read only bit on rk3576, writing on this bit have no effect.*/ + [VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3568_CLUSTER_CTRL, 13, 13), + + [VOP2_WIN_VP_SEL] = REG_FIELD(RK3576_CLUSTER_PORT_SEL_IMD, 0, 1), + [VOP2_WIN_DLY_NUM] = REG_FIELD(RK3576_CLUSTER_DLY_NUM, 0, 7), + + /* Scale */ + [VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 0, 15), + [VOP2_WIN_SCALE_YRGB_Y] = REG_FIELD(RK3568_CLUSTER_WIN_SCL_FACTOR_YRGB, 16, 31), + [VOP2_WIN_BIC_COE_SEL] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 2, 3), + [VOP2_WIN_YRGB_VER_SCL_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 14, 15), + [VOP2_WIN_YRGB_HOR_SCL_MODE] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 22, 23), + [VOP2_WIN_VSD_YRGB_GT2] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 28, 28), + [VOP2_WIN_VSD_YRGB_GT4] = REG_FIELD(RK3568_CLUSTER_WIN_CTRL1, 29, 29), + + /* cluster regs */ + [VOP2_WIN_AFBC_ENABLE] = REG_FIELD(RK3568_CLUSTER_CTRL, 1, 1), + [VOP2_WIN_CLUSTER_ENABLE] = REG_FIELD(RK3568_CLUSTER_CTRL, 0, 0), + [VOP2_WIN_CLUSTER_LB_MODE] = REG_FIELD(RK3568_CLUSTER_CTRL, 4, 7), + + /* afbc regs */ + [VOP2_WIN_AFBC_FORMAT] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 2, 6), + [VOP2_WIN_AFBC_RB_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 9, 9), + [VOP2_WIN_AFBC_UV_SWAP] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 10, 10), + [VOP2_WIN_AFBC_AUTO_GATING_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_OUTPUT_CTRL, 4, 4), + [VOP2_WIN_AFBC_HALF_BLOCK_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 7, 7), + [VOP2_WIN_AFBC_BLOCK_SPLIT_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 8, 8), + [VOP2_WIN_AFBC_PLD_OFFSET_EN] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_CTRL, 16, 16), + [VOP2_WIN_AFBC_HDR_PTR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_HDR_PTR, 0, 31), + [VOP2_WIN_AFBC_PIC_SIZE] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_PIC_SIZE, 0, 31), + [VOP2_WIN_AFBC_PIC_VIR_WIDTH] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_VIR_WIDTH, 0, 15), + [VOP2_WIN_AFBC_TILE_NUM] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_VIR_WIDTH, 16, 31), + [VOP2_WIN_AFBC_PIC_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_PIC_OFFSET, 0, 31), + [VOP2_WIN_AFBC_DSP_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_DSP_OFFSET, 0, 31), + [VOP2_WIN_AFBC_PLD_OFFSET] = REG_FIELD(RK3576_CLUSTER_WIN_AFBCD_PLD_PTR_OFFSET, 0, 31), + [VOP2_WIN_TRANSFORM_OFFSET] = REG_FIELD(RK3568_CLUSTER_WIN_TRANSFORM_OFFSET, 0, 31), + [VOP2_WIN_AFBC_ROTATE_90] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 0, 0), + [VOP2_WIN_AFBC_ROTATE_270] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 1, 1), + [VOP2_WIN_XMIRROR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 2, 2), + [VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_CLUSTER_WIN_AFBCD_ROTATE_MODE, 3, 3), + [VOP2_WIN_COLOR_KEY] = { .reg = 0xffffffff }, + [VOP2_WIN_COLOR_KEY_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_SCALE_CBCR_X] = { .reg = 0xffffffff }, + [VOP2_WIN_SCALE_CBCR_Y] = { .reg = 0xffffffff }, + [VOP2_WIN_YRGB_HSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_YRGB_VSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_VER_SCL_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_HSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_HOR_SCL_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_VSCL_FILTER_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_VSD_CBCR_GT2] = { .reg = 0xffffffff }, + [VOP2_WIN_VSD_CBCR_GT4] = { .reg = 0xffffffff }, +}; + +static const struct reg_field rk3576_vop_smart_regs[VOP2_WIN_MAX_REG] = { + [VOP2_WIN_ENABLE] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 0, 0), + [VOP2_WIN_FORMAT] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 1, 5), + [VOP2_WIN_DITHER_UP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 12, 12), + [VOP2_WIN_RB_SWAP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 14, 14), + [VOP2_WIN_UV_SWAP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 16, 16), + [VOP2_WIN_ACT_INFO] = REG_FIELD(RK3568_SMART_REGION0_ACT_INFO, 0, 31), + [VOP2_WIN_DSP_INFO] = REG_FIELD(RK3568_SMART_REGION0_DSP_INFO, 0, 31), + [VOP2_WIN_DSP_ST] = REG_FIELD(RK3568_SMART_REGION0_DSP_ST, 0, 28), + [VOP2_WIN_YRGB_MST] = REG_FIELD(RK3568_SMART_REGION0_YRGB_MST, 0, 31), + [VOP2_WIN_UV_MST] = REG_FIELD(RK3568_SMART_REGION0_CBR_MST, 0, 31), + [VOP2_WIN_YUV_CLIP] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 17, 17), + [VOP2_WIN_YRGB_VIR] = REG_FIELD(RK3568_SMART_REGION0_VIR, 0, 15), + [VOP2_WIN_UV_VIR] = REG_FIELD(RK3568_SMART_REGION0_VIR, 16, 31), + [VOP2_WIN_Y2R_EN] = REG_FIELD(RK3568_SMART_CTRL0, 0, 0), + [VOP2_WIN_R2Y_EN] = REG_FIELD(RK3568_SMART_CTRL0, 1, 1), + [VOP2_WIN_CSC_MODE] = REG_FIELD(RK3568_SMART_CTRL0, 2, 3), + [VOP2_WIN_YMIRROR] = REG_FIELD(RK3568_SMART_CTRL1, 31, 31), + [VOP2_WIN_COLOR_KEY] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 0, 29), + [VOP2_WIN_COLOR_KEY_EN] = REG_FIELD(RK3568_SMART_COLOR_KEY_CTRL, 31, 31), + [VOP2_WIN_VP_SEL] = REG_FIELD(RK3576_SMART_PORT_SEL_IMD, 0, 1), + [VOP2_WIN_DLY_NUM] = REG_FIELD(RK3576_SMART_DLY_NUM, 0, 7), + [VOP2_WIN_AXI_YRGB_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 4, 8), + [VOP2_WIN_AXI_UV_R_ID] = REG_FIELD(RK3568_SMART_CTRL1, 12, 16), + [VOP2_WIN_AXI_BUS_ID] = REG_FIELD(RK3588_SMART_AXI_CTRL, 1, 1), + + /* Scale */ + [VOP2_WIN_SCALE_YRGB_X] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 0, 15), + [VOP2_WIN_SCALE_YRGB_Y] = REG_FIELD(RK3568_SMART_REGION0_SCL_FACTOR_YRGB, 16, 31), + [VOP2_WIN_YRGB_HOR_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 0, 1), + [VOP2_WIN_YRGB_HSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 2, 3), + [VOP2_WIN_YRGB_VER_SCL_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 4, 5), + [VOP2_WIN_YRGB_VSCL_FILTER_MODE] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 6, 7), + [VOP2_WIN_BIC_COE_SEL] = REG_FIELD(RK3568_SMART_REGION0_SCL_CTRL, 16, 17), + [VOP2_WIN_VSD_YRGB_GT2] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 8, 8), + [VOP2_WIN_VSD_YRGB_GT4] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 9, 9), + [VOP2_WIN_VSD_CBCR_GT2] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 10, 10), + [VOP2_WIN_VSD_CBCR_GT4] = REG_FIELD(RK3568_SMART_REGION0_CTRL, 11, 11), + [VOP2_WIN_XMIRROR] = { .reg = 0xffffffff }, + + /* CBCR share the same scale factor as YRGB */ + [VOP2_WIN_SCALE_CBCR_X] = { .reg = 0xffffffff }, + [VOP2_WIN_SCALE_CBCR_Y] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_HOR_SCL_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_CBCR_HSCL_FILTER_MODE] = { .reg = 0xffffffff}, + [VOP2_WIN_CBCR_VER_SCL_MODE] = { .reg = 0xffffffff}, + [VOP2_WIN_CBCR_VSCL_FILTER_MODE] = { .reg = 0xffffffff}, + + [VOP2_WIN_CLUSTER_ENABLE] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_ENABLE] = { .reg = 0xffffffff }, + [VOP2_WIN_CLUSTER_LB_MODE] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_FORMAT] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_RB_SWAP] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_UV_SWAP] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_AUTO_GATING_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_BLOCK_SPLIT_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_PIC_VIR_WIDTH] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_TILE_NUM] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_PIC_OFFSET] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_PIC_SIZE] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_DSP_OFFSET] = { .reg = 0xffffffff }, + [VOP2_WIN_TRANSFORM_OFFSET] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_HDR_PTR] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_HALF_BLOCK_EN] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_ROTATE_270] = { .reg = 0xffffffff }, + [VOP2_WIN_AFBC_ROTATE_90] = { .reg = 0xffffffff }, +}; + static const struct vop2_video_port_data rk3568_vop_video_ports[] = { { .id = 0, @@ -177,10 +597,12 @@ static const struct vop2_win_data rk3568_vop_win_data[] = { .name = "Smart0-win0", .phys_id = ROCKCHIP_VOP2_SMART0, .base = 0x1c00, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2), .formats = formats_smart, .nformats = ARRAY_SIZE(formats_smart), .format_modifiers = format_modifiers, - .layer_sel_id = 3, + /* 0xf means this layer can't attached to this VP */ + .layer_sel_id = { 3, 3, 3, 0xf }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, .max_upscale_factor = 8, @@ -189,11 +611,12 @@ static const struct vop2_win_data rk3568_vop_win_data[] = { }, { .name = "Smart1-win0", .phys_id = ROCKCHIP_VOP2_SMART1, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2), .formats = formats_smart, .nformats = ARRAY_SIZE(formats_smart), .format_modifiers = format_modifiers, .base = 0x1e00, - .layer_sel_id = 7, + .layer_sel_id = { 7, 7, 7, 0xf }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, .max_upscale_factor = 8, @@ -202,11 +625,12 @@ static const struct vop2_win_data rk3568_vop_win_data[] = { }, { .name = "Esmart1-win0", .phys_id = ROCKCHIP_VOP2_ESMART1, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2), .formats = formats_rk356x_esmart, .nformats = ARRAY_SIZE(formats_rk356x_esmart), .format_modifiers = format_modifiers, .base = 0x1a00, - .layer_sel_id = 6, + .layer_sel_id = { 6, 6, 6, 0xf }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, .max_upscale_factor = 8, @@ -215,11 +639,12 @@ static const struct vop2_win_data rk3568_vop_win_data[] = { }, { .name = "Esmart0-win0", .phys_id = ROCKCHIP_VOP2_ESMART0, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2), .formats = formats_rk356x_esmart, .nformats = ARRAY_SIZE(formats_rk356x_esmart), .format_modifiers = format_modifiers, .base = 0x1800, - .layer_sel_id = 2, + .layer_sel_id = { 2, 2, 2, 0xf }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, .max_upscale_factor = 8, @@ -229,10 +654,11 @@ static const struct vop2_win_data rk3568_vop_win_data[] = { .name = "Cluster0-win0", .phys_id = ROCKCHIP_VOP2_CLUSTER0, .base = 0x1000, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2), .formats = formats_cluster, .nformats = ARRAY_SIZE(formats_cluster), .format_modifiers = format_modifiers_afbc, - .layer_sel_id = 0, + .layer_sel_id = { 0, 0, 0, 0xf }, .supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, .max_upscale_factor = 4, @@ -244,10 +670,11 @@ static const struct vop2_win_data rk3568_vop_win_data[] = { .name = "Cluster1-win0", .phys_id = ROCKCHIP_VOP2_CLUSTER1, .base = 0x1200, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2), .formats = formats_cluster, .nformats = ARRAY_SIZE(formats_cluster), .format_modifiers = format_modifiers_afbc, - .layer_sel_id = 1, + .layer_sel_id = { 1, 1, 1, 0xf }, .supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_OVERLAY, @@ -340,6 +767,292 @@ static const struct vop2_regs_dump rk3568_regs_dump[] = { }, }; +static const struct vop2_video_port_data rk3576_vop_video_ports[] = { + { + .id = 0, + .feature = VOP2_VP_FEATURE_OUTPUT_10BIT, + .gamma_lut_len = 1024, + .cubic_lut_len = 9 * 9 * 9, /* 9x9x9 */ + .max_output = { 4096, 2304 }, + /* win layer_mix hdr */ + .pre_scan_max_dly = { 10, 8, 2, 0 }, + .offset = 0xc00, + .pixel_rate = 2, + }, { + .id = 1, + .feature = VOP2_VP_FEATURE_OUTPUT_10BIT, + .gamma_lut_len = 1024, + .cubic_lut_len = 729, /* 9x9x9 */ + .max_output = { 2560, 1600 }, + /* win layer_mix hdr */ + .pre_scan_max_dly = { 10, 6, 0, 0 }, + .offset = 0xd00, + .pixel_rate = 1, + }, { + .id = 2, + .gamma_lut_len = 1024, + .max_output = { 1920, 1080 }, + /* win layer_mix hdr */ + .pre_scan_max_dly = { 10, 6, 0, 0 }, + .offset = 0xe00, + .pixel_rate = 1, + }, +}; + +/* + * rk3576 vop with 2 cluster, 4 esmart win. + * Every cluster can work as 4K win or split into two 2K win. + * All win in cluster support AFBCD. + * + * Every esmart win support 4 Multi-region. + * + * VP0 can use Cluster0/1 and Esmart0/2 + * VP1 can use Cluster0/1 and Esmart1/3 + * VP2 can use Esmart0/1/2/3 + * + * Scale filter mode: + * + * * Cluster: + * * Support prescale down: + * * H/V: gt2/avg2 or gt4/avg4 + * * After prescale down: + * * nearest-neighbor/bilinear/multi-phase filter for scale up + * * nearest-neighbor/bilinear/multi-phase filter for scale down + * + * * Esmart: + * * Support prescale down: + * * H: gt2/avg2 or gt4/avg4 + * * V: gt2 or gt4 + * * After prescale down: + * * nearest-neighbor/bilinear/bicubic for scale up + * * nearest-neighbor/bilinear for scale down + * + * AXI config:: + * + * * Cluster0 win0: 0xa, 0xb [AXI0] + * * Cluster0 win1: 0xc, 0xd [AXI0] + * * Cluster1 win0: 0x6, 0x7 [AXI0] + * * Cluster1 win1: 0x8, 0x9 [AXI0] + * * Esmart0: 0x10, 0x11 [AXI0] + * * Esmart1: 0x12, 0x13 [AXI0] + * * Esmart2: 0xa, 0xb [AXI1] + * * Esmart3: 0xc, 0xd [AXI1] + * * Lut dma rid: 0x1, 0x2, 0x3 [AXI0] + * * DCI dma rid: 0x4 [AXI0] + * * Metadata rid: 0x5 [AXI0] + * + * * Limit: + * * (1) Cluster0/1 are fixed on AXI0 by IC design + * * (2) 0x0 and 0xf can't be used; + * * (3) 5 Bits ID for eache axi bus + * * (3) cluster and lut/dci/metadata rid must smaller than 0xf, + * * if Cluster rid is bigger than 0xf, VOP will dead at the + * * system bandwidth very terrible scene. + */ +static const struct vop2_win_data rk3576_vop_win_data[] = { + { + .name = "Cluster0-win0", + .phys_id = ROCKCHIP_VOP2_CLUSTER0, + .base = 0x1000, + .possible_vp_mask = BIT(0) | BIT(1), + .formats = formats_rk3576_cluster, + .nformats = ARRAY_SIZE(formats_rk3576_cluster), + .format_modifiers = format_modifiers_rk3576_afbc, + .layer_sel_id = { 0, 0, 0xf, 0xf }, + .supported_rotations = DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, + .type = DRM_PLANE_TYPE_PRIMARY, + .axi_bus_id = 0, + .axi_yrgb_r_id = 0xa, + .axi_uv_r_id = 0xb, + .max_upscale_factor = 4, + .max_downscale_factor = 4, + .feature = WIN_FEATURE_AFBDC | WIN_FEATURE_CLUSTER, + }, { + .name = "Cluster1-win0", + .phys_id = ROCKCHIP_VOP2_CLUSTER1, + .base = 0x1200, + .possible_vp_mask = BIT(0) | BIT(1), + .formats = formats_rk3576_cluster, + .nformats = ARRAY_SIZE(formats_rk3576_cluster), + .format_modifiers = format_modifiers_rk3576_afbc, + .layer_sel_id = { 1, 1, 0xf, 0xf }, + .supported_rotations = DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, + .type = DRM_PLANE_TYPE_PRIMARY, + .axi_bus_id = 0, + .axi_yrgb_r_id = 6, + .axi_uv_r_id = 7, + .max_upscale_factor = 4, + .max_downscale_factor = 4, + .feature = WIN_FEATURE_AFBDC | WIN_FEATURE_CLUSTER, + }, { + .name = "Esmart0-win0", + .phys_id = ROCKCHIP_VOP2_ESMART0, + .base = 0x1800, + .possible_vp_mask = BIT(0) | BIT(2), + .formats = formats_rk3576_esmart, + .nformats = ARRAY_SIZE(formats_rk3576_esmart), + .format_modifiers = format_modifiers, + .layer_sel_id = { 2, 0xf, 0, 0xf }, + .supported_rotations = DRM_MODE_REFLECT_Y, + .type = DRM_PLANE_TYPE_OVERLAY, + .axi_bus_id = 0, + .axi_yrgb_r_id = 0x10, + .axi_uv_r_id = 0x11, + .max_upscale_factor = 8, + .max_downscale_factor = 8, + }, { + .name = "Esmart1-win0", + .phys_id = ROCKCHIP_VOP2_ESMART1, + .base = 0x1a00, + .possible_vp_mask = BIT(1) | BIT(2), + .formats = formats_rk3576_esmart, + .nformats = ARRAY_SIZE(formats_rk3576_esmart), + .format_modifiers = format_modifiers, + .layer_sel_id = { 0xf, 2, 1, 0xf }, + .supported_rotations = DRM_MODE_REFLECT_Y, + .type = DRM_PLANE_TYPE_OVERLAY, + .axi_bus_id = 0, + .axi_yrgb_r_id = 0x12, + .axi_uv_r_id = 0x13, + .max_upscale_factor = 8, + .max_downscale_factor = 8, + }, { + .name = "Esmart2-win0", + .phys_id = ROCKCHIP_VOP2_ESMART2, + .base = 0x1c00, + .possible_vp_mask = BIT(0) | BIT(2), + .formats = formats_rk3576_esmart, + .nformats = ARRAY_SIZE(formats_rk3576_esmart), + .format_modifiers = format_modifiers, + .layer_sel_id = { 3, 0xf, 2, 0xf }, + .supported_rotations = DRM_MODE_REFLECT_Y, + .type = DRM_PLANE_TYPE_OVERLAY, + .axi_bus_id = 1, + .axi_yrgb_r_id = 0x0a, + .axi_uv_r_id = 0x0b, + .max_upscale_factor = 8, + .max_downscale_factor = 8, + }, { + .name = "Esmart3-win0", + .phys_id = ROCKCHIP_VOP2_ESMART3, + .base = 0x1e00, + .possible_vp_mask = BIT(1) | BIT(2), + .formats = formats_rk3576_esmart, + .nformats = ARRAY_SIZE(formats_rk3576_esmart), + .format_modifiers = format_modifiers, + .layer_sel_id = { 0xf, 3, 3, 0xf }, + .supported_rotations = DRM_MODE_REFLECT_Y, + .type = DRM_PLANE_TYPE_OVERLAY, + .axi_bus_id = 1, + .axi_yrgb_r_id = 0x0c, + .axi_uv_r_id = 0x0d, + .max_upscale_factor = 8, + .max_downscale_factor = 8, + }, +}; + +static const struct vop2_regs_dump rk3576_regs_dump[] = { + { + .name = "SYS", + .base = RK3568_REG_CFG_DONE, + .size = 0x200, + .en_reg = 0, + .en_val = 0, + .en_mask = 0 + }, { + .name = "OVL_SYS", + .base = RK3576_SYS_EXTRA_ALPHA_CTRL, + .size = 0x50, + .en_reg = 0, + .en_val = 0, + .en_mask = 0, + }, { + .name = "OVL_VP0", + .base = RK3576_OVL_CTRL(0), + .size = 0x80, + .en_reg = 0, + .en_val = 0, + .en_mask = 0, + }, { + .name = "OVL_VP1", + .base = RK3576_OVL_CTRL(1), + .size = 0x80, + .en_reg = 0, + .en_val = 0, + .en_mask = 0, + }, { + .name = "OVL_VP2", + .base = RK3576_OVL_CTRL(2), + .size = 0x80, + .en_reg = 0, + .en_val = 0, + .en_mask = 0, + }, { + .name = "VP0", + .base = RK3568_VP0_CTRL_BASE, + .size = 0x100, + .en_reg = RK3568_VP_DSP_CTRL, + .en_val = 0, + .en_mask = RK3568_VP_DSP_CTRL__STANDBY, + }, { + .name = "VP1", + .base = RK3568_VP1_CTRL_BASE, + .size = 0x100, + .en_reg = RK3568_VP_DSP_CTRL, + .en_val = 0, + .en_mask = RK3568_VP_DSP_CTRL__STANDBY, + }, { + .name = "VP2", + .base = RK3568_VP2_CTRL_BASE, + .size = 0x100, + .en_reg = RK3568_VP_DSP_CTRL, + .en_val = 0, + .en_mask = RK3568_VP_DSP_CTRL__STANDBY, + }, { + .name = "Cluster0", + .base = RK3568_CLUSTER0_CTRL_BASE, + .size = 0x200, + .en_reg = RK3568_CLUSTER_WIN_CTRL0, + .en_val = RK3568_CLUSTER_WIN_CTRL0__WIN0_EN, + .en_mask = RK3568_CLUSTER_WIN_CTRL0__WIN0_EN, + }, { + .name = "Cluster1", + .base = RK3568_CLUSTER1_CTRL_BASE, + .size = 0x200, + .en_reg = RK3568_CLUSTER_WIN_CTRL0, + .en_val = RK3568_CLUSTER_WIN_CTRL0__WIN0_EN, + .en_mask = RK3568_CLUSTER_WIN_CTRL0__WIN0_EN, + }, { + .name = "Esmart0", + .base = RK3568_ESMART0_CTRL_BASE, + .size = 0xf0, + .en_reg = RK3568_SMART_REGION0_CTRL, + .en_val = RK3568_SMART_REGION0_CTRL__WIN0_EN, + .en_mask = RK3568_SMART_REGION0_CTRL__WIN0_EN, + }, { + .name = "Esmart1", + .base = RK3568_ESMART1_CTRL_BASE, + .size = 0xf0, + .en_reg = RK3568_SMART_REGION0_CTRL, + .en_val = RK3568_SMART_REGION0_CTRL__WIN0_EN, + .en_mask = RK3568_SMART_REGION0_CTRL__WIN0_EN, + }, { + .name = "Esmart2", + .base = RK3588_ESMART2_CTRL_BASE, + .size = 0xf0, + .en_reg = RK3568_SMART_REGION0_CTRL, + .en_val = RK3568_SMART_REGION0_CTRL__WIN0_EN, + .en_mask = RK3568_SMART_REGION0_CTRL__WIN0_EN, + }, { + .name = "Esmart3", + .base = RK3588_ESMART3_CTRL_BASE, + .size = 0xf0, + .en_reg = RK3568_SMART_REGION0_CTRL, + .en_val = RK3568_SMART_REGION0_CTRL__WIN0_EN, + .en_mask = RK3568_SMART_REGION0_CTRL__WIN0_EN, + }, +}; + static const struct vop2_video_port_data rk3588_vop_video_ports[] = { { .id = 0, @@ -409,10 +1122,11 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { .name = "Cluster0-win0", .phys_id = ROCKCHIP_VOP2_CLUSTER0, .base = 0x1000, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_cluster, .nformats = ARRAY_SIZE(formats_cluster), .format_modifiers = format_modifiers_afbc, - .layer_sel_id = 0, + .layer_sel_id = { 0, 0, 0, 0 }, .supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, .axi_bus_id = 0, @@ -427,10 +1141,11 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { .name = "Cluster1-win0", .phys_id = ROCKCHIP_VOP2_CLUSTER1, .base = 0x1200, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_cluster, .nformats = ARRAY_SIZE(formats_cluster), .format_modifiers = format_modifiers_afbc, - .layer_sel_id = 1, + .layer_sel_id = { 1, 1, 1, 1 }, .supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, @@ -445,10 +1160,11 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { .name = "Cluster2-win0", .phys_id = ROCKCHIP_VOP2_CLUSTER2, .base = 0x1400, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_cluster, .nformats = ARRAY_SIZE(formats_cluster), .format_modifiers = format_modifiers_afbc, - .layer_sel_id = 4, + .layer_sel_id = { 4, 4, 4, 4 }, .supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, @@ -463,10 +1179,11 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { .name = "Cluster3-win0", .phys_id = ROCKCHIP_VOP2_CLUSTER3, .base = 0x1600, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_cluster, .nformats = ARRAY_SIZE(formats_cluster), .format_modifiers = format_modifiers_afbc, - .layer_sel_id = 5, + .layer_sel_id = { 5, 5, 5, 5 }, .supported_rotations = DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_PRIMARY, @@ -480,11 +1197,12 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { }, { .name = "Esmart0-win0", .phys_id = ROCKCHIP_VOP2_ESMART0, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_esmart, .nformats = ARRAY_SIZE(formats_esmart), .format_modifiers = format_modifiers, .base = 0x1800, - .layer_sel_id = 2, + .layer_sel_id = { 2, 2, 2, 2 }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_OVERLAY, .axi_bus_id = 0, @@ -496,11 +1214,12 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { }, { .name = "Esmart1-win0", .phys_id = ROCKCHIP_VOP2_ESMART1, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_esmart, .nformats = ARRAY_SIZE(formats_esmart), .format_modifiers = format_modifiers, .base = 0x1a00, - .layer_sel_id = 3, + .layer_sel_id = { 3, 3, 3, 3 }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_OVERLAY, .axi_bus_id = 0, @@ -513,10 +1232,11 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { .name = "Esmart2-win0", .phys_id = ROCKCHIP_VOP2_ESMART2, .base = 0x1c00, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_esmart, .nformats = ARRAY_SIZE(formats_esmart), .format_modifiers = format_modifiers, - .layer_sel_id = 6, + .layer_sel_id = { 6, 6, 6, 6 }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_OVERLAY, .axi_bus_id = 1, @@ -528,11 +1248,12 @@ static const struct vop2_win_data rk3588_vop_win_data[] = { }, { .name = "Esmart3-win0", .phys_id = ROCKCHIP_VOP2_ESMART3, + .possible_vp_mask = BIT(0) | BIT(1) | BIT(2) | BIT(3), .formats = formats_esmart, .nformats = ARRAY_SIZE(formats_esmart), .format_modifiers = format_modifiers, .base = 0x1e00, - .layer_sel_id = 7, + .layer_sel_id = { 7, 7, 7, 7 }, .supported_rotations = DRM_MODE_REFLECT_Y, .type = DRM_PLANE_TYPE_OVERLAY, .axi_bus_id = 1, @@ -647,7 +1368,1017 @@ static const struct vop2_regs_dump rk3588_regs_dump[] = { }, }; +static unsigned long rk3568_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_crtc *crtc = &vp->crtc; + u32 die, dip; + + die = vop2_readl(vop2, RK3568_DSP_IF_EN); + dip = vop2_readl(vop2, RK3568_DSP_IF_POL); + + switch (id) { + case ROCKCHIP_VOP2_EP_RGB0: + die &= ~RK3568_SYS_DSP_INFACE_EN_RGB_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_RGB | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_RGB_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL, polflags); + if (polflags & POLFLAG_DCLK_INV) + regmap_write(vop2->sys_grf, RK3568_GRF_VO_CON1, BIT(3 + 16) | BIT(3)); + else + regmap_write(vop2->sys_grf, RK3568_GRF_VO_CON1, BIT(3 + 16)); + break; + case ROCKCHIP_VOP2_EP_HDMI0: + die &= ~RK3568_SYS_DSP_INFACE_EN_HDMI_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_HDMI | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_HDMI_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__HDMI_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__HDMI_PIN_POL, polflags); + break; + case ROCKCHIP_VOP2_EP_EDP0: + die &= ~RK3568_SYS_DSP_INFACE_EN_EDP_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_EDP | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_EDP_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__EDP_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__EDP_PIN_POL, polflags); + break; + case ROCKCHIP_VOP2_EP_MIPI0: + die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_MIPI0 | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__MIPI_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__MIPI_PIN_POL, polflags); + break; + case ROCKCHIP_VOP2_EP_MIPI1: + die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI1_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_MIPI1 | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_MIPI1_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__MIPI_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__MIPI_PIN_POL, polflags); + break; + case ROCKCHIP_VOP2_EP_LVDS0: + die &= ~RK3568_SYS_DSP_INFACE_EN_LVDS0_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_LVDS0 | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_LVDS0_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL, polflags); + break; + case ROCKCHIP_VOP2_EP_LVDS1: + die &= ~RK3568_SYS_DSP_INFACE_EN_LVDS1_MUX; + die |= RK3568_SYS_DSP_INFACE_EN_LVDS1 | + FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_LVDS1_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__RGB_LVDS_PIN_POL, polflags); + break; + default: + drm_err(vop2->drm, "Invalid interface id %d on vp%d\n", id, vp->id); + return 0; + } + + dip |= RK3568_DSP_IF_POL__CFG_DONE_IMD; + + vop2_writel(vop2, RK3568_DSP_IF_EN, die); + vop2_writel(vop2, RK3568_DSP_IF_POL, dip); + + return crtc->state->adjusted_mode.crtc_clock * 1000LL; +} + +static unsigned long rk3576_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_crtc *crtc = &vp->crtc; + struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode; + struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(crtc->state); + u8 port_pix_rate = vp->data->pixel_rate; + int dclk_core_div, dclk_out_div, if_pixclk_div, if_dclk_sel; + u32 ctrl, vp_clk_div, reg, dclk_div; + unsigned long dclk_in_rate, dclk_core_rate; + + if (vcstate->output_mode == ROCKCHIP_OUT_MODE_YUV420 || adjusted_mode->crtc_clock > 600000) + dclk_div = 2; + else + dclk_div = 1; + + if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) + dclk_core_rate = adjusted_mode->crtc_clock / 2; + else + dclk_core_rate = adjusted_mode->crtc_clock / port_pix_rate; + + dclk_in_rate = adjusted_mode->crtc_clock / dclk_div; + + dclk_core_div = dclk_in_rate > dclk_core_rate ? 1 : 0; + + if (vop2_output_if_is_edp(id)) + if_pixclk_div = port_pix_rate == 2 ? RK3576_DSP_IF_PCLK_DIV : 0; + else + if_pixclk_div = port_pix_rate == 1 ? RK3576_DSP_IF_PCLK_DIV : 0; + + if (vcstate->output_mode == ROCKCHIP_OUT_MODE_YUV420) { + if_dclk_sel = RK3576_DSP_IF_DCLK_SEL_OUT; + dclk_out_div = 1; + } else { + if_dclk_sel = 0; + dclk_out_div = 0; + } + + switch (id) { + case ROCKCHIP_VOP2_EP_HDMI0: + reg = RK3576_HDMI0_IF_CTRL; + break; + case ROCKCHIP_VOP2_EP_EDP0: + reg = RK3576_EDP0_IF_CTRL; + break; + case ROCKCHIP_VOP2_EP_MIPI0: + reg = RK3576_MIPI0_IF_CTRL; + break; + case ROCKCHIP_VOP2_EP_DP0: + reg = RK3576_DP0_IF_CTRL; + break; + case ROCKCHIP_VOP2_EP_DP1: + reg = RK3576_DP1_IF_CTRL; + break; + default: + drm_err(vop2->drm, "Invalid interface id %d on vp%d\n", id, vp->id); + return 0; + } + + ctrl = vop2_readl(vop2, reg); + ctrl &= ~RK3576_DSP_IF_DCLK_SEL_OUT; + ctrl &= ~RK3576_DSP_IF_PCLK_DIV; + ctrl &= ~RK3576_DSP_IF_MUX; + ctrl |= RK3576_DSP_IF_CFG_DONE_IMD; + ctrl |= if_dclk_sel | if_pixclk_div; + ctrl |= RK3576_DSP_IF_CLK_OUT_EN | RK3576_DSP_IF_EN; + ctrl |= FIELD_PREP(RK3576_DSP_IF_MUX, vp->id); + ctrl |= FIELD_PREP(RK3576_DSP_IF_PIN_POL, polflags); + vop2_writel(vop2, reg, ctrl); + + vp_clk_div = FIELD_PREP(RK3588_VP_CLK_CTRL__DCLK_CORE_DIV, dclk_core_div); + vp_clk_div |= FIELD_PREP(RK3588_VP_CLK_CTRL__DCLK_OUT_DIV, dclk_out_div); + + vop2_vp_write(vp, RK3588_VP_CLK_CTRL, vp_clk_div); + + return dclk_in_rate * 1000LL; +} + +/* + * calc the dclk on rk3588 + * the available div of dclk is 1, 2, 4 + */ +static unsigned long rk3588_calc_dclk(unsigned long child_clk, unsigned long max_dclk) +{ + if (child_clk * 4 <= max_dclk) + return child_clk * 4; + else if (child_clk * 2 <= max_dclk) + return child_clk * 2; + else if (child_clk <= max_dclk) + return child_clk; + else + return 0; +} + +/* + * 4 pixclk/cycle on rk3588 + * RGB/eDP/HDMI: if_pixclk >= dclk_core + * DP: dp_pixclk = dclk_out <= dclk_core + * DSI: mipi_pixclk <= dclk_out <= dclk_core + */ +static unsigned long rk3588_calc_cru_cfg(struct vop2_video_port *vp, int id, + int *dclk_core_div, int *dclk_out_div, + int *if_pixclk_div, int *if_dclk_div) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_crtc *crtc = &vp->crtc; + struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode; + struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(crtc->state); + int output_mode = vcstate->output_mode; + unsigned long v_pixclk = adjusted_mode->crtc_clock * 1000LL; /* video timing pixclk */ + unsigned long dclk_core_rate = v_pixclk >> 2; + unsigned long dclk_rate = v_pixclk; + unsigned long dclk_out_rate; + unsigned long if_pixclk_rate; + int K = 1; + + if (vop2_output_if_is_hdmi(id)) { + /* + * K = 2: dclk_core = if_pixclk_rate > if_dclk_rate + * K = 1: dclk_core = hdmie_edp_dclk > if_pixclk_rate + */ + if (output_mode == ROCKCHIP_OUT_MODE_YUV420) { + dclk_rate = dclk_rate >> 1; + K = 2; + } + + /* + * if_pixclk_rate = (dclk_core_rate << 1) / K; + * if_dclk_rate = dclk_core_rate / K; + * *if_pixclk_div = dclk_rate / if_pixclk_rate; + * *if_dclk_div = dclk_rate / if_dclk_rate; + */ + *if_pixclk_div = 2; + *if_dclk_div = 4; + } else if (vop2_output_if_is_edp(id)) { + /* + * edp_pixclk = edp_dclk > dclk_core + */ + if_pixclk_rate = v_pixclk / K; + dclk_rate = if_pixclk_rate * K; + /* + * *if_pixclk_div = dclk_rate / if_pixclk_rate; + * *if_dclk_div = *if_pixclk_div; + */ + *if_pixclk_div = K; + *if_dclk_div = K; + } else if (vop2_output_if_is_dp(id)) { + if (output_mode == ROCKCHIP_OUT_MODE_YUV420) + dclk_out_rate = v_pixclk >> 3; + else + dclk_out_rate = v_pixclk >> 2; + + dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000000); + if (!dclk_rate) { + drm_err(vop2->drm, "DP dclk_out_rate out of range, dclk_out_rate: %ld Hz\n", + dclk_out_rate); + return 0; + } + *dclk_out_div = dclk_rate / dclk_out_rate; + } else if (vop2_output_if_is_mipi(id)) { + if_pixclk_rate = dclk_core_rate / K; + /* + * dclk_core = dclk_out * K = if_pixclk * K = v_pixclk / 4 + */ + dclk_out_rate = if_pixclk_rate; + /* + * dclk_rate = N * dclk_core_rate N = (1,2,4 ), + * we get a little factor here + */ + dclk_rate = rk3588_calc_dclk(dclk_out_rate, 600000000); + if (!dclk_rate) { + drm_err(vop2->drm, "MIPI dclk out of range, dclk_out_rate: %ld Hz\n", + dclk_out_rate); + return 0; + } + *dclk_out_div = dclk_rate / dclk_out_rate; + /* + * mipi pixclk == dclk_out + */ + *if_pixclk_div = 1; + } else if (vop2_output_if_is_dpi(id)) { + dclk_rate = v_pixclk; + } + + *dclk_core_div = dclk_rate / dclk_core_rate; + *if_pixclk_div = ilog2(*if_pixclk_div); + *if_dclk_div = ilog2(*if_dclk_div); + *dclk_core_div = ilog2(*dclk_core_div); + *dclk_out_div = ilog2(*dclk_out_div); + + drm_dbg(vop2->drm, "dclk: %ld, pixclk_div: %d, dclk_div: %d\n", + dclk_rate, *if_pixclk_div, *if_dclk_div); + + return dclk_rate; +} + +/* + * MIPI port mux on rk3588: + * 0: Video Port2 + * 1: Video Port3 + * 3: Video Port 1(MIPI1 only) + */ +static u32 rk3588_get_mipi_port_mux(int vp_id) +{ + if (vp_id == 1) + return 3; + else if (vp_id == 3) + return 1; + else + return 0; +} + +static u32 rk3588_get_hdmi_pol(u32 flags) +{ + u32 val; + + val = (flags & DRM_MODE_FLAG_NHSYNC) ? BIT(HSYNC_POSITIVE) : 0; + val |= (flags & DRM_MODE_FLAG_NVSYNC) ? BIT(VSYNC_POSITIVE) : 0; + + return val; +} + +static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32 polflags) +{ + struct vop2 *vop2 = vp->vop2; + int dclk_core_div, dclk_out_div, if_pixclk_div, if_dclk_div; + unsigned long clock; + u32 die, dip, div, vp_clk_div, val; + + clock = rk3588_calc_cru_cfg(vp, id, &dclk_core_div, &dclk_out_div, + &if_pixclk_div, &if_dclk_div); + if (!clock) + return 0; + + vp_clk_div = FIELD_PREP(RK3588_VP_CLK_CTRL__DCLK_CORE_DIV, dclk_core_div); + vp_clk_div |= FIELD_PREP(RK3588_VP_CLK_CTRL__DCLK_OUT_DIV, dclk_out_div); + + die = vop2_readl(vop2, RK3568_DSP_IF_EN); + dip = vop2_readl(vop2, RK3568_DSP_IF_POL); + div = vop2_readl(vop2, RK3568_DSP_IF_CTRL); + + switch (id) { + case ROCKCHIP_VOP2_EP_HDMI0: + div &= ~RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV; + div &= ~RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV; + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV, if_dclk_div); + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV, if_pixclk_div); + die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX; + die |= RK3588_SYS_DSP_INFACE_EN_HDMI0 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX, vp->id); + val = rk3588_get_hdmi_pol(polflags); + regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 1, 1)); + regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0, HIWORD_UPDATE(val, 6, 5)); + break; + case ROCKCHIP_VOP2_EP_HDMI1: + div &= ~RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV; + div &= ~RK3588_DSP_IF_EDP_HDMI1_PCLK_DIV; + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV, if_dclk_div); + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI1_PCLK_DIV, if_pixclk_div); + die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX; + die |= RK3588_SYS_DSP_INFACE_EN_HDMI1 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX, vp->id); + val = rk3588_get_hdmi_pol(polflags); + regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 4, 4)); + regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0, HIWORD_UPDATE(val, 8, 7)); + break; + case ROCKCHIP_VOP2_EP_EDP0: + div &= ~RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV; + div &= ~RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV; + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV, if_dclk_div); + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV, if_pixclk_div); + die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX; + die |= RK3588_SYS_DSP_INFACE_EN_EDP0 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX, vp->id); + regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 0, 0)); + break; + case ROCKCHIP_VOP2_EP_EDP1: + div &= ~RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV; + div &= ~RK3588_DSP_IF_EDP_HDMI1_PCLK_DIV; + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV, if_dclk_div); + div |= FIELD_PREP(RK3588_DSP_IF_EDP_HDMI0_PCLK_DIV, if_pixclk_div); + die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX; + die |= RK3588_SYS_DSP_INFACE_EN_EDP1 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX, vp->id); + regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 3, 3)); + break; + case ROCKCHIP_VOP2_EP_MIPI0: + div &= ~RK3588_DSP_IF_MIPI0_PCLK_DIV; + div |= FIELD_PREP(RK3588_DSP_IF_MIPI0_PCLK_DIV, if_pixclk_div); + die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI0_MUX; + val = rk3588_get_mipi_port_mux(vp->id); + die |= RK3588_SYS_DSP_INFACE_EN_MIPI0 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI0_MUX, !!val); + break; + case ROCKCHIP_VOP2_EP_MIPI1: + div &= ~RK3588_DSP_IF_MIPI1_PCLK_DIV; + div |= FIELD_PREP(RK3588_DSP_IF_MIPI1_PCLK_DIV, if_pixclk_div); + die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX; + val = rk3588_get_mipi_port_mux(vp->id); + die |= RK3588_SYS_DSP_INFACE_EN_MIPI1 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX, val); + break; + case ROCKCHIP_VOP2_EP_DP0: + die &= ~RK3588_SYS_DSP_INFACE_EN_DP0_MUX; + die |= RK3588_SYS_DSP_INFACE_EN_DP0 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_DP0_MUX, vp->id); + dip &= ~RK3588_DSP_IF_POL__DP0_PIN_POL; + dip |= FIELD_PREP(RK3588_DSP_IF_POL__DP0_PIN_POL, polflags); + break; + case ROCKCHIP_VOP2_EP_DP1: + die &= ~RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX; + die |= RK3588_SYS_DSP_INFACE_EN_MIPI1 | + FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_MIPI1_MUX, vp->id); + dip &= ~RK3588_DSP_IF_POL__DP1_PIN_POL; + dip |= FIELD_PREP(RK3588_DSP_IF_POL__DP1_PIN_POL, polflags); + break; + default: + drm_err(vop2->drm, "Invalid interface id %d on vp%d\n", id, vp->id); + return 0; + } + + dip |= RK3568_DSP_IF_POL__CFG_DONE_IMD; + + vop2_vp_write(vp, RK3588_VP_CLK_CTRL, vp_clk_div); + vop2_writel(vop2, RK3568_DSP_IF_EN, die); + vop2_writel(vop2, RK3568_DSP_IF_CTRL, div); + vop2_writel(vop2, RK3568_DSP_IF_POL, dip); + + return clock; +} + +static bool is_opaque(u16 alpha) +{ + return (alpha >> 8) == 0xff; +} + +static void vop2_parse_alpha(struct vop2_alpha_config *alpha_config, + struct vop2_alpha *alpha) +{ + int src_glb_alpha_en = is_opaque(alpha_config->src_glb_alpha_value) ? 0 : 1; + int dst_glb_alpha_en = is_opaque(alpha_config->dst_glb_alpha_value) ? 0 : 1; + int src_color_mode = alpha_config->src_premulti_en ? + ALPHA_SRC_PRE_MUL : ALPHA_SRC_NO_PRE_MUL; + int dst_color_mode = alpha_config->dst_premulti_en ? + ALPHA_SRC_PRE_MUL : ALPHA_SRC_NO_PRE_MUL; + + alpha->src_color_ctrl.val = 0; + alpha->dst_color_ctrl.val = 0; + alpha->src_alpha_ctrl.val = 0; + alpha->dst_alpha_ctrl.val = 0; + + if (!alpha_config->src_pixel_alpha_en) + alpha->src_color_ctrl.bits.blend_mode = ALPHA_GLOBAL; + else if (alpha_config->src_pixel_alpha_en && !src_glb_alpha_en) + alpha->src_color_ctrl.bits.blend_mode = ALPHA_PER_PIX; + else + alpha->src_color_ctrl.bits.blend_mode = ALPHA_PER_PIX_GLOBAL; + + alpha->src_color_ctrl.bits.alpha_en = 1; + + if (alpha->src_color_ctrl.bits.blend_mode == ALPHA_GLOBAL) { + alpha->src_color_ctrl.bits.color_mode = src_color_mode; + alpha->src_color_ctrl.bits.factor_mode = SRC_FAC_ALPHA_SRC_GLOBAL; + } else if (alpha->src_color_ctrl.bits.blend_mode == ALPHA_PER_PIX) { + alpha->src_color_ctrl.bits.color_mode = src_color_mode; + alpha->src_color_ctrl.bits.factor_mode = SRC_FAC_ALPHA_ONE; + } else { + alpha->src_color_ctrl.bits.color_mode = ALPHA_SRC_PRE_MUL; + alpha->src_color_ctrl.bits.factor_mode = SRC_FAC_ALPHA_SRC_GLOBAL; + } + alpha->src_color_ctrl.bits.glb_alpha = alpha_config->src_glb_alpha_value >> 8; + alpha->src_color_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; + alpha->src_color_ctrl.bits.alpha_cal_mode = ALPHA_SATURATION; + + alpha->dst_color_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; + alpha->dst_color_ctrl.bits.alpha_cal_mode = ALPHA_SATURATION; + alpha->dst_color_ctrl.bits.blend_mode = ALPHA_GLOBAL; + alpha->dst_color_ctrl.bits.glb_alpha = alpha_config->dst_glb_alpha_value >> 8; + alpha->dst_color_ctrl.bits.color_mode = dst_color_mode; + alpha->dst_color_ctrl.bits.factor_mode = ALPHA_SRC_INVERSE; + + alpha->src_alpha_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; + alpha->src_alpha_ctrl.bits.blend_mode = alpha->src_color_ctrl.bits.blend_mode; + alpha->src_alpha_ctrl.bits.alpha_cal_mode = ALPHA_SATURATION; + alpha->src_alpha_ctrl.bits.factor_mode = ALPHA_ONE; + + alpha->dst_alpha_ctrl.bits.alpha_mode = ALPHA_STRAIGHT; + if (alpha_config->dst_pixel_alpha_en && !dst_glb_alpha_en) + alpha->dst_alpha_ctrl.bits.blend_mode = ALPHA_PER_PIX; + else + alpha->dst_alpha_ctrl.bits.blend_mode = ALPHA_PER_PIX_GLOBAL; + alpha->dst_alpha_ctrl.bits.alpha_cal_mode = ALPHA_NO_SATURATION; + alpha->dst_alpha_ctrl.bits.factor_mode = ALPHA_SRC_INVERSE; +} + +static int vop2_find_start_mixer_id_for_vp(struct vop2 *vop2, u8 port_id) +{ + struct vop2_video_port *vp; + int used_layer = 0; + int i; + + for (i = 0; i < port_id; i++) { + vp = &vop2->vps[i]; + used_layer += hweight32(vp->win_mask); + } + + return used_layer; +} + +static void vop2_setup_cluster_alpha(struct vop2 *vop2, struct vop2_win *main_win) +{ + struct vop2_alpha_config alpha_config; + struct vop2_alpha alpha; + struct drm_plane_state *bottom_win_pstate; + bool src_pixel_alpha_en = false; + u16 src_glb_alpha_val, dst_glb_alpha_val; + u32 src_color_ctrl_reg, dst_color_ctrl_reg, src_alpha_ctrl_reg, dst_alpha_ctrl_reg; + u32 offset = 0; + bool premulti_en = false; + bool swap = false; + + /* At one win mode, win0 is dst/bottom win, and win1 is a all zero src/top win */ + bottom_win_pstate = main_win->base.state; + src_glb_alpha_val = 0; + dst_glb_alpha_val = main_win->base.state->alpha; + + if (!bottom_win_pstate->fb) + return; + + alpha_config.src_premulti_en = premulti_en; + alpha_config.dst_premulti_en = false; + alpha_config.src_pixel_alpha_en = src_pixel_alpha_en; + alpha_config.dst_pixel_alpha_en = true; /* alpha value need transfer to next mix */ + alpha_config.src_glb_alpha_value = src_glb_alpha_val; + alpha_config.dst_glb_alpha_value = dst_glb_alpha_val; + vop2_parse_alpha(&alpha_config, &alpha); + + alpha.src_color_ctrl.bits.src_dst_swap = swap; + + switch (main_win->data->phys_id) { + case ROCKCHIP_VOP2_CLUSTER0: + offset = 0x0; + break; + case ROCKCHIP_VOP2_CLUSTER1: + offset = 0x10; + break; + case ROCKCHIP_VOP2_CLUSTER2: + offset = 0x20; + break; + case ROCKCHIP_VOP2_CLUSTER3: + offset = 0x30; + break; + } + + if (vop2->version <= VOP_VERSION_RK3588) { + src_color_ctrl_reg = RK3568_CLUSTER0_MIX_SRC_COLOR_CTRL; + dst_color_ctrl_reg = RK3568_CLUSTER0_MIX_DST_COLOR_CTRL; + src_alpha_ctrl_reg = RK3568_CLUSTER0_MIX_SRC_ALPHA_CTRL; + dst_alpha_ctrl_reg = RK3568_CLUSTER0_MIX_DST_ALPHA_CTRL; + } else { + src_color_ctrl_reg = RK3576_CLUSTER0_MIX_SRC_COLOR_CTRL; + dst_color_ctrl_reg = RK3576_CLUSTER0_MIX_DST_COLOR_CTRL; + src_alpha_ctrl_reg = RK3576_CLUSTER0_MIX_SRC_ALPHA_CTRL; + dst_alpha_ctrl_reg = RK3576_CLUSTER0_MIX_DST_ALPHA_CTRL; + } + + vop2_writel(vop2, src_color_ctrl_reg + offset, alpha.src_color_ctrl.val); + vop2_writel(vop2, dst_color_ctrl_reg + offset, alpha.dst_color_ctrl.val); + vop2_writel(vop2, src_alpha_ctrl_reg + offset, alpha.src_alpha_ctrl.val); + vop2_writel(vop2, dst_alpha_ctrl_reg + offset, alpha.dst_alpha_ctrl.val); +} + +static void vop2_setup_alpha(struct vop2_video_port *vp) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_framebuffer *fb; + struct vop2_alpha_config alpha_config; + struct vop2_alpha alpha; + struct drm_plane *plane; + int pixel_alpha_en; + int premulti_en, gpremulti_en = 0; + int mixer_id; + u32 src_color_ctrl_reg, dst_color_ctrl_reg, src_alpha_ctrl_reg, dst_alpha_ctrl_reg; + u32 offset; + bool bottom_layer_alpha_en = false; + u32 dst_global_alpha = DRM_BLEND_ALPHA_OPAQUE; + + if (vop2->version <= VOP_VERSION_RK3588) + mixer_id = vop2_find_start_mixer_id_for_vp(vop2, vp->id); + else + mixer_id = 0; + + alpha_config.dst_pixel_alpha_en = true; /* alpha value need transfer to next mix */ + + drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { + struct vop2_win *win = to_vop2_win(plane); + + if (plane->state->normalized_zpos == 0 && + !is_opaque(plane->state->alpha) && + !vop2_cluster_window(win)) { + /* + * If bottom layer have global alpha effect [except cluster layer, + * because cluster have deal with bottom layer global alpha value + * at cluster mix], bottom layer mix need deal with global alpha. + */ + bottom_layer_alpha_en = true; + dst_global_alpha = plane->state->alpha; + } + } + + if (vop2->version <= VOP_VERSION_RK3588) { + src_color_ctrl_reg = RK3568_MIX0_SRC_COLOR_CTRL; + dst_color_ctrl_reg = RK3568_MIX0_DST_COLOR_CTRL; + src_alpha_ctrl_reg = RK3568_MIX0_SRC_ALPHA_CTRL; + dst_alpha_ctrl_reg = RK3568_MIX0_DST_ALPHA_CTRL; + } else { + src_color_ctrl_reg = RK3576_OVL_MIX0_SRC_COLOR_CTRL(vp->id); + dst_color_ctrl_reg = RK3576_OVL_MIX0_DST_COLOR_CTRL(vp->id); + src_alpha_ctrl_reg = RK3576_OVL_MIX0_SRC_ALPHA_CTRL(vp->id); + dst_alpha_ctrl_reg = RK3576_OVL_MIX0_DST_ALPHA_CTRL(vp->id); + } + + drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { + struct vop2_win *win = to_vop2_win(plane); + int zpos = plane->state->normalized_zpos; + + /* + * Need to configure alpha from second layer. + */ + if (zpos == 0) + continue; + + if (plane->state->pixel_blend_mode == DRM_MODE_BLEND_PREMULTI) + premulti_en = 1; + else + premulti_en = 0; + + plane = &win->base; + fb = plane->state->fb; + + pixel_alpha_en = fb->format->has_alpha; + + alpha_config.src_premulti_en = premulti_en; + + if (bottom_layer_alpha_en && zpos == 1) { + gpremulti_en = premulti_en; + /* Cd = Cs + (1 - As) * Cd * Agd */ + alpha_config.dst_premulti_en = false; + alpha_config.src_pixel_alpha_en = pixel_alpha_en; + alpha_config.src_glb_alpha_value = plane->state->alpha; + alpha_config.dst_glb_alpha_value = dst_global_alpha; + } else if (vop2_cluster_window(win)) { + /* Mix output data only have pixel alpha */ + alpha_config.dst_premulti_en = true; + alpha_config.src_pixel_alpha_en = true; + alpha_config.src_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; + alpha_config.dst_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; + } else { + /* Cd = Cs + (1 - As) * Cd */ + alpha_config.dst_premulti_en = true; + alpha_config.src_pixel_alpha_en = pixel_alpha_en; + alpha_config.src_glb_alpha_value = plane->state->alpha; + alpha_config.dst_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; + } + + vop2_parse_alpha(&alpha_config, &alpha); + + offset = (mixer_id + zpos - 1) * 0x10; + + vop2_writel(vop2, src_color_ctrl_reg + offset, alpha.src_color_ctrl.val); + vop2_writel(vop2, dst_color_ctrl_reg + offset, alpha.dst_color_ctrl.val); + vop2_writel(vop2, src_alpha_ctrl_reg + offset, alpha.src_alpha_ctrl.val); + vop2_writel(vop2, dst_alpha_ctrl_reg + offset, alpha.dst_alpha_ctrl.val); + } + + if (vp->id == 0) { + if (vop2->version <= VOP_VERSION_RK3588) { + src_color_ctrl_reg = RK3568_HDR0_SRC_COLOR_CTRL; + dst_color_ctrl_reg = RK3568_HDR0_DST_COLOR_CTRL; + src_alpha_ctrl_reg = RK3568_HDR0_SRC_ALPHA_CTRL; + dst_alpha_ctrl_reg = RK3568_HDR0_DST_ALPHA_CTRL; + } else { + src_color_ctrl_reg = RK3576_OVL_HDR_SRC_COLOR_CTRL(vp->id); + dst_color_ctrl_reg = RK3576_OVL_HDR_DST_COLOR_CTRL(vp->id); + src_alpha_ctrl_reg = RK3576_OVL_HDR_SRC_ALPHA_CTRL(vp->id); + dst_alpha_ctrl_reg = RK3576_OVL_HDR_DST_ALPHA_CTRL(vp->id); + } + + if (bottom_layer_alpha_en) { + /* Transfer pixel alpha to hdr mix */ + alpha_config.src_premulti_en = gpremulti_en; + alpha_config.dst_premulti_en = true; + alpha_config.src_pixel_alpha_en = true; + alpha_config.src_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; + alpha_config.dst_glb_alpha_value = DRM_BLEND_ALPHA_OPAQUE; + + vop2_parse_alpha(&alpha_config, &alpha); + + vop2_writel(vop2, src_color_ctrl_reg, alpha.src_color_ctrl.val); + vop2_writel(vop2, dst_color_ctrl_reg, alpha.dst_color_ctrl.val); + vop2_writel(vop2, src_alpha_ctrl_reg, alpha.src_alpha_ctrl.val); + vop2_writel(vop2, dst_alpha_ctrl_reg, alpha.dst_alpha_ctrl.val); + } else { + vop2_writel(vop2, src_color_ctrl_reg, 0); + } + } +} + +static void rk3568_vop2_setup_layer_mixer(struct vop2_video_port *vp) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_plane *plane; + u32 layer_sel = 0; + u32 port_sel; + u8 layer_id; + u8 old_layer_id; + u8 layer_sel_id; + unsigned int ofs; + u32 ovl_ctrl; + int i; + struct vop2_video_port *vp0 = &vop2->vps[0]; + struct vop2_video_port *vp1 = &vop2->vps[1]; + struct vop2_video_port *vp2 = &vop2->vps[2]; + struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(vp->crtc.state); + + ovl_ctrl = vop2_readl(vop2, RK3568_OVL_CTRL); + ovl_ctrl |= RK3568_OVL_CTRL__LAYERSEL_REGDONE_IMD; + if (vcstate->yuv_overlay) + ovl_ctrl |= RK3568_OVL_CTRL__YUV_MODE(vp->id); + else + ovl_ctrl &= ~RK3568_OVL_CTRL__YUV_MODE(vp->id); + + vop2_writel(vop2, RK3568_OVL_CTRL, ovl_ctrl); + + port_sel = vop2_readl(vop2, RK3568_OVL_PORT_SEL); + port_sel &= RK3568_OVL_PORT_SEL__SEL_PORT; + + if (vp0->nlayers) + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT0_MUX, + vp0->nlayers - 1); + else + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT0_MUX, 8); + + if (vp1->nlayers) + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT1_MUX, + (vp0->nlayers + vp1->nlayers - 1)); + else + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT1_MUX, 8); + + if (vp2->nlayers) + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, + (vp2->nlayers + vp1->nlayers + vp0->nlayers - 1)); + else + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, 8); + + layer_sel = vop2_readl(vop2, RK3568_OVL_LAYER_SEL); + + ofs = 0; + for (i = 0; i < vp->id; i++) + ofs += vop2->vps[i].nlayers; + + drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { + struct vop2_win *win = to_vop2_win(plane); + struct vop2_win *old_win; + + layer_id = (u8)(plane->state->normalized_zpos + ofs); + /* + * Find the layer this win bind in old state. + */ + for (old_layer_id = 0; old_layer_id < vop2->data->win_size; old_layer_id++) { + layer_sel_id = (layer_sel >> (4 * old_layer_id)) & 0xf; + if (layer_sel_id == win->data->layer_sel_id[vp->id]) + break; + } + + /* + * Find the win bind to this layer in old state + */ + for (i = 0; i < vop2->data->win_size; i++) { + old_win = &vop2->win[i]; + layer_sel_id = (layer_sel >> (4 * layer_id)) & 0xf; + if (layer_sel_id == old_win->data->layer_sel_id[vp->id]) + break; + } + + switch (win->data->phys_id) { + case ROCKCHIP_VOP2_CLUSTER0: + port_sel &= ~RK3568_OVL_PORT_SEL__CLUSTER0; + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__CLUSTER0, vp->id); + break; + case ROCKCHIP_VOP2_CLUSTER1: + port_sel &= ~RK3568_OVL_PORT_SEL__CLUSTER1; + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__CLUSTER1, vp->id); + break; + case ROCKCHIP_VOP2_CLUSTER2: + port_sel &= ~RK3588_OVL_PORT_SEL__CLUSTER2; + port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__CLUSTER2, vp->id); + break; + case ROCKCHIP_VOP2_CLUSTER3: + port_sel &= ~RK3588_OVL_PORT_SEL__CLUSTER3; + port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__CLUSTER3, vp->id); + break; + case ROCKCHIP_VOP2_ESMART0: + port_sel &= ~RK3568_OVL_PORT_SEL__ESMART0; + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__ESMART0, vp->id); + break; + case ROCKCHIP_VOP2_ESMART1: + port_sel &= ~RK3568_OVL_PORT_SEL__ESMART1; + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__ESMART1, vp->id); + break; + case ROCKCHIP_VOP2_ESMART2: + port_sel &= ~RK3588_OVL_PORT_SEL__ESMART2; + port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__ESMART2, vp->id); + break; + case ROCKCHIP_VOP2_ESMART3: + port_sel &= ~RK3588_OVL_PORT_SEL__ESMART3; + port_sel |= FIELD_PREP(RK3588_OVL_PORT_SEL__ESMART3, vp->id); + break; + case ROCKCHIP_VOP2_SMART0: + port_sel &= ~RK3568_OVL_PORT_SEL__SMART0; + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__SMART0, vp->id); + break; + case ROCKCHIP_VOP2_SMART1: + port_sel &= ~RK3568_OVL_PORT_SEL__SMART1; + port_sel |= FIELD_PREP(RK3568_OVL_PORT_SEL__SMART1, vp->id); + break; + } + + layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(layer_id, 0x7); + layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(layer_id, win->data->layer_sel_id[vp->id]); + /* + * When we bind a window from layerM to layerN, we also need to move the old + * window on layerN to layerM to avoid one window selected by two or more layers. + */ + layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(old_layer_id, 0x7); + layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(old_layer_id, + old_win->data->layer_sel_id[vp->id]); + } + + vop2_writel(vop2, RK3568_OVL_LAYER_SEL, layer_sel); + vop2_writel(vop2, RK3568_OVL_PORT_SEL, port_sel); +} + +static void rk3568_vop2_setup_dly_for_windows(struct vop2_video_port *vp) +{ + struct vop2 *vop2 = vp->vop2; + struct vop2_win *win; + int i = 0; + u32 cdly = 0, sdly = 0; + + for (i = 0; i < vop2->data->win_size; i++) { + u32 dly; + + win = &vop2->win[i]; + dly = win->delay; + + switch (win->data->phys_id) { + case ROCKCHIP_VOP2_CLUSTER0: + cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER0_0, dly); + cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER0_1, dly); + break; + case ROCKCHIP_VOP2_CLUSTER1: + cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER1_0, dly); + cdly |= FIELD_PREP(RK3568_CLUSTER_DLY_NUM__CLUSTER1_1, dly); + break; + case ROCKCHIP_VOP2_ESMART0: + sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__ESMART0, dly); + break; + case ROCKCHIP_VOP2_ESMART1: + sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__ESMART1, dly); + break; + case ROCKCHIP_VOP2_SMART0: + case ROCKCHIP_VOP2_ESMART2: + sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__SMART0, dly); + break; + case ROCKCHIP_VOP2_SMART1: + case ROCKCHIP_VOP2_ESMART3: + sdly |= FIELD_PREP(RK3568_SMART_DLY_NUM__SMART1, dly); + break; + } + } + + vop2_writel(vop2, RK3568_CLUSTER_DLY_NUM, cdly); + vop2_writel(vop2, RK3568_SMART_DLY_NUM, sdly); +} + +static void rk3568_vop2_setup_overlay(struct vop2_video_port *vp) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_crtc *crtc = &vp->crtc; + struct drm_plane *plane; + + vp->win_mask = 0; + + drm_atomic_crtc_for_each_plane(plane, crtc) { + struct vop2_win *win = to_vop2_win(plane); + + win->delay = win->data->dly[VOP2_DLY_MODE_DEFAULT]; + + vp->win_mask |= BIT(win->data->phys_id); + + if (vop2_cluster_window(win)) + vop2_setup_cluster_alpha(vop2, win); + } + + if (!vp->win_mask) + return; + + rk3568_vop2_setup_layer_mixer(vp); + vop2_setup_alpha(vp); + rk3568_vop2_setup_dly_for_windows(vp); +} + +static void rk3576_vop2_setup_layer_mixer(struct vop2_video_port *vp) +{ + struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(vp->crtc.state); + struct vop2 *vop2 = vp->vop2; + struct drm_plane *plane; + u32 layer_sel = 0xffff; /* 0xf means this layer is disabled */ + u32 ovl_ctrl; + + ovl_ctrl = vop2_readl(vop2, RK3576_OVL_CTRL(vp->id)); + if (vcstate->yuv_overlay) + ovl_ctrl |= RK3576_OVL_CTRL__YUV_MODE; + else + ovl_ctrl &= ~RK3576_OVL_CTRL__YUV_MODE; + + vop2_writel(vop2, RK3576_OVL_CTRL(vp->id), ovl_ctrl); + + drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { + struct vop2_win *win = to_vop2_win(plane); + + layer_sel &= ~RK3568_OVL_LAYER_SEL__LAYER(plane->state->normalized_zpos, + 0xf); + layer_sel |= RK3568_OVL_LAYER_SEL__LAYER(plane->state->normalized_zpos, + win->data->layer_sel_id[vp->id]); + } + + vop2_writel(vop2, RK3576_OVL_LAYER_SEL(vp->id), layer_sel); +} + +static void rk3576_vop2_setup_dly_for_windows(struct vop2_video_port *vp) +{ + struct drm_plane *plane; + struct vop2_win *win; + + drm_atomic_crtc_for_each_plane(plane, &vp->crtc) { + win = to_vop2_win(plane); + vop2_win_write(win, VOP2_WIN_DLY_NUM, 0); + } +} + +static void rk3576_vop2_setup_overlay(struct vop2_video_port *vp) +{ + struct vop2 *vop2 = vp->vop2; + struct drm_crtc *crtc = &vp->crtc; + struct drm_plane *plane; + + vp->win_mask = 0; + + drm_atomic_crtc_for_each_plane(plane, crtc) { + struct vop2_win *win = to_vop2_win(plane); + + win->delay = win->data->dly[VOP2_DLY_MODE_DEFAULT]; + vp->win_mask |= BIT(win->data->phys_id); + + if (vop2_cluster_window(win)) + vop2_setup_cluster_alpha(vop2, win); + } + + if (!vp->win_mask) + return; + + rk3576_vop2_setup_layer_mixer(vp); + vop2_setup_alpha(vp); + rk3576_vop2_setup_dly_for_windows(vp); +} + +static void rk3568_vop2_setup_bg_dly(struct vop2_video_port *vp) +{ + struct drm_crtc *crtc = &vp->crtc; + struct drm_display_mode *mode = &crtc->state->adjusted_mode; + u16 hdisplay = mode->crtc_hdisplay; + u16 hsync_len = mode->crtc_hsync_end - mode->crtc_hsync_start; + u32 bg_dly; + u32 pre_scan_dly; + + bg_dly = vp->data->pre_scan_max_dly[3]; + vop2_writel(vp->vop2, RK3568_VP_BG_MIX_CTRL(vp->id), + FIELD_PREP(RK3568_VP_BG_MIX_CTRL__BG_DLY, bg_dly)); + + pre_scan_dly = ((bg_dly + (hdisplay >> 1) - 1) << 16) | hsync_len; + vop2_vp_write(vp, RK3568_VP_PRE_SCAN_HTIMING, pre_scan_dly); +} + +static void rk3576_vop2_setup_bg_dly(struct vop2_video_port *vp) +{ + struct drm_crtc *crtc = &vp->crtc; + struct drm_display_mode *mode = &crtc->state->adjusted_mode; + u16 hdisplay = mode->crtc_hdisplay; + u16 hsync_len = mode->crtc_hsync_end - mode->crtc_hsync_start; + u32 bg_dly; + u32 pre_scan_dly; + + bg_dly = vp->data->pre_scan_max_dly[VOP2_DLY_WIN] + + vp->data->pre_scan_max_dly[VOP2_DLY_LAYER_MIX] + + vp->data->pre_scan_max_dly[VOP2_DLY_HDR_MIX]; + + vop2_writel(vp->vop2, RK3576_OVL_BG_MIX_CTRL(vp->id), + FIELD_PREP(RK3576_OVL_BG_MIX_CTRL__BG_DLY, bg_dly)); + + pre_scan_dly = ((bg_dly + (hdisplay >> 1) - 1) << 16) | hsync_len; + vop2_vp_write(vp, RK3568_VP_PRE_SCAN_HTIMING, pre_scan_dly); +} + +static const struct vop2_ops rk3568_vop_ops = { + .setup_intf_mux = rk3568_set_intf_mux, + .setup_bg_dly = rk3568_vop2_setup_bg_dly, + .setup_overlay = rk3568_vop2_setup_overlay, +}; + +static const struct vop2_ops rk3576_vop_ops = { + .setup_intf_mux = rk3576_set_intf_mux, + .setup_bg_dly = rk3576_vop2_setup_bg_dly, + .setup_overlay = rk3576_vop2_setup_overlay, +}; + +static const struct vop2_ops rk3588_vop_ops = { + .setup_intf_mux = rk3588_set_intf_mux, + .setup_bg_dly = rk3568_vop2_setup_bg_dly, + .setup_overlay = rk3568_vop2_setup_overlay, +}; + static const struct vop2_data rk3566_vop = { + .version = VOP_VERSION_RK3568, .feature = VOP2_FEATURE_HAS_SYS_GRF, .nr_vps = 3, .max_input = { 4096, 2304 }, @@ -655,12 +2386,18 @@ static const struct vop2_data rk3566_vop = { .vp = rk3568_vop_video_ports, .win = rk3568_vop_win_data, .win_size = ARRAY_SIZE(rk3568_vop_win_data), + .cluster_reg = rk3568_vop_cluster_regs, + .nr_cluster_regs = ARRAY_SIZE(rk3568_vop_cluster_regs), + .smart_reg = rk3568_vop_smart_regs, + .nr_smart_regs = ARRAY_SIZE(rk3568_vop_smart_regs), .regs_dump = rk3568_regs_dump, .regs_dump_size = ARRAY_SIZE(rk3568_regs_dump), + .ops = &rk3568_vop_ops, .soc_id = 3566, }; static const struct vop2_data rk3568_vop = { + .version = VOP_VERSION_RK3568, .feature = VOP2_FEATURE_HAS_SYS_GRF, .nr_vps = 3, .max_input = { 4096, 2304 }, @@ -668,12 +2405,37 @@ static const struct vop2_data rk3568_vop = { .vp = rk3568_vop_video_ports, .win = rk3568_vop_win_data, .win_size = ARRAY_SIZE(rk3568_vop_win_data), + .cluster_reg = rk3568_vop_cluster_regs, + .nr_cluster_regs = ARRAY_SIZE(rk3568_vop_cluster_regs), + .smart_reg = rk3568_vop_smart_regs, + .nr_smart_regs = ARRAY_SIZE(rk3568_vop_smart_regs), .regs_dump = rk3568_regs_dump, .regs_dump_size = ARRAY_SIZE(rk3568_regs_dump), + .ops = &rk3568_vop_ops, .soc_id = 3568, }; +static const struct vop2_data rk3576_vop = { + .version = VOP_VERSION_RK3576, + .feature = VOP2_FEATURE_HAS_SYS_PMU, + .nr_vps = 3, + .max_input = { 4096, 4320 }, + .max_output = { 4096, 4320 }, + .vp = rk3576_vop_video_ports, + .win = rk3576_vop_win_data, + .win_size = ARRAY_SIZE(rk3576_vop_win_data), + .cluster_reg = rk3576_vop_cluster_regs, + .nr_cluster_regs = ARRAY_SIZE(rk3576_vop_cluster_regs), + .smart_reg = rk3576_vop_smart_regs, + .nr_smart_regs = ARRAY_SIZE(rk3576_vop_smart_regs), + .regs_dump = rk3576_regs_dump, + .regs_dump_size = ARRAY_SIZE(rk3576_regs_dump), + .ops = &rk3576_vop_ops, + .soc_id = 3576, +}; + static const struct vop2_data rk3588_vop = { + .version = VOP_VERSION_RK3588, .feature = VOP2_FEATURE_HAS_SYS_GRF | VOP2_FEATURE_HAS_VO1_GRF | VOP2_FEATURE_HAS_VOP_GRF | VOP2_FEATURE_HAS_SYS_PMU, .nr_vps = 4, @@ -682,8 +2444,13 @@ static const struct vop2_data rk3588_vop = { .vp = rk3588_vop_video_ports, .win = rk3588_vop_win_data, .win_size = ARRAY_SIZE(rk3588_vop_win_data), + .cluster_reg = rk3568_vop_cluster_regs, + .nr_cluster_regs = ARRAY_SIZE(rk3568_vop_cluster_regs), + .smart_reg = rk3568_vop_smart_regs, + .nr_smart_regs = ARRAY_SIZE(rk3568_vop_smart_regs), .regs_dump = rk3588_regs_dump, .regs_dump_size = ARRAY_SIZE(rk3588_regs_dump), + .ops = &rk3588_vop_ops, .soc_id = 3588, }; @@ -695,6 +2462,9 @@ static const struct of_device_id vop2_dt_match[] = { .compatible = "rockchip,rk3568-vop", .data = &rk3568_vop, }, { + .compatible = "rockchip,rk3576-vop", + .data = &rk3576_vop, + }, { .compatible = "rockchip,rk3588-vop", .data = &rk3588_vop }, { diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 69bcf0e99d57..a6d2a4722d82 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -28,10 +28,9 @@ #include <drm/drm_print.h> #include <drm/gpu_scheduler.h> -#include "gpu_scheduler_trace.h" +#include "sched_internal.h" -#define to_drm_sched_job(sched_job) \ - container_of((sched_job), struct drm_sched_job, queue_node) +#include "gpu_scheduler_trace.h" /** * drm_sched_entity_init - Init a context entity used by scheduler when @@ -92,7 +91,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, * the lowest priority available. */ if (entity->priority >= sched_list[0]->num_rqs) { - drm_err(sched_list[0], "entity with out-of-bounds priority:%u num_rqs:%u\n", + dev_err(sched_list[0]->dev, "entity has out-of-bounds priority: %u. num_rqs: %u\n", entity->priority, sched_list[0]->num_rqs); entity->priority = max_t(s32, (s32) sched_list[0]->num_rqs - 1, (s32) DRM_SCHED_PRIORITY_KERNEL); @@ -152,18 +151,6 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity) return false; } -/* Return true if entity could provide a job. */ -bool drm_sched_entity_is_ready(struct drm_sched_entity *entity) -{ - if (spsc_queue_peek(&entity->job_queue) == NULL) - return false; - - if (READ_ONCE(entity->dependency)) - return false; - - return true; -} - /** * drm_sched_entity_error - return error of last scheduled job * @entity: scheduler entity to check @@ -255,7 +242,7 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity) /* The entity is guaranteed to not be used by the scheduler */ prev = rcu_dereference_check(entity->last_scheduled, true); dma_fence_get(prev); - while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) { + while ((job = drm_sched_entity_queue_pop(entity))) { struct drm_sched_fence *s_fence = job->s_fence; dma_fence_get(&s_fence->finished); @@ -477,7 +464,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) { struct drm_sched_job *sched_job; - sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue)); + sched_job = drm_sched_entity_queue_peek(entity); if (!sched_job) return NULL; @@ -513,7 +500,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) { struct drm_sched_job *next; - next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue)); + next = drm_sched_entity_queue_peek(entity); if (next) { struct drm_sched_rq *rq; diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index 0f35f009b9d3..e971528504a5 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -29,6 +29,8 @@ #include <drm/gpu_scheduler.h> +#include "sched_internal.h" + static struct kmem_cache *sched_fence_slab; static int __init drm_sched_fence_slab_init(void) diff --git a/drivers/gpu/drm/scheduler/sched_internal.h b/drivers/gpu/drm/scheduler/sched_internal.h new file mode 100644 index 000000000000..599cf6e1bb74 --- /dev/null +++ b/drivers/gpu/drm/scheduler/sched_internal.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef _DRM_GPU_SCHEDULER_INTERNAL_H_ +#define _DRM_GPU_SCHEDULER_INTERNAL_H_ + + +/* Used to choose between FIFO and RR job-scheduling */ +extern int drm_sched_policy; + +#define DRM_SCHED_POLICY_RR 0 +#define DRM_SCHED_POLICY_FIFO 1 + +void drm_sched_wakeup(struct drm_gpu_scheduler *sched); + +void drm_sched_rq_add_entity(struct drm_sched_rq *rq, + struct drm_sched_entity *entity); +void drm_sched_rq_remove_entity(struct drm_sched_rq *rq, + struct drm_sched_entity *entity); + +void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, + struct drm_sched_rq *rq, ktime_t ts); + +void drm_sched_entity_select_rq(struct drm_sched_entity *entity); +struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity); + +struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *s_entity, + void *owner); +void drm_sched_fence_init(struct drm_sched_fence *fence, + struct drm_sched_entity *entity); +void drm_sched_fence_free(struct drm_sched_fence *fence); + +void drm_sched_fence_scheduled(struct drm_sched_fence *fence, + struct dma_fence *parent); +void drm_sched_fence_finished(struct drm_sched_fence *fence, int result); + +/** + * drm_sched_entity_queue_pop - Low level helper for popping queued jobs + * + * @entity: scheduler entity + * + * Low level helper for popping queued jobs. + * + * Returns: The job dequeued or NULL. + */ +static inline struct drm_sched_job * +drm_sched_entity_queue_pop(struct drm_sched_entity *entity) +{ + struct spsc_node *node; + + node = spsc_queue_pop(&entity->job_queue); + if (!node) + return NULL; + + return container_of(node, struct drm_sched_job, queue_node); +} + +/** + * drm_sched_entity_queue_peek - Low level helper for peeking at the job queue + * + * @entity: scheduler entity + * + * Low level helper for peeking at the job queue + * + * Returns: The job at the head of the queue or NULL. + */ +static inline struct drm_sched_job * +drm_sched_entity_queue_peek(struct drm_sched_entity *entity) +{ + struct spsc_node *node; + + node = spsc_queue_peek(&entity->job_queue); + if (!node) + return NULL; + + return container_of(node, struct drm_sched_job, queue_node); +} + +/* Return true if entity could provide a job. */ +static inline bool +drm_sched_entity_is_ready(struct drm_sched_entity *entity) +{ + if (!spsc_queue_count(&entity->job_queue)) + return false; + + if (READ_ONCE(entity->dependency)) + return false; + + return true; +} + +#endif diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 8c36a59afb72..bfea608a7106 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -78,6 +78,8 @@ #include <drm/gpu_scheduler.h> #include <drm/spsc_queue.h> +#include "sched_internal.h" + #define CREATE_TRACE_POINTS #include "gpu_scheduler_trace.h" @@ -87,9 +89,6 @@ static struct lockdep_map drm_sched_lockdep_map = { }; #endif -#define to_drm_sched_job(sched_job) \ - container_of((sched_job), struct drm_sched_job, queue_node) - int drm_sched_policy = DRM_SCHED_POLICY_FIFO; /** @@ -103,9 +102,9 @@ static u32 drm_sched_available_credits(struct drm_gpu_scheduler *sched) { u32 credits; - drm_WARN_ON(sched, check_sub_overflow(sched->credit_limit, - atomic_read(&sched->credit_count), - &credits)); + WARN_ON(check_sub_overflow(sched->credit_limit, + atomic_read(&sched->credit_count), + &credits)); return credits; } @@ -123,16 +122,18 @@ static bool drm_sched_can_queue(struct drm_gpu_scheduler *sched, { struct drm_sched_job *s_job; - s_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue)); + s_job = drm_sched_entity_queue_peek(entity); if (!s_job) return false; /* If a job exceeds the credit limit, truncate it to the credit limit * itself to guarantee forward progress. */ - if (drm_WARN(sched, s_job->credits > sched->credit_limit, - "Jobs may not exceed the credit limit, truncate.\n")) + if (s_job->credits > sched->credit_limit) { + dev_WARN(sched->dev, + "Jobs may not exceed the credit limit, truncate.\n"); s_job->credits = sched->credit_limit; + } return drm_sched_available_credits(sched) >= s_job->credits; } @@ -790,7 +791,7 @@ int drm_sched_job_init(struct drm_sched_job *job, * or worse--a blank screen--leave a trail in the * logs, so this can be debugged easier. */ - drm_err(job->sched, "%s: entity has no rq!\n", __func__); + dev_err(job->sched->dev, "%s: entity has no rq!\n", __func__); return -ENOENT; } @@ -1014,11 +1015,13 @@ EXPORT_SYMBOL(drm_sched_job_has_dependency); * Cleans up the resources allocated with drm_sched_job_init(). * * Drivers should call this from their error unwind code if @job is aborted - * before drm_sched_job_arm() is called. + * before it was submitted to an entity with drm_sched_entity_push_job(). + * + * Since calling drm_sched_job_arm() causes the job's fences to be initialized, + * it is up to the driver to ensure that fences that were exposed to external + * parties get signaled. drm_sched_job_cleanup() does not ensure this. * - * After that point of no return @job is committed to be executed by the - * scheduler, and this function should be called from the - * &drm_sched_backend_ops.free_job callback. + * This function must also be called in &struct drm_sched_backend_ops.free_job */ void drm_sched_job_cleanup(struct drm_sched_job *job) { @@ -1029,7 +1032,7 @@ void drm_sched_job_cleanup(struct drm_sched_job *job) /* drm_sched_job_arm() has been called */ dma_fence_put(&job->s_fence->finished); } else { - /* aborted job before committing to run it */ + /* aborted job before arming */ drm_sched_fence_free(job->s_fence); } @@ -1264,7 +1267,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_ if (args->num_rqs > DRM_SCHED_PRIORITY_COUNT) { /* This is a gross violation--tell drivers what the problem is. */ - drm_err(sched, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n", + dev_err(sched->dev, "%s: num_rqs cannot be greater than DRM_SCHED_PRIORITY_COUNT\n", __func__); return -EINVAL; } else if (sched->sched_rq) { @@ -1272,7 +1275,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_ * fine-tune their DRM calling order, and return all * is good. */ - drm_warn(sched, "%s: scheduler already initialized!\n", __func__); + dev_warn(sched->dev, "%s: scheduler already initialized!\n", __func__); return 0; } @@ -1327,7 +1330,7 @@ Out_unroll: Out_check_own: if (sched->own_submit_wq) destroy_workqueue(sched->submit_wq); - drm_err(sched, "%s: Failed to setup GPU scheduler--out of memory\n", __func__); + dev_err(sched->dev, "%s: Failed to setup GPU scheduler--out of memory\n", __func__); return -ENOMEM; } EXPORT_SYMBOL(drm_sched_init); diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 54a73753eff9..ba315c66a04d 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -1900,7 +1900,6 @@ int ltdc_load(struct drm_device *ddev) struct drm_panel *panel; struct drm_crtc *crtc; struct reset_control *rstc; - struct resource *res; int irq, i, nb_endpoints; int ret = -ENODEV; @@ -1966,8 +1965,7 @@ int ltdc_load(struct drm_device *ddev) reset_control_deassert(rstc); } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ldev->regs = devm_ioremap_resource(dev, res); + ldev->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ldev->regs)) { DRM_ERROR("Unable to get ltdc registers\n"); ret = PTR_ERR(ldev->regs); diff --git a/drivers/gpu/drm/tests/drm_atomic_state_test.c b/drivers/gpu/drm/tests/drm_atomic_state_test.c index 5945c3298901..2f6ac7a09f44 100644 --- a/drivers/gpu/drm/tests/drm_atomic_state_test.c +++ b/drivers/gpu/drm/tests/drm_atomic_state_test.c @@ -189,7 +189,7 @@ static int set_up_atomic_state(struct kunit *test, static void drm_test_check_connector_changed_modeset(struct kunit *test) { struct drm_atomic_test_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector *old_conn, *new_conn; struct drm_atomic_state *state; struct drm_device *drm; @@ -203,14 +203,13 @@ static void drm_test_check_connector_changed_modeset(struct kunit *test) old_conn = &priv->connectors[0]; new_conn = &priv->connectors[1]; - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); // first modeset to enable - ret = set_up_atomic_state(test, priv, old_conn, ctx); + ret = set_up_atomic_state(test, priv, old_conn, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); new_conn_state = drm_atomic_get_connector_state(state, new_conn); @@ -231,6 +230,9 @@ static void drm_test_check_connector_changed_modeset(struct kunit *test) ret = drm_atomic_commit(state); KUNIT_ASSERT_EQ(test, ret, 0); KUNIT_ASSERT_EQ(test, modeset_counter, initial_modeset_count + 1); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -263,7 +265,7 @@ static void drm_test_check_valid_clones(struct kunit *test) int ret; const struct drm_clone_mode_test *param = test->param_value; struct drm_atomic_test_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_device *drm; struct drm_atomic_state *state; struct drm_crtc_state *crtc_state; @@ -273,13 +275,12 @@ static void drm_test_check_valid_clones(struct kunit *test) drm = &priv->drm; - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = set_up_atomic_state(test, priv, NULL, ctx); + ret = set_up_atomic_state(test, priv, NULL, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); crtc_state = drm_atomic_get_crtc_state(state, priv->crtc); @@ -292,6 +293,9 @@ static void drm_test_check_valid_clones(struct kunit *test) ret = drm_atomic_helper_check_modeset(drm, state); KUNIT_ASSERT_EQ(test, ret, param->expected_result); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } static void drm_check_in_clone_mode_desc(const struct drm_clone_mode_test *t, diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c index 08992636ec05..35cd3405d045 100644 --- a/drivers/gpu/drm/tests/drm_format_helper_test.c +++ b/drivers/gpu/drm/tests/drm_format_helper_test.c @@ -60,6 +60,11 @@ struct convert_to_rgb888_result { const u8 expected[TEST_BUF_SIZE]; }; +struct convert_to_bgr888_result { + unsigned int dst_pitch; + const u8 expected[TEST_BUF_SIZE]; +}; + struct convert_to_argb8888_result { unsigned int dst_pitch; const u32 expected[TEST_BUF_SIZE]; @@ -107,6 +112,7 @@ struct convert_xrgb8888_case { struct convert_to_argb1555_result argb1555_result; struct convert_to_rgba5551_result rgba5551_result; struct convert_to_rgb888_result rgb888_result; + struct convert_to_bgr888_result bgr888_result; struct convert_to_argb8888_result argb8888_result; struct convert_to_xrgb2101010_result xrgb2101010_result; struct convert_to_argb2101010_result argb2101010_result; @@ -151,6 +157,10 @@ static struct convert_xrgb8888_case convert_xrgb8888_cases[] = { .dst_pitch = TEST_USE_DEFAULT_PITCH, .expected = { 0x00, 0x00, 0xFF }, }, + .bgr888_result = { + .dst_pitch = TEST_USE_DEFAULT_PITCH, + .expected = { 0xFF, 0x00, 0x00 }, + }, .argb8888_result = { .dst_pitch = TEST_USE_DEFAULT_PITCH, .expected = { 0xFFFF0000 }, @@ -217,6 +227,10 @@ static struct convert_xrgb8888_case convert_xrgb8888_cases[] = { .dst_pitch = TEST_USE_DEFAULT_PITCH, .expected = { 0x00, 0x00, 0xFF }, }, + .bgr888_result = { + .dst_pitch = TEST_USE_DEFAULT_PITCH, + .expected = { 0xFF, 0x00, 0x00 }, + }, .argb8888_result = { .dst_pitch = TEST_USE_DEFAULT_PITCH, .expected = { 0xFFFF0000 }, @@ -330,6 +344,15 @@ static struct convert_xrgb8888_case convert_xrgb8888_cases[] = { 0x00, 0xFF, 0xFF, 0xFF, 0xFF, 0x00, }, }, + .bgr888_result = { + .dst_pitch = TEST_USE_DEFAULT_PITCH, + .expected = { + 0xFF, 0xFF, 0xFF, 0x00, 0x00, 0x00, + 0xFF, 0x00, 0x00, 0x00, 0xFF, 0x00, + 0x00, 0x00, 0xFF, 0xFF, 0x00, 0xFF, + 0xFF, 0xFF, 0x00, 0x00, 0xFF, 0xFF, + }, + }, .argb8888_result = { .dst_pitch = TEST_USE_DEFAULT_PITCH, .expected = { @@ -468,6 +491,17 @@ static struct convert_xrgb8888_case convert_xrgb8888_cases[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, }, }, + .bgr888_result = { + .dst_pitch = 15, + .expected = { + 0x0E, 0x44, 0x9C, 0x11, 0x4D, 0x05, 0xA8, 0xF3, 0x03, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x6C, 0xF0, 0x73, 0x0E, 0x44, 0x9C, 0x11, 0x4D, 0x05, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0xA8, 0x03, 0x03, 0x6C, 0xF0, 0x73, 0x0E, 0x44, 0x9C, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + }, + }, .argb8888_result = { .dst_pitch = 20, .expected = { @@ -914,6 +948,52 @@ static void drm_test_fb_xrgb8888_to_rgb888(struct kunit *test) KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } +static void drm_test_fb_xrgb8888_to_bgr888(struct kunit *test) +{ + const struct convert_xrgb8888_case *params = test->param_value; + const struct convert_to_bgr888_result *result = ¶ms->bgr888_result; + size_t dst_size; + u8 *buf = NULL; + __le32 *xrgb8888 = NULL; + struct iosys_map dst, src; + + struct drm_framebuffer fb = { + .format = drm_format_info(DRM_FORMAT_XRGB8888), + .pitches = { params->pitch, 0, 0 }, + }; + + dst_size = conversion_buf_size(DRM_FORMAT_BGR888, result->dst_pitch, + ¶ms->clip, 0); + KUNIT_ASSERT_GT(test, dst_size, 0); + + buf = kunit_kzalloc(test, dst_size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf); + iosys_map_set_vaddr(&dst, buf); + + xrgb8888 = cpubuf_to_le32(test, params->xrgb8888, TEST_BUF_SIZE); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, xrgb8888); + iosys_map_set_vaddr(&src, xrgb8888); + + /* + * BGR888 expected results are already in little-endian + * order, so there's no need to convert the test output. + */ + drm_fb_xrgb8888_to_bgr888(&dst, &result->dst_pitch, &src, &fb, ¶ms->clip, + &fmtcnv_state); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); + + buf = dst.vaddr; /* restore original value of buf */ + memset(buf, 0, dst_size); + + int blit_result = 0; + + blit_result = drm_fb_blit(&dst, &result->dst_pitch, DRM_FORMAT_BGR888, &src, &fb, ¶ms->clip, + &fmtcnv_state); + + KUNIT_EXPECT_FALSE(test, blit_result); + KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); +} + static void drm_test_fb_xrgb8888_to_argb8888(struct kunit *test) { const struct convert_xrgb8888_case *params = test->param_value; @@ -1851,6 +1931,7 @@ static struct kunit_case drm_format_helper_test_cases[] = { KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_argb1555, convert_xrgb8888_gen_params), KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_rgba5551, convert_xrgb8888_gen_params), KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_rgb888, convert_xrgb8888_gen_params), + KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_bgr888, convert_xrgb8888_gen_params), KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_argb8888, convert_xrgb8888_gen_params), KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_xrgb2101010, convert_xrgb8888_gen_params), KUNIT_CASE_PARAM(drm_test_fb_xrgb8888_to_argb2101010, convert_xrgb8888_gen_params), diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c index 23ecc00accb2..e97efd3af9ed 100644 --- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c +++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c @@ -273,7 +273,7 @@ drm_kunit_helper_connector_hdmi_init(struct kunit *test, static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *old_conn_state; struct drm_connector_state *new_conn_state; struct drm_crtc_state *crtc_state; @@ -296,13 +296,12 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); new_conn_state = drm_atomic_get_connector_state(state, conn); @@ -327,6 +326,9 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) crtc_state = drm_atomic_get_new_crtc_state(state, crtc); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); KUNIT_EXPECT_TRUE(test, crtc_state->mode_changed); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -337,7 +339,7 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *old_conn_state; struct drm_connector_state *new_conn_state; struct drm_crtc_state *crtc_state; @@ -360,13 +362,12 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); new_conn_state = drm_atomic_get_connector_state(state, conn); @@ -393,6 +394,9 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes crtc_state = drm_atomic_get_new_crtc_state(state, crtc); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); KUNIT_EXPECT_FALSE(test, crtc_state->mode_changed); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -403,7 +407,7 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_atomic_state *state; struct drm_display_mode *preferred; @@ -426,13 +430,12 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); conn_state = drm_atomic_get_connector_state(state, conn); @@ -449,6 +452,9 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state); KUNIT_EXPECT_TRUE(test, conn_state->hdmi.is_limited_range); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -459,7 +465,7 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_atomic_state *state; struct drm_display_mode *mode; @@ -477,17 +483,16 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); crtc = priv->crtc; - ret = light_up_connector(test, drm, crtc, conn, mode, ctx); + ret = light_up_connector(test, drm, crtc, conn, mode, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); conn_state = drm_atomic_get_connector_state(state, conn); @@ -504,6 +509,9 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state); KUNIT_EXPECT_FALSE(test, conn_state->hdmi.is_limited_range); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -514,7 +522,7 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_atomic_state *state; struct drm_display_mode *preferred; @@ -537,13 +545,12 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); conn_state = drm_atomic_get_connector_state(state, conn); @@ -562,6 +569,9 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) DRM_HDMI_BROADCAST_RGB_FULL); KUNIT_EXPECT_FALSE(test, conn_state->hdmi.is_limited_range); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -572,7 +582,7 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_atomic_state *state; struct drm_display_mode *mode; @@ -590,17 +600,16 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); crtc = priv->crtc; - ret = light_up_connector(test, drm, crtc, conn, mode, ctx); + ret = light_up_connector(test, drm, crtc, conn, mode, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); conn_state = drm_atomic_get_connector_state(state, conn); @@ -619,6 +628,9 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) DRM_HDMI_BROADCAST_RGB_FULL); KUNIT_EXPECT_FALSE(test, conn_state->hdmi.is_limited_range); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -629,7 +641,7 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_atomic_state *state; struct drm_display_mode *preferred; @@ -652,13 +664,12 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); conn_state = drm_atomic_get_connector_state(state, conn); @@ -677,6 +688,9 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) DRM_HDMI_BROADCAST_RGB_LIMITED); KUNIT_EXPECT_TRUE(test, conn_state->hdmi.is_limited_range); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -687,7 +701,7 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_atomic_state *state; struct drm_display_mode *mode; @@ -705,17 +719,16 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); crtc = priv->crtc; - ret = light_up_connector(test, drm, crtc, conn, mode, ctx); + ret = light_up_connector(test, drm, crtc, conn, mode, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); conn_state = drm_atomic_get_connector_state(state, conn); @@ -734,6 +747,9 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te DRM_HDMI_BROADCAST_RGB_LIMITED); KUNIT_EXPECT_TRUE(test, conn_state->hdmi.is_limited_range); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -744,7 +760,7 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *old_conn_state; struct drm_connector_state *new_conn_state; struct drm_crtc_state *crtc_state; @@ -771,13 +787,12 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); new_conn_state = drm_atomic_get_connector_state(state, conn); @@ -808,6 +823,9 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) crtc_state = drm_atomic_get_new_crtc_state(state, crtc); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); KUNIT_EXPECT_TRUE(test, crtc_state->mode_changed); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -818,7 +836,7 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *old_conn_state; struct drm_connector_state *new_conn_state; struct drm_crtc_state *crtc_state; @@ -845,13 +863,12 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); new_conn_state = drm_atomic_get_connector_state(state, conn); @@ -880,6 +897,9 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) crtc_state = drm_atomic_get_new_crtc_state(state, crtc); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, crtc_state); KUNIT_EXPECT_FALSE(test, crtc_state->mode_changed); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -889,7 +909,7 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) static void drm_test_check_output_bpc_dvi(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -919,10 +939,9 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -930,6 +949,9 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_bpc, 8); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -939,7 +961,7 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_mode *preferred; struct drm_connector *conn; @@ -964,10 +986,9 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -976,6 +997,9 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) KUNIT_ASSERT_EQ(test, conn_state->hdmi.output_bpc, 8); KUNIT_ASSERT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); KUNIT_EXPECT_EQ(test, conn_state->hdmi.tmds_char_rate, preferred->clock * 1000); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -986,7 +1010,7 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_mode *preferred; struct drm_connector *conn; @@ -1011,10 +1035,9 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -1023,6 +1046,9 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) KUNIT_ASSERT_EQ(test, conn_state->hdmi.output_bpc, 10); KUNIT_ASSERT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); KUNIT_EXPECT_EQ(test, conn_state->hdmi.tmds_char_rate, preferred->clock * 1250); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1033,7 +1059,7 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_mode *preferred; struct drm_connector *conn; @@ -1058,10 +1084,9 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); conn_state = conn->state; @@ -1070,6 +1095,9 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) KUNIT_ASSERT_EQ(test, conn_state->hdmi.output_bpc, 12); KUNIT_ASSERT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); KUNIT_EXPECT_EQ(test, conn_state->hdmi.tmds_char_rate, preferred->clock * 1500); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1083,7 +1111,7 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_atomic_state *state; struct drm_display_mode *preferred; struct drm_crtc_state *crtc_state; @@ -1104,16 +1132,15 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); /* You shouldn't be doing that at home. */ conn->hdmi.funcs = &reject_connector_hdmi_funcs; - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); crtc_state = drm_atomic_get_crtc_state(state, crtc); @@ -1123,6 +1150,9 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) ret = drm_atomic_check_only(state); KUNIT_EXPECT_LT(test, ret, 0); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1139,7 +1169,7 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -1176,10 +1206,9 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 10, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1188,6 +1217,9 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_bpc, 10); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); KUNIT_EXPECT_EQ(test, conn_state->hdmi.tmds_char_rate, preferred->clock * 1250); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1206,7 +1238,7 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -1248,10 +1280,9 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1259,6 +1290,9 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_bpc, 10); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1269,7 +1303,7 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *mode; @@ -1310,11 +1344,10 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) rate = mode->clock * 1500; KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); crtc = priv->crtc; - ret = light_up_connector(test, drm, crtc, conn, mode, ctx); + ret = light_up_connector(test, drm, crtc, conn, mode, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1322,6 +1355,9 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_bpc, 8); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1331,7 +1367,7 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -1376,10 +1412,9 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1387,6 +1422,9 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) KUNIT_EXPECT_LT(test, conn_state->hdmi.output_bpc, 12); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1396,7 +1434,7 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -1443,10 +1481,9 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1454,6 +1491,9 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test KUNIT_EXPECT_LT(test, conn_state->hdmi.output_bpc, 12); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1464,7 +1504,7 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -1501,10 +1541,9 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1512,6 +1551,9 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_bpc, 8); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -1522,7 +1564,7 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_display_info *info; struct drm_display_mode *preferred; @@ -1561,10 +1603,9 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_EXPECT_EQ(test, ret, 0); conn_state = conn->state; @@ -1572,13 +1613,16 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_bpc, 8); KUNIT_EXPECT_EQ(test, conn_state->hdmi.output_format, HDMI_COLORSPACE_RGB); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* Test that atomic check succeeds when disabling a connector. */ static void drm_test_check_disable_connector(struct kunit *test) { struct drm_atomic_helper_connector_hdmi_priv *priv; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_connector_state *conn_state; struct drm_crtc_state *crtc_state; struct drm_atomic_state *state; @@ -1593,8 +1637,7 @@ static void drm_test_check_disable_connector(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); conn = &priv->connector; preferred = find_preferred_mode(conn); @@ -1602,10 +1645,10 @@ static void drm_test_check_disable_connector(struct kunit *test) drm = &priv->drm; crtc = priv->crtc; - ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, &ctx); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); crtc_state = drm_atomic_get_crtc_state(state, crtc); @@ -1623,6 +1666,9 @@ static void drm_test_check_disable_connector(struct kunit *test) ret = drm_atomic_check_only(state); KUNIT_ASSERT_EQ(test, ret, 0); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } static struct kunit_case drm_atomic_helper_connector_hdmi_check_tests[] = { diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c index 3c0b7824c0be..a4eb68f0decc 100644 --- a/drivers/gpu/drm/tests/drm_kunit_helpers.c +++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c @@ -80,47 +80,6 @@ __drm_kunit_helper_alloc_drm_device_with_driver(struct kunit *test, } EXPORT_SYMBOL_GPL(__drm_kunit_helper_alloc_drm_device_with_driver); -static void action_drm_release_context(void *ptr) -{ - struct drm_modeset_acquire_ctx *ctx = ptr; - - drm_modeset_drop_locks(ctx); - drm_modeset_acquire_fini(ctx); -} - -/** - * drm_kunit_helper_acquire_ctx_alloc - Allocates an acquire context - * @test: The test context object - * - * Allocates and initializes a modeset acquire context. - * - * The context is tied to the kunit test context, so we must not call - * drm_modeset_acquire_fini() on it, it will be done so automatically. - * - * Returns: - * An ERR_PTR on error, a pointer to the newly allocated context otherwise - */ -struct drm_modeset_acquire_ctx * -drm_kunit_helper_acquire_ctx_alloc(struct kunit *test) -{ - struct drm_modeset_acquire_ctx *ctx; - int ret; - - ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); - KUNIT_ASSERT_NOT_NULL(test, ctx); - - drm_modeset_acquire_init(ctx, 0); - - ret = kunit_add_action_or_reset(test, - action_drm_release_context, - ctx); - if (ret) - return ERR_PTR(ret); - - return ctx; -} -EXPORT_SYMBOL_GPL(drm_kunit_helper_acquire_ctx_alloc); - static void kunit_action_drm_atomic_state_put(void *ptr) { struct drm_atomic_state *state = ptr; diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index 94cbdb1337c0..54c84c9801c1 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -1,5 +1,17 @@ # SPDX-License-Identifier: GPL-2.0-only +config DRM_APPLETBDRM + tristate "DRM support for Apple Touch Bars" + depends on DRM && USB && MMU + select DRM_GEM_SHMEM_HELPER + select DRM_KMS_HELPER + help + Say Y here if you want support for the display of Touch Bars on x86 + MacBook Pros. + + To compile this driver as a module, choose M here: the + module will be called appletbdrm. + config DRM_ARCPGU tristate "ARC PGU" depends on DRM && OF diff --git a/drivers/gpu/drm/tiny/Makefile b/drivers/gpu/drm/tiny/Makefile index 60816d2eb4ff..0a3a7837a58b 100644 --- a/drivers/gpu/drm/tiny/Makefile +++ b/drivers/gpu/drm/tiny/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DRM_APPLETBDRM) += appletbdrm.o obj-$(CONFIG_DRM_ARCPGU) += arcpgu.o obj-$(CONFIG_DRM_BOCHS) += bochs.o obj-$(CONFIG_DRM_CIRRUS_QEMU) += cirrus-qemu.o diff --git a/drivers/gpu/drm/tiny/appletbdrm.c b/drivers/gpu/drm/tiny/appletbdrm.c new file mode 100644 index 000000000000..394c8f9bd41a --- /dev/null +++ b/drivers/gpu/drm/tiny/appletbdrm.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Apple Touch Bar DRM Driver + * + * Copyright (c) 2023 Kerem Karabay <kekrby@gmail.com> + */ + +#include <linux/align.h> +#include <linux/array_size.h> +#include <linux/bitops.h> +#include <linux/bug.h> +#include <linux/container_of.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/overflow.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/unaligned.h> +#include <linux/usb.h> + +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc.h> +#include <drm/drm_damage_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_encoder.h> +#include <drm/drm_format_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_plane.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> + +#define APPLETBDRM_PIXEL_FORMAT cpu_to_le32(0x52474241) /* RGBA, the actual format is BGR888 */ +#define APPLETBDRM_BITS_PER_PIXEL 24 + +#define APPLETBDRM_MSG_CLEAR_DISPLAY cpu_to_le32(0x434c5244) /* CLRD */ +#define APPLETBDRM_MSG_GET_INFORMATION cpu_to_le32(0x47494e46) /* GINF */ +#define APPLETBDRM_MSG_UPDATE_COMPLETE cpu_to_le32(0x5544434c) /* UDCL */ +#define APPLETBDRM_MSG_SIGNAL_READINESS cpu_to_le32(0x52454459) /* REDY */ + +#define APPLETBDRM_BULK_MSG_TIMEOUT 1000 + +#define drm_to_adev(_drm) container_of(_drm, struct appletbdrm_device, drm) +#define adev_to_udev(adev) interface_to_usbdev(to_usb_interface(adev->dmadev)) + +struct appletbdrm_msg_request_header { + __le16 unk_00; + __le16 unk_02; + __le32 unk_04; + __le32 unk_08; + __le32 size; +} __packed; + +struct appletbdrm_msg_response_header { + u8 unk_00[16]; + __le32 msg; +} __packed; + +struct appletbdrm_msg_simple_request { + struct appletbdrm_msg_request_header header; + __le32 msg; + u8 unk_14[8]; + __le32 size; +} __packed; + +struct appletbdrm_msg_information { + struct appletbdrm_msg_response_header header; + u8 unk_14[12]; + __le32 width; + __le32 height; + u8 bits_per_pixel; + __le32 bytes_per_row; + __le32 orientation; + __le32 bitmap_info; + __le32 pixel_format; + __le32 width_inches; /* floating point */ + __le32 height_inches; /* floating point */ +} __packed; + +struct appletbdrm_frame { + __le16 begin_x; + __le16 begin_y; + __le16 width; + __le16 height; + __le32 buf_size; + u8 buf[]; +} __packed; + +struct appletbdrm_fb_request_footer { + u8 unk_00[12]; + __le32 unk_0c; + u8 unk_10[12]; + __le32 unk_1c; + __le64 timestamp; + u8 unk_28[12]; + __le32 unk_34; + u8 unk_38[20]; + __le32 unk_4c; +} __packed; + +struct appletbdrm_fb_request { + struct appletbdrm_msg_request_header header; + __le16 unk_10; + u8 msg_id; + u8 unk_13[29]; + /* + * Contents of `data`: + * - struct appletbdrm_frame frames[]; + * - struct appletbdrm_fb_request_footer footer; + * - padding to make the total size a multiple of 16 + */ + u8 data[]; +} __packed; + +struct appletbdrm_fb_request_response { + struct appletbdrm_msg_response_header header; + u8 unk_14[12]; + __le64 timestamp; +} __packed; + +struct appletbdrm_device { + struct device *dmadev; + + unsigned int in_ep; + unsigned int out_ep; + + unsigned int width; + unsigned int height; + + struct drm_device drm; + struct drm_display_mode mode; + struct drm_connector connector; + struct drm_plane primary_plane; + struct drm_crtc crtc; + struct drm_encoder encoder; +}; + +struct appletbdrm_plane_state { + struct drm_shadow_plane_state base; + struct appletbdrm_fb_request *request; + struct appletbdrm_fb_request_response *response; + size_t request_size; + size_t frames_size; +}; + +static inline struct appletbdrm_plane_state *to_appletbdrm_plane_state(struct drm_plane_state *state) +{ + return container_of(state, struct appletbdrm_plane_state, base.base); +} + +static int appletbdrm_send_request(struct appletbdrm_device *adev, + struct appletbdrm_msg_request_header *request, size_t size) +{ + struct usb_device *udev = adev_to_udev(adev); + struct drm_device *drm = &adev->drm; + int ret, actual_size; + + ret = usb_bulk_msg(udev, usb_sndbulkpipe(udev, adev->out_ep), + request, size, &actual_size, APPLETBDRM_BULK_MSG_TIMEOUT); + if (ret) { + drm_err(drm, "Failed to send message (%d)\n", ret); + return ret; + } + + if (actual_size != size) { + drm_err(drm, "Actual size (%d) doesn't match expected size (%zu)\n", + actual_size, size); + return -EIO; + } + + return 0; +} + +static int appletbdrm_read_response(struct appletbdrm_device *adev, + struct appletbdrm_msg_response_header *response, + size_t size, __le32 expected_response) +{ + struct usb_device *udev = adev_to_udev(adev); + struct drm_device *drm = &adev->drm; + int ret, actual_size; + bool readiness_signal_received = false; + +retry: + ret = usb_bulk_msg(udev, usb_rcvbulkpipe(udev, adev->in_ep), + response, size, &actual_size, APPLETBDRM_BULK_MSG_TIMEOUT); + if (ret) { + drm_err(drm, "Failed to read response (%d)\n", ret); + return ret; + } + + /* + * The device responds to the first request sent in a particular + * timeframe after the USB device configuration is set with a readiness + * signal, in which case the response should be read again + */ + if (response->msg == APPLETBDRM_MSG_SIGNAL_READINESS) { + if (!readiness_signal_received) { + readiness_signal_received = true; + goto retry; + } + + drm_err(drm, "Encountered unexpected readiness signal\n"); + return -EINTR; + } + + if (actual_size != size) { + drm_err(drm, "Actual size (%d) doesn't match expected size (%zu)\n", + actual_size, size); + return -EBADMSG; + } + + if (response->msg != expected_response) { + drm_err(drm, "Unexpected response from device (expected %p4cc found %p4cc)\n", + &expected_response, &response->msg); + return -EIO; + } + + return 0; +} + +static int appletbdrm_send_msg(struct appletbdrm_device *adev, __le32 msg) +{ + struct appletbdrm_msg_simple_request *request; + int ret; + + request = kzalloc(sizeof(*request), GFP_KERNEL); + if (!request) + return -ENOMEM; + + request->header.unk_00 = cpu_to_le16(2); + request->header.unk_02 = cpu_to_le16(0x1512); + request->header.size = cpu_to_le32(sizeof(*request) - sizeof(request->header)); + request->msg = msg; + request->size = request->header.size; + + ret = appletbdrm_send_request(adev, &request->header, sizeof(*request)); + + kfree(request); + + return ret; +} + +static int appletbdrm_clear_display(struct appletbdrm_device *adev) +{ + return appletbdrm_send_msg(adev, APPLETBDRM_MSG_CLEAR_DISPLAY); +} + +static int appletbdrm_signal_readiness(struct appletbdrm_device *adev) +{ + return appletbdrm_send_msg(adev, APPLETBDRM_MSG_SIGNAL_READINESS); +} + +static int appletbdrm_get_information(struct appletbdrm_device *adev) +{ + struct appletbdrm_msg_information *info; + struct drm_device *drm = &adev->drm; + u8 bits_per_pixel; + __le32 pixel_format; + int ret; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + ret = appletbdrm_send_msg(adev, APPLETBDRM_MSG_GET_INFORMATION); + if (ret) + return ret; + + ret = appletbdrm_read_response(adev, &info->header, sizeof(*info), + APPLETBDRM_MSG_GET_INFORMATION); + if (ret) + goto free_info; + + bits_per_pixel = info->bits_per_pixel; + pixel_format = get_unaligned(&info->pixel_format); + + adev->width = get_unaligned_le32(&info->width); + adev->height = get_unaligned_le32(&info->height); + + if (bits_per_pixel != APPLETBDRM_BITS_PER_PIXEL) { + drm_err(drm, "Encountered unexpected bits per pixel value (%d)\n", bits_per_pixel); + ret = -EINVAL; + goto free_info; + } + + if (pixel_format != APPLETBDRM_PIXEL_FORMAT) { + drm_err(drm, "Encountered unknown pixel format (%p4cc)\n", &pixel_format); + ret = -EINVAL; + goto free_info; + } + +free_info: + kfree(info); + + return ret; +} + +static u32 rect_size(struct drm_rect *rect) +{ + return drm_rect_width(rect) * drm_rect_height(rect) * + (BITS_TO_BYTES(APPLETBDRM_BITS_PER_PIXEL)); +} + +static int appletbdrm_connector_helper_get_modes(struct drm_connector *connector) +{ + struct appletbdrm_device *adev = drm_to_adev(connector->dev); + + return drm_connector_helper_get_modes_fixed(connector, &adev->mode); +} + +static const u32 appletbdrm_primary_plane_formats[] = { + DRM_FORMAT_BGR888, + DRM_FORMAT_XRGB8888, /* emulated */ +}; + +static int appletbdrm_primary_plane_helper_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); + struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); + struct drm_crtc *new_crtc = new_plane_state->crtc; + struct drm_crtc_state *new_crtc_state = NULL; + struct appletbdrm_plane_state *appletbdrm_state = to_appletbdrm_plane_state(new_plane_state); + struct drm_atomic_helper_damage_iter iter; + struct drm_rect damage; + size_t frames_size = 0; + size_t request_size; + int ret; + + if (new_crtc) + new_crtc_state = drm_atomic_get_new_crtc_state(state, new_crtc); + + ret = drm_atomic_helper_check_plane_state(new_plane_state, new_crtc_state, + DRM_PLANE_NO_SCALING, + DRM_PLANE_NO_SCALING, + false, false); + if (ret) + return ret; + else if (!new_plane_state->visible) + return 0; + + drm_atomic_helper_damage_iter_init(&iter, old_plane_state, new_plane_state); + drm_atomic_for_each_plane_damage(&iter, &damage) { + frames_size += struct_size((struct appletbdrm_frame *)0, buf, rect_size(&damage)); + } + + if (!frames_size) + return 0; + + request_size = ALIGN(sizeof(struct appletbdrm_fb_request) + + frames_size + + sizeof(struct appletbdrm_fb_request_footer), 16); + + appletbdrm_state->request = kzalloc(request_size, GFP_KERNEL); + + if (!appletbdrm_state->request) + return -ENOMEM; + + appletbdrm_state->response = kzalloc(sizeof(*appletbdrm_state->response), GFP_KERNEL); + + if (!appletbdrm_state->response) + return -ENOMEM; + + appletbdrm_state->request_size = request_size; + appletbdrm_state->frames_size = frames_size; + + return 0; +} + +static int appletbdrm_flush_damage(struct appletbdrm_device *adev, + struct drm_plane_state *old_state, + struct drm_plane_state *state) +{ + struct appletbdrm_plane_state *appletbdrm_state = to_appletbdrm_plane_state(state); + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(state); + struct appletbdrm_fb_request_response *response = appletbdrm_state->response; + struct appletbdrm_fb_request_footer *footer; + struct drm_atomic_helper_damage_iter iter; + struct drm_framebuffer *fb = state->fb; + struct appletbdrm_fb_request *request = appletbdrm_state->request; + struct drm_device *drm = &adev->drm; + struct appletbdrm_frame *frame; + u64 timestamp = ktime_get_ns(); + struct drm_rect damage; + size_t frames_size = appletbdrm_state->frames_size; + size_t request_size = appletbdrm_state->request_size; + int ret; + + if (!frames_size) + return 0; + + ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE); + if (ret) { + drm_err(drm, "Failed to start CPU framebuffer access (%d)\n", ret); + goto end_fb_cpu_access; + } + + request->header.unk_00 = cpu_to_le16(2); + request->header.unk_02 = cpu_to_le16(0x12); + request->header.unk_04 = cpu_to_le32(9); + request->header.size = cpu_to_le32(request_size - sizeof(request->header)); + request->unk_10 = cpu_to_le16(1); + request->msg_id = timestamp; + + frame = (struct appletbdrm_frame *)request->data; + + drm_atomic_helper_damage_iter_init(&iter, old_state, state); + drm_atomic_for_each_plane_damage(&iter, &damage) { + struct drm_rect dst_clip = state->dst; + struct iosys_map dst = IOSYS_MAP_INIT_VADDR(frame->buf); + u32 buf_size = rect_size(&damage); + + if (!drm_rect_intersect(&dst_clip, &damage)) + continue; + + /* + * The coordinates need to be translated to the coordinate + * system the device expects, see the comment in + * appletbdrm_setup_mode_config + */ + frame->begin_x = cpu_to_le16(damage.y1); + frame->begin_y = cpu_to_le16(adev->height - damage.x2); + frame->width = cpu_to_le16(drm_rect_height(&damage)); + frame->height = cpu_to_le16(drm_rect_width(&damage)); + frame->buf_size = cpu_to_le32(buf_size); + + switch (fb->format->format) { + case DRM_FORMAT_XRGB8888: + drm_fb_xrgb8888_to_bgr888(&dst, NULL, &shadow_plane_state->data[0], fb, &damage, &shadow_plane_state->fmtcnv_state); + break; + default: + drm_fb_memcpy(&dst, NULL, &shadow_plane_state->data[0], fb, &damage); + break; + } + + frame = (void *)frame + struct_size(frame, buf, buf_size); + } + + footer = (struct appletbdrm_fb_request_footer *)&request->data[frames_size]; + + footer->unk_0c = cpu_to_le32(0xfffe); + footer->unk_1c = cpu_to_le32(0x80001); + footer->unk_34 = cpu_to_le32(0x80002); + footer->unk_4c = cpu_to_le32(0xffff); + footer->timestamp = cpu_to_le64(timestamp); + + ret = appletbdrm_send_request(adev, &request->header, request_size); + if (ret) + goto end_fb_cpu_access; + + ret = appletbdrm_read_response(adev, &response->header, sizeof(*response), + APPLETBDRM_MSG_UPDATE_COMPLETE); + if (ret) + goto end_fb_cpu_access; + + if (response->timestamp != footer->timestamp) { + drm_err(drm, "Response timestamp (%llu) doesn't match request timestamp (%llu)\n", + le64_to_cpu(response->timestamp), timestamp); + goto end_fb_cpu_access; + } + +end_fb_cpu_access: + drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); + + return ret; +} + +static void appletbdrm_primary_plane_helper_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *old_state) +{ + struct appletbdrm_device *adev = drm_to_adev(plane->dev); + struct drm_device *drm = plane->dev; + struct drm_plane_state *plane_state = plane->state; + struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(old_state, plane); + int idx; + + if (!drm_dev_enter(drm, &idx)) + return; + + appletbdrm_flush_damage(adev, old_plane_state, plane_state); + + drm_dev_exit(idx); +} + +static void appletbdrm_primary_plane_helper_atomic_disable(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_device *dev = plane->dev; + struct appletbdrm_device *adev = drm_to_adev(dev); + int idx; + + if (!drm_dev_enter(dev, &idx)) + return; + + appletbdrm_clear_display(adev); + + drm_dev_exit(idx); +} + +static void appletbdrm_primary_plane_reset(struct drm_plane *plane) +{ + struct appletbdrm_plane_state *appletbdrm_state; + + WARN_ON(plane->state); + + appletbdrm_state = kzalloc(sizeof(*appletbdrm_state), GFP_KERNEL); + if (!appletbdrm_state) + return; + + __drm_gem_reset_shadow_plane(plane, &appletbdrm_state->base); +} + +static struct drm_plane_state *appletbdrm_primary_plane_duplicate_state(struct drm_plane *plane) +{ + struct drm_shadow_plane_state *new_shadow_plane_state; + struct appletbdrm_plane_state *appletbdrm_state; + + if (WARN_ON(!plane->state)) + return NULL; + + appletbdrm_state = kzalloc(sizeof(*appletbdrm_state), GFP_KERNEL); + if (!appletbdrm_state) + return NULL; + + /* Request and response are not duplicated and are allocated in .atomic_check */ + appletbdrm_state->request = NULL; + appletbdrm_state->response = NULL; + + appletbdrm_state->request_size = 0; + appletbdrm_state->frames_size = 0; + + new_shadow_plane_state = &appletbdrm_state->base; + + __drm_gem_duplicate_shadow_plane_state(plane, new_shadow_plane_state); + + return &new_shadow_plane_state->base; +} + +static void appletbdrm_primary_plane_destroy_state(struct drm_plane *plane, + struct drm_plane_state *state) +{ + struct appletbdrm_plane_state *appletbdrm_state = to_appletbdrm_plane_state(state); + + kfree(appletbdrm_state->request); + kfree(appletbdrm_state->response); + + __drm_gem_destroy_shadow_plane_state(&appletbdrm_state->base); + + kfree(appletbdrm_state); +} + +static const struct drm_plane_helper_funcs appletbdrm_primary_plane_helper_funcs = { + DRM_GEM_SHADOW_PLANE_HELPER_FUNCS, + .atomic_check = appletbdrm_primary_plane_helper_atomic_check, + .atomic_update = appletbdrm_primary_plane_helper_atomic_update, + .atomic_disable = appletbdrm_primary_plane_helper_atomic_disable, +}; + +static const struct drm_plane_funcs appletbdrm_primary_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .reset = appletbdrm_primary_plane_reset, + .atomic_duplicate_state = appletbdrm_primary_plane_duplicate_state, + .atomic_destroy_state = appletbdrm_primary_plane_destroy_state, + .destroy = drm_plane_cleanup, +}; + +static enum drm_mode_status appletbdrm_crtc_helper_mode_valid(struct drm_crtc *crtc, + const struct drm_display_mode *mode) +{ + struct appletbdrm_device *adev = drm_to_adev(crtc->dev); + + return drm_crtc_helper_mode_valid_fixed(crtc, mode, &adev->mode); +} + +static const struct drm_mode_config_funcs appletbdrm_mode_config_funcs = { + .fb_create = drm_gem_fb_create_with_dirty, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static const struct drm_connector_funcs appletbdrm_connector_funcs = { + .reset = drm_atomic_helper_connector_reset, + .destroy = drm_connector_cleanup, + .fill_modes = drm_helper_probe_single_connector_modes, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, +}; + +static const struct drm_connector_helper_funcs appletbdrm_connector_helper_funcs = { + .get_modes = appletbdrm_connector_helper_get_modes, +}; + +static const struct drm_crtc_helper_funcs appletbdrm_crtc_helper_funcs = { + .mode_valid = appletbdrm_crtc_helper_mode_valid, +}; + +static const struct drm_crtc_funcs appletbdrm_crtc_funcs = { + .reset = drm_atomic_helper_crtc_reset, + .destroy = drm_crtc_cleanup, + .set_config = drm_atomic_helper_set_config, + .page_flip = drm_atomic_helper_page_flip, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, +}; + +static const struct drm_encoder_funcs appletbdrm_encoder_funcs = { + .destroy = drm_encoder_cleanup, +}; + +static struct drm_gem_object *appletbdrm_driver_gem_prime_import(struct drm_device *dev, + struct dma_buf *dma_buf) +{ + struct appletbdrm_device *adev = drm_to_adev(dev); + + if (!adev->dmadev) + return ERR_PTR(-ENODEV); + + return drm_gem_prime_import_dev(dev, dma_buf, adev->dmadev); +} + +DEFINE_DRM_GEM_FOPS(appletbdrm_drm_fops); + +static const struct drm_driver appletbdrm_drm_driver = { + DRM_GEM_SHMEM_DRIVER_OPS, + .gem_prime_import = appletbdrm_driver_gem_prime_import, + .name = "appletbdrm", + .desc = "Apple Touch Bar DRM Driver", + .major = 1, + .minor = 0, + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, + .fops = &appletbdrm_drm_fops, +}; + +static int appletbdrm_setup_mode_config(struct appletbdrm_device *adev) +{ + struct drm_connector *connector = &adev->connector; + struct drm_plane *primary_plane; + struct drm_crtc *crtc; + struct drm_encoder *encoder; + struct drm_device *drm = &adev->drm; + int ret; + + ret = drmm_mode_config_init(drm); + if (ret) { + drm_err(drm, "Failed to initialize mode configuration\n"); + return ret; + } + + primary_plane = &adev->primary_plane; + ret = drm_universal_plane_init(drm, primary_plane, 0, + &appletbdrm_primary_plane_funcs, + appletbdrm_primary_plane_formats, + ARRAY_SIZE(appletbdrm_primary_plane_formats), + NULL, + DRM_PLANE_TYPE_PRIMARY, NULL); + if (ret) { + drm_err(drm, "Failed to initialize universal plane object\n"); + return ret; + } + + drm_plane_helper_add(primary_plane, &appletbdrm_primary_plane_helper_funcs); + drm_plane_enable_fb_damage_clips(primary_plane); + + crtc = &adev->crtc; + ret = drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL, + &appletbdrm_crtc_funcs, NULL); + if (ret) { + drm_err(drm, "Failed to initialize CRTC object\n"); + return ret; + } + + drm_crtc_helper_add(crtc, &appletbdrm_crtc_helper_funcs); + + encoder = &adev->encoder; + ret = drm_encoder_init(drm, encoder, &appletbdrm_encoder_funcs, + DRM_MODE_ENCODER_DAC, NULL); + if (ret) { + drm_err(drm, "Failed to initialize encoder\n"); + return ret; + } + + encoder->possible_crtcs = drm_crtc_mask(crtc); + + /* + * The coordinate system used by the device is different from the + * coordinate system of the framebuffer in that the x and y axes are + * swapped, and that the y axis is inverted; so what the device reports + * as the height is actually the width of the framebuffer and vice + * versa. + */ + drm->mode_config.max_width = max(adev->height, DRM_SHADOW_PLANE_MAX_WIDTH); + drm->mode_config.max_height = max(adev->width, DRM_SHADOW_PLANE_MAX_HEIGHT); + drm->mode_config.preferred_depth = APPLETBDRM_BITS_PER_PIXEL; + drm->mode_config.funcs = &appletbdrm_mode_config_funcs; + + adev->mode = (struct drm_display_mode) { + DRM_MODE_INIT(60, adev->height, adev->width, + DRM_MODE_RES_MM(adev->height, 218), + DRM_MODE_RES_MM(adev->width, 218)) + }; + + ret = drm_connector_init(drm, connector, + &appletbdrm_connector_funcs, DRM_MODE_CONNECTOR_USB); + if (ret) { + drm_err(drm, "Failed to initialize connector\n"); + return ret; + } + + drm_connector_helper_add(connector, &appletbdrm_connector_helper_funcs); + + ret = drm_connector_set_panel_orientation(connector, + DRM_MODE_PANEL_ORIENTATION_RIGHT_UP); + if (ret) { + drm_err(drm, "Failed to set panel orientation\n"); + return ret; + } + + connector->display_info.non_desktop = true; + ret = drm_object_property_set_value(&connector->base, + drm->mode_config.non_desktop_property, true); + if (ret) { + drm_err(drm, "Failed to set non-desktop property\n"); + return ret; + } + + ret = drm_connector_attach_encoder(connector, encoder); + + if (ret) { + drm_err(drm, "Failed to initialize simple display pipe\n"); + return ret; + } + + drm_mode_config_reset(drm); + + return 0; +} + +static int appletbdrm_probe(struct usb_interface *intf, + const struct usb_device_id *id) +{ + struct usb_endpoint_descriptor *bulk_in, *bulk_out; + struct device *dev = &intf->dev; + struct appletbdrm_device *adev; + struct drm_device *drm = NULL; + int ret; + + ret = usb_find_common_endpoints(intf->cur_altsetting, &bulk_in, &bulk_out, NULL, NULL); + if (ret) { + drm_err(drm, "appletbdrm: Failed to find bulk endpoints\n"); + return ret; + } + + adev = devm_drm_dev_alloc(dev, &appletbdrm_drm_driver, struct appletbdrm_device, drm); + if (IS_ERR(adev)) + return PTR_ERR(adev); + + adev->in_ep = bulk_in->bEndpointAddress; + adev->out_ep = bulk_out->bEndpointAddress; + adev->dmadev = dev; + + drm = &adev->drm; + + usb_set_intfdata(intf, adev); + + ret = appletbdrm_get_information(adev); + if (ret) { + drm_err(drm, "Failed to get display information\n"); + return ret; + } + + ret = appletbdrm_signal_readiness(adev); + if (ret) { + drm_err(drm, "Failed to signal readiness\n"); + return ret; + } + + ret = appletbdrm_setup_mode_config(adev); + if (ret) { + drm_err(drm, "Failed to setup mode config\n"); + return ret; + } + + ret = drm_dev_register(drm, 0); + if (ret) { + drm_err(drm, "Failed to register DRM device\n"); + return ret; + } + + ret = appletbdrm_clear_display(adev); + if (ret) { + drm_err(drm, "Failed to clear display\n"); + return ret; + } + + return 0; +} + +static void appletbdrm_disconnect(struct usb_interface *intf) +{ + struct appletbdrm_device *adev = usb_get_intfdata(intf); + struct drm_device *drm = &adev->drm; + + put_device(adev->dmadev); + drm_dev_unplug(drm); + drm_atomic_helper_shutdown(drm); +} + +static void appletbdrm_shutdown(struct usb_interface *intf) +{ + struct appletbdrm_device *adev = usb_get_intfdata(intf); + + /* + * The framebuffer needs to be cleared on shutdown since its content + * persists across boots + */ + drm_atomic_helper_shutdown(&adev->drm); +} + +static const struct usb_device_id appletbdrm_usb_id_table[] = { + { USB_DEVICE_INTERFACE_CLASS(0x05ac, 0x8302, USB_CLASS_AUDIO_VIDEO) }, + {} +}; +MODULE_DEVICE_TABLE(usb, appletbdrm_usb_id_table); + +static struct usb_driver appletbdrm_usb_driver = { + .name = "appletbdrm", + .probe = appletbdrm_probe, + .disconnect = appletbdrm_disconnect, + .shutdown = appletbdrm_shutdown, + .id_table = appletbdrm_usb_id_table, +}; +module_usb_driver(appletbdrm_usb_driver); + +MODULE_AUTHOR("Kerem Karabay <kekrby@gmail.com>"); +MODULE_DESCRIPTION("Apple Touch Bar DRM Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/tiny/arcpgu.c b/drivers/gpu/drm/tiny/arcpgu.c index 2748d1f21d86..7cf0f0ea1bfe 100644 --- a/drivers/gpu/drm/tiny/arcpgu.c +++ b/drivers/gpu/drm/tiny/arcpgu.c @@ -253,7 +253,6 @@ static int arcpgu_load(struct arcpgu_drm_private *arcpgu) struct device_node *encoder_node = NULL, *endpoint_node = NULL; struct drm_connector *connector = NULL; struct drm_device *drm = &arcpgu->drm; - struct resource *res; int ret; arcpgu->clk = devm_clk_get(drm->dev, "pxlclk"); @@ -270,8 +269,7 @@ static int arcpgu_load(struct arcpgu_drm_private *arcpgu) drm->mode_config.max_height = 1080; drm->mode_config.funcs = &arcpgu_drm_modecfg_funcs; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - arcpgu->regs = devm_ioremap_resource(&pdev->dev, res); + arcpgu->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(arcpgu->regs)) return PTR_ERR(arcpgu->regs); diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index 52ba6c699bc8..5c3b51eb0a97 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -456,7 +456,7 @@ static void repaper_frame_fixed_repeat(struct repaper_epd *epd, u8 fixed_value, enum repaper_stage stage) { u64 start = local_clock(); - u64 end = start + (epd->factored_stage_time * 1000 * 1000); + u64 end = start + ((u64)epd->factored_stage_time * 1000 * 1000); do { repaper_frame_fixed(epd, fixed_value, stage); @@ -467,7 +467,7 @@ static void repaper_frame_data_repeat(struct repaper_epd *epd, const u8 *image, const u8 *mask, enum repaper_stage stage) { u64 start = local_clock(); - u64 end = start + (epd->factored_stage_time * 1000 * 1000); + u64 end = start + ((u64)epd->factored_stage_time * 1000 * 1000); do { repaper_frame_data(epd, image, mask, stage); diff --git a/drivers/gpu/drm/ttm/Makefile b/drivers/gpu/drm/ttm/Makefile index dad298127226..40d07a35293a 100644 --- a/drivers/gpu/drm/ttm/Makefile +++ b/drivers/gpu/drm/ttm/Makefile @@ -4,7 +4,7 @@ ttm-y := ttm_tt.o ttm_bo.o ttm_bo_util.o ttm_bo_vm.o ttm_module.o \ ttm_execbuf_util.o ttm_range_manager.o ttm_resource.o ttm_pool.o \ - ttm_device.o ttm_sys_manager.o + ttm_device.o ttm_sys_manager.o ttm_backup.o ttm-$(CONFIG_AGP) += ttm_agp_backend.o obj-$(CONFIG_DRM_TTM) += ttm.o diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c new file mode 100644 index 000000000000..93c007f18855 --- /dev/null +++ b/drivers/gpu/drm/ttm/ttm_backup.c @@ -0,0 +1,207 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include <drm/ttm/ttm_backup.h> +#include <linux/page-flags.h> +#include <linux/swap.h> + +/* + * Casting from randomized struct file * to struct ttm_backup * is fine since + * struct ttm_backup is never defined nor dereferenced. + */ +static struct file *ttm_backup_to_file(struct ttm_backup *backup) +{ + return (void *)backup; +} + +static struct ttm_backup *ttm_file_to_backup(struct file *file) +{ + return (void *)file; +} + +/* + * Need to map shmem indices to handle since a handle value + * of 0 means error, following the swp_entry_t convention. + */ +static unsigned long ttm_backup_shmem_idx_to_handle(pgoff_t idx) +{ + return (unsigned long)idx + 1; +} + +static pgoff_t ttm_backup_handle_to_shmem_idx(pgoff_t handle) +{ + return handle - 1; +} + +/** + * ttm_backup_drop() - release memory associated with a handle + * @backup: The struct backup pointer used to obtain the handle + * @handle: The handle obtained from the @backup_page function. + */ +void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle) +{ + loff_t start = ttm_backup_handle_to_shmem_idx(handle); + + start <<= PAGE_SHIFT; + shmem_truncate_range(file_inode(ttm_backup_to_file(backup)), start, + start + PAGE_SIZE - 1); +} + +/** + * ttm_backup_copy_page() - Copy the contents of a previously backed + * up page + * @backup: The struct backup pointer used to back up the page. + * @dst: The struct page to copy into. + * @handle: The handle returned when the page was backed up. + * @intr: Try to perform waits interruptable or at least killable. + * + * Return: 0 on success, Negative error code on failure, notably + * -EINTR if @intr was set to true and a signal is pending. + */ +int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst, + pgoff_t handle, bool intr) +{ + struct file *filp = ttm_backup_to_file(backup); + struct address_space *mapping = filp->f_mapping; + struct folio *from_folio; + pgoff_t idx = ttm_backup_handle_to_shmem_idx(handle); + + from_folio = shmem_read_folio(mapping, idx); + if (IS_ERR(from_folio)) + return PTR_ERR(from_folio); + + copy_highpage(dst, folio_file_page(from_folio, idx)); + folio_put(from_folio); + + return 0; +} + +/** + * ttm_backup_backup_page() - Backup a page + * @backup: The struct backup pointer to use. + * @page: The page to back up. + * @writeback: Whether to perform immediate writeback of the page. + * This may have performance implications. + * @idx: A unique integer for each page and each struct backup. + * This allows the backup implementation to avoid managing + * its address space separately. + * @page_gfp: The gfp value used when the page was allocated. + * This is used for accounting purposes. + * @alloc_gfp: The gfp to be used when allocating memory. + * + * Context: If called from reclaim context, the caller needs to + * assert that the shrinker gfp has __GFP_FS set, to avoid + * deadlocking on lock_page(). If @writeback is set to true and + * called from reclaim context, the caller also needs to assert + * that the shrinker gfp has __GFP_IO set, since without it, + * we're not allowed to start backup IO. + * + * Return: A handle on success. Negative error code on failure. + * + * Note: This function could be extended to back up a folio and + * implementations would then split the folio internally if needed. + * Drawback is that the caller would then have to keep track of + * the folio size- and usage. + */ +s64 +ttm_backup_backup_page(struct ttm_backup *backup, struct page *page, + bool writeback, pgoff_t idx, gfp_t page_gfp, + gfp_t alloc_gfp) +{ + struct file *filp = ttm_backup_to_file(backup); + struct address_space *mapping = filp->f_mapping; + unsigned long handle = 0; + struct folio *to_folio; + int ret; + + to_folio = shmem_read_folio_gfp(mapping, idx, alloc_gfp); + if (IS_ERR(to_folio)) + return PTR_ERR(to_folio); + + folio_mark_accessed(to_folio); + folio_lock(to_folio); + folio_mark_dirty(to_folio); + copy_highpage(folio_file_page(to_folio, idx), page); + handle = ttm_backup_shmem_idx_to_handle(idx); + + if (writeback && !folio_mapped(to_folio) && + folio_clear_dirty_for_io(to_folio)) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = SWAP_CLUSTER_MAX, + .range_start = 0, + .range_end = LLONG_MAX, + .for_reclaim = 1, + }; + folio_set_reclaim(to_folio); + ret = mapping->a_ops->writepage(folio_file_page(to_folio, idx), &wbc); + if (!folio_test_writeback(to_folio)) + folio_clear_reclaim(to_folio); + /* + * If writepage succeeds, it unlocks the folio. + * writepage() errors are otherwise dropped, since writepage() + * is only best effort here. + */ + if (ret) + folio_unlock(to_folio); + } else { + folio_unlock(to_folio); + } + + folio_put(to_folio); + + return handle; +} + +/** + * ttm_backup_fini() - Free the struct backup resources after last use. + * @backup: Pointer to the struct backup whose resources to free. + * + * After a call to this function, it's illegal to use the @backup pointer. + */ +void ttm_backup_fini(struct ttm_backup *backup) +{ + fput(ttm_backup_to_file(backup)); +} + +/** + * ttm_backup_bytes_avail() - Report the approximate number of bytes of backup space + * left for backup. + * + * This function is intended also for driver use to indicate whether a + * backup attempt is meaningful. + * + * Return: An approximate size of backup space available. + */ +u64 ttm_backup_bytes_avail(void) +{ + /* + * The idea behind backing up to shmem is that shmem objects may + * eventually be swapped out. So no point swapping out if there + * is no or low swap-space available. But the accuracy of this + * number also depends on shmem actually swapping out backed-up + * shmem objects without too much buffering. + */ + return (u64)get_nr_swap_pages() << PAGE_SHIFT; +} +EXPORT_SYMBOL_GPL(ttm_backup_bytes_avail); + +/** + * ttm_backup_shmem_create() - Create a shmem-based struct backup. + * @size: The maximum size (in bytes) to back up. + * + * Create a backup utilizing shmem objects. + * + * Return: A pointer to a struct ttm_backup on success, + * an error pointer on error. + */ +struct ttm_backup *ttm_backup_shmem_create(loff_t size) +{ + struct file *filp; + + filp = shmem_file_setup("ttm shmem backup", size, 0); + + return ttm_file_to_backup(filp); +} diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 917096bd5f68..15cab9bda17f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -28,7 +28,7 @@ /* * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ - +#include <linux/swap.h> #include <linux/vmalloc.h> #include <drm/ttm/ttm_bo.h> @@ -769,12 +769,10 @@ error_destroy_tt: return ret; } -static bool ttm_lru_walk_trylock(struct ttm_lru_walk *walk, +static bool ttm_lru_walk_trylock(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, bool *needs_unlock) { - struct ttm_operation_ctx *ctx = walk->ctx; - *needs_unlock = false; if (dma_resv_trylock(bo->base.resv)) { @@ -877,7 +875,7 @@ s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev, * since if we do it the other way around, and the trylock fails, * we need to drop the lru lock to put the bo. */ - if (ttm_lru_walk_trylock(walk, bo, &bo_needs_unlock)) + if (ttm_lru_walk_trylock(walk->ctx, bo, &bo_needs_unlock)) bo_locked = true; else if (!walk->ticket || walk->ctx->no_wait_gpu || walk->trylock_only) @@ -920,3 +918,242 @@ s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev, return progress; } +EXPORT_SYMBOL(ttm_lru_walk_for_evict); + +static void ttm_bo_lru_cursor_cleanup_bo(struct ttm_bo_lru_cursor *curs) +{ + struct ttm_buffer_object *bo = curs->bo; + + if (bo) { + if (curs->needs_unlock) + dma_resv_unlock(bo->base.resv); + ttm_bo_put(bo); + curs->bo = NULL; + } +} + +/** + * ttm_bo_lru_cursor_fini() - Stop using a struct ttm_bo_lru_cursor + * and clean up any iteration it was used for. + * @curs: The cursor. + */ +void ttm_bo_lru_cursor_fini(struct ttm_bo_lru_cursor *curs) +{ + spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock; + + ttm_bo_lru_cursor_cleanup_bo(curs); + spin_lock(lru_lock); + ttm_resource_cursor_fini(&curs->res_curs); + spin_unlock(lru_lock); +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_fini); + +/** + * ttm_bo_lru_cursor_init() - Initialize a struct ttm_bo_lru_cursor + * @curs: The ttm_bo_lru_cursor to initialize. + * @man: The ttm resource_manager whose LRU lists to iterate over. + * @ctx: The ttm_operation_ctx to govern the locking. + * + * Initialize a struct ttm_bo_lru_cursor. Currently only trylocking + * or prelocked buffer objects are available as detailed by + * @ctx::resv and @ctx::allow_res_evict. Ticketlocking is not + * supported. + * + * Return: Pointer to @curs. The function does not fail. + */ +struct ttm_bo_lru_cursor * +ttm_bo_lru_cursor_init(struct ttm_bo_lru_cursor *curs, + struct ttm_resource_manager *man, + struct ttm_operation_ctx *ctx) +{ + memset(curs, 0, sizeof(*curs)); + ttm_resource_cursor_init(&curs->res_curs, man); + curs->ctx = ctx; + + return curs; +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_init); + +static struct ttm_buffer_object * +ttm_bo_from_res_reserved(struct ttm_resource *res, struct ttm_bo_lru_cursor *curs) +{ + struct ttm_buffer_object *bo = res->bo; + + if (!ttm_lru_walk_trylock(curs->ctx, bo, &curs->needs_unlock)) + return NULL; + + if (!ttm_bo_get_unless_zero(bo)) { + if (curs->needs_unlock) + dma_resv_unlock(bo->base.resv); + return NULL; + } + + curs->bo = bo; + return bo; +} + +/** + * ttm_bo_lru_cursor_next() - Continue iterating a manager's LRU lists + * to find and lock buffer object. + * @curs: The cursor initialized using ttm_bo_lru_cursor_init() and + * ttm_bo_lru_cursor_first(). + * + * Return: A pointer to a locked and reference-counted buffer object, + * or NULL if none could be found and looping should be terminated. + */ +struct ttm_buffer_object *ttm_bo_lru_cursor_next(struct ttm_bo_lru_cursor *curs) +{ + spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock; + struct ttm_resource *res = NULL; + struct ttm_buffer_object *bo; + + ttm_bo_lru_cursor_cleanup_bo(curs); + + spin_lock(lru_lock); + for (;;) { + res = ttm_resource_manager_next(&curs->res_curs); + if (!res) + break; + + bo = ttm_bo_from_res_reserved(res, curs); + if (bo) + break; + } + + spin_unlock(lru_lock); + return res ? bo : NULL; +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_next); + +/** + * ttm_bo_lru_cursor_first() - Start iterating a manager's LRU lists + * to find and lock buffer object. + * @curs: The cursor initialized using ttm_bo_lru_cursor_init(). + * + * Return: A pointer to a locked and reference-counted buffer object, + * or NULL if none could be found and looping should be terminated. + */ +struct ttm_buffer_object *ttm_bo_lru_cursor_first(struct ttm_bo_lru_cursor *curs) +{ + spinlock_t *lru_lock = &curs->res_curs.man->bdev->lru_lock; + struct ttm_buffer_object *bo; + struct ttm_resource *res; + + spin_lock(lru_lock); + res = ttm_resource_manager_first(&curs->res_curs); + if (!res) { + spin_unlock(lru_lock); + return NULL; + } + + bo = ttm_bo_from_res_reserved(res, curs); + spin_unlock(lru_lock); + + return bo ? bo : ttm_bo_lru_cursor_next(curs); +} +EXPORT_SYMBOL(ttm_bo_lru_cursor_first); + +/** + * ttm_bo_shrink() - Helper to shrink a ttm buffer object. + * @ctx: The struct ttm_operation_ctx used for the shrinking operation. + * @bo: The buffer object. + * @flags: Flags governing the shrinking behaviour. + * + * The function uses the ttm_tt_back_up functionality to back up or + * purge a struct ttm_tt. If the bo is not in system, it's first + * moved there. + * + * Return: The number of pages shrunken or purged, or + * negative error code on failure. + */ +long ttm_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, + const struct ttm_bo_shrink_flags flags) +{ + static const struct ttm_place sys_placement_flags = { + .fpfn = 0, + .lpfn = 0, + .mem_type = TTM_PL_SYSTEM, + .flags = 0, + }; + static struct ttm_placement sys_placement = { + .num_placement = 1, + .placement = &sys_placement_flags, + }; + struct ttm_tt *tt = bo->ttm; + long lret; + + dma_resv_assert_held(bo->base.resv); + + if (flags.allow_move && bo->resource->mem_type != TTM_PL_SYSTEM) { + int ret = ttm_bo_validate(bo, &sys_placement, ctx); + + /* Consider -ENOMEM and -ENOSPC non-fatal. */ + if (ret) { + if (ret == -ENOMEM || ret == -ENOSPC) + ret = -EBUSY; + return ret; + } + } + + ttm_bo_unmap_virtual(bo); + lret = ttm_bo_wait_ctx(bo, ctx); + if (lret < 0) + return lret; + + if (bo->bulk_move) { + spin_lock(&bo->bdev->lru_lock); + ttm_resource_del_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); + } + + lret = ttm_tt_backup(bo->bdev, tt, (struct ttm_backup_flags) + {.purge = flags.purge, + .writeback = flags.writeback}); + + if (lret <= 0 && bo->bulk_move) { + spin_lock(&bo->bdev->lru_lock); + ttm_resource_add_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); + } + + if (lret < 0 && lret != -EINTR) + return -EBUSY; + + return lret; +} +EXPORT_SYMBOL(ttm_bo_shrink); + +/** + * ttm_bo_shrink_suitable() - Whether a bo is suitable for shinking + * @ctx: The struct ttm_operation_ctx governing the shrinking. + * @bo: The candidate for shrinking. + * + * Check whether the object, given the information available to TTM, + * is suitable for shinking, This function can and should be used + * before attempting to shrink an object. + * + * Return: true if suitable. false if not. + */ +bool ttm_bo_shrink_suitable(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) +{ + return bo->ttm && ttm_tt_is_populated(bo->ttm) && !bo->pin_count && + (!ctx->no_wait_gpu || + dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP)); +} +EXPORT_SYMBOL(ttm_bo_shrink_suitable); + +/** + * ttm_bo_shrink_avoid_wait() - Whether to avoid waiting for GPU + * during shrinking + * + * In some situations, like direct reclaim, waiting (in particular gpu waiting) + * should be avoided since it may stall a system that could otherwise make progress + * shrinking something else less time consuming. + * + * Return: true if gpu waiting should be avoided, false if not. + */ +bool ttm_bo_shrink_avoid_wait(void) +{ + return !current_is_kswapd(); +} +EXPORT_SYMBOL(ttm_bo_shrink_avoid_wait); diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index c9eba76d5143..83b10706ba89 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -41,12 +41,20 @@ #include <asm/set_memory.h> #endif +#include <drm/ttm/ttm_backup.h> #include <drm/ttm/ttm_pool.h> #include <drm/ttm/ttm_tt.h> #include <drm/ttm/ttm_bo.h> #include "ttm_module.h" +#ifdef CONFIG_FAULT_INJECTION +#include <linux/fault-inject.h> +static DECLARE_FAULT_ATTR(backup_fault_inject); +#else +#define should_fail(...) false +#endif + /** * struct ttm_pool_dma - Helper object for coherent DMA mappings * @@ -75,6 +83,35 @@ struct ttm_pool_alloc_state { enum ttm_caching tt_caching; }; +/** + * struct ttm_pool_tt_restore - State representing restore from backup + * @pool: The pool used for page allocation while restoring. + * @snapshot_alloc: A snapshot of the most recent struct ttm_pool_alloc_state. + * @alloced_page: Pointer to the page most recently allocated from a pool or system. + * @first_dma: The dma address corresponding to @alloced_page if dma_mapping + * is requested. + * @alloced_pages: The number of allocated pages present in the struct ttm_tt + * page vector from this restore session. + * @restored_pages: The number of 4K pages restored for @alloced_page (which + * is typically a multi-order page). + * @page_caching: The struct ttm_tt requested caching + * @order: The order of @alloced_page. + * + * Recovery from backup might fail when we've recovered less than the + * full ttm_tt. In order not to loose any data (yet), keep information + * around that allows us to restart a failed ttm backup recovery. + */ +struct ttm_pool_tt_restore { + struct ttm_pool *pool; + struct ttm_pool_alloc_state snapshot_alloc; + struct page *alloced_page; + dma_addr_t first_dma; + pgoff_t alloced_pages; + pgoff_t restored_pages; + enum ttm_caching page_caching; + unsigned int order; +}; + static unsigned long page_pool_size; MODULE_PARM_DESC(page_pool_size, "Number of pages in the WC/UC/DMA pool"); @@ -199,12 +236,11 @@ static int ttm_pool_apply_caching(struct ttm_pool_alloc_state *alloc) return 0; } -/* Map pages of 1 << order size and fill the DMA address array */ +/* DMA Map pages of 1 << order size and return the resulting dma_address. */ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order, - struct page *p, dma_addr_t **dma_addr) + struct page *p, dma_addr_t *dma_addr) { dma_addr_t addr; - unsigned int i; if (pool->use_dma_alloc) { struct ttm_pool_dma *dma = (void *)p->private; @@ -218,10 +254,7 @@ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order, return -EFAULT; } - for (i = 1 << order; i ; --i) { - *(*dma_addr)++ = addr; - addr += PAGE_SIZE; - } + *dma_addr = addr; return 0; } @@ -372,6 +405,196 @@ static unsigned int ttm_pool_page_order(struct ttm_pool *pool, struct page *p) } /* + * Split larger pages so that we can free each PAGE_SIZE page as soon + * as it has been backed up, in order to avoid memory pressure during + * reclaim. + */ +static void ttm_pool_split_for_swap(struct ttm_pool *pool, struct page *p) +{ + unsigned int order = ttm_pool_page_order(pool, p); + pgoff_t nr; + + if (!order) + return; + + split_page(p, order); + nr = 1UL << order; + while (nr--) + (p++)->private = 0; +} + +/** + * DOC: Partial backup and restoration of a struct ttm_tt. + * + * Swapout using ttm_backup_backup_page() and swapin using + * ttm_backup_copy_page() may fail. + * The former most likely due to lack of swap-space or memory, the latter due + * to lack of memory or because of signal interruption during waits. + * + * Backup failure is easily handled by using a ttm_tt pages vector that holds + * both backup handles and page pointers. This has to be taken into account when + * restoring such a ttm_tt from backup, and when freeing it while backed up. + * When restoring, for simplicity, new pages are actually allocated from the + * pool and the contents of any old pages are copied in and then the old pages + * are released. + * + * For restoration failures, the struct ttm_pool_tt_restore holds sufficient state + * to be able to resume an interrupted restore, and that structure is freed once + * the restoration is complete. If the struct ttm_tt is destroyed while there + * is a valid struct ttm_pool_tt_restore attached, that is also properly taken + * care of. + */ + +/* Is restore ongoing for the currently allocated page? */ +static bool ttm_pool_restore_valid(const struct ttm_pool_tt_restore *restore) +{ + return restore && restore->restored_pages < (1 << restore->order); +} + +/* DMA unmap and free a multi-order page, either to the relevant pool or to system. */ +static pgoff_t ttm_pool_unmap_and_free(struct ttm_pool *pool, struct page *page, + const dma_addr_t *dma_addr, enum ttm_caching caching) +{ + struct ttm_pool_type *pt = NULL; + unsigned int order; + pgoff_t nr; + + if (pool) { + order = ttm_pool_page_order(pool, page); + nr = (1UL << order); + if (dma_addr) + ttm_pool_unmap(pool, *dma_addr, nr); + + pt = ttm_pool_select_type(pool, caching, order); + } else { + order = page->private; + nr = (1UL << order); + } + + if (pt) + ttm_pool_type_give(pt, page); + else + ttm_pool_free_page(pool, caching, order, page); + + return nr; +} + +/* Populate the page-array using the most recent allocated multi-order page. */ +static void ttm_pool_allocated_page_commit(struct page *allocated, + dma_addr_t first_dma, + struct ttm_pool_alloc_state *alloc, + pgoff_t nr) +{ + pgoff_t i; + + for (i = 0; i < nr; ++i) + *alloc->pages++ = allocated++; + + alloc->remaining_pages -= nr; + + if (!alloc->dma_addr) + return; + + for (i = 0; i < nr; ++i) { + *alloc->dma_addr++ = first_dma; + first_dma += PAGE_SIZE; + } +} + +/* + * When restoring, restore backed-up content to the newly allocated page and + * if successful, populate the page-table and dma-address arrays. + */ +static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore, + struct ttm_backup *backup, + const struct ttm_operation_ctx *ctx, + struct ttm_pool_alloc_state *alloc) + +{ + pgoff_t i, nr = 1UL << restore->order; + struct page **first_page = alloc->pages; + struct page *p; + int ret = 0; + + for (i = restore->restored_pages; i < nr; ++i) { + p = first_page[i]; + if (ttm_backup_page_ptr_is_handle(p)) { + unsigned long handle = ttm_backup_page_ptr_to_handle(p); + + if (IS_ENABLED(CONFIG_FAULT_INJECTION) && ctx->interruptible && + should_fail(&backup_fault_inject, 1)) { + ret = -EINTR; + break; + } + + if (handle == 0) { + restore->restored_pages++; + continue; + } + + ret = ttm_backup_copy_page(backup, restore->alloced_page + i, + handle, ctx->interruptible); + if (ret) + break; + + ttm_backup_drop(backup, handle); + } else if (p) { + /* + * We could probably avoid splitting the old page + * using clever logic, but ATM we don't care, as + * we prioritize releasing memory ASAP. Note that + * here, the old retained page is always write-back + * cached. + */ + ttm_pool_split_for_swap(restore->pool, p); + copy_highpage(restore->alloced_page + i, p); + __free_pages(p, 0); + } + + restore->restored_pages++; + first_page[i] = ttm_backup_handle_to_page_ptr(0); + } + + if (ret) { + if (!restore->restored_pages) { + dma_addr_t *dma_addr = alloc->dma_addr ? &restore->first_dma : NULL; + + ttm_pool_unmap_and_free(restore->pool, restore->alloced_page, + dma_addr, restore->page_caching); + restore->restored_pages = nr; + } + return ret; + } + + ttm_pool_allocated_page_commit(restore->alloced_page, restore->first_dma, + alloc, nr); + if (restore->page_caching == alloc->tt_caching || PageHighMem(restore->alloced_page)) + alloc->caching_divide = alloc->pages; + restore->snapshot_alloc = *alloc; + restore->alloced_pages += nr; + + return 0; +} + +/* If restoring, save information needed for ttm_pool_restore_commit(). */ +static void +ttm_pool_page_allocated_restore(struct ttm_pool *pool, unsigned int order, + struct page *p, + enum ttm_caching page_caching, + dma_addr_t first_dma, + struct ttm_pool_tt_restore *restore, + const struct ttm_pool_alloc_state *alloc) +{ + restore->pool = pool; + restore->order = order; + restore->restored_pages = 0; + restore->page_caching = page_caching; + restore->first_dma = first_dma; + restore->alloced_page = p; + restore->snapshot_alloc = *alloc; +} + +/* * Called when we got a page, either from a pool or newly allocated. * if needed, dma map the page and populate the dma address array. * Populate the page address array. @@ -380,10 +603,11 @@ static unsigned int ttm_pool_page_order(struct ttm_pool *pool, struct page *p) */ static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order, struct page *p, enum ttm_caching page_caching, - struct ttm_pool_alloc_state *alloc) + struct ttm_pool_alloc_state *alloc, + struct ttm_pool_tt_restore *restore) { - pgoff_t i, nr = 1UL << order; bool caching_consistent; + dma_addr_t first_dma; int r = 0; caching_consistent = (page_caching == alloc->tt_caching) || PageHighMem(p); @@ -395,17 +619,20 @@ static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order, } if (alloc->dma_addr) { - r = ttm_pool_map(pool, order, p, &alloc->dma_addr); + r = ttm_pool_map(pool, order, p, &first_dma); if (r) return r; } - alloc->remaining_pages -= nr; - for (i = 0; i < nr; ++i) - *alloc->pages++ = p++; + if (restore) { + ttm_pool_page_allocated_restore(pool, order, p, page_caching, + first_dma, restore, alloc); + } else { + ttm_pool_allocated_page_commit(p, first_dma, alloc, 1UL << order); - if (caching_consistent) - alloc->caching_divide = alloc->pages; + if (caching_consistent) + alloc->caching_divide = alloc->pages; + } return 0; } @@ -428,22 +655,24 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt, pgoff_t start_page, pgoff_t end_page) { struct page **pages = &tt->pages[start_page]; - unsigned int order; + struct ttm_backup *backup = tt->backup; pgoff_t i, nr; for (i = start_page; i < end_page; i += nr, pages += nr) { - struct ttm_pool_type *pt = NULL; + struct page *p = *pages; - order = ttm_pool_page_order(pool, *pages); - nr = (1UL << order); - if (tt->dma_address) - ttm_pool_unmap(pool, tt->dma_address[i], nr); + nr = 1; + if (ttm_backup_page_ptr_is_handle(p)) { + unsigned long handle = ttm_backup_page_ptr_to_handle(p); - pt = ttm_pool_select_type(pool, caching, order); - if (pt) - ttm_pool_type_give(pt, *pages); - else - ttm_pool_free_page(pool, caching, order, *pages); + if (handle != 0) + ttm_backup_drop(backup, handle); + } else if (p) { + dma_addr_t *dma_addr = tt->dma_address ? + tt->dma_address + i : NULL; + + nr = ttm_pool_unmap_and_free(pool, p, dma_addr, caching); + } } } @@ -467,22 +696,11 @@ static unsigned int ttm_pool_alloc_find_order(unsigned int highest, return min_t(unsigned int, highest, __fls(alloc->remaining_pages)); } -/** - * ttm_pool_alloc - Fill a ttm_tt object - * - * @pool: ttm_pool to use - * @tt: ttm_tt object to fill - * @ctx: operation context - * - * Fill the ttm_tt object with pages and also make sure to DMA map them when - * necessary. - * - * Returns: 0 on successe, negative error code otherwise. - */ -int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, - struct ttm_operation_ctx *ctx) +static int __ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx, + struct ttm_pool_alloc_state *alloc, + struct ttm_pool_tt_restore *restore) { - struct ttm_pool_alloc_state alloc; enum ttm_caching page_caching; gfp_t gfp_flags = GFP_USER; pgoff_t caching_divide; @@ -491,10 +709,8 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, struct page *p; int r; - ttm_pool_alloc_state_init(tt, &alloc); - - WARN_ON(!alloc.remaining_pages || ttm_tt_is_populated(tt)); - WARN_ON(alloc.dma_addr && !pool->dev); + WARN_ON(!alloc->remaining_pages || ttm_tt_is_populated(tt)); + WARN_ON(alloc->dma_addr && !pool->dev); if (tt->page_flags & TTM_TT_FLAG_ZERO_ALLOC) gfp_flags |= __GFP_ZERO; @@ -509,9 +725,9 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, page_caching = tt->caching; allow_pools = true; - for (order = ttm_pool_alloc_find_order(MAX_PAGE_ORDER, &alloc); - alloc.remaining_pages; - order = ttm_pool_alloc_find_order(order, &alloc)) { + for (order = ttm_pool_alloc_find_order(MAX_PAGE_ORDER, alloc); + alloc->remaining_pages; + order = ttm_pool_alloc_find_order(order, alloc)) { struct ttm_pool_type *pt; /* First, try to allocate a page from a pool if one exists. */ @@ -541,31 +757,121 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, r = -ENOMEM; goto error_free_all; } - r = ttm_pool_page_allocated(pool, order, p, page_caching, &alloc); + r = ttm_pool_page_allocated(pool, order, p, page_caching, alloc, + restore); if (r) goto error_free_page; + + if (ttm_pool_restore_valid(restore)) { + r = ttm_pool_restore_commit(restore, tt->backup, ctx, alloc); + if (r) + goto error_free_all; + } } - r = ttm_pool_apply_caching(&alloc); + r = ttm_pool_apply_caching(alloc); if (r) goto error_free_all; + kfree(tt->restore); + tt->restore = NULL; + return 0; error_free_page: ttm_pool_free_page(pool, page_caching, order, p); error_free_all: - caching_divide = alloc.caching_divide - tt->pages; + if (tt->restore) + return r; + + caching_divide = alloc->caching_divide - tt->pages; ttm_pool_free_range(pool, tt, tt->caching, 0, caching_divide); ttm_pool_free_range(pool, tt, ttm_cached, caching_divide, - tt->num_pages - alloc.remaining_pages); + tt->num_pages - alloc->remaining_pages); return r; } + +/** + * ttm_pool_alloc - Fill a ttm_tt object + * + * @pool: ttm_pool to use + * @tt: ttm_tt object to fill + * @ctx: operation context + * + * Fill the ttm_tt object with pages and also make sure to DMA map them when + * necessary. + * + * Returns: 0 on successe, negative error code otherwise. + */ +int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + struct ttm_operation_ctx *ctx) +{ + struct ttm_pool_alloc_state alloc; + + if (WARN_ON(ttm_tt_is_backed_up(tt))) + return -EINVAL; + + ttm_pool_alloc_state_init(tt, &alloc); + + return __ttm_pool_alloc(pool, tt, ctx, &alloc, NULL); +} EXPORT_SYMBOL(ttm_pool_alloc); /** + * ttm_pool_restore_and_alloc - Fill a ttm_tt, restoring previously backed-up + * content. + * + * @pool: ttm_pool to use + * @tt: ttm_tt object to fill + * @ctx: operation context + * + * Fill the ttm_tt object with pages and also make sure to DMA map them when + * necessary. Read in backed-up content. + * + * Returns: 0 on successe, negative error code otherwise. + */ +int ttm_pool_restore_and_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx) +{ + struct ttm_pool_alloc_state alloc; + + if (WARN_ON(!ttm_tt_is_backed_up(tt))) + return -EINVAL; + + if (!tt->restore) { + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + + ttm_pool_alloc_state_init(tt, &alloc); + if (ctx->gfp_retry_mayfail) + gfp |= __GFP_RETRY_MAYFAIL; + + tt->restore = kzalloc(sizeof(*tt->restore), gfp); + if (!tt->restore) + return -ENOMEM; + + tt->restore->snapshot_alloc = alloc; + tt->restore->pool = pool; + tt->restore->restored_pages = 1; + } else { + struct ttm_pool_tt_restore *restore = tt->restore; + int ret; + + alloc = restore->snapshot_alloc; + if (ttm_pool_restore_valid(tt->restore)) { + ret = ttm_pool_restore_commit(restore, tt->backup, ctx, &alloc); + if (ret) + return ret; + } + if (!alloc.remaining_pages) + return 0; + } + + return __ttm_pool_alloc(pool, tt, ctx, &alloc, tt->restore); +} + +/** * ttm_pool_free - Free the backing pages from a ttm_tt object * * @pool: Pool to give pages back to. @@ -583,6 +889,169 @@ void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt) EXPORT_SYMBOL(ttm_pool_free); /** + * ttm_pool_drop_backed_up() - Release content of a swapped-out struct ttm_tt + * @tt: The struct ttm_tt. + * + * Release handles with associated content or any remaining pages of + * a backed-up struct ttm_tt. + */ +void ttm_pool_drop_backed_up(struct ttm_tt *tt) +{ + struct ttm_pool_tt_restore *restore; + pgoff_t start_page = 0; + + WARN_ON(!ttm_tt_is_backed_up(tt)); + + restore = tt->restore; + + /* + * Unmap and free any uncommitted restore page. + * any tt page-array backup entries already read back has + * been cleared already + */ + if (ttm_pool_restore_valid(restore)) { + dma_addr_t *dma_addr = tt->dma_address ? &restore->first_dma : NULL; + + ttm_pool_unmap_and_free(restore->pool, restore->alloced_page, + dma_addr, restore->page_caching); + restore->restored_pages = 1UL << restore->order; + } + + /* + * If a restore is ongoing, part of the tt pages may have a + * caching different than writeback. + */ + if (restore) { + pgoff_t mid = restore->snapshot_alloc.caching_divide - tt->pages; + + start_page = restore->alloced_pages; + WARN_ON(mid > start_page); + /* Pages that might be dma-mapped and non-cached */ + ttm_pool_free_range(restore->pool, tt, tt->caching, + 0, mid); + /* Pages that might be dma-mapped but cached */ + ttm_pool_free_range(restore->pool, tt, ttm_cached, + mid, restore->alloced_pages); + kfree(restore); + tt->restore = NULL; + } + + ttm_pool_free_range(NULL, tt, ttm_cached, start_page, tt->num_pages); +} + +/** + * ttm_pool_backup() - Back up or purge a struct ttm_tt + * @pool: The pool used when allocating the struct ttm_tt. + * @tt: The struct ttm_tt. + * @flags: Flags to govern the backup behaviour. + * + * Back up or purge a struct ttm_tt. If @purge is true, then + * all pages will be freed directly to the system rather than to the pool + * they were allocated from, making the function behave similarly to + * ttm_pool_free(). If @purge is false the pages will be backed up instead, + * exchanged for handles. + * A subsequent call to ttm_pool_restore_and_alloc() will then read back the content and + * a subsequent call to ttm_pool_drop_backed_up() will drop it. + * If backup of a page fails for whatever reason, @ttm will still be + * partially backed up, retaining those pages for which backup fails. + * In that case, this function can be retried, possibly after freeing up + * memory resources. + * + * Return: Number of pages actually backed up or freed, or negative + * error code on error. + */ +long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_backup_flags *flags) +{ + struct ttm_backup *backup = tt->backup; + struct page *page; + unsigned long handle; + gfp_t alloc_gfp; + gfp_t gfp; + int ret = 0; + pgoff_t shrunken = 0; + pgoff_t i, num_pages; + + if (WARN_ON(ttm_tt_is_backed_up(tt))) + return -EINVAL; + + if ((!ttm_backup_bytes_avail() && !flags->purge) || + pool->use_dma_alloc || ttm_tt_is_backed_up(tt)) + return -EBUSY; + +#ifdef CONFIG_X86 + /* Anything returned to the system needs to be cached. */ + if (tt->caching != ttm_cached) + set_pages_array_wb(tt->pages, tt->num_pages); +#endif + + if (tt->dma_address || flags->purge) { + for (i = 0; i < tt->num_pages; i += num_pages) { + unsigned int order; + + page = tt->pages[i]; + if (unlikely(!page)) { + num_pages = 1; + continue; + } + + order = ttm_pool_page_order(pool, page); + num_pages = 1UL << order; + if (tt->dma_address) + ttm_pool_unmap(pool, tt->dma_address[i], + num_pages); + if (flags->purge) { + shrunken += num_pages; + page->private = 0; + __free_pages(page, order); + memset(tt->pages + i, 0, + num_pages * sizeof(*tt->pages)); + } + } + } + + if (flags->purge) + return shrunken; + + if (pool->use_dma32) + gfp = GFP_DMA32; + else + gfp = GFP_HIGHUSER; + + alloc_gfp = GFP_KERNEL | __GFP_HIGH | __GFP_NOWARN | __GFP_RETRY_MAYFAIL; + + num_pages = tt->num_pages; + + /* Pretend doing fault injection by shrinking only half of the pages. */ + if (IS_ENABLED(CONFIG_FAULT_INJECTION) && should_fail(&backup_fault_inject, 1)) + num_pages = DIV_ROUND_UP(num_pages, 2); + + for (i = 0; i < num_pages; ++i) { + s64 shandle; + + page = tt->pages[i]; + if (unlikely(!page)) + continue; + + ttm_pool_split_for_swap(pool, page); + + shandle = ttm_backup_backup_page(backup, page, flags->writeback, i, + gfp, alloc_gfp); + if (shandle < 0) { + /* We allow partially shrunken tts */ + ret = shandle; + break; + } + handle = shandle; + tt->pages[i] = ttm_backup_handle_to_page_ptr(handle); + put_page(page); + shrunken++; + } + + return shrunken ? shrunken : ret; +} + +/** * ttm_pool_init - Initialize a pool * * @pool: the pool to initialize @@ -843,6 +1312,10 @@ int ttm_pool_mgr_init(unsigned long num_pages) &ttm_pool_debugfs_globals_fops); debugfs_create_file("page_pool_shrink", 0400, ttm_debugfs_root, NULL, &ttm_pool_debugfs_shrink_fops); +#ifdef CONFIG_FAULT_INJECTION + fault_create_debugfs_attr("backup_fault_inject", ttm_debugfs_root, + &backup_fault_inject); +#endif #endif mm_shrinker = shrinker_alloc(0, "drm-ttm_pool"); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 3baf215eca23..df0aa6c4b8b8 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -40,6 +40,7 @@ #include <drm/drm_cache.h> #include <drm/drm_device.h> #include <drm/drm_util.h> +#include <drm/ttm/ttm_backup.h> #include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_tt.h> @@ -158,6 +159,8 @@ static void ttm_tt_init_fields(struct ttm_tt *ttm, ttm->swap_storage = NULL; ttm->sg = bo->sg; ttm->caching = caching; + ttm->restore = NULL; + ttm->backup = NULL; } int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, @@ -182,6 +185,13 @@ void ttm_tt_fini(struct ttm_tt *ttm) fput(ttm->swap_storage); ttm->swap_storage = NULL; + if (ttm_tt_is_backed_up(ttm)) + ttm_pool_drop_backed_up(ttm); + if (ttm->backup) { + ttm_backup_fini(ttm->backup); + ttm->backup = NULL; + } + if (ttm->pages) kvfree(ttm->pages); else @@ -254,6 +264,49 @@ out_err: EXPORT_SYMBOL_FOR_TESTS_ONLY(ttm_tt_swapin); /** + * ttm_tt_backup() - Helper to back up a struct ttm_tt. + * @bdev: The TTM device. + * @tt: The struct ttm_tt. + * @flags: Flags that govern the backup behaviour. + * + * Update the page accounting and call ttm_pool_shrink_tt to free pages + * or back them up. + * + * Return: Number of pages freed or swapped out, or negative error code on + * error. + */ +long ttm_tt_backup(struct ttm_device *bdev, struct ttm_tt *tt, + const struct ttm_backup_flags flags) +{ + long ret; + + if (WARN_ON(IS_ERR_OR_NULL(tt->backup))) + return 0; + + ret = ttm_pool_backup(&bdev->pool, tt, &flags); + if (ret > 0) { + tt->page_flags &= ~TTM_TT_FLAG_PRIV_POPULATED; + tt->page_flags |= TTM_TT_FLAG_BACKED_UP; + } + + return ret; +} + +int ttm_tt_restore(struct ttm_device *bdev, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx) +{ + int ret = ttm_pool_restore_and_alloc(&bdev->pool, tt, ctx); + + if (ret) + return ret; + + tt->page_flags &= ~TTM_TT_FLAG_BACKED_UP; + + return 0; +} +EXPORT_SYMBOL(ttm_tt_restore); + +/** * ttm_tt_swapout - swap out tt object * * @bdev: TTM device structure. @@ -348,6 +401,7 @@ int ttm_tt_populate(struct ttm_device *bdev, goto error; ttm->page_flags |= TTM_TT_FLAG_PRIV_POPULATED; + ttm->page_flags &= ~TTM_TT_FLAG_BACKED_UP; if (unlikely(ttm->page_flags & TTM_TT_FLAG_SWAPPED)) { ret = ttm_tt_swapin(ttm); if (unlikely(ret != 0)) { @@ -477,3 +531,32 @@ unsigned long ttm_tt_pages_limit(void) return ttm_pages_limit; } EXPORT_SYMBOL(ttm_tt_pages_limit); + +/** + * ttm_tt_setup_backup() - Allocate and assign a backup structure for a ttm_tt + * @tt: The ttm_tt for wich to allocate and assign a backup structure. + * + * Assign a backup structure to be used for tt backup. This should + * typically be done at bo creation, to avoid allocations at shrinking + * time. + * + * Return: 0 on success, negative error code on failure. + */ +int ttm_tt_setup_backup(struct ttm_tt *tt) +{ + struct ttm_backup *backup = + ttm_backup_shmem_create(((loff_t)tt->num_pages) << PAGE_SHIFT); + + if (WARN_ON_ONCE(!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE))) + return -EINVAL; + + if (IS_ERR(backup)) + return PTR_ERR(backup); + + if (tt->backup) + ttm_backup_fini(tt->backup); + + tt->backup = backup; + return 0; +} +EXPORT_SYMBOL(ttm_tt_setup_backup); diff --git a/drivers/gpu/drm/vboxvideo/hgsmi_base.c b/drivers/gpu/drm/vboxvideo/hgsmi_base.c index 87dccaecc3e5..db994aeaa0f9 100644 --- a/drivers/gpu/drm/vboxvideo/hgsmi_base.c +++ b/drivers/gpu/drm/vboxvideo/hgsmi_base.c @@ -181,40 +181,3 @@ int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, return rc; } - -/** - * hgsmi_cursor_position - Report the guest cursor position. The host may - * wish to use this information to re-position its - * own cursor (though this is currently unlikely). - * The current host cursor position is returned. - * Return: 0 or negative errno value. - * @ctx: The context containing the heap used. - * @report_position: Are we reporting a position? - * @x: Guest cursor X position. - * @y: Guest cursor Y position. - * @x_host: Host cursor X position is stored here. Optional. - * @y_host: Host cursor Y position is stored here. Optional. - */ -int hgsmi_cursor_position(struct gen_pool *ctx, bool report_position, - u32 x, u32 y, u32 *x_host, u32 *y_host) -{ - struct vbva_cursor_position *p; - - p = hgsmi_buffer_alloc(ctx, sizeof(*p), HGSMI_CH_VBVA, - VBVA_CURSOR_POSITION); - if (!p) - return -ENOMEM; - - p->report_position = report_position; - p->x = x; - p->y = y; - - hgsmi_buffer_submit(ctx, p); - - *x_host = p->x; - *y_host = p->y; - - hgsmi_buffer_free(ctx, p); - - return 0; -} diff --git a/drivers/gpu/drm/vboxvideo/vboxvideo_guest.h b/drivers/gpu/drm/vboxvideo/vboxvideo_guest.h index 55fcee3a6470..643c4448bdcb 100644 --- a/drivers/gpu/drm/vboxvideo/vboxvideo_guest.h +++ b/drivers/gpu/drm/vboxvideo/vboxvideo_guest.h @@ -34,8 +34,6 @@ int hgsmi_query_conf(struct gen_pool *ctx, u32 index, u32 *value_ret); int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, u32 hot_x, u32 hot_y, u32 width, u32 height, u8 *pixels, u32 len); -int hgsmi_cursor_position(struct gen_pool *ctx, bool report_position, - u32 x, u32 y, u32 *x_host, u32 *y_host); bool vbva_enable(struct vbva_buf_ctx *vbva_ctx, struct gen_pool *ctx, struct vbva_buffer *vbva, s32 screen); diff --git a/drivers/gpu/drm/vc4/tests/vc4_test_pv_muxing.c b/drivers/gpu/drm/vc4/tests/vc4_test_pv_muxing.c index 40a05869a50e..992e8f5c5c6e 100644 --- a/drivers/gpu/drm/vc4/tests/vc4_test_pv_muxing.c +++ b/drivers/gpu/drm/vc4/tests/vc4_test_pv_muxing.c @@ -724,7 +724,7 @@ static void drm_vc4_test_pv_muxing_invalid(struct kunit *test) static int vc4_pv_muxing_test_init(struct kunit *test) { const struct pv_muxing_param *params = test->param_value; - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct pv_muxing_priv *priv; struct drm_device *drm; struct vc4_dev *vc4; @@ -737,13 +737,15 @@ static int vc4_pv_muxing_test_init(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vc4); priv->vc4 = vc4; - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); drm = &vc4->base; - priv->state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + priv->state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->state); + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + return 0; } @@ -782,7 +784,7 @@ static struct kunit_suite vc5_pv_muxing_test_suite = { */ static void drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable(struct kunit *test) { - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_atomic_state *state; struct vc4_crtc_state *new_vc4_crtc_state; struct vc4_hvs_state *new_hvs_state; @@ -795,11 +797,10 @@ static void drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable(struct kunit *tes vc4 = vc5_mock_device(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vc4); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); drm = &vc4->base; - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); ret = vc4_mock_atomic_add_output(test, state, VC4_ENCODER_TYPE_HDMI0); @@ -822,7 +823,7 @@ static void drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable(struct kunit *tes ret = drm_atomic_helper_swap_state(state, false); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); ret = vc4_mock_atomic_add_output(test, state, VC4_ENCODER_TYPE_HDMI1); @@ -843,6 +844,9 @@ static void drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable(struct kunit *tes KUNIT_ASSERT_TRUE(test, new_hvs_state->fifo_state[hdmi1_channel].in_use); KUNIT_EXPECT_NE(test, hdmi0_channel, hdmi1_channel); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -854,7 +858,7 @@ static void drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable(struct kunit *tes */ static void drm_test_vc5_pv_muxing_bugs_stable_fifo(struct kunit *test) { - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_atomic_state *state; struct vc4_crtc_state *new_vc4_crtc_state; struct vc4_hvs_state *new_hvs_state; @@ -867,11 +871,10 @@ static void drm_test_vc5_pv_muxing_bugs_stable_fifo(struct kunit *test) vc4 = vc5_mock_device(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vc4); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); drm = &vc4->base; - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); ret = vc4_mock_atomic_add_output(test, state, VC4_ENCODER_TYPE_HDMI0); @@ -905,7 +908,7 @@ static void drm_test_vc5_pv_muxing_bugs_stable_fifo(struct kunit *test) ret = drm_atomic_helper_swap_state(state, false); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); ret = vc4_mock_atomic_del_output(test, state, VC4_ENCODER_TYPE_HDMI0); @@ -929,6 +932,9 @@ static void drm_test_vc5_pv_muxing_bugs_stable_fifo(struct kunit *test) KUNIT_EXPECT_EQ(test, old_hdmi1_channel, hdmi1_channel); } + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } /* @@ -949,7 +955,7 @@ static void drm_test_vc5_pv_muxing_bugs_stable_fifo(struct kunit *test) static void drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable_too_many_crtc_state(struct kunit *test) { - struct drm_modeset_acquire_ctx *ctx; + struct drm_modeset_acquire_ctx ctx; struct drm_atomic_state *state; struct vc4_crtc_state *new_vc4_crtc_state; struct drm_device *drm; @@ -959,11 +965,10 @@ drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable_too_many_crtc_state(struct ku vc4 = vc5_mock_device(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, vc4); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + drm_modeset_acquire_init(&ctx, 0); drm = &vc4->base; - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); ret = vc4_mock_atomic_add_output(test, state, VC4_ENCODER_TYPE_HDMI0); @@ -975,7 +980,7 @@ drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable_too_many_crtc_state(struct ku ret = drm_atomic_helper_swap_state(state, false); KUNIT_ASSERT_EQ(test, ret, 0); - state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); + state = drm_kunit_helper_atomic_state_alloc(test, drm, &ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); ret = vc4_mock_atomic_add_output(test, state, VC4_ENCODER_TYPE_HDMI1); @@ -987,6 +992,9 @@ drm_test_vc5_pv_muxing_bugs_subsequent_crtc_enable_too_many_crtc_state(struct ku new_vc4_crtc_state = get_vc4_crtc_state_for_encoder(test, state, VC4_ENCODER_TYPE_HDMI0); KUNIT_EXPECT_NULL(test, new_vc4_crtc_state); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); } static struct kunit_case vc5_pv_muxing_bugs_tests[] = { diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index e878eddc9c3f..37238a12baa5 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -2926,15 +2926,16 @@ static int vc5_hdmi_init_resources(struct drm_device *drm, struct resource *res; int ret; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hdmi"); - if (!res) - return -ENODEV; - - vc4_hdmi->hdmicore_regs = devm_ioremap(dev, res->start, - resource_size(res)); - if (!vc4_hdmi->hdmicore_regs) - return -ENOMEM; + vc4_hdmi->hdmicore_regs = devm_platform_ioremap_resource_byname(pdev, + "hdmi"); + if (IS_ERR(vc4_hdmi->hdmicore_regs)) + return PTR_ERR(vc4_hdmi->hdmicore_regs); + /* This is shared between both HDMI controllers. Cannot + * claim for both instances. Lets not convert to using + * devm_platform_ioremap_resource_byname() like + * the rest + */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "hd"); if (!res) return -ENODEV; @@ -2943,53 +2944,35 @@ static int vc5_hdmi_init_resources(struct drm_device *drm, if (!vc4_hdmi->hd_regs) return -ENOMEM; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cec"); - if (!res) - return -ENODEV; - - vc4_hdmi->cec_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!vc4_hdmi->cec_regs) - return -ENOMEM; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "csc"); - if (!res) - return -ENODEV; - - vc4_hdmi->csc_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!vc4_hdmi->csc_regs) - return -ENOMEM; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dvp"); - if (!res) - return -ENODEV; + vc4_hdmi->cec_regs = devm_platform_ioremap_resource_byname(pdev, + "cec"); + if (IS_ERR(vc4_hdmi->cec_regs)) + return PTR_ERR(vc4_hdmi->cec_regs); - vc4_hdmi->dvp_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!vc4_hdmi->dvp_regs) - return -ENOMEM; + vc4_hdmi->csc_regs = devm_platform_ioremap_resource_byname(pdev, + "csc"); + if (IS_ERR(vc4_hdmi->csc_regs)) + return PTR_ERR(vc4_hdmi->csc_regs); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "phy"); - if (!res) - return -ENODEV; + vc4_hdmi->dvp_regs = devm_platform_ioremap_resource_byname(pdev, + "dvp"); + if (IS_ERR(vc4_hdmi->dvp_regs)) + return PTR_ERR(vc4_hdmi->dvp_regs); - vc4_hdmi->phy_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!vc4_hdmi->phy_regs) - return -ENOMEM; + vc4_hdmi->phy_regs = devm_platform_ioremap_resource_byname(pdev, + "phy"); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "packet"); - if (!res) - return -ENODEV; + if (IS_ERR(vc4_hdmi->phy_regs)) + return PTR_ERR(vc4_hdmi->phy_regs); - vc4_hdmi->ram_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!vc4_hdmi->ram_regs) - return -ENOMEM; + vc4_hdmi->ram_regs = devm_platform_ioremap_resource_byname(pdev, + "packet"); + if (IS_ERR(vc4_hdmi->ram_regs)) + return PTR_ERR(vc4_hdmi->ram_regs); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rm"); - if (!res) - return -ENODEV; - - vc4_hdmi->rm_regs = devm_ioremap(dev, res->start, resource_size(res)); - if (!vc4_hdmi->rm_regs) - return -ENOMEM; + vc4_hdmi->rm_regs = devm_platform_ioremap_resource_byname(pdev, "rm"); + if (IS_ERR(vc4_hdmi->rm_regs)) + return PTR_ERR(vc4_hdmi->rm_regs); vc4_hdmi->hsm_clock = devm_clk_get(dev, "hdmi"); if (IS_ERR(vc4_hdmi->hsm_clock)) { diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 75a79390a0e3..9699b08585f7 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -100,6 +100,7 @@ xe-y += xe_bb.o \ xe_rtp.o \ xe_sa.o \ xe_sched_job.o \ + xe_shrinker.o \ xe_step.o \ xe_survivability_mode.o \ xe_sync.o \ diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index 6795d1d916e4..9fde67ca989f 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -514,8 +514,13 @@ static int shrink_test_run_device(struct xe_device *xe) * other way around, they may not be subject to swapping... */ if (alloced < purgeable) { + xe_ttm_tt_account_subtract(&xe_tt->ttm); xe_tt->purgeable = true; + xe_ttm_tt_account_add(&xe_tt->ttm); bo->ttm.priority = 0; + spin_lock(&bo->ttm.bdev->lru_lock); + ttm_bo_move_to_lru_tail(&bo->ttm); + spin_unlock(&bo->ttm.bdev->lru_lock); } else { int ret = shrink_test_fill_random(bo, &prng, link); @@ -570,7 +575,6 @@ static int shrink_test_run_device(struct xe_device *xe) if (ret == -EINTR) intr = true; } while (ret == -EINTR && !signal_pending(current)); - if (!ret && !purgeable) failed = shrink_test_verify(test, bo, count, &prng, link); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 0c7a7f5e5596..64f9c936eea0 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -11,6 +11,7 @@ #include <drm/drm_drv.h> #include <drm/drm_gem_ttm_helper.h> #include <drm/drm_managed.h> +#include <drm/ttm/ttm_backup.h> #include <drm/ttm/ttm_device.h> #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_tt.h> @@ -29,6 +30,7 @@ #include "xe_preempt_fence.h" #include "xe_pxp.h" #include "xe_res_cursor.h" +#include "xe_shrinker.h" #include "xe_trace_bo.h" #include "xe_ttm_stolen_mgr.h" #include "xe_vm.h" @@ -315,9 +317,11 @@ static void xe_evict_flags(struct ttm_buffer_object *tbo, } } +/* struct xe_ttm_tt - Subclassed ttm_tt for xe */ struct xe_ttm_tt { struct ttm_tt ttm; - struct device *dev; + /** @xe - The xe device */ + struct xe_device *xe; struct sg_table sgt; struct sg_table *sg; /** @purgeable: Whether the content of the pages of @ttm is purgeable. */ @@ -330,7 +334,8 @@ static int xe_tt_map_sg(struct ttm_tt *tt) unsigned long num_pages = tt->num_pages; int ret; - XE_WARN_ON(tt->page_flags & TTM_TT_FLAG_EXTERNAL); + XE_WARN_ON((tt->page_flags & TTM_TT_FLAG_EXTERNAL) && + !(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)); if (xe_tt->sg) return 0; @@ -338,13 +343,13 @@ static int xe_tt_map_sg(struct ttm_tt *tt) ret = sg_alloc_table_from_pages_segment(&xe_tt->sgt, tt->pages, num_pages, 0, (u64)num_pages << PAGE_SHIFT, - xe_sg_segment_size(xe_tt->dev), + xe_sg_segment_size(xe_tt->xe->drm.dev), GFP_KERNEL); if (ret) return ret; xe_tt->sg = &xe_tt->sgt; - ret = dma_map_sgtable(xe_tt->dev, xe_tt->sg, DMA_BIDIRECTIONAL, + ret = dma_map_sgtable(xe_tt->xe->drm.dev, xe_tt->sg, DMA_BIDIRECTIONAL, DMA_ATTR_SKIP_CPU_SYNC); if (ret) { sg_free_table(xe_tt->sg); @@ -360,7 +365,7 @@ static void xe_tt_unmap_sg(struct ttm_tt *tt) struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm); if (xe_tt->sg) { - dma_unmap_sgtable(xe_tt->dev, xe_tt->sg, + dma_unmap_sgtable(xe_tt->xe->drm.dev, xe_tt->sg, DMA_BIDIRECTIONAL, 0); sg_free_table(xe_tt->sg); xe_tt->sg = NULL; @@ -375,21 +380,47 @@ struct sg_table *xe_bo_sg(struct xe_bo *bo) return xe_tt->sg; } +/* + * Account ttm pages against the device shrinker's shrinkable and + * purgeable counts. + */ +static void xe_ttm_tt_account_add(struct ttm_tt *tt) +{ + struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm); + + if (xe_tt->purgeable) + xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, 0, tt->num_pages); + else + xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, tt->num_pages, 0); +} + +static void xe_ttm_tt_account_subtract(struct ttm_tt *tt) +{ + struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm); + + if (xe_tt->purgeable) + xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, 0, -(long)tt->num_pages); + else + xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, -(long)tt->num_pages, 0); +} + static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo, u32 page_flags) { struct xe_bo *bo = ttm_to_xe_bo(ttm_bo); struct xe_device *xe = xe_bo_device(bo); - struct xe_ttm_tt *tt; + struct xe_ttm_tt *xe_tt; + struct ttm_tt *tt; unsigned long extra_pages; enum ttm_caching caching = ttm_cached; int err; - tt = kzalloc(sizeof(*tt), GFP_KERNEL); - if (!tt) + xe_tt = kzalloc(sizeof(*xe_tt), GFP_KERNEL); + if (!xe_tt) return NULL; - tt->dev = xe->drm.dev; + tt = &xe_tt->ttm; + xe_tt->xe = xe; extra_pages = 0; if (xe_bo_needs_ccs_pages(bo)) @@ -435,42 +466,66 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo, caching = ttm_uncached; } - err = ttm_tt_init(&tt->ttm, &bo->ttm, page_flags, caching, extra_pages); + if (ttm_bo->type != ttm_bo_type_sg) + page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE; + + err = ttm_tt_init(tt, &bo->ttm, page_flags, caching, extra_pages); if (err) { - kfree(tt); + kfree(xe_tt); return NULL; } - return &tt->ttm; + if (ttm_bo->type != ttm_bo_type_sg) { + err = ttm_tt_setup_backup(tt); + if (err) { + ttm_tt_fini(tt); + kfree(xe_tt); + return NULL; + } + } + + return tt; } static int xe_ttm_tt_populate(struct ttm_device *ttm_dev, struct ttm_tt *tt, struct ttm_operation_ctx *ctx) { + struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm); int err; /* * dma-bufs are not populated with pages, and the dma- * addresses are set up when moved to XE_PL_TT. */ - if (tt->page_flags & TTM_TT_FLAG_EXTERNAL) + if ((tt->page_flags & TTM_TT_FLAG_EXTERNAL) && + !(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)) return 0; - err = ttm_pool_alloc(&ttm_dev->pool, tt, ctx); + if (ttm_tt_is_backed_up(tt) && !xe_tt->purgeable) { + err = ttm_tt_restore(ttm_dev, tt, ctx); + } else { + ttm_tt_clear_backed_up(tt); + err = ttm_pool_alloc(&ttm_dev->pool, tt, ctx); + } if (err) return err; - return err; + xe_tt->purgeable = false; + xe_ttm_tt_account_add(tt); + + return 0; } static void xe_ttm_tt_unpopulate(struct ttm_device *ttm_dev, struct ttm_tt *tt) { - if (tt->page_flags & TTM_TT_FLAG_EXTERNAL) + if ((tt->page_flags & TTM_TT_FLAG_EXTERNAL) && + !(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE)) return; xe_tt_unmap_sg(tt); - return ttm_pool_free(&ttm_dev->pool, tt); + ttm_pool_free(&ttm_dev->pool, tt); + xe_ttm_tt_account_subtract(tt); } static void xe_ttm_tt_destroy(struct ttm_device *ttm_dev, struct ttm_tt *tt) @@ -934,6 +989,111 @@ out: return ret; } +static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx, + struct ttm_buffer_object *bo, + unsigned long *scanned) +{ + long lret; + + /* Fake move to system, without copying data. */ + if (bo->resource->mem_type != XE_PL_SYSTEM) { + struct ttm_resource *new_resource; + + lret = ttm_bo_wait_ctx(bo, ctx); + if (lret) + return lret; + + lret = ttm_bo_mem_space(bo, &sys_placement, &new_resource, ctx); + if (lret) + return lret; + + xe_tt_unmap_sg(bo->ttm); + ttm_bo_move_null(bo, new_resource); + } + + *scanned += bo->ttm->num_pages; + lret = ttm_bo_shrink(ctx, bo, (struct ttm_bo_shrink_flags) + {.purge = true, + .writeback = false, + .allow_move = false}); + + if (lret > 0) + xe_ttm_tt_account_subtract(bo->ttm); + + return lret; +} + +/** + * xe_bo_shrink() - Try to shrink an xe bo. + * @ctx: The struct ttm_operation_ctx used for shrinking. + * @bo: The TTM buffer object whose pages to shrink. + * @flags: Flags governing the shrink behaviour. + * @scanned: Pointer to a counter of the number of pages + * attempted to shrink. + * + * Try to shrink- or purge a bo, and if it succeeds, unmap dma. + * Note that we need to be able to handle also non xe bos + * (ghost bos), but only if the struct ttm_tt is embedded in + * a struct xe_ttm_tt. When the function attempts to shrink + * the pages of a buffer object, The value pointed to by @scanned + * is updated. + * + * Return: The number of pages shrunken or purged, or negative error + * code on failure. + */ +long xe_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, + const struct xe_bo_shrink_flags flags, + unsigned long *scanned) +{ + struct ttm_tt *tt = bo->ttm; + struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm); + struct ttm_place place = {.mem_type = bo->resource->mem_type}; + struct xe_bo *xe_bo = ttm_to_xe_bo(bo); + struct xe_device *xe = xe_tt->xe; + bool needs_rpm; + long lret = 0L; + + if (!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE) || + (flags.purge && !xe_tt->purgeable)) + return -EBUSY; + + if (!ttm_bo_eviction_valuable(bo, &place)) + return -EBUSY; + + if (!xe_bo_is_xe_bo(bo) || !xe_bo_get_unless_zero(xe_bo)) + return xe_bo_shrink_purge(ctx, bo, scanned); + + if (xe_tt->purgeable) { + if (bo->resource->mem_type != XE_PL_SYSTEM) + lret = xe_bo_move_notify(xe_bo, ctx); + if (!lret) + lret = xe_bo_shrink_purge(ctx, bo, scanned); + goto out_unref; + } + + /* System CCS needs gpu copy when moving PL_TT -> PL_SYSTEM */ + needs_rpm = (!IS_DGFX(xe) && bo->resource->mem_type != XE_PL_SYSTEM && + xe_bo_needs_ccs_pages(xe_bo)); + if (needs_rpm && !xe_pm_runtime_get_if_active(xe)) + goto out_unref; + + *scanned += tt->num_pages; + lret = ttm_bo_shrink(ctx, bo, (struct ttm_bo_shrink_flags) + {.purge = false, + .writeback = flags.writeback, + .allow_move = true}); + if (needs_rpm) + xe_pm_runtime_put(xe); + + if (lret > 0) + xe_ttm_tt_account_subtract(tt); + +out_unref: + xe_bo_put(xe_bo); + + return lret; +} + /** * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory * @bo: The buffer object to move. @@ -1951,6 +2111,8 @@ int xe_bo_pin_external(struct xe_bo *bo) } ttm_bo_pin(&bo->ttm); + if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) + xe_ttm_tt_account_subtract(bo->ttm.ttm); /* * FIXME: If we always use the reserve / unreserve functions for locking @@ -2010,6 +2172,8 @@ int xe_bo_pin(struct xe_bo *bo) } ttm_bo_pin(&bo->ttm); + if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) + xe_ttm_tt_account_subtract(bo->ttm.ttm); /* * FIXME: If we always use the reserve / unreserve functions for locking @@ -2044,6 +2208,8 @@ void xe_bo_unpin_external(struct xe_bo *bo) spin_unlock(&xe->pinned.lock); ttm_bo_unpin(&bo->ttm); + if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) + xe_ttm_tt_account_add(bo->ttm.ttm); /* * FIXME: If we always use the reserve / unreserve functions for locking @@ -2067,6 +2233,8 @@ void xe_bo_unpin(struct xe_bo *bo) spin_unlock(&xe->pinned.lock); } ttm_bo_unpin(&bo->ttm); + if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) + xe_ttm_tt_account_add(bo->ttm.ttm); } /** diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 2b9c0b0778a2..bda3fdd408da 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -149,6 +149,28 @@ static inline struct xe_bo *xe_bo_get(struct xe_bo *bo) void xe_bo_put(struct xe_bo *bo); +/* + * xe_bo_get_unless_zero() - Conditionally obtain a GEM object refcount on an + * xe bo + * @bo: The bo for which we want to obtain a refcount. + * + * There is a short window between where the bo's GEM object refcount reaches + * zero and where we put the final ttm_bo reference. Code in the eviction- and + * shrinking path should therefore attempt to grab a gem object reference before + * trying to use members outside of the base class ttm object. This function is + * intended for that purpose. On successful return, this function must be paired + * with an xe_bo_put(). + * + * Return: @bo on success, NULL on failure. + */ +static inline __must_check struct xe_bo *xe_bo_get_unless_zero(struct xe_bo *bo) +{ + if (!bo || !kref_get_unless_zero(&bo->ttm.base.refcount)) + return NULL; + + return bo; +} + static inline void __xe_bo_unset_bulk_move(struct xe_bo *bo) { if (bo) @@ -369,6 +391,20 @@ static inline unsigned int xe_sg_segment_size(struct device *dev) return round_down(max / 2, PAGE_SIZE); } +/** + * struct xe_bo_shrink_flags - flags governing the shrink behaviour. + * @purge: Only purging allowed. Don't shrink if bo not purgeable. + * @writeback: Attempt to immediately move content to swap. + */ +struct xe_bo_shrink_flags { + u32 purge : 1; + u32 writeback : 1; +}; + +long xe_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, + const struct xe_bo_shrink_flags flags, + unsigned long *scanned); + #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST) /** * xe_bo_is_mem_type - Whether the bo currently resides in the given diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index a7dd9c7b95e5..5d79b439dd62 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -52,6 +52,7 @@ #include "xe_pmu.h" #include "xe_pxp.h" #include "xe_query.h" +#include "xe_shrinker.h" #include "xe_sriov.h" #include "xe_tile.h" #include "xe_ttm_stolen_mgr.h" @@ -398,6 +399,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy) if (xe->unordered_wq) destroy_workqueue(xe->unordered_wq); + if (!IS_ERR_OR_NULL(xe->mem.shrinker)) + xe_shrinker_destroy(xe->mem.shrinker); + if (xe->destroy_wq) destroy_workqueue(xe->destroy_wq); @@ -431,6 +435,10 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, if (err) goto err; + xe->mem.shrinker = xe_shrinker_create(xe); + if (IS_ERR(xe->mem.shrinker)) + return ERR_CAST(xe->mem.shrinker); + xe->info.devid = pdev->device; xe->info.revid = pdev->revision; xe->info.force_execlist = xe_modparam.force_execlist; diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index fac488942316..72ef0b6fc425 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -386,6 +386,8 @@ struct xe_device { struct xe_vram_region vram; /** @mem.sys_mgr: system TTM manager */ struct ttm_resource_manager sys_mgr; + /** @mem.sys_mgr: system memory shrinker. */ + struct xe_shrinker *shrinker; } mem; /** @sriov: device level virtualization data */ diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c new file mode 100644 index 000000000000..8184390f9c7b --- /dev/null +++ b/drivers/gpu/drm/xe/xe_shrinker.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include <linux/shrinker.h> + +#include <drm/ttm/ttm_backup.h> +#include <drm/ttm/ttm_bo.h> +#include <drm/ttm/ttm_tt.h> + +#include "xe_bo.h" +#include "xe_pm.h" +#include "xe_shrinker.h" + +/** + * struct xe_shrinker - per-device shrinker + * @xe: Back pointer to the device. + * @lock: Lock protecting accounting. + * @shrinkable_pages: Number of pages that are currently shrinkable. + * @purgeable_pages: Number of pages that are currently purgeable. + * @shrink: Pointer to the mm shrinker. + * @pm_worker: Worker to wake up the device if required. + */ +struct xe_shrinker { + struct xe_device *xe; + rwlock_t lock; + long shrinkable_pages; + long purgeable_pages; + struct shrinker *shrink; + struct work_struct pm_worker; +}; + +static struct xe_shrinker *to_xe_shrinker(struct shrinker *shrink) +{ + return shrink->private_data; +} + +/** + * xe_shrinker_mod_pages() - Modify shrinker page accounting + * @shrinker: Pointer to the struct xe_shrinker. + * @shrinkable: Shrinkable pages delta. May be negative. + * @purgeable: Purgeable page delta. May be negative. + * + * Modifies the shrinkable and purgeable pages accounting. + */ +void +xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgeable) +{ + write_lock(&shrinker->lock); + shrinker->shrinkable_pages += shrinkable; + shrinker->purgeable_pages += purgeable; + write_unlock(&shrinker->lock); +} + +static s64 xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) +{ + unsigned int mem_type; + s64 freed = 0, lret; + + for (mem_type = XE_PL_SYSTEM; mem_type <= XE_PL_TT; ++mem_type) { + struct ttm_resource_manager *man = ttm_manager_type(&xe->ttm, mem_type); + struct ttm_bo_lru_cursor curs; + struct ttm_buffer_object *ttm_bo; + + if (!man || !man->use_tt) + continue; + + ttm_bo_lru_for_each_reserved_guarded(&curs, man, ctx, ttm_bo) { + if (!ttm_bo_shrink_suitable(ttm_bo, ctx)) + continue; + + lret = xe_bo_shrink(ctx, ttm_bo, flags, scanned); + if (lret < 0) + return lret; + + freed += lret; + if (*scanned >= to_scan) + break; + } + } + + return freed; +} + +static unsigned long +xe_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct xe_shrinker *shrinker = to_xe_shrinker(shrink); + unsigned long num_pages; + bool can_backup = !!(sc->gfp_mask & __GFP_FS); + + num_pages = ttm_backup_bytes_avail() >> PAGE_SHIFT; + read_lock(&shrinker->lock); + + if (can_backup) + num_pages = min_t(unsigned long, num_pages, shrinker->shrinkable_pages); + else + num_pages = 0; + + num_pages += shrinker->purgeable_pages; + read_unlock(&shrinker->lock); + + return num_pages ? num_pages : SHRINK_EMPTY; +} + +/* + * Check if we need runtime pm, and if so try to grab a reference if + * already active. If grabbing a reference fails, queue a worker that + * does it for us outside of reclaim, but don't wait for it to complete. + * If bo shrinking needs an rpm reference and we don't have it (yet), + * that bo will be skipped anyway. + */ +static bool xe_shrinker_runtime_pm_get(struct xe_shrinker *shrinker, bool force, + unsigned long nr_to_scan, bool can_backup) +{ + struct xe_device *xe = shrinker->xe; + + if (IS_DGFX(xe) || !xe_device_has_flat_ccs(xe) || + !ttm_backup_bytes_avail()) + return false; + + if (!force) { + read_lock(&shrinker->lock); + force = (nr_to_scan > shrinker->purgeable_pages && can_backup); + read_unlock(&shrinker->lock); + if (!force) + return false; + } + + if (!xe_pm_runtime_get_if_active(xe)) { + if (xe_rpm_reclaim_safe(xe) && !ttm_bo_shrink_avoid_wait()) { + xe_pm_runtime_get(xe); + return true; + } + queue_work(xe->unordered_wq, &shrinker->pm_worker); + return false; + } + + return true; +} + +static void xe_shrinker_runtime_pm_put(struct xe_shrinker *shrinker, bool runtime_pm) +{ + if (runtime_pm) + xe_pm_runtime_put(shrinker->xe); +} + +static unsigned long xe_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + struct xe_shrinker *shrinker = to_xe_shrinker(shrink); + struct ttm_operation_ctx ctx = { + .interruptible = false, + .no_wait_gpu = ttm_bo_shrink_avoid_wait(), + }; + unsigned long nr_to_scan, nr_scanned = 0, freed = 0; + struct xe_bo_shrink_flags shrink_flags = { + .purge = true, + /* Don't request writeback without __GFP_IO. */ + .writeback = !ctx.no_wait_gpu && (sc->gfp_mask & __GFP_IO), + }; + bool runtime_pm; + bool purgeable; + bool can_backup = !!(sc->gfp_mask & __GFP_FS); + s64 lret; + + nr_to_scan = sc->nr_to_scan; + + read_lock(&shrinker->lock); + purgeable = !!shrinker->purgeable_pages; + read_unlock(&shrinker->lock); + + /* Might need runtime PM. Try to wake early if it looks like it. */ + runtime_pm = xe_shrinker_runtime_pm_get(shrinker, false, nr_to_scan, can_backup); + + if (purgeable && nr_scanned < nr_to_scan) { + lret = xe_shrinker_walk(shrinker->xe, &ctx, shrink_flags, + nr_to_scan, &nr_scanned); + if (lret >= 0) + freed += lret; + } + + sc->nr_scanned = nr_scanned; + if (nr_scanned >= nr_to_scan || !can_backup) + goto out; + + /* If we didn't wake before, try to do it now if needed. */ + if (!runtime_pm) + runtime_pm = xe_shrinker_runtime_pm_get(shrinker, true, 0, can_backup); + + shrink_flags.purge = false; + lret = xe_shrinker_walk(shrinker->xe, &ctx, shrink_flags, + nr_to_scan, &nr_scanned); + if (lret >= 0) + freed += lret; + + sc->nr_scanned = nr_scanned; +out: + xe_shrinker_runtime_pm_put(shrinker, runtime_pm); + return nr_scanned ? freed : SHRINK_STOP; +} + +/* Wake up the device for shrinking. */ +static void xe_shrinker_pm(struct work_struct *work) +{ + struct xe_shrinker *shrinker = + container_of(work, typeof(*shrinker), pm_worker); + + xe_pm_runtime_get(shrinker->xe); + xe_pm_runtime_put(shrinker->xe); +} + +/** + * xe_shrinker_create() - Create an xe per-device shrinker + * @xe: Pointer to the xe device. + * + * Returns: A pointer to the created shrinker on success, + * Negative error code on failure. + */ +struct xe_shrinker *xe_shrinker_create(struct xe_device *xe) +{ + struct xe_shrinker *shrinker = kzalloc(sizeof(*shrinker), GFP_KERNEL); + + if (!shrinker) + return ERR_PTR(-ENOMEM); + + shrinker->shrink = shrinker_alloc(0, "xe system shrinker"); + if (!shrinker->shrink) { + kfree(shrinker); + return ERR_PTR(-ENOMEM); + } + + INIT_WORK(&shrinker->pm_worker, xe_shrinker_pm); + shrinker->xe = xe; + rwlock_init(&shrinker->lock); + shrinker->shrink->count_objects = xe_shrinker_count; + shrinker->shrink->scan_objects = xe_shrinker_scan; + shrinker->shrink->private_data = shrinker; + shrinker_register(shrinker->shrink); + + return shrinker; +} + +/** + * xe_shrinker_destroy() - Destroy an xe per-device shrinker + * @shrinker: Pointer to the shrinker to destroy. + */ +void xe_shrinker_destroy(struct xe_shrinker *shrinker) +{ + xe_assert(shrinker->xe, !shrinker->shrinkable_pages); + xe_assert(shrinker->xe, !shrinker->purgeable_pages); + shrinker_free(shrinker->shrink); + flush_work(&shrinker->pm_worker); + kfree(shrinker); +} diff --git a/drivers/gpu/drm/xe/xe_shrinker.h b/drivers/gpu/drm/xe/xe_shrinker.h new file mode 100644 index 000000000000..28a038f4fcbf --- /dev/null +++ b/drivers/gpu/drm/xe/xe_shrinker.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef _XE_SHRINKER_H_ +#define _XE_SHRINKER_H_ + +struct xe_shrinker; +struct xe_device; + +void xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgeable); + +struct xe_shrinker *xe_shrinker_create(struct xe_device *xe); + +void xe_shrinker_destroy(struct xe_shrinker *shrinker); + +#endif diff --git a/drivers/gpu/drm/xe/xe_ttm_sys_mgr.c b/drivers/gpu/drm/xe/xe_ttm_sys_mgr.c index 9844a8edbfe1..d38b91872da3 100644 --- a/drivers/gpu/drm/xe/xe_ttm_sys_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_sys_mgr.c @@ -108,9 +108,8 @@ int xe_ttm_sys_mgr_init(struct xe_device *xe) u64 gtt_size; si_meminfo(&si); + /* Potentially restrict amount of TT memory here. */ gtt_size = (u64)si.totalram * si.mem_unit; - /* TTM limits allocation of all TTM devices by 50% of system memory */ - gtt_size /= 2; man->use_tt = true; man->func = &xe_ttm_sys_mgr_func; diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c index a18cc8d8caf5..6433c00d5d7e 100644 --- a/drivers/gpu/host1x/debug.c +++ b/drivers/gpu/host1x/debug.c @@ -216,12 +216,3 @@ void host1x_debug_dump(struct host1x *host1x) show_all(host1x, &o, true); } - -void host1x_debug_dump_syncpts(struct host1x *host1x) -{ - struct output o = { - .fn = write_to_printk - }; - - show_syncpts(host1x, &o, false); -} diff --git a/drivers/gpu/host1x/debug.h b/drivers/gpu/host1x/debug.h index 62bd8a091fa7..c43c61d876a9 100644 --- a/drivers/gpu/host1x/debug.h +++ b/drivers/gpu/host1x/debug.h @@ -41,6 +41,5 @@ extern unsigned int host1x_debug_trace_cmdbuf; void host1x_debug_init(struct host1x *host1x); void host1x_debug_deinit(struct host1x *host1x); void host1x_debug_dump(struct host1x *host1x); -void host1x_debug_dump_syncpts(struct host1x *host1x); #endif diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 947323f4a234..fa77e4e64f12 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -165,38 +165,6 @@ int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees, } EXPORT_SYMBOL_GPL(ipu_degrees_to_rot_mode); -int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode, - bool hflip, bool vflip) -{ - u32 r90, vf, hf; - - r90 = ((u32)mode >> 2) & 0x1; - hf = ((u32)mode >> 1) & 0x1; - vf = ((u32)mode >> 0) & 0x1; - hf ^= (u32)hflip; - vf ^= (u32)vflip; - - switch ((enum ipu_rotate_mode)((r90 << 2) | (hf << 1) | vf)) { - case IPU_ROTATE_NONE: - *degrees = 0; - break; - case IPU_ROTATE_90_RIGHT: - *degrees = 90; - break; - case IPU_ROTATE_180: - *degrees = 180; - break; - case IPU_ROTATE_90_LEFT: - *degrees = 270; - break; - default: - return -EINVAL; - } - - return 0; -} -EXPORT_SYMBOL_GPL(ipu_rot_mode_to_degrees); - struct ipuv3_channel *ipu_idmac_get(struct ipu_soc *ipu, unsigned num) { struct ipuv3_channel *channel; @@ -516,12 +484,6 @@ int ipu_idmac_enable_channel(struct ipuv3_channel *channel) } EXPORT_SYMBOL_GPL(ipu_idmac_enable_channel); -bool ipu_idmac_channel_busy(struct ipu_soc *ipu, unsigned int chno) -{ - return (ipu_idmac_read(ipu, IDMAC_CHA_BUSY(chno)) & idma_mask(chno)); -} -EXPORT_SYMBOL_GPL(ipu_idmac_channel_busy); - int ipu_idmac_wait_busy(struct ipuv3_channel *channel, int ms) { struct ipu_soc *ipu = channel->ipu; diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c index 82b244cb313e..07866b1369c6 100644 --- a/drivers/gpu/ipu-v3/ipu-cpmem.c +++ b/drivers/gpu/ipu-v3/ipu-cpmem.c @@ -337,12 +337,6 @@ void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id) } EXPORT_SYMBOL_GPL(ipu_cpmem_set_axi_id); -int ipu_cpmem_get_burstsize(struct ipuv3_channel *ch) -{ - return ipu_ch_param_read_field(ch, IPU_FIELD_NPB) + 1; -} -EXPORT_SYMBOL_GPL(ipu_cpmem_get_burstsize); - void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize) { ipu_ch_param_write_field(ch, IPU_FIELD_NPB, burstsize - 1); @@ -452,23 +446,6 @@ int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width) } EXPORT_SYMBOL_GPL(ipu_cpmem_set_format_passthrough); -void ipu_cpmem_set_yuv_interleaved(struct ipuv3_channel *ch, u32 pixel_format) -{ - switch (pixel_format) { - case V4L2_PIX_FMT_UYVY: - ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3); /* bits/pixel */ - ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 0xA);/* pix fmt */ - ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);/* burst size */ - break; - case V4L2_PIX_FMT_YUYV: - ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3); /* bits/pixel */ - ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 0x8);/* pix fmt */ - ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);/* burst size */ - break; - } -} -EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_interleaved); - void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch, unsigned int uv_stride, unsigned int u_offset, unsigned int v_offset) diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index 778bc26d3ba5..d576b7d28437 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -186,32 +186,6 @@ static inline void ipu_csi_write(struct ipu_csi *csi, u32 value, } /* - * Set mclk division ratio for generating test mode mclk. Only used - * for test generator. - */ -static int ipu_csi_set_testgen_mclk(struct ipu_csi *csi, u32 pixel_clk, - u32 ipu_clk) -{ - u32 temp; - int div_ratio; - - div_ratio = (ipu_clk / pixel_clk) - 1; - - if (div_ratio > 0xFF || div_ratio < 0) { - dev_err(csi->ipu->dev, - "value of pixel_clk extends normal range\n"); - return -EINVAL; - } - - temp = ipu_csi_read(csi, CSI_SENS_CONF); - temp &= ~CSI_SENS_CONF_DIVRATIO_MASK; - ipu_csi_write(csi, temp | (div_ratio << CSI_SENS_CONF_DIVRATIO_SHIFT), - CSI_SENS_CONF); - - return 0; -} - -/* * Find the CSI data format and data width for the given V4L2 media * bus pixel format code. */ @@ -538,56 +512,6 @@ out_unlock: } EXPORT_SYMBOL_GPL(ipu_csi_init_interface); -bool ipu_csi_is_interlaced(struct ipu_csi *csi) -{ - unsigned long flags; - u32 sensor_protocol; - - spin_lock_irqsave(&csi->lock, flags); - sensor_protocol = - (ipu_csi_read(csi, CSI_SENS_CONF) & - CSI_SENS_CONF_SENS_PRTCL_MASK) >> - CSI_SENS_CONF_SENS_PRTCL_SHIFT; - spin_unlock_irqrestore(&csi->lock, flags); - - switch (sensor_protocol) { - case IPU_CSI_CLK_MODE_GATED_CLK: - case IPU_CSI_CLK_MODE_NONGATED_CLK: - case IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE: - case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR: - case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR: - return false; - case IPU_CSI_CLK_MODE_CCIR656_INTERLACED: - case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR: - case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR: - return true; - default: - dev_err(csi->ipu->dev, - "CSI %d sensor protocol unsupported\n", csi->id); - return false; - } -} -EXPORT_SYMBOL_GPL(ipu_csi_is_interlaced); - -void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w) -{ - unsigned long flags; - u32 reg; - - spin_lock_irqsave(&csi->lock, flags); - - reg = ipu_csi_read(csi, CSI_ACT_FRM_SIZE); - w->width = (reg & 0xFFFF) + 1; - w->height = (reg >> 16 & 0xFFFF) + 1; - - reg = ipu_csi_read(csi, CSI_OUT_FRM_CTRL); - w->left = (reg & CSI_HSC_MASK) >> CSI_HSC_SHIFT; - w->top = (reg & CSI_VSC_MASK) >> CSI_VSC_SHIFT; - - spin_unlock_irqrestore(&csi->lock, flags); -} -EXPORT_SYMBOL_GPL(ipu_csi_get_window); - void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w) { unsigned long flags; @@ -624,38 +548,6 @@ void ipu_csi_set_downsize(struct ipu_csi *csi, bool horiz, bool vert) } EXPORT_SYMBOL_GPL(ipu_csi_set_downsize); -void ipu_csi_set_test_generator(struct ipu_csi *csi, bool active, - u32 r_value, u32 g_value, u32 b_value, - u32 pix_clk) -{ - unsigned long flags; - u32 ipu_clk = clk_get_rate(csi->clk_ipu); - u32 temp; - - spin_lock_irqsave(&csi->lock, flags); - - temp = ipu_csi_read(csi, CSI_TST_CTRL); - - if (!active) { - temp &= ~CSI_TEST_GEN_MODE_EN; - ipu_csi_write(csi, temp, CSI_TST_CTRL); - } else { - /* Set sensb_mclk div_ratio */ - ipu_csi_set_testgen_mclk(csi, pix_clk, ipu_clk); - - temp &= ~(CSI_TEST_GEN_R_MASK | CSI_TEST_GEN_G_MASK | - CSI_TEST_GEN_B_MASK); - temp |= CSI_TEST_GEN_MODE_EN; - temp |= (r_value << CSI_TEST_GEN_R_SHIFT) | - (g_value << CSI_TEST_GEN_G_SHIFT) | - (b_value << CSI_TEST_GEN_B_SHIFT); - ipu_csi_write(csi, temp, CSI_TST_CTRL); - } - - spin_unlock_irqrestore(&csi->lock, flags); -} -EXPORT_SYMBOL_GPL(ipu_csi_set_test_generator); - int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc, struct v4l2_mbus_framefmt *mbus_fmt) { diff --git a/drivers/gpu/ipu-v3/ipu-ic.c b/drivers/gpu/ipu-v3/ipu-ic.c index 846461bac70d..acd76ecc5221 100644 --- a/drivers/gpu/ipu-v3/ipu-ic.c +++ b/drivers/gpu/ipu-v3/ipu-ic.c @@ -321,79 +321,6 @@ void ipu_ic_task_disable(struct ipu_ic *ic) } EXPORT_SYMBOL_GPL(ipu_ic_task_disable); -int ipu_ic_task_graphics_init(struct ipu_ic *ic, - const struct ipu_ic_colorspace *g_in_cs, - bool galpha_en, u32 galpha, - bool colorkey_en, u32 colorkey) -{ - struct ipu_ic_priv *priv = ic->priv; - struct ipu_ic_csc csc2; - unsigned long flags; - u32 reg, ic_conf; - int ret = 0; - - if (ic->task == IC_TASK_ENCODER) - return -EINVAL; - - spin_lock_irqsave(&priv->lock, flags); - - ic_conf = ipu_ic_read(ic, IC_CONF); - - if (!(ic_conf & ic->bit->ic_conf_csc1_en)) { - struct ipu_ic_csc csc1; - - ret = ipu_ic_calc_csc(&csc1, - V4L2_YCBCR_ENC_601, - V4L2_QUANTIZATION_FULL_RANGE, - IPUV3_COLORSPACE_RGB, - V4L2_YCBCR_ENC_601, - V4L2_QUANTIZATION_FULL_RANGE, - IPUV3_COLORSPACE_RGB); - if (ret) - goto unlock; - - /* need transparent CSC1 conversion */ - ret = init_csc(ic, &csc1, 0); - if (ret) - goto unlock; - } - - ic->g_in_cs = *g_in_cs; - csc2.in_cs = ic->g_in_cs; - csc2.out_cs = ic->out_cs; - - ret = __ipu_ic_calc_csc(&csc2); - if (ret) - goto unlock; - - ret = init_csc(ic, &csc2, 1); - if (ret) - goto unlock; - - if (galpha_en) { - ic_conf |= IC_CONF_IC_GLB_LOC_A; - reg = ipu_ic_read(ic, IC_CMBP_1); - reg &= ~(0xff << ic->bit->ic_cmb_galpha_bit); - reg |= (galpha << ic->bit->ic_cmb_galpha_bit); - ipu_ic_write(ic, reg, IC_CMBP_1); - } else - ic_conf &= ~IC_CONF_IC_GLB_LOC_A; - - if (colorkey_en) { - ic_conf |= IC_CONF_KEY_COLOR_EN; - ipu_ic_write(ic, colorkey, IC_CMBP_2); - } else - ic_conf &= ~IC_CONF_KEY_COLOR_EN; - - ipu_ic_write(ic, ic_conf, IC_CONF); - - ic->graphics = true; -unlock: - spin_unlock_irqrestore(&priv->lock, flags); - return ret; -} -EXPORT_SYMBOL_GPL(ipu_ic_task_graphics_init); - int ipu_ic_task_init_rsc(struct ipu_ic *ic, const struct ipu_ic_csc *csc, int in_width, int in_height, diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c index 841316582ea9..3c33b4defab5 100644 --- a/drivers/gpu/ipu-v3/ipu-image-convert.c +++ b/drivers/gpu/ipu-v3/ipu-image-convert.c @@ -355,20 +355,6 @@ static void dump_format(struct ipu_image_convert_ctx *ctx, (ic_image->fmt->fourcc >> 24) & 0xff); } -int ipu_image_convert_enum_format(int index, u32 *fourcc) -{ - const struct ipu_image_pixfmt *fmt; - - if (index >= (int)ARRAY_SIZE(image_convert_formats)) - return -EINVAL; - - /* Format found */ - fmt = &image_convert_formats[index]; - *fourcc = fmt->fourcc; - return 0; -} -EXPORT_SYMBOL_GPL(ipu_image_convert_enum_format); - static void free_dma_buf(struct ipu_image_convert_priv *priv, struct ipu_image_convert_dma_buf *buf) { @@ -2437,40 +2423,6 @@ ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task, } EXPORT_SYMBOL_GPL(ipu_image_convert); -/* "Canned" synchronous single image conversion */ -static void image_convert_sync_complete(struct ipu_image_convert_run *run, - void *data) -{ - struct completion *comp = data; - - complete(comp); -} - -int ipu_image_convert_sync(struct ipu_soc *ipu, enum ipu_ic_task ic_task, - struct ipu_image *in, struct ipu_image *out, - enum ipu_rotate_mode rot_mode) -{ - struct ipu_image_convert_run *run; - struct completion comp; - int ret; - - init_completion(&comp); - - run = ipu_image_convert(ipu, ic_task, in, out, rot_mode, - image_convert_sync_complete, &comp); - if (IS_ERR(run)) - return PTR_ERR(run); - - ret = wait_for_completion_timeout(&comp, msecs_to_jiffies(10000)); - ret = (ret == 0) ? -ETIMEDOUT : 0; - - ipu_image_convert_unprepare(run->ctx); - kfree(run); - - return ret; -} -EXPORT_SYMBOL_GPL(ipu_image_convert_sync); - int ipu_image_convert_init(struct ipu_soc *ipu, struct device *dev) { struct ipu_image_convert_priv *priv; diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h index 3884acb7995a..16322b2137f8 100644 --- a/drivers/gpu/ipu-v3/ipu-prv.h +++ b/drivers/gpu/ipu-v3/ipu-prv.h @@ -216,8 +216,6 @@ void ipu_srm_dp_update(struct ipu_soc *ipu, bool sync); int ipu_module_enable(struct ipu_soc *ipu, u32 mask); int ipu_module_disable(struct ipu_soc *ipu, u32 mask); -bool ipu_idmac_channel_busy(struct ipu_soc *ipu, unsigned int chno); - int ipu_csi_init(struct ipu_soc *ipu, struct device *dev, int id, unsigned long base, u32 module, struct clk *clk_ipu); void ipu_csi_exit(struct ipu_soc *ipu, int id); diff --git a/drivers/gpu/ipu-v3/ipu-vdi.c b/drivers/gpu/ipu-v3/ipu-vdi.c index a593b232b6d3..af9631fd4256 100644 --- a/drivers/gpu/ipu-v3/ipu-vdi.c +++ b/drivers/gpu/ipu-v3/ipu-vdi.c @@ -150,17 +150,6 @@ void ipu_vdi_setup(struct ipu_vdi *vdi, u32 code, int xres, int yres) } EXPORT_SYMBOL_GPL(ipu_vdi_setup); -void ipu_vdi_unsetup(struct ipu_vdi *vdi) -{ - unsigned long flags; - - spin_lock_irqsave(&vdi->lock, flags); - ipu_vdi_write(vdi, 0, VDI_FSIZE); - ipu_vdi_write(vdi, 0, VDI_C); - spin_unlock_irqrestore(&vdi->lock, flags); -} -EXPORT_SYMBOL_GPL(ipu_vdi_unsetup); - int ipu_vdi_enable(struct ipu_vdi *vdi) { unsigned long flags; diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c index 4cfa494243b9..da9c64152a60 100644 --- a/drivers/staging/fbtft/fbtft-core.c +++ b/drivers/staging/fbtft/fbtft-core.c @@ -337,9 +337,7 @@ static void fbtft_deferred_io(struct fb_info *info, struct list_head *pagereflis list_for_each_entry(pageref, pagereflist, list) { y_low = pageref->offset / info->fix.line_length; y_high = (pageref->offset + PAGE_SIZE - 1) / info->fix.line_length; - dev_dbg(info->device, - "page->index=%lu y_low=%d y_high=%d\n", - pageref->page->index, y_low, y_high); + dev_dbg(info->device, "y_low=%d y_high=%d\n", y_low, y_high); if (y_high > info->var.yres - 1) y_high = info->var.yres - 1; if (y_low < dirty_lines_start) diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 89a34dff85a4..5ae4241959f2 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -630,6 +630,8 @@ int drm_dp_read_lttpr_phy_caps(struct drm_dp_aux *aux, u8 caps[DP_LTTPR_PHY_CAP_SIZE]); int drm_dp_lttpr_count(const u8 cap[DP_LTTPR_COMMON_CAP_SIZE]); int drm_dp_lttpr_max_link_rate(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_lttpr_set_transparent_mode(struct drm_dp_aux *aux, bool enable); +int drm_dp_lttpr_init(struct drm_dp_aux *aux, int lttpr_count); int drm_dp_lttpr_max_lane_count(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); bool drm_dp_lttpr_voltage_swing_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); bool drm_dp_lttpr_pre_emphasis_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index a1347e47e9d5..d8539174ca11 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -96,6 +96,9 @@ void drm_fb_xrgb8888_to_rgba5551(struct iosys_map *dst, const unsigned int *dst_ void drm_fb_xrgb8888_to_rgb888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state); +void drm_fb_xrgb8888_to_bgr888(struct iosys_map *dst, const unsigned int *dst_pitch, + const struct iosys_map *src, const struct drm_framebuffer *fb, + const struct drm_rect *clip, struct drm_format_conv_state *state); void drm_fb_xrgb8888_to_argb8888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state); diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index fdae947682cd..2bf893eabb4b 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -35,6 +35,7 @@ */ #include <linux/kref.h> +#include <linux/dma-buf.h> #include <linux/dma-resv.h> #include <linux/list.h> #include <linux/mutex.h> @@ -575,6 +576,19 @@ static inline bool drm_gem_object_is_shared_for_memory_stats(struct drm_gem_obje return (obj->handle_count > 1) || obj->dma_buf; } +/** + * drm_gem_is_imported() - Tests if GEM object's buffer has been imported + * @obj: the GEM object + * + * Returns: + * True if the GEM object's buffer has been imported, false otherwise + */ +static inline bool drm_gem_is_imported(const struct drm_gem_object *obj) +{ + /* The dma-buf's priv field points to the original GEM object. */ + return obj->dma_buf && (obj->dma_buf->priv != obj); +} + #ifdef CONFIG_LOCKDEP /** * drm_gem_gpuva_set_lock() - Set the lock protecting accesses to the gpuva list. diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index d22e3fb53631..cef5a6b5a4d6 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -120,7 +120,7 @@ static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem { return (shmem->madv > 0) && !shmem->vmap_use_count && shmem->sgt && - !shmem->base.dma_buf && !shmem->base.import_attach; + !shmem->base.dma_buf && !drm_gem_is_imported(&shmem->base); } void drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem); diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h index afdd46ef04f7..11d59ce0bac0 100644 --- a/include/drm/drm_kunit_helpers.h +++ b/include/drm/drm_kunit_helpers.h @@ -95,8 +95,6 @@ __drm_kunit_helper_alloc_drm_device(struct kunit *test, sizeof(_type), \ offsetof(_type, _member), \ _feat)) -struct drm_modeset_acquire_ctx * -drm_kunit_helper_acquire_ctx_alloc(struct kunit *test); struct drm_atomic_state * drm_kunit_helper_atomic_state_alloc(struct kunit *test, diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 94400a78031f..bd40a443385c 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -346,7 +346,6 @@ int mipi_dsi_dcs_set_column_address(struct mipi_dsi_device *dsi, u16 start, u16 end); int mipi_dsi_dcs_set_page_address(struct mipi_dsi_device *dsi, u16 start, u16 end); -int mipi_dsi_dcs_set_tear_off(struct mipi_dsi_device *dsi); int mipi_dsi_dcs_set_tear_on(struct mipi_dsi_device *dsi, enum mipi_dsi_dcs_tear_mode mode); int mipi_dsi_dcs_set_pixel_format(struct mipi_dsi_device *dsi, u8 format); @@ -379,6 +378,7 @@ void mipi_dsi_dcs_set_page_address_multi(struct mipi_dsi_multi_context *ctx, u16 start, u16 end); void mipi_dsi_dcs_set_tear_scanline_multi(struct mipi_dsi_multi_context *ctx, u16 scanline); +void mipi_dsi_dcs_set_tear_off_multi(struct mipi_dsi_multi_context *ctx); /** * mipi_dsi_generic_write_seq - transmit data using a generic write packet diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 9732f514566d..f31eba1c7cab 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -584,9 +584,15 @@ void __drm_dev_dbg(struct _ddebug *desc, const struct device *dev, * Prefer drm_device based logging over device or prink based logging. */ +/* Helper to enforce struct drm_device type */ +static inline struct device *__drm_to_dev(const struct drm_device *drm) +{ + return drm ? drm->dev : NULL; +} + /* Helper for struct drm_device based logging. */ #define __drm_printk(drm, level, type, fmt, ...) \ - dev_##level##type((drm) ? (drm)->dev : NULL, "[drm] " fmt, ##__VA_ARGS__) + dev_##level##type(__drm_to_dev(drm), "[drm] " fmt, ##__VA_ARGS__) #define drm_info(drm, fmt, ...) \ @@ -620,25 +626,25 @@ void __drm_dev_dbg(struct _ddebug *desc, const struct device *dev, #define drm_dbg_core(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_CORE, fmt, ##__VA_ARGS__) -#define drm_dbg_driver(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_DRIVER, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_CORE, fmt, ##__VA_ARGS__) +#define drm_dbg_driver(drm, fmt, ...) \ + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_DRIVER, fmt, ##__VA_ARGS__) #define drm_dbg_kms(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_KMS, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_KMS, fmt, ##__VA_ARGS__) #define drm_dbg_prime(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_PRIME, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_PRIME, fmt, ##__VA_ARGS__) #define drm_dbg_atomic(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_ATOMIC, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_ATOMIC, fmt, ##__VA_ARGS__) #define drm_dbg_vbl(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_VBL, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_VBL, fmt, ##__VA_ARGS__) #define drm_dbg_state(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_STATE, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_STATE, fmt, ##__VA_ARGS__) #define drm_dbg_lease(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_LEASE, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_LEASE, fmt, ##__VA_ARGS__) #define drm_dbg_dp(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_DP, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_DP, fmt, ##__VA_ARGS__) #define drm_dbg_drmres(drm, fmt, ...) \ - drm_dev_dbg((drm) ? (drm)->dev : NULL, DRM_UT_DRMRES, fmt, ##__VA_ARGS__) + drm_dev_dbg(__drm_to_dev(drm), DRM_UT_DRMRES, fmt, ##__VA_ARGS__) #define drm_dbg(drm, fmt, ...) drm_dbg_driver(drm, fmt, ##__VA_ARGS__) @@ -727,10 +733,9 @@ void __drm_err(const char *format, ...); #define __DRM_DEFINE_DBG_RATELIMITED(category, drm, fmt, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(rs_, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);\ - const struct drm_device *drm_ = (drm); \ \ if (drm_debug_enabled(DRM_UT_ ## category) && __ratelimit(&rs_)) \ - drm_dev_printk(drm_ ? drm_->dev : NULL, KERN_DEBUG, fmt, ## __VA_ARGS__); \ + drm_dev_printk(__drm_to_dev(drm), KERN_DEBUG, fmt, ## __VA_ARGS__); \ }) #define drm_dbg_ratelimited(drm, fmt, ...) \ @@ -752,13 +757,13 @@ void __drm_err(const char *format, ...); /* Helper for struct drm_device based WARNs */ #define drm_WARN(drm, condition, format, arg...) \ WARN(condition, "%s %s: [drm] " format, \ - dev_driver_string((drm)->dev), \ - dev_name((drm)->dev), ## arg) + dev_driver_string(__drm_to_dev(drm)), \ + dev_name(__drm_to_dev(drm)), ## arg) #define drm_WARN_ONCE(drm, condition, format, arg...) \ WARN_ONCE(condition, "%s %s: [drm] " format, \ - dev_driver_string((drm)->dev), \ - dev_name((drm)->dev), ## arg) + dev_driver_string(__drm_to_dev(drm)), \ + dev_name(__drm_to_dev(drm)), ## arg) #define drm_WARN_ON(drm, x) \ drm_WARN((drm), (x), "%s", \ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 6bf458dbce84..50928a7ae98e 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -71,12 +71,6 @@ enum drm_sched_priority { DRM_SCHED_PRIORITY_COUNT }; -/* Used to choose between FIFO and RR job-scheduling */ -extern int drm_sched_policy; - -#define DRM_SCHED_POLICY_RR 0 -#define DRM_SCHED_POLICY_FIFO 1 - /** * struct drm_sched_entity - A wrapper around a job queue (typically * attached to the DRM file_priv). @@ -338,8 +332,14 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * to schedule the job. */ struct drm_sched_job { - struct spsc_node queue_node; - struct list_head list; + u64 id; + + /** + * @submit_ts: + * + * When the job was pushed into the entity queue. + */ + ktime_t submit_ts; /** * @sched: @@ -349,24 +349,30 @@ struct drm_sched_job { * has finished. */ struct drm_gpu_scheduler *sched; + struct drm_sched_fence *s_fence; + struct drm_sched_entity *entity; + enum drm_sched_priority s_priority; u32 credits; + /** @last_dependency: tracks @dependencies as they signal */ + unsigned int last_dependency; + atomic_t karma; + + struct spsc_node queue_node; + struct list_head list; /* * work is used only after finish_cb has been used and will not be * accessed anymore. */ union { - struct dma_fence_cb finish_cb; - struct work_struct work; + struct dma_fence_cb finish_cb; + struct work_struct work; }; - uint64_t id; - atomic_t karma; - enum drm_sched_priority s_priority; - struct drm_sched_entity *entity; struct dma_fence_cb cb; + /** * @dependencies: * @@ -375,24 +381,8 @@ struct drm_sched_job { * drm_sched_job_add_implicit_dependencies(). */ struct xarray dependencies; - - /** @last_dependency: tracks @dependencies as they signal */ - unsigned long last_dependency; - - /** - * @submit_ts: - * - * When the job was pushed into the entity queue. - */ - ktime_t submit_ts; }; -static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, - int threshold) -{ - return s_job && atomic_inc_return(&s_job->karma) > threshold; -} - enum drm_gpu_sched_stat { DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */ DRM_GPU_SCHED_STAT_NOMINAL, @@ -570,14 +560,36 @@ struct drm_sched_init_args { struct device *dev; }; +/* Scheduler operations */ + int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_init_args *args); void drm_sched_fini(struct drm_gpu_scheduler *sched); + +unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched); +void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched, + unsigned long remaining); +void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched); +bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched); +void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched); +void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched); +void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad); +void drm_sched_start(struct drm_gpu_scheduler *sched, int errno); +void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched); +void drm_sched_fault(struct drm_gpu_scheduler *sched); + +struct drm_gpu_scheduler * +drm_sched_pick_best(struct drm_gpu_scheduler **sched_list, + unsigned int num_sched_list); + +/* Jobs */ + int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, u32 credits, void *owner); void drm_sched_job_arm(struct drm_sched_job *job); +void drm_sched_entity_push_job(struct drm_sched_job *sched_job); int drm_sched_job_add_dependency(struct drm_sched_job *job, struct dma_fence *fence); int drm_sched_job_add_syncobj_dependency(struct drm_sched_job *job, @@ -592,30 +604,16 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, bool write); bool drm_sched_job_has_dependency(struct drm_sched_job *job, struct dma_fence *fence); - -void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, - struct drm_gpu_scheduler **sched_list, - unsigned int num_sched_list); - -void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched); void drm_sched_job_cleanup(struct drm_sched_job *job); -void drm_sched_wakeup(struct drm_gpu_scheduler *sched); -bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched); -void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched); -void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched); -void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad); -void drm_sched_start(struct drm_gpu_scheduler *sched, int errno); -void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched); void drm_sched_increase_karma(struct drm_sched_job *bad); -void drm_sched_fault(struct drm_gpu_scheduler *sched); -void drm_sched_rq_add_entity(struct drm_sched_rq *rq, - struct drm_sched_entity *entity); -void drm_sched_rq_remove_entity(struct drm_sched_rq *rq, - struct drm_sched_entity *entity); +static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, + int threshold) +{ + return s_job && atomic_inc_return(&s_job->karma) > threshold; +} -void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, - struct drm_sched_rq *rq, ktime_t ts); +/* Entities */ int drm_sched_entity_init(struct drm_sched_entity *entity, enum drm_sched_priority priority, @@ -625,29 +623,11 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout); void drm_sched_entity_fini(struct drm_sched_entity *entity); void drm_sched_entity_destroy(struct drm_sched_entity *entity); -void drm_sched_entity_select_rq(struct drm_sched_entity *entity); -struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity); -void drm_sched_entity_push_job(struct drm_sched_job *sched_job); void drm_sched_entity_set_priority(struct drm_sched_entity *entity, enum drm_sched_priority priority); -bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); int drm_sched_entity_error(struct drm_sched_entity *entity); - -struct drm_sched_fence *drm_sched_fence_alloc( - struct drm_sched_entity *s_entity, void *owner); -void drm_sched_fence_init(struct drm_sched_fence *fence, - struct drm_sched_entity *entity); -void drm_sched_fence_free(struct drm_sched_fence *fence); - -void drm_sched_fence_scheduled(struct drm_sched_fence *fence, - struct dma_fence *parent); -void drm_sched_fence_finished(struct drm_sched_fence *fence, int result); - -unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched); -void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched, - unsigned long remaining); -struct drm_gpu_scheduler * -drm_sched_pick_best(struct drm_gpu_scheduler **sched_list, - unsigned int num_sched_list); +void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, + struct drm_gpu_scheduler **sched_list, + unsigned int num_sched_list); #endif diff --git a/include/drm/ttm/ttm_backup.h b/include/drm/ttm/ttm_backup.h new file mode 100644 index 000000000000..24ad120b8827 --- /dev/null +++ b/include/drm/ttm/ttm_backup.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef _TTM_BACKUP_H_ +#define _TTM_BACKUP_H_ + +#include <linux/mm_types.h> +#include <linux/shmem_fs.h> + +struct ttm_backup; + +/** + * ttm_backup_handle_to_page_ptr() - Convert handle to struct page pointer + * @handle: The handle to convert. + * + * Converts an opaque handle received from the + * struct ttm_backoup_ops::backup_page() function to an (invalid) + * struct page pointer suitable for a struct page array. + * + * Return: An (invalid) struct page pointer. + */ +static inline struct page * +ttm_backup_handle_to_page_ptr(unsigned long handle) +{ + return (struct page *)(handle << 1 | 1); +} + +/** + * ttm_backup_page_ptr_is_handle() - Whether a struct page pointer is a handle + * @page: The struct page pointer to check. + * + * Return: true if the struct page pointer is a handld returned from + * ttm_backup_handle_to_page_ptr(). False otherwise. + */ +static inline bool ttm_backup_page_ptr_is_handle(const struct page *page) +{ + return (unsigned long)page & 1; +} + +/** + * ttm_backup_page_ptr_to_handle() - Convert a struct page pointer to a handle + * @page: The struct page pointer to convert + * + * Return: The handle that was previously used in + * ttm_backup_handle_to_page_ptr() to obtain a struct page pointer, suitable + * for use as argument in the struct ttm_backup_ops drop() or + * copy_backed_up_page() functions. + */ +static inline unsigned long +ttm_backup_page_ptr_to_handle(const struct page *page) +{ + WARN_ON(!ttm_backup_page_ptr_is_handle(page)); + return (unsigned long)page >> 1; +} + +void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle); + +int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst, + pgoff_t handle, bool intr); + +s64 +ttm_backup_backup_page(struct ttm_backup *backup, struct page *page, + bool writeback, pgoff_t idx, gfp_t page_gfp, + gfp_t alloc_gfp); + +void ttm_backup_fini(struct ttm_backup *backup); + +u64 ttm_backup_bytes_avail(void); + +struct ttm_backup *ttm_backup_shmem_create(loff_t size); + +#endif diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h index 8ea11cd8df39..903cd1030110 100644 --- a/include/drm/ttm/ttm_bo.h +++ b/include/drm/ttm/ttm_bo.h @@ -226,6 +226,27 @@ s64 ttm_lru_walk_for_evict(struct ttm_lru_walk *walk, struct ttm_device *bdev, struct ttm_resource_manager *man, s64 target); /** + * struct ttm_bo_shrink_flags - flags to govern the bo shrinking behaviour + * @purge: Purge the content rather than backing it up. + * @writeback: Attempt to immediately write content to swap space. + * @allow_move: Allow moving to system before shrinking. This is typically + * not desired for zombie- or ghost objects (with zombie object meaning + * objects with a zero gem object refcount) + */ +struct ttm_bo_shrink_flags { + u32 purge : 1; + u32 writeback : 1; + u32 allow_move : 1; +}; + +long ttm_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo, + const struct ttm_bo_shrink_flags flags); + +bool ttm_bo_shrink_suitable(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx); + +bool ttm_bo_shrink_avoid_wait(void); + +/** * ttm_bo_get - reference a struct ttm_buffer_object * * @bo: The buffer object. @@ -467,4 +488,76 @@ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo); int ttm_bo_populate(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx); +/* Driver LRU walk helpers initially targeted for shrinking. */ + +/** + * struct ttm_bo_lru_cursor - Iterator cursor for TTM LRU list looping + */ +struct ttm_bo_lru_cursor { + /** @res_curs: Embedded struct ttm_resource_cursor. */ + struct ttm_resource_cursor res_curs; + /** + * @ctx: The struct ttm_operation_ctx used while looping. + * governs the locking mode. + */ + struct ttm_operation_ctx *ctx; + /** + * @bo: Buffer object pointer if a buffer object is refcounted, + * NULL otherwise. + */ + struct ttm_buffer_object *bo; + /** + * @needs_unlock: Valid iff @bo != NULL. The bo resv needs + * unlock before the next iteration or after loop exit. + */ + bool needs_unlock; +}; + +void ttm_bo_lru_cursor_fini(struct ttm_bo_lru_cursor *curs); + +struct ttm_bo_lru_cursor * +ttm_bo_lru_cursor_init(struct ttm_bo_lru_cursor *curs, + struct ttm_resource_manager *man, + struct ttm_operation_ctx *ctx); + +struct ttm_buffer_object *ttm_bo_lru_cursor_first(struct ttm_bo_lru_cursor *curs); + +struct ttm_buffer_object *ttm_bo_lru_cursor_next(struct ttm_bo_lru_cursor *curs); + +/* + * Defines needed to use autocleanup (linux/cleanup.h) with struct ttm_bo_lru_cursor. + */ +DEFINE_CLASS(ttm_bo_lru_cursor, struct ttm_bo_lru_cursor *, + if (_T) {ttm_bo_lru_cursor_fini(_T); }, + ttm_bo_lru_cursor_init(curs, man, ctx), + struct ttm_bo_lru_cursor *curs, struct ttm_resource_manager *man, + struct ttm_operation_ctx *ctx); +static inline void * +class_ttm_bo_lru_cursor_lock_ptr(class_ttm_bo_lru_cursor_t *_T) +{ return *_T; } +#define class_ttm_bo_lru_cursor_is_conditional false + +/** + * ttm_bo_lru_for_each_reserved_guarded() - Iterate over buffer objects owning + * resources on LRU lists. + * @_cursor: struct ttm_bo_lru_cursor to use for the iteration. + * @_man: The resource manager whose LRU lists to iterate over. + * @_ctx: The struct ttm_operation_context to govern the @_bo locking. + * @_bo: The struct ttm_buffer_object pointer pointing to the buffer object + * for the current iteration. + * + * Iterate over all resources of @_man and for each resource, attempt to + * reference and lock (using the locking mode detailed in @_ctx) the buffer + * object it points to. If successful, assign @_bo to the address of the + * buffer object and update @_cursor. The iteration is guarded in the + * sense that @_cursor will be initialized before looping start and cleaned + * up at looping termination, even if terminated prematurely by, for + * example a return or break statement. Exiting the loop will also unlock + * (if needed) and unreference @_bo. + */ +#define ttm_bo_lru_for_each_reserved_guarded(_cursor, _man, _ctx, _bo) \ + scoped_guard(ttm_bo_lru_cursor, _cursor, _man, _ctx) \ + for ((_bo) = ttm_bo_lru_cursor_first(_cursor); (_bo); \ + (_bo) = ttm_bo_lru_cursor_next(_cursor)) + #endif diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h index 160d954a261e..54cd34a6e4c0 100644 --- a/include/drm/ttm/ttm_pool.h +++ b/include/drm/ttm/ttm_pool.h @@ -33,6 +33,7 @@ struct device; struct seq_file; +struct ttm_backup_flags; struct ttm_operation_ctx; struct ttm_pool; struct ttm_tt; @@ -89,6 +90,13 @@ void ttm_pool_fini(struct ttm_pool *pool); int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m); +void ttm_pool_drop_backed_up(struct ttm_tt *tt); + +long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *ttm, + const struct ttm_backup_flags *flags); +int ttm_pool_restore_and_alloc(struct ttm_pool *pool, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx); + int ttm_pool_mgr_init(unsigned long num_pages); void ttm_pool_mgr_fini(void); diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 991edafdb2dd..13cf47f3322f 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -32,11 +32,13 @@ #include <drm/ttm/ttm_caching.h> #include <drm/ttm/ttm_kmap_iter.h> +struct ttm_backup; struct ttm_device; struct ttm_tt; struct ttm_resource; struct ttm_buffer_object; struct ttm_operation_ctx; +struct ttm_pool_tt_restore; /** * struct ttm_tt - This is a structure holding the pages, caching- and aperture @@ -85,17 +87,22 @@ struct ttm_tt { * fault handling abuses the DMA api a bit and dma_map_attrs can't be * used to assure pgprot always matches. * + * TTM_TT_FLAG_BACKED_UP: TTM internal only. This is set if the + * struct ttm_tt has been (possibly partially) backed up. + * * TTM_TT_FLAG_PRIV_POPULATED: TTM internal only. DO NOT USE. This is * set by TTM after ttm_tt_populate() has successfully returned, and is * then unset when TTM calls ttm_tt_unpopulate(). + * */ #define TTM_TT_FLAG_SWAPPED BIT(0) #define TTM_TT_FLAG_ZERO_ALLOC BIT(1) #define TTM_TT_FLAG_EXTERNAL BIT(2) #define TTM_TT_FLAG_EXTERNAL_MAPPABLE BIT(3) #define TTM_TT_FLAG_DECRYPTED BIT(4) +#define TTM_TT_FLAG_BACKED_UP BIT(5) -#define TTM_TT_FLAG_PRIV_POPULATED BIT(5) +#define TTM_TT_FLAG_PRIV_POPULATED BIT(6) uint32_t page_flags; /** @num_pages: Number of pages in the page array. */ uint32_t num_pages; @@ -106,10 +113,19 @@ struct ttm_tt { /** @swap_storage: Pointer to shmem struct file for swap storage. */ struct file *swap_storage; /** + * @backup: Pointer to backup struct for backed up tts. + * Could be unified with @swap_storage. Meanwhile, the driver's + * ttm_tt_create() callback is responsible for assigning + * this field. + */ + struct ttm_backup *backup; + /** * @caching: The current caching state of the pages, see enum * ttm_caching. */ enum ttm_caching caching; + /** @restore: Partial restoration from backup state. TTM private */ + struct ttm_pool_tt_restore *restore; }; /** @@ -129,9 +145,38 @@ static inline bool ttm_tt_is_populated(struct ttm_tt *tt) return tt->page_flags & TTM_TT_FLAG_PRIV_POPULATED; } +/** + * ttm_tt_is_swapped() - Whether the ttm_tt is swapped out or backed up + * @tt: The struct ttm_tt. + * + * Return: true if swapped or backed up, false otherwise. + */ static inline bool ttm_tt_is_swapped(const struct ttm_tt *tt) { - return tt->page_flags & TTM_TT_FLAG_SWAPPED; + return tt->page_flags & (TTM_TT_FLAG_SWAPPED | TTM_TT_FLAG_BACKED_UP); +} + +/** + * ttm_tt_is_backed_up() - Whether the ttm_tt backed up + * @tt: The struct ttm_tt. + * + * Return: true if swapped or backed up, false otherwise. + */ +static inline bool ttm_tt_is_backed_up(const struct ttm_tt *tt) +{ + return tt->page_flags & TTM_TT_FLAG_BACKED_UP; +} + +/** + * ttm_tt_clear_backed_up() - Clear the ttm_tt backed-up status + * @tt: The struct ttm_tt. + * + * Drivers can use this functionto clear the backed-up status, + * for example before destroying or re-validating a purged tt. + */ +static inline void ttm_tt_clear_backed_up(struct ttm_tt *tt) +{ + tt->page_flags &= ~TTM_TT_FLAG_BACKED_UP; } /** @@ -235,6 +280,26 @@ void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages); struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, struct ttm_tt *tt); unsigned long ttm_tt_pages_limit(void); + +/** + * struct ttm_backup_flags - Flags to govern backup behaviour. + * @purge: Free pages without backing up. Bypass pools. + * @writeback: Attempt to copy contents directly to swap space, even + * if that means blocking on writes to external memory. + */ +struct ttm_backup_flags { + u32 purge : 1; + u32 writeback : 1; +}; + +long ttm_tt_backup(struct ttm_device *bdev, struct ttm_tt *tt, + const struct ttm_backup_flags flags); + +int ttm_tt_restore(struct ttm_device *bdev, struct ttm_tt *tt, + const struct ttm_operation_ctx *ctx); + +int ttm_tt_setup_backup(struct ttm_tt *tt); + #if IS_ENABLED(CONFIG_AGP) #include <linux/agp_backend.h> diff --git a/include/dt-bindings/clock/qcom,dsi-phy-28nm.h b/include/dt-bindings/clock/qcom,dsi-phy-28nm.h new file mode 100644 index 000000000000..ab94d58377a1 --- /dev/null +++ b/include/dt-bindings/clock/qcom,dsi-phy-28nm.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ + +#ifndef _DT_BINDINGS_CLK_QCOM_DSI_PHY_28NM_H +#define _DT_BINDINGS_CLK_QCOM_DSI_PHY_28NM_H + +#define DSI_BYTE_PLL_CLK 0 +#define DSI_PIXEL_PLL_CLK 1 + +#endif diff --git a/include/linux/component.h b/include/linux/component.h index df4aa75c9e7c..9d6c66401280 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -3,7 +3,7 @@ #define COMPONENT_H #include <linux/stddef.h> - +#include <linux/types.h> struct device; @@ -90,6 +90,8 @@ int component_compare_dev_name(struct device *dev, void *data); void component_master_del(struct device *, const struct component_master_ops *); +bool component_master_is_bound(struct device *parent, + const struct component_master_ops *ops); struct component_match; diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index fa9f9846b88e..1e59344c5673 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -43,9 +43,10 @@ * - 1.15 - Enable managing mappings in compute VMs with GEM_VA ioctl * - 1.16 - Add contiguous VRAM allocation flag * - 1.17 - Add SDMA queue creation with target SDMA engine ID + * - 1.18 - Rename pad in set_memory_policy_args to misc_process_flag */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 17 +#define KFD_IOCTL_MINOR_VERSION 18 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -62,6 +63,8 @@ struct kfd_ioctl_get_version_args { #define KFD_MAX_QUEUE_PERCENTAGE 100 #define KFD_MAX_QUEUE_PRIORITY 15 +#define KFD_MIN_QUEUE_RING_SIZE 1024 + struct kfd_ioctl_create_queue_args { __u64 ring_base_address; /* to KFD */ __u64 write_pointer_address; /* from KFD */ @@ -148,6 +151,9 @@ struct kfd_dbg_device_info_entry { #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 +/* Misc. per process flags */ +#define KFD_PROC_FLAG_MFMA_HIGH_PRECISION (1 << 0) + struct kfd_ioctl_set_memory_policy_args { __u64 alternate_aperture_base; /* to KFD */ __u64 alternate_aperture_size; /* to KFD */ @@ -155,7 +161,7 @@ struct kfd_ioctl_set_memory_policy_args { __u32 gpu_id; /* to KFD */ __u32 default_policy; /* to KFD */ __u32 alternate_policy; /* to KFD */ - __u32 pad; + __u32 misc_process_flag; /* to KFD */ }; /* diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h index 859b8e91d4d3..1125fe47959f 100644 --- a/include/uapi/linux/kfd_sysfs.h +++ b/include/uapi/linux/kfd_sysfs.h @@ -63,6 +63,9 @@ #define HSA_CAP_PER_QUEUE_RESET_SUPPORTED 0x80000000 #define HSA_CAP_RESERVED 0x000f8000 +#define HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED 0x00000001 +#define HSA_CAP2_RESERVED 0xfffffffe + /* debug_prop bits in node properties */ #define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK 0x0000000f #define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_SHIFT 0 diff --git a/include/video/imx-ipu-image-convert.h b/include/video/imx-ipu-image-convert.h index 3c71b8b94b33..003b3927ede5 100644 --- a/include/video/imx-ipu-image-convert.h +++ b/include/video/imx-ipu-image-convert.h @@ -41,19 +41,6 @@ typedef void (*ipu_image_convert_cb_t)(struct ipu_image_convert_run *run, void *ctx); /** - * ipu_image_convert_enum_format() - enumerate the image converter's - * supported input and output pixel formats. - * - * @index: pixel format index - * @fourcc: v4l2 fourcc for this index - * - * Returns 0 with a valid index and fills in v4l2 fourcc, -EINVAL otherwise. - * - * In V4L2, drivers can call ipu_image_enum_format() in .enum_fmt. - */ -int ipu_image_convert_enum_format(int index, u32 *fourcc); - -/** * ipu_image_convert_adjust() - adjust input/output images to IPU restrictions. * * @in: input image format, adjusted on return @@ -176,23 +163,4 @@ ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task, ipu_image_convert_cb_t complete, void *complete_context); -/** - * ipu_image_convert_sync() - synchronous single image conversion request - * - * @ipu: the IPU handle to use for the conversion - * @ic_task: the IC task to use for the conversion - * @in: input image format - * @out: output image format - * @rot_mode: rotation mode - * - * Carry out a single image conversion. Returns when the conversion - * completes. The input/output formats and rotation mode must already - * meet IPU retrictions. The created context is automatically unprepared - * and the run freed on return. - */ -int ipu_image_convert_sync(struct ipu_soc *ipu, enum ipu_ic_task ic_task, - struct ipu_image *in, struct ipu_image *out, - enum ipu_rotate_mode rot_mode); - - #endif /* __IMX_IPU_IMAGE_CONVERT_H__ */ diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index c422a403c099..c89574b6f527 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -262,7 +262,6 @@ void ipu_cpmem_set_uv_offset(struct ipuv3_channel *ch, u32 u_off, u32 v_off); void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride, u32 pixelformat); void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id); -int ipu_cpmem_get_burstsize(struct ipuv3_channel *ch); void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize); void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch); void ipu_cpmem_set_rotation(struct ipuv3_channel *ch, @@ -270,7 +269,6 @@ void ipu_cpmem_set_rotation(struct ipuv3_channel *ch, int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch, const struct ipu_rgb *rgb); int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width); -void ipu_cpmem_set_yuv_interleaved(struct ipuv3_channel *ch, u32 pixel_format); void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch, unsigned int uv_stride, unsigned int u_offset, @@ -361,13 +359,8 @@ int ipu_csi_init_interface(struct ipu_csi *csi, const struct v4l2_mbus_config *mbus_cfg, const struct v4l2_mbus_framefmt *infmt, const struct v4l2_mbus_framefmt *outfmt); -bool ipu_csi_is_interlaced(struct ipu_csi *csi); -void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w); void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w); void ipu_csi_set_downsize(struct ipu_csi *csi, bool horiz, bool vert); -void ipu_csi_set_test_generator(struct ipu_csi *csi, bool active, - u32 r_value, u32 g_value, u32 b_value, - u32 pix_clk); int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc, struct v4l2_mbus_framefmt *mbus_fmt); int ipu_csi_set_skip_smfc(struct ipu_csi *csi, u32 skip, @@ -445,10 +438,6 @@ int ipu_ic_task_init_rsc(struct ipu_ic *ic, int in_width, int in_height, int out_width, int out_height, u32 rsc); -int ipu_ic_task_graphics_init(struct ipu_ic *ic, - const struct ipu_ic_colorspace *g_in_cs, - bool galpha_en, u32 galpha, - bool colorkey_en, u32 colorkey); void ipu_ic_task_enable(struct ipu_ic *ic); void ipu_ic_task_disable(struct ipu_ic *ic); int ipu_ic_task_idma_init(struct ipu_ic *ic, struct ipuv3_channel *channel, @@ -467,7 +456,6 @@ struct ipu_vdi; void ipu_vdi_set_field_order(struct ipu_vdi *vdi, v4l2_std_id std, u32 field); void ipu_vdi_set_motion(struct ipu_vdi *vdi, enum ipu_motion_sel motion_sel); void ipu_vdi_setup(struct ipu_vdi *vdi, u32 code, int xres, int yres); -void ipu_vdi_unsetup(struct ipu_vdi *vdi); int ipu_vdi_enable(struct ipu_vdi *vdi); int ipu_vdi_disable(struct ipu_vdi *vdi); struct ipu_vdi *ipu_vdi_get(struct ipu_soc *ipu); @@ -488,8 +476,6 @@ enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc); enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat); int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees, bool hflip, bool vflip); -int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode, - bool hflip, bool vflip); struct ipu_client_platformdata { int csi; |