Merge 477f70cd2a ("Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm") into android-mainline

Steps on the way to 5.15-rc1

Resolves merge conflicts in:
	drivers/firmware/Makefile

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Icdf4539d0985fd5a3430455c3a2b603b2b456a44

Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers

@@ -0,0 +1,24 @@
+What:		/sys/kernel/dmabuf/buffers
+Date:		May 2021
+KernelVersion:	v5.13
+Contact:	Hridya Valsaraju <hridya@google.com>
+Description:	The /sys/kernel/dmabuf/buffers directory contains a
+		snapshot of the internal state of every DMA-BUF.
+		/sys/kernel/dmabuf/buffers/<inode_number> will contain the
+		statistics for the DMA-BUF with the unique inode number
+		<inode_number>
+Users:		kernel memory tuning/debugging tools
+
+What:		/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name
+Date:		May 2021
+KernelVersion:	v5.13
+Contact:	Hridya Valsaraju <hridya@google.com>
+Description:	This file is read-only and contains the name of the exporter of
+		the DMA-BUF.
+
+What:		/sys/kernel/dmabuf/buffers/<inode_number>/size
+Date:		May 2021
+KernelVersion:	v5.13
+Contact:	Hridya Valsaraju <hridya@google.com>
+Description:	This file is read-only and specifies the size of the DMA-BUF in
+		bytes.

Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml

@@ -22,6 +22,9 @@ properties:
               - ti,ths8134a
               - ti,ths8134b
           - const: ti,ths8134
+      - items:
+          - const: corpro,gm7123
+          - const: adi,adv7123
       - enum:
           - adi,adv7123
           - dumb-vga-dac

Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml

@@ -70,6 +70,9 @@ properties:
     const: 1
     description: See ../../pwm/pwm.yaml for description of the cell formats.
 
+  aux-bus:
+    $ref: /schemas/display/dp-aux-bus.yaml#
+
   ports:
     $ref: /schemas/graph.yaml#/properties/ports
 
@@ -150,7 +153,6 @@ properties:
 required:
   - compatible
   - reg
-  - enable-gpios
   - vccio-supply
   - vpll-supply
   - vcca-supply
@@ -201,11 +203,26 @@ examples:
 
           port@1 {
             reg = <1>;
-            endpoint {
+            sn65dsi86_out: endpoint {
               remote-endpoint = <&panel_in_edp>;
             };
           };
         };
+
+        aux-bus {
+          panel {
+            compatible = "boe,nv133fhm-n62";
+            power-supply = <&pp3300_dx_edp>;
+            backlight = <&backlight>;
+            hpd-gpios = <&sn65dsi86_bridge 2 GPIO_ACTIVE_HIGH>;
+
+            port {
+              panel_in_edp: endpoint {
+                remote-endpoint = <&sn65dsi86_out>;
+              };
+            };
+          };
+        };
       };
     };
   - |

Documentation/devicetree/bindings/display/dp-aux-bus.yaml

@@ -0,0 +1,37 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/dp-aux-bus.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: DisplayPort AUX bus
+
+maintainers:
+  - Douglas Anderson <dianders@chromium.org>
+
+description:
+  DisplayPort controllers provide a control channel to the sinks that
+  are hooked up to them. This is the DP AUX bus. Over the DP AUX bus
+  we can query properties about a sink and also configure it. In
+  particular, DP sinks support DDC over DP AUX which allows tunneling
+  a standard I2C DDC connection over the AUX channel.
+
+  To model this relationship, DP sinks should be placed as children
+  of the DP controller under the "aux-bus" node.
+
+  At the moment, this binding only handles the eDP case. It is
+  possible it will be extended in the future to handle the DP case.
+  For DP, presumably a connector would be listed under the DP AUX
+  bus instead of a panel.
+
+properties:
+  $nodename:
+    const: "aux-bus"
+
+  panel:
+    $ref: panel/panel-common.yaml#
+
+additionalProperties: false
+
+required:
+  - panel

Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt

@@ -7,7 +7,7 @@ channel output.
 
 Required properties:
 - compatible: "mediatek,<chip>-dsi"
-- the supported chips are mt2701, mt7623, mt8173 and mt8183.
+- the supported chips are mt2701, mt7623, mt8167, mt8173 and mt8183.
 - reg: Physical base address and length of the controller's registers
 - interrupts: The interrupt signal from the function block.
 - clocks: device clocks

Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml

@@ -64,6 +64,18 @@ properties:
       Indicates if the DSI controller is driving a panel which needs
       2 DSI links.
 
+  assigned-clocks:
+    minItems: 2
+    maxItems: 2
+    description: |
+      Parents of "byte" and "pixel" for the given platform.
+
+  assigned-clock-parents:
+    minItems: 2
+    maxItems: 2
+    description: |
+      The Byte clock and Pixel clock PLL outputs provided by a DSI PHY block.
+
   power-domains:
     maxItems: 1
 
@@ -119,6 +131,8 @@ required:
   - clock-names
   - phys
   - phy-names
+  - assigned-clocks
+  - assigned-clock-parents
   - power-domains
   - operating-points-v2
   - ports
@@ -159,6 +173,9 @@ examples:
            phys = <&dsi0_phy>;
            phy-names = "dsi";
 
+           assigned-clocks = <&dispcc DISP_CC_MDSS_BYTE0_CLK_SRC>, <&dispcc DISP_CC_MDSS_PCLK0_CLK_SRC>;
+           assigned-clock-parents = <&dsi_phy 0>, <&dsi_phy 1>;
+
            power-domains = <&rpmhpd SC7180_CX>;
            operating-points-v2 = <&dsi_opp_table>;
 

Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml

@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only or BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/msm/dsi-phy-7nm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display DSI 7nm PHY
+
+maintainers:
+  - Jonathan Marek <jonathan@marek.ca>
+
+allOf:
+  - $ref: dsi-phy-common.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: qcom,dsi-phy-7nm
+      - const: qcom,dsi-phy-7nm-8150
+      - const: qcom,sc7280-dsi-phy-7nm
+
+  reg:
+    items:
+      - description: dsi phy register set
+      - description: dsi phy lane register set
+      - description: dsi pll register set
+
+  reg-names:
+    items:
+      - const: dsi_phy
+      - const: dsi_phy_lane
+      - const: dsi_pll
+
+  vdds-supply:
+    description: |
+      Connected to VDD_A_DSI_PLL_0P9 pin (or VDDA_DSI{0,1}_PLL_0P9 for sm8150)
+
+  phy-type:
+    description: D-PHY (default) or C-PHY mode
+    enum: [ 10, 11 ]
+    default: 10
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - vdds-supply
+
+unevaluatedProperties: false
+
+examples:
+  - |
+     #include <dt-bindings/clock/qcom,dispcc-sm8250.h>
+     #include <dt-bindings/clock/qcom,rpmh.h>
+
+     dsi-phy@ae94400 {
+         compatible = "qcom,dsi-phy-7nm";
+         reg = <0x0ae94400 0x200>,
+               <0x0ae94600 0x280>,
+               <0x0ae94900 0x260>;
+         reg-names = "dsi_phy",
+                     "dsi_phy_lane",
+                     "dsi_pll";
+
+         #clock-cells = <1>;
+         #phy-cells = <0>;
+
+         vdds-supply = <&vreg_l5a_0p88>;
+         clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+                  <&rpmhcc RPMH_CXO_CLK>;
+         clock-names = "iface", "ref";
+     };

Documentation/devicetree/bindings/display/panel/ilitek,ili9341.yaml

@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/ilitek,ili9341.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Ilitek-9341 Display Panel
+
+maintainers:
+  - Dillon Min <dillon.minfei@gmail.com>
+
+description: |
+  Ilitek ILI9341 TFT panel driver with SPI control bus
+  This is a driver for 320x240 TFT panels, accepting a rgb input
+  streams with 16 bits or 18 bits.
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    items:
+      - enum:
+          # ili9341 240*320 Color on stm32f429-disco board
+        - st,sf-tc240t-9370-t
+      - const: ilitek,ili9341
+
+  reg: true
+
+  dc-gpios:
+    maxItems: 1
+    description: Display data/command selection (D/CX) of this DBI panel
+
+  spi-3wire: true
+
+  spi-max-frequency:
+    const: 10000000
+
+  port: true
+
+  vci-supply:
+    description: Analog voltage supply (2.5 .. 3.3V)
+
+  vddi-supply:
+    description: Voltage supply for interface logic (1.65 .. 3.3 V)
+
+  vddi-led-supply:
+    description: Voltage supply for the LED driver (1.65 .. 3.3 V)
+
+additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - dc-gpios
+  - port
+
+examples:
+  - |+
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel: display@0 {
+                 compatible = "st,sf-tc240t-9370-t",
+                              "ilitek,ili9341";
+                 reg = <0>;
+                 spi-3wire;
+                 spi-max-frequency = <10000000>;
+                 dc-gpios = <&gpiod 13 0>;
+                 port {
+                         panel_in: endpoint {
+                           remote-endpoint = <&display_out>;
+                      };
+                 };
+             };
+        };
+...
+

Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml

@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/innolux,ej030na.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Innolux EJ030NA 3.0" (320x480 pixels) 24-bit TFT LCD panel
+
+description: |
+  The panel must obey the rules for a SPI slave device as specified in
+  spi/spi-controller.yaml
+
+maintainers:
+  - Paul Cercueil <paul@crapouillou.net>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: innolux,ej030na
+
+  backlight: true
+  port: true
+  power-supply: true
+  reg: true
+  reset-gpios: true
+
+required:
+  - compatible
+  - reg
+  - power-supply
+  - reset-gpios
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        panel@0 {
+            compatible = "innolux,ej030na";
+            reg = <0>;
+
+            spi-max-frequency = <10000000>;
+
+            reset-gpios = <&gpe 4 GPIO_ACTIVE_LOW>;
+            power-supply = <&lcd_power>;
+
+            backlight = <&backlight>;
+
+            port {
+                panel_input: endpoint {
+                    remote-endpoint = <&panel_output>;
+                };
+            };
+        };
+    };

Documentation/devicetree/bindings/display/panel/panel-simple.yaml

@@ -46,9 +46,13 @@ properties:
         # AU Optronics Corporation 11.6" HD (1366x768) color TFT-LCD panel
       - auo,b116xw03
         # AU Optronics Corporation 13.3" FHD (1920x1080) color TFT-LCD panel
+      - auo,b133han05
+        # AU Optronics Corporation 13.3" FHD (1920x1080) color TFT-LCD panel
       - auo,b133htn01
         # AU Optronics Corporation 13.3" WXGA (1366x768) TFT LCD panel
       - auo,b133xtn01
+        # AU Optronics Corporation 14.0" FHD (1920x1080) color TFT-LCD panel
+      - auo,b140han06
         # AU Optronics Corporation 7.0" FHD (800 x 480) TFT LCD panel
       - auo,g070vvn01
         # AU Optronics Corporation 10.1" (1280x800) color TFT LCD panel
@@ -110,6 +114,9 @@ properties:
         # Emerging Display Technology Corp. 5.7" VGA TFT LCD panel
       - edt,et057090dhu
       - edt,et070080dh6
+        # Emerging Display Technology Corp. 3.5" WVGA TFT LCD panel with
+        # capacitive multitouch
+      - edt,etm0350g0dh6
         # Emerging Display Technology Corp. 480x272 TFT Display with capacitive touch
       - edt,etm043080dh6gp
         # Emerging Display Technology Corp. 480x272 TFT Display
@@ -128,6 +135,11 @@ properties:
         # Emerging Display Technology Corp. WVGA TFT Display with capacitive touch
       - edt,etm0700g0dh6
       - edt,etm0700g0edh6
+        # Emerging Display Technology Corp. 5.7" VGA TFT LCD panel with
+        # capacitive touch
+      - edt,etmv570g2dhu
+        # E Ink VB3300-KCA
+      - eink,vb3300-kca
         # Evervision Electronics Co. Ltd. VGG804821 5.0" WVGA TFT LCD Panel
       - evervision,vgg804821
         # Foxlink Group 5" WVGA TFT LCD panel
@@ -202,8 +214,14 @@ properties:
       - logictechno,lt161010-2nhr
         # Logic Technologies LT170410-2WHC 10.1" 1280x800 IPS TFT Cap Touch Mod.
       - logictechno,lt170410-2whc
+        # Logic Technologies LTTD800x480 L2RT 7" 800x480 TFT Resistive Touch Module
+      - logictechno,lttd800480070-l2rt
+        # Logic Technologies LTTD800480070-L6WH-RT 7” 800x480 TFT Resistive Touch Module
+      - logictechno,lttd800480070-l6wh-rt
         # Mitsubishi "AA070MC01 7.0" WVGA TFT LCD panel
       - mitsubishi,aa070mc01-ca1
+        # Multi-Inno Technology Co.,Ltd MI1010AIT-1CP 10.1" 1280x800 LVDS IPS Cap Touch Mod.
+      - multi-inno,mi1010ait-1cp
         # NEC LCD Technologies, Ltd. 12.1" WXGA (1280x800) LVDS TFT LCD panel
       - nec,nl12880bc20-05
         # NEC LCD Technologies,Ltd. WQVGA TFT LCD panel
@@ -238,10 +256,14 @@ properties:
       - powertip,ph800480t013-idf02
         # QiaoDian XianShi Corporation 4"3 TFT LCD panel
       - qiaodian,qd43003c0-40
+        # Shenzhen QiShenglong Industrialist Co., Ltd. Gopher 2b 4.3" 480(RGB)x272 TFT LCD panel
+      - qishenglong,gopher2b-lcd
         # Rocktech Displays Ltd. RK101II01D-CT 10.1" TFT 1280x800
       - rocktech,rk101ii01d-ct
         # Rocktech Display Ltd. RK070ER9427 800(RGB)x480 TFT LCD panel
       - rocktech,rk070er9427
+        # Samsung 13.3" FHD (1920x1080 pixels) eDP AMOLED panel
+      - samsung,atna33xc20
         # Samsung 12.2" (2560x1600 pixels) TFT LCD panel
       - samsung,lsn122dl01-c01
         # Samsung Electronics 10.1" WSVGA TFT LCD panel
@@ -298,6 +320,8 @@ properties:
   enable-gpios: true
   port: true
   power-supply: true
+  no-hpd: true
+  hpd-gpios: true
 
 additionalProperties: false
 

Documentation/devicetree/bindings/display/panel/samsung,lms380kf01.yaml

@@ -0,0 +1,99 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/samsung,lms380kf01.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung LMS380KF01 display panel
+
+description: The LMS380KF01 is a 480x800 DPI display panel from Samsung Mobile
+  Displays (SMD) utilizing the WideChips WS2401 display controller. It can be
+  used with internal or external backlight control.
+  The panel must obey the rules for a SPI slave device as specified in
+  spi/spi-controller.yaml
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: samsung,lms380kf01
+
+  reg: true
+
+  interrupts:
+    description: provides an optional ESD (electrostatic discharge)
+      interrupt that signals abnormalities in the display hardware.
+      This can also be raised for other reasons like erroneous
+      configuration.
+    maxItems: 1
+
+  reset-gpios: true
+
+  vci-supply:
+    description: regulator that supplies the VCI analog voltage
+      usually around 3.0 V
+
+  vccio-supply:
+    description: regulator that supplies the VCCIO voltage usually
+      around 1.8 V
+
+  backlight: true
+
+  spi-cpha: true
+
+  spi-cpol: true
+
+  spi-max-frequency:
+    maximum: 1200000
+
+  port: true
+
+required:
+  - compatible
+  - reg
+  - spi-cpha
+  - spi-cpol
+  - port
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    spi {
+        compatible = "spi-gpio";
+        sck-gpios = <&gpio 0 GPIO_ACTIVE_HIGH>;
+        miso-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>;
+        mosi-gpios = <&gpio 2 GPIO_ACTIVE_HIGH>;
+        cs-gpios = <&gpio 3 GPIO_ACTIVE_HIGH>;
+        num-chipselects = <1>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        panel@0 {
+            compatible = "samsung,lms380kf01";
+            spi-max-frequency = <1200000>;
+            spi-cpha;
+            spi-cpol;
+            reg = <0>;
+            vci-supply = <&lcd_3v0_reg>;
+            vccio-supply = <&lcd_1v8_reg>;
+            reset-gpios = <&gpio 4 GPIO_ACTIVE_LOW>;
+            interrupt-parent = <&gpio>;
+            interrupts = <5 IRQ_TYPE_EDGE_RISING>;
+
+            port {
+                panel_in: endpoint {
+                    remote-endpoint = <&display_out>;
+                };
+            };
+        };
+    };
+
+...

Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml

@@ -33,8 +33,11 @@ properties:
 
   backlight: true
 
+  spi-cpha: true
+
+  spi-cpol: true
+
   spi-max-frequency:
-    $ref: /schemas/types.yaml#/definitions/uint32
     description: inherited as a SPI client node, the datasheet specifies
       maximum 300 ns minimum cycle which gives around 3 MHz max frequency
     maximum: 3000000
@@ -44,6 +47,9 @@ properties:
 required:
   - compatible
   - reg
+  - spi-cpha
+  - spi-cpol
+  - port
 
 additionalProperties: false
 
@@ -52,15 +58,23 @@ examples:
     #include <dt-bindings/gpio/gpio.h>
 
     spi {
+      compatible = "spi-gpio";
+      sck-gpios = <&gpio 0 GPIO_ACTIVE_HIGH>;
+      miso-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>;
+      mosi-gpios = <&gpio 2 GPIO_ACTIVE_HIGH>;
+      cs-gpios = <&gpio 3 GPIO_ACTIVE_HIGH>;
+      num-chipselects = <1>;
       #address-cells = <1>;
       #size-cells = <0>;
       panel@0 {
         compatible = "samsung,lms397kf04";
         spi-max-frequency = <3000000>;
+        spi-cpha;
+        spi-cpol;
         reg = <0>;
         vci-supply = <&lcd_3v0_reg>;
         vccio-supply = <&lcd_1v8_reg>;
-        reset-gpios = <&gpio 1 GPIO_ACTIVE_LOW>;
+        reset-gpios = <&gpio 4 GPIO_ACTIVE_LOW>;
         backlight = <&ktd259>;
 
         port {

Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt

@@ -23,6 +23,7 @@ Required properties:
 Optional properties:
 - phys: from general PHY binding: the phandle for the PHY device.
 - phy-names: Should be "dphy" if phys references an external phy.
+- #phy-cells: Defined when used as ISP phy, should be 0.
 - power-domains: a phandle to mipi dsi power domain node.
 - resets: list of phandle + reset specifier pairs, as described in [3].
 - reset-names: string reset name, must be "apb".

Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml

@@ -0,0 +1,208 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/solomon,ssd1307fb.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Solomon SSD1307 OLED Controller Framebuffer
+
+maintainers:
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    enum:
+      - solomon,ssd1305fb-i2c
+      - solomon,ssd1306fb-i2c
+      - solomon,ssd1307fb-i2c
+      - solomon,ssd1309fb-i2c
+
+  reg:
+    maxItems: 1
+
+  pwms:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  vbat-supply:
+    description: The supply for VBAT
+
+  solomon,height:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 16
+    description:
+      Height in pixel of the screen driven by the controller
+
+  solomon,width:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 96
+    description:
+      Width in pixel of the screen driven by the controller
+
+  solomon,page-offset:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 1
+    description:
+      Offset of pages (band of 8 pixels) that the screen is mapped to
+
+  solomon,segment-no-remap:
+    type: boolean
+    description:
+      Display needs normal (non-inverted) data column to segment mapping
+
+  solomon,col-offset:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 0
+    description:
+      Offset of columns (COL/SEG) that the screen is mapped to
+
+  solomon,com-seq:
+    type: boolean
+    description:
+      Display uses sequential COM pin configuration
+
+  solomon,com-lrremap:
+    type: boolean
+    description:
+      Display uses left-right COM pin remap
+
+  solomon,com-invdir:
+    type: boolean
+    description:
+      Display uses inverted COM pin scan direction
+
+  solomon,com-offset:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 0
+    description:
+      Number of the COM pin wired to the first display line
+
+  solomon,prechargep1:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 2
+    description:
+      Length of deselect period (phase 1) in clock cycles
+
+  solomon,prechargep2:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 2
+    description:
+      Length of precharge period (phase 2) in clock cycles.  This needs to be
+      the higher, the higher the capacitance of the OLED's pixels is.
+
+  solomon,dclk-div:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 1
+    maximum: 16
+    description:
+      Clock divisor. The default value is controller-dependent.
+
+  solomon,dclk-frq:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 15
+    description:
+      Clock frequency, higher value means higher frequency.
+      The default value is controller-dependent.
+
+  solomon,lookup-table:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    maxItems: 4
+    description:
+      8 bit value array of current drive pulse widths for BANK0, and colors A,
+      B, and C. Each value in range of 31 to 63 for pulse widths of 32 to 64.
+      Color D is always width 64.
+
+  solomon,area-color-enable:
+    type: boolean
+    description:
+      Display uses color mode
+
+  solomon,low-power:
+    type: boolean
+    description:
+      Display runs in low power mode
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: solomon,ssd1305fb-i2c
+    then:
+      properties:
+        solomon,dclk-div:
+          default: 1
+        solomon,dclk-frq:
+          default: 7
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: solomon,ssd1306fb-i2c
+    then:
+      properties:
+        solomon,dclk-div:
+          default: 1
+        solomon,dclk-frq:
+          default: 8
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: solomon,ssd1307fb-i2c
+    then:
+      properties:
+        solomon,dclk-div:
+          default: 2
+        solomon,dclk-frq:
+          default: 12
+      required:
+        - pwms
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: solomon,ssd1309fb-i2c
+    then:
+      properties:
+        solomon,dclk-div:
+          default: 1
+        solomon,dclk-frq:
+          default: 10
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c1 {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            ssd1307: oled@3c {
+                    compatible = "solomon,ssd1307fb-i2c";
+                    reg = <0x3c>;
+                    pwms = <&pwm 4 3000>;
+                    reset-gpios = <&gpio2 7>;
+            };
+
+            ssd1306: oled@3d {
+                    compatible = "solomon,ssd1306fb-i2c";
+                    reg = <0x3c>;
+                    pwms = <&pwm 4 3000>;
+                    reset-gpios = <&gpio2 7>;
+                    solomon,com-lrremap;
+                    solomon,com-invdir;
+                    solomon,com-offset = <32>;
+                    solomon,lookup-table = /bits/ 8 <0x3f 0x3f 0x3f 0x3f>;
+            };
+    };

Documentation/devicetree/bindings/display/ssd1307fb.txt

@@ -1,60 +0,0 @@
-* Solomon SSD1307 Framebuffer Driver
-
-Required properties:
-  - compatible: Should be "solomon,<chip>fb-<bus>". The only supported bus for
-    now is i2c, and the supported chips are ssd1305, ssd1306, ssd1307 and
-    ssd1309.
-  - reg: Should contain address of the controller on the I2C bus. Most likely
-         0x3c or 0x3d
-  - pwm: Should contain the pwm to use according to the OF device tree PWM
-         specification [0]. Only required for the ssd1307.
-  - solomon,height: Height in pixel of the screen driven by the controller
-  - solomon,width: Width in pixel of the screen driven by the controller
-  - solomon,page-offset: Offset of pages (band of 8 pixels) that the screen is
-    mapped to.
-
-Optional properties:
-  - reset-gpios: The GPIO used to reset the OLED display, if available. See
-                 Documentation/devicetree/bindings/gpio/gpio.txt for details.
-  - vbat-supply: The supply for VBAT
-  - solomon,segment-no-remap: Display needs normal (non-inverted) data column
-                              to segment mapping
-  - solomon,col-offset: Offset of columns (COL/SEG) that the screen is mapped to.
-  - solomon,com-seq: Display uses sequential COM pin configuration
-  - solomon,com-lrremap: Display uses left-right COM pin remap
-  - solomon,com-invdir: Display uses inverted COM pin scan direction
-  - solomon,com-offset: Number of the COM pin wired to the first display line
-  - solomon,prechargep1: Length of deselect period (phase 1) in clock cycles.
-  - solomon,prechargep2: Length of precharge period (phase 2) in clock cycles.
-                         This needs to be the higher, the higher the capacitance
-                         of the OLED's pixels is
-  - solomon,dclk-div: Clock divisor 1 to 16
-  - solomon,dclk-frq: Clock frequency 0 to 15, higher value means higher
-                      frequency
-  - solomon,lookup-table: 8 bit value array of current drive pulse widths for
-                          BANK0, and colors A, B, and C. Each value in range
-                          of 31 to 63 for pulse widths of 32 to 64. Color D
-                          is always width 64.
-  - solomon,area-color-enable: Display uses color mode
-  - solomon,low-power. Display runs in low power mode
-
-[0]: Documentation/devicetree/bindings/pwm/pwm.txt
-
-Examples:
-ssd1307: oled@3c {
-        compatible = "solomon,ssd1307fb-i2c";
-        reg = <0x3c>;
-        pwms = <&pwm 4 3000>;
-        reset-gpios = <&gpio2 7>;
-};
-
-ssd1306: oled@3c {
-        compatible = "solomon,ssd1306fb-i2c";
-        reg = <0x3c>;
-        pwms = <&pwm 4 3000>;
-        reset-gpios = <&gpio2 7>;
-        solomon,com-lrremap;
-        solomon,com-invdir;
-        solomon,com-offset = <32>;
-        solomon,lookup-table = /bits/ 8 <0x3f 0x3f 0x3f 0x3f>;
-};

Documentation/devicetree/bindings/vendor-prefixes.yaml

@@ -341,6 +341,8 @@ patternProperties:
     description: eGalax_eMPIA Technology Inc
   "^einfochips,.*":
     description: Einfochips
+  "^eink,.*":
+    description: E Ink Corporation
   "^elan,.*":
     description: Elan Microelectronic Corp.
   "^element14,.*":
@@ -938,6 +940,8 @@ patternProperties:
     description: Chengdu Kaixuan Information Technology Co., Ltd.
   "^qiaodian,.*":
     description: QiaoDian XianShi Corporation
+  "^qishenglong,.*":
+    description: Shenzhen QiShenglong Industrialist Co., Ltd.
   "^qnap,.*":
     description: QNAP Systems, Inc.
   "^radxa,.*":

Documentation/driver-api/dma-buf.rst

@@ -88,6 +88,9 @@ consider though:
 - The DMA buffer FD is also pollable, see `Implicit Fence Poll Support`_ below for
   details.
 
+- The DMA buffer FD also supports a few dma-buf-specific ioctls, see
+  `DMA Buffer ioctls`_ below for details.
+
 Basic Operation and Device DMA Access
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -106,6 +109,16 @@ Implicit Fence Poll Support
 .. kernel-doc:: drivers/dma-buf/dma-buf.c
    :doc: implicit fence polling
 
+DMA-BUF statistics
+~~~~~~~~~~~~~~~~~~
+.. kernel-doc:: drivers/dma-buf/dma-buf-sysfs-stats.c
+   :doc: overview
+
+DMA Buffer ioctls
+~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/uapi/linux/dma-buf.h
+
 Kernel Functions and Structures Reference
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

Documentation/driver-api/thermal/nouveau_thermal.rst

@@ -90,7 +90,7 @@ Bug reports
 -----------
 
 Thermal management on Nouveau is new and may not work on all cards. If you have
-inquiries, please ping mupuf on IRC (#nouveau, freenode).
+inquiries, please ping mupuf on IRC (#nouveau, OFTC).
 
 Bug reports should be filled on Freedesktop's bug tracker. Please follow
 https://nouveau.freedesktop.org/wiki/Bugs

Documentation/gpu/drm-kms.rst

@@ -159,6 +159,8 @@ KMS Core Structures and Functions
 .. kernel-doc:: drivers/gpu/drm/drm_mode_config.c
    :export:
 
+.. _kms_base_object_abstraction:
+
 Modeset Base Object Abstraction
 ===============================
 
@@ -463,6 +465,35 @@ KMS Properties
 This section of the documentation is primarily aimed at user-space developers.
 For the driver APIs, see the other sections.
 
+Requirements
+------------
+
+KMS drivers might need to add extra properties to support new features. Each
+new property introduced in a driver needs to meet a few requirements, in
+addition to the one mentioned above:
+
+* It must be standardized, documenting:
+
+  * The full, exact, name string;
+  * If the property is an enum, all the valid value name strings;
+  * What values are accepted, and what these values mean;
+  * What the property does and how it can be used;
+  * How the property might interact with other, existing properties.
+
+* It must provide a generic helper in the core code to register that
+  property on the object it attaches to.
+
+* Its content must be decoded by the core and provided in the object's
+  associated state structure. That includes anything drivers might want
+  to precompute, like struct drm_clip_rect for planes.
+
+* Its initial state must match the behavior prior to the property
+  introduction. This might be a fixed value matching what the hardware
+  does, or it may be inherited from the state the firmware left the
+  system in during boot.
+
+* An IGT test must be submitted where reasonable.
+
 Property Types and Blob Property Support
 ----------------------------------------
 
@@ -508,8 +539,8 @@ Plane Composition Properties
 Damage Tracking Properties
 --------------------------
 
-.. kernel-doc:: drivers/gpu/drm/drm_damage_helper.c
+.. kernel-doc:: drivers/gpu/drm/drm_plane.c
-   :doc: overview
+   :doc: damage tracking
 
 Color Management Properties
 ---------------------------

Documentation/gpu/drm-uapi.rst

@@ -37,6 +37,15 @@ Primary Nodes, DRM Master and Authentication
 .. kernel-doc:: include/drm/drm_auth.h
    :internal:
 
+
+.. _drm_leasing:
+
+DRM Display Resource Leasing
+============================
+
+.. kernel-doc:: drivers/gpu/drm/drm_lease.c
+   :doc: drm leasing
+
 Open-Source Userspace Requirements
 ==================================
 
@@ -457,6 +466,19 @@ Userspace API Structures
 .. kernel-doc:: include/uapi/drm/drm_mode.h
    :doc: overview
 
+.. _crtc_index:
+
+CRTC index
+----------
+
+CRTC's have both an object ID and an index, and they are not the same thing.
+The index is used in cases where a densely packed identifier for a CRTC is
+needed, for instance a bitmask of CRTC's. The member possible_crtcs of struct
+drm_mode_get_plane is an example.
+
+DRM_IOCTL_MODE_GETRESOURCES populates a structure with an array of CRTC ID's,
+and the CRTC index is its position in this array.
+
 .. kernel-doc:: include/uapi/drm/drm.h
    :internal:
 

Documentation/gpu/i915.rst

@@ -422,9 +422,16 @@ Batchbuffer Parsing
 User Batchbuffer Execution
 --------------------------
 
+.. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+
 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
    :doc: User command execution
 
+Scheduling
+----------
+.. kernel-doc:: drivers/gpu/drm/i915/i915_scheduler_types.h
+   :functions: i915_sched_engine
+
 Logical Rings, Logical Ring Contexts and Execlists
 --------------------------------------------------
 
@@ -518,6 +525,14 @@ GuC-based command submission
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
    :doc: GuC-based command submission
 
+GuC ABI
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
+
 HuC
 ---
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c

Documentation/gpu/rfc/i915_parallel_execbuf.h

@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
+
+/**
+ * struct drm_i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior described below. Lastly, the default is to not allow BBs to
+ * preempted mid BB rather insert coordinated preemption on all hardware
+ * contexts between each set of BBs. Flags may be added in the future to change
+ * both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Example 1 pseudo code:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can also be thought of as 2 virtual engines described by 2-D array
+ *	in the engines the field with bonds placed between each index of the
+ *	virtual engines. e.g. CS[0] is bonded to CS[1], CS[2] is bonded to
+ *	CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logical contiguous, return -EINVAL
+ */
+struct drm_i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[0];
+
+} __packed;
+

Documentation/gpu/rfc/i915_scheduler.rst

@@ -0,0 +1,148 @@
+=========================================
+I915 GuC Submission/DRM Scheduler Section
+=========================================
+
+Upstream plan
+=============
+For upstream the overall plan for landing GuC submission and integrating the
+i915 with the DRM scheduler is:
+
+* Merge basic GuC submission
+	* Basic submission support for all gen11+ platforms
+	* Not enabled by default on any current platforms but can be enabled via
+	  modparam enable_guc
+	* Lots of rework will need to be done to integrate with DRM scheduler so
+	  no need to nit pick everything in the code, it just should be
+	  functional, no major coding style / layering errors, and not regress
+	  execlists
+	* Update IGTs / selftests as needed to work with GuC submission
+	* Enable CI on supported platforms for a baseline
+	* Rework / get CI heathly for GuC submission in place as needed
+* Merge new parallel submission uAPI
+	* Bonding uAPI completely incompatible with GuC submission, plus it has
+	  severe design issues in general, which is why we want to retire it no
+	  matter what
+	* New uAPI adds I915_CONTEXT_ENGINES_EXT_PARALLEL context setup step
+	  which configures a slot with N contexts
+	* After I915_CONTEXT_ENGINES_EXT_PARALLEL a user can submit N batches to
+	  a slot in a single execbuf IOCTL and the batches run on the GPU in
+	  paralllel
+	* Initially only for GuC submission but execlists can be supported if
+	  needed
+* Convert the i915 to use the DRM scheduler
+	* GuC submission backend fully integrated with DRM scheduler
+		* All request queues removed from backend (e.g. all backpressure
+		  handled in DRM scheduler)
+		* Resets / cancels hook in DRM scheduler
+		* Watchdog hooks into DRM scheduler
+		* Lots of complexity of the GuC backend can be pulled out once
+		  integrated with DRM scheduler (e.g. state machine gets
+		  simplier, locking gets simplier, etc...)
+	* Execlists backend will minimum required to hook in the DRM scheduler
+		* Legacy interface
+		* Features like timeslicing / preemption / virtual engines would
+		  be difficult to integrate with the DRM scheduler and these
+		  features are not required for GuC submission as the GuC does
+		  these things for us
+		* ROI low on fully integrating into DRM scheduler
+		* Fully integrating would add lots of complexity to DRM
+		  scheduler
+	* Port i915 priority inheritance / boosting feature in DRM scheduler
+		* Used for i915 page flip, may be useful to other DRM drivers as
+		  well
+		* Will be an optional feature in the DRM scheduler
+	* Remove in-order completion assumptions from DRM scheduler
+		* Even when using the DRM scheduler the backends will handle
+		  preemption, timeslicing, etc... so it is possible for jobs to
+		  finish out of order
+	* Pull out i915 priority levels and use DRM priority levels
+	* Optimize DRM scheduler as needed
+
+TODOs for GuC submission upstream
+=================================
+
+* Need an update to GuC firmware / i915 to enable error state capture
+* Open source tool to decode GuC logs
+* Public GuC spec
+
+New uAPI for basic GuC submission
+=================================
+No major changes are required to the uAPI for basic GuC submission. The only
+change is a new scheduler attribute: I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP.
+This attribute indicates the 2k i915 user priority levels are statically mapped
+into 3 levels as follows:
+
+* -1k to -1 Low priority
+* 0 Medium priority
+* 1 to 1k High priority
+
+This is needed because the GuC only has 4 priority bands. The highest priority
+band is reserved with the kernel. This aligns with the DRM scheduler priority
+levels too.
+
+Spec references:
+----------------
+* https://www.khronos.org/registry/EGL/extensions/IMG/EGL_IMG_context_priority.txt
+* https://www.khronos.org/registry/vulkan/specs/1.2-extensions/html/chap5.html#devsandqueues-priority
+* https://spec.oneapi.com/level-zero/latest/core/api.html#ze-command-queue-priority-t
+
+New parallel submission uAPI
+============================
+The existing bonding uAPI is completely broken with GuC submission because
+whether a submission is a single context submit or parallel submit isn't known
+until execbuf time activated via the I915_SUBMIT_FENCE. To submit multiple
+contexts in parallel with the GuC the context must be explicitly registered with
+N contexts and all N contexts must be submitted in a single command to the GuC.
+The GuC interfaces do not support dynamically changing between N contexts as the
+bonding uAPI does. Hence the need for a new parallel submission interface. Also
+the legacy bonding uAPI is quite confusing and not intuitive at all. Furthermore
+I915_SUBMIT_FENCE is by design a future fence, so not really something we should
+continue to support.
+
+The new parallel submission uAPI consists of 3 parts:
+
+* Export engines logical mapping
+* A 'set_parallel' extension to configure contexts for parallel
+  submission
+* Extend execbuf2 IOCTL to support submitting N BBs in a single IOCTL
+
+Export engines logical mapping
+------------------------------
+Certain use cases require BBs to be placed on engine instances in logical order
+(e.g. split-frame on gen11+). The logical mapping of engine instances can change
+based on fusing. Rather than making UMDs be aware of fusing, simply expose the
+logical mapping with the existing query engine info IOCTL. Also the GuC
+submission interface currently only supports submitting multiple contexts to
+engines in logical order which is a new requirement compared to execlists.
+Lastly, all current platforms have at most 2 engine instances and the logical
+order is the same as uAPI order. This will change on platforms with more than 2
+engine instances.
+
+A single bit will be added to drm_i915_engine_info.flags indicating that the
+logical instance has been returned and a new field,
+drm_i915_engine_info.logical_instance, returns the logical instance.
+
+A 'set_parallel' extension to configure contexts for parallel submission
+------------------------------------------------------------------------
+The 'set_parallel' extension configures a slot for parallel submission of N BBs.
+It is a setup step that must be called before using any of the contexts. See
+I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE or I915_CONTEXT_ENGINES_EXT_BOND for
+similar existing examples. Once a slot is configured for parallel submission the
+execbuf2 IOCTL can be called submitting N BBs in a single IOCTL. Initially only
+supports GuC submission. Execlists supports can be added later if needed.
+
+Add I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT and
+drm_i915_context_engines_parallel_submit to the uAPI to implement this
+extension.
+
+.. kernel-doc:: Documentation/gpu/rfc/i915_parallel_execbuf.h
+        :functions: drm_i915_context_engines_parallel_submit
+
+Extend execbuf2 IOCTL to support submitting N BBs in a single IOCTL
+-------------------------------------------------------------------
+Contexts that have been configured with the 'set_parallel' extension can only
+submit N BBs in a single execbuf2 IOCTL. The BBs are either the last N objects
+in the drm_i915_gem_exec_object2 list or the first N if I915_EXEC_BATCH_FIRST is
+set. The number of BBs is implicit based on the slot submitted and how it has
+been configured by 'set_parallel' or other extensions. No uAPI changes are
+required to the execbuf2 IOCTL.

Documentation/gpu/rfc/index.rst

@@ -19,3 +19,7 @@ host such documentation:
 .. toctree::
 
     i915_gem_lmem.rst
+
+.. toctree::
+
+    i915_scheduler.rst

Documentation/gpu/vkms.rst

@@ -98,9 +98,17 @@ with VKMS maintainers.
 IGT better support
 ------------------
 
-- Investigate: (1) test cases on kms_plane that are failing due to timeout on
+Debugging:
-  capturing CRC; (2) when running kms_flip test cases in sequence, some
+
-  successful individual test cases are failing randomly.
+- kms_plane: some test cases are failing due to timeout on capturing CRC;
+
+- kms_flip: when running test cases in sequence, some successful individual
+  test cases are failing randomly; when individually, some successful test
+  cases display in the log the following error::
+
+  [drm:vkms_prepare_fb [vkms]] ERROR vmap failed: -4
+
+Virtual hardware (vblank-less) mode:
 
 - VKMS already has support for vblanks simulated via hrtimers, which can be
   tested with kms_flip test; in some way, we can say that VKMS already mimics
@@ -116,7 +124,17 @@ Add Plane Features
 
 There's lots of plane features we could add support for:
 
-- Real overlay planes, not just cursor.
+- Multiple overlay planes. [Good to get started]
+
+- Clearing primary plane: clear primary plane before plane composition (at the
+  start) for correctness of pixel blend ops. It also guarantees alpha channel
+  is cleared in the target buffer for stable crc. [Good to get started]
+
+- ARGB format on primary plane: blend the primary plane into background with
+  translucent alpha.
+
+- Support when the primary plane isn't exactly matching the output size: blend
+  the primary plane into the black background.
 
 - Full alpha blending on all planes.
 
@@ -129,13 +147,8 @@ There's lots of plane features we could add support for:
   cursor api).
 
 For all of these, we also want to review the igt test coverage and make sure
-all relevant igt testcases work on vkms.
+all relevant igt testcases work on vkms. They are good options for internship
-
+project.
-Prime Buffer Sharing
---------------------
-
-- Syzbot report - WARNING in vkms_gem_free_object:
-  https://syzkaller.appspot.com/bug?extid=e7ad70d406e74d8fc9d0
 
 Runtime Configuration
 ---------------------
@@ -153,7 +166,7 @@ module. Use/Test-cases:
   the refresh rate.
 
 The currently proposed solution is to expose vkms configuration through
-configfs.  All existing module options should be supported through configfs
+configfs. All existing module options should be supported through configfs
 too.
 
 Writeback support
@@ -162,6 +175,7 @@ Writeback support
 - The writeback and CRC capture operations share the use of composer_enabled
   boolean to ensure vblanks. Probably, when these operations work together,
   composer_enabled needs to refcounting the composer state to proper work.
+  [Good to get started]
 
 - Add support for cloned writeback outputs and related test cases using a
   cloned output in the IGT kms_writeback.

MAINTAINERS

@@ -1703,7 +1703,7 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 W:	https://asahilinux.org
 B:	https://github.com/AsahiLinux/linux/issues
-C:	irc://chat.freenode.net/asahi-dev
+C:	irc://irc.oftc.net/asahi-dev
 T:	git https://github.com/AsahiLinux/linux.git
 F:	Documentation/devicetree/bindings/arm/apple.yaml
 F:	Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
@@ -5799,7 +5799,7 @@ M:	Gerd Hoffmann <kraxel@redhat.com>
 L:	virtualization@lists.linux-foundation.org
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm-misc
-F:	drivers/gpu/drm/bochs/
+F:	drivers/gpu/drm/tiny/bochs.c
 
 DRM DRIVER FOR BOE HIMAX8279D PANELS
 M:	Jerry Han <hanxu5@huaqin.corp-partner.google.com>
@@ -5984,6 +5984,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/display/panel/raydium,rm67191.yaml
 F:	drivers/gpu/drm/panel/panel-raydium-rm67191.c
 
+DRM DRIVER FOR SAMSUNG DB7430 PANELS
+M:	Linus Walleij <linus.walleij@linaro.org>
+S:	Maintained
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+F:	Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml
+F:	drivers/gpu/drm/panel/panel-samsung-db7430.c
+
 DRM DRIVER FOR SITRONIX ST7703 PANELS
 M:	Guido Günther <agx@sigxcpu.org>
 R:	Purism Kernel Team <kernel@puri.sm>
@@ -6082,21 +6089,27 @@ F:	drivers/gpu/drm/vboxvideo/
 
 DRM DRIVER FOR VMWARE VIRTUAL GPU
 M:	"VMware Graphics" <linux-graphics-maintainer@vmware.com>
-M:	Roland Scheidegger <sroland@vmware.com>
 M:	Zack Rusin <zackr@vmware.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
-T:	git git://people.freedesktop.org/~sroland/linux
+T:	git git://anongit.freedesktop.org/drm/drm-misc
 F:	drivers/gpu/drm/vmwgfx/
 F:	include/uapi/drm/vmwgfx_drm.h
 
+DRM DRIVER FOR WIDECHIPS WS2401 PANELS
+M:	Linus Walleij <linus.walleij@linaro.org>
+S:	Maintained
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+F:	Documentation/devicetree/bindings/display/panel/samsung,lms380kf01.yaml
+F:	drivers/gpu/drm/panel/panel-widechips-ws2401.c
+
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>
 M:	Daniel Vetter <daniel@ffwll.ch>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 B:	https://gitlab.freedesktop.org/drm
-C:	irc://chat.freenode.net/dri-devel
+C:	irc://irc.oftc.net/dri-devel
 T:	git git://anongit.freedesktop.org/drm/drm
 F:	Documentation/devicetree/bindings/display/
 F:	Documentation/devicetree/bindings/gpu/
@@ -9295,7 +9308,7 @@ S:	Supported
 W:	https://01.org/linuxgraphics/
 Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 B:	https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
-C:	irc://chat.freenode.net/intel-gfx
+C:	irc://irc.oftc.net/intel-gfx
 T:	git git://anongit.freedesktop.org/drm-intel
 F:	Documentation/gpu/i915.rst
 F:	drivers/gpu/drm/i915/

arch/arm/include/asm/efi.h

@@ -17,6 +17,7 @@
 
 #ifdef CONFIG_EFI
 void efi_init(void);
+extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 
 int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
 int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
@@ -52,10 +53,6 @@ void efi_virtmap_unload(void);
 struct screen_info *alloc_screen_info(void);
 void free_screen_info(struct screen_info *si);
 
-static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
-{
-}
-
 /*
  * A reasonable upper bound for the uncompressed kernel size is 32 MBytes,
  * so we will reserve that amount of memory. We have no easy way to tell what

arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi

@@ -255,21 +255,6 @@
 		#sound-dai-cells = <0>;
 	};
 
-	panel: panel {
-		/* Compatible will be filled in per-board */
-		power-supply = <&pp3300_dx_edp>;
-		backlight = <&backlight>;
-		hpd-gpios = <&sn65dsi86_bridge 2 GPIO_ACTIVE_HIGH>;
-
-		ports {
-			port {
-				panel_in_edp: endpoint {
-					remote-endpoint = <&sn65dsi86_out>;
-				};
-			};
-		};
-	};
-
 	pwmleds {
 		compatible = "pwm-leds";
 		keyboard_backlight: keyboard-backlight {
@@ -666,6 +651,21 @@ edp_brij_i2c: &i2c2 {
 				};
 			};
 		};
+
+		aux-bus {
+			panel: panel {
+				/* Compatible will be filled in per-board */
+				power-supply = <&pp3300_dx_edp>;
+				backlight = <&backlight>;
+				hpd-gpios = <&sn65dsi86_bridge 2 GPIO_ACTIVE_HIGH>;
+
+				port {
+					panel_in_edp: endpoint {
+						remote-endpoint = <&sn65dsi86_out>;
+					};
+				};
+			};
+		};
 	};
 };
 

arch/arm64/include/asm/efi.h

@@ -14,6 +14,7 @@
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
+extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 #else
 #define efi_init()
 #endif
@@ -85,10 +86,6 @@ static inline void free_screen_info(struct screen_info *si)
 {
 }
 
-static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
-{
-}
-
 #define EFI_ALLOC_ALIGN		SZ_64K
 
 /*

arch/riscv/include/asm/efi.h

@@ -13,6 +13,7 @@
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
+extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 #else
 #define efi_init()
 #endif
@@ -39,10 +40,6 @@ static inline void free_screen_info(struct screen_info *si)
 {
 }
 
-static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
-{
-}
-
 void efi_virtmap_load(void);
 void efi_virtmap_unload(void);
 

arch/x86/Kconfig

@@ -2767,32 +2767,6 @@ config AMD_NB
 	def_bool y
 	depends on CPU_SUP_AMD && PCI
 
-config X86_SYSFB
-	bool "Mark VGA/VBE/EFI FB as generic system framebuffer"
-	help
-	  Firmwares often provide initial graphics framebuffers so the BIOS,
-	  bootloader or kernel can show basic video-output during boot for
-	  user-guidance and debugging. Historically, x86 used the VESA BIOS
-	  Extensions and EFI-framebuffers for this, which are mostly limited
-	  to x86.
-	  This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
-	  framebuffers so the new generic system-framebuffer drivers can be
-	  used on x86. If the framebuffer is not compatible with the generic
-	  modes, it is advertised as fallback platform framebuffer so legacy
-	  drivers like efifb, vesafb and uvesafb can pick it up.
-	  If this option is not selected, all system framebuffers are always
-	  marked as fallback platform framebuffers as usual.
-
-	  Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will
-	  not be able to pick up generic system framebuffers if this option
-	  is selected. You are highly encouraged to enable simplefb as
-	  replacement if you select this option. simplefb can correctly deal
-	  with generic system framebuffers. But you should still keep vesafb
-	  and others enabled as fallback if a system framebuffer is
-	  incompatible with simplefb.
-
-	  If unsure, say Y.
-
 endmenu
 
 

arch/x86/kernel/Makefile

@@ -136,9 +136,6 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
 obj-$(CONFIG_OF)			+= devicetree.o
 obj-$(CONFIG_UPROBES)			+= uprobes.o
-obj-y					+= sysfb.o
-obj-$(CONFIG_X86_SYSFB)			+= sysfb_simplefb.o
-obj-$(CONFIG_EFI)			+= sysfb_efi.o
 
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o

drivers/dma-buf/Kconfig

@@ -72,6 +72,17 @@ menuconfig DMABUF_HEAPS
 	  allows userspace to allocate dma-bufs that can be shared
 	  between drivers.
 
+menuconfig DMABUF_SYSFS_STATS
+	bool "DMA-BUF sysfs statistics"
+	select DMA_SHARED_BUFFER
+	help
+	   Choose this option to enable DMA-BUF sysfs statistics
+	   in location /sys/kernel/dmabuf/buffers.
+
+	   /sys/kernel/dmabuf/buffers/<inode_number> will contain
+	   statistics for the DMA-BUF with the unique inode number
+	   <inode_number>.
+
 source "drivers/dma-buf/heaps/Kconfig"
 
 endmenu

drivers/dma-buf/Makefile

@@ -6,6 +6,7 @@ obj-$(CONFIG_DMABUF_HEAPS)	+= heaps/
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
+obj-$(CONFIG_DMABUF_SYSFS_STATS) += dma-buf-sysfs-stats.o
 
 dmabuf_selftests-y := \
 	selftest.o \

drivers/dma-buf/dma-buf-sysfs-stats.c

@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * DMA-BUF sysfs statistics.
+ *
+ * Copyright (C) 2021 Google LLC.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/dma-resv.h>
+#include <linux/kobject.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+#include "dma-buf-sysfs-stats.h"
+
+#define to_dma_buf_entry_from_kobj(x) container_of(x, struct dma_buf_sysfs_entry, kobj)
+
+/**
+ * DOC: overview
+ *
+ * ``/sys/kernel/debug/dma_buf/bufinfo`` provides an overview of every DMA-BUF
+ * in the system. However, since debugfs is not safe to be mounted in
+ * production, procfs and sysfs can be used to gather DMA-BUF statistics on
+ * production systems.
+ *
+ * The ``/proc/<pid>/fdinfo/<fd>`` files in procfs can be used to gather
+ * information about DMA-BUF fds. Detailed documentation about the interface
+ * is present in Documentation/filesystems/proc.rst.
+ *
+ * Unfortunately, the existing procfs interfaces can only provide information
+ * about the DMA-BUFs for which processes hold fds or have the buffers mmapped
+ * into their address space. This necessitated the creation of the DMA-BUF sysfs
+ * statistics interface to provide per-buffer information on production systems.
+ *
+ * The interface at ``/sys/kernel/dma-buf/buffers`` exposes information about
+ * every DMA-BUF when ``CONFIG_DMABUF_SYSFS_STATS`` is enabled.
+ *
+ * The following stats are exposed by the interface:
+ *
+ * * ``/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name``
+ * * ``/sys/kernel/dmabuf/buffers/<inode_number>/size``
+ *
+ * The information in the interface can also be used to derive per-exporter
+ * statistics. The data from the interface can be gathered on error conditions
+ * or other important events to provide a snapshot of DMA-BUF usage.
+ * It can also be collected periodically by telemetry to monitor various metrics.
+ *
+ * Detailed documentation about the interface is present in
+ * Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers.
+ */
+
+struct dma_buf_stats_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct dma_buf *dmabuf,
+			struct dma_buf_stats_attribute *attr, char *buf);
+};
+#define to_dma_buf_stats_attr(x) container_of(x, struct dma_buf_stats_attribute, attr)
+
+static ssize_t dma_buf_stats_attribute_show(struct kobject *kobj,
+					    struct attribute *attr,
+					    char *buf)
+{
+	struct dma_buf_stats_attribute *attribute;
+	struct dma_buf_sysfs_entry *sysfs_entry;
+	struct dma_buf *dmabuf;
+
+	attribute = to_dma_buf_stats_attr(attr);
+	sysfs_entry = to_dma_buf_entry_from_kobj(kobj);
+	dmabuf = sysfs_entry->dmabuf;
+
+	if (!dmabuf || !attribute->show)
+		return -EIO;
+
+	return attribute->show(dmabuf, attribute, buf);
+}
+
+static const struct sysfs_ops dma_buf_stats_sysfs_ops = {
+	.show = dma_buf_stats_attribute_show,
+};
+
+static ssize_t exporter_name_show(struct dma_buf *dmabuf,
+				  struct dma_buf_stats_attribute *attr,
+				  char *buf)
+{
+	return sysfs_emit(buf, "%s\n", dmabuf->exp_name);
+}
+
+static ssize_t size_show(struct dma_buf *dmabuf,
+			 struct dma_buf_stats_attribute *attr,
+			 char *buf)
+{
+	return sysfs_emit(buf, "%zu\n", dmabuf->size);
+}
+
+static struct dma_buf_stats_attribute exporter_name_attribute =
+	__ATTR_RO(exporter_name);
+static struct dma_buf_stats_attribute size_attribute = __ATTR_RO(size);
+
+static struct attribute *dma_buf_stats_default_attrs[] = {
+	&exporter_name_attribute.attr,
+	&size_attribute.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(dma_buf_stats_default);
+
+static void dma_buf_sysfs_release(struct kobject *kobj)
+{
+	struct dma_buf_sysfs_entry *sysfs_entry;
+
+	sysfs_entry = to_dma_buf_entry_from_kobj(kobj);
+	kfree(sysfs_entry);
+}
+
+static struct kobj_type dma_buf_ktype = {
+	.sysfs_ops = &dma_buf_stats_sysfs_ops,
+	.release = dma_buf_sysfs_release,
+	.default_groups = dma_buf_stats_default_groups,
+};
+
+void dma_buf_stats_teardown(struct dma_buf *dmabuf)
+{
+	struct dma_buf_sysfs_entry *sysfs_entry;
+
+	sysfs_entry = dmabuf->sysfs_entry;
+	if (!sysfs_entry)
+		return;
+
+	kobject_del(&sysfs_entry->kobj);
+	kobject_put(&sysfs_entry->kobj);
+}
+
+
+/* Statistics files do not need to send uevents. */
+static int dmabuf_sysfs_uevent_filter(struct kset *kset, struct kobject *kobj)
+{
+	return 0;
+}
+
+static const struct kset_uevent_ops dmabuf_sysfs_no_uevent_ops = {
+	.filter = dmabuf_sysfs_uevent_filter,
+};
+
+static struct kset *dma_buf_stats_kset;
+static struct kset *dma_buf_per_buffer_stats_kset;
+int dma_buf_init_sysfs_statistics(void)
+{
+	dma_buf_stats_kset = kset_create_and_add("dmabuf",
+						 &dmabuf_sysfs_no_uevent_ops,
+						 kernel_kobj);
+	if (!dma_buf_stats_kset)
+		return -ENOMEM;
+
+	dma_buf_per_buffer_stats_kset = kset_create_and_add("buffers",
+							    &dmabuf_sysfs_no_uevent_ops,
+							    &dma_buf_stats_kset->kobj);
+	if (!dma_buf_per_buffer_stats_kset) {
+		kset_unregister(dma_buf_stats_kset);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void dma_buf_uninit_sysfs_statistics(void)
+{
+	kset_unregister(dma_buf_per_buffer_stats_kset);
+	kset_unregister(dma_buf_stats_kset);
+}
+
+int dma_buf_stats_setup(struct dma_buf *dmabuf)
+{
+	struct dma_buf_sysfs_entry *sysfs_entry;
+	int ret;
+
+	if (!dmabuf || !dmabuf->file)
+		return -EINVAL;
+
+	if (!dmabuf->exp_name) {
+		pr_err("exporter name must not be empty if stats needed\n");
+		return -EINVAL;
+	}
+
+	sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL);
+	if (!sysfs_entry)
+		return -ENOMEM;
+
+	sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset;
+	sysfs_entry->dmabuf = dmabuf;
+
+	dmabuf->sysfs_entry = sysfs_entry;
+
+	/* create the directory for buffer stats */
+	ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
+				   "%lu", file_inode(dmabuf->file)->i_ino);
+	if (ret)
+		goto err_sysfs_dmabuf;
+
+	return 0;
+
+err_sysfs_dmabuf:
+	kobject_put(&sysfs_entry->kobj);
+	dmabuf->sysfs_entry = NULL;
+	return ret;
+}

drivers/dma-buf/dma-buf-sysfs-stats.h

@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * DMA-BUF sysfs statistics.
+ *
+ * Copyright (C) 2021 Google LLC.
+ */
+
+#ifndef _DMA_BUF_SYSFS_STATS_H
+#define _DMA_BUF_SYSFS_STATS_H
+
+#ifdef CONFIG_DMABUF_SYSFS_STATS
+
+int dma_buf_init_sysfs_statistics(void);
+void dma_buf_uninit_sysfs_statistics(void);
+
+int dma_buf_stats_setup(struct dma_buf *dmabuf);
+
+void dma_buf_stats_teardown(struct dma_buf *dmabuf);
+#else
+
+static inline int dma_buf_init_sysfs_statistics(void)
+{
+	return 0;
+}
+
+static inline void dma_buf_uninit_sysfs_statistics(void) {}
+
+static inline int dma_buf_stats_setup(struct dma_buf *dmabuf)
+{
+	return 0;
+}
+
+static inline void dma_buf_stats_teardown(struct dma_buf *dmabuf) {}
+#endif
+#endif // _DMA_BUF_SYSFS_STATS_H

drivers/dma-buf/dma-buf.c

@@ -29,6 +29,8 @@
 #include <uapi/linux/dma-buf.h>
 #include <uapi/linux/magic.h>
 
+#include "dma-buf-sysfs-stats.h"
+
 static inline int is_dma_buf_file(struct file *);
 
 struct dma_buf_list {
@@ -74,6 +76,7 @@ static void dma_buf_release(struct dentry *dentry)
 	 */
 	BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active);
 
+	dma_buf_stats_teardown(dmabuf);
 	dmabuf->ops->release(dmabuf);
 
 	if (dmabuf->resv == (struct dma_resv *)&dmabuf[1])
@@ -580,6 +583,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	file->f_mode |= FMODE_LSEEK;
 	dmabuf->file = file;
 
+	ret = dma_buf_stats_setup(dmabuf);
+	if (ret)
+		goto err_sysfs;
+
 	mutex_init(&dmabuf->lock);
 	INIT_LIST_HEAD(&dmabuf->attachments);
 
@@ -589,6 +596,14 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 
 	return dmabuf;
 
+err_sysfs:
+	/*
+	 * Set file->f_path.dentry->d_fsdata to NULL so that when
+	 * dma_buf_release() gets invoked by dentry_ops, it exits
+	 * early before calling the release() dma_buf op.
+	 */
+	file->f_path.dentry->d_fsdata = NULL;
+	fput(file);
 err_dmabuf:
 	kfree(dmabuf);
 err_module:
@@ -926,6 +941,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unpin);
  * the underlying backing storage is pinned for as long as a mapping exists,
  * therefore users/importers should not hold onto a mapping for undue amounts of
  * time.
+ *
+ * Important: Dynamic importers must wait for the exclusive fence of the struct
+ * dma_resv attached to the DMA-BUF first.
  */
 struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 					enum dma_data_direction direction)
@@ -992,7 +1010,6 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		}
 	}
 #endif /* CONFIG_DMA_API_DEBUG */
-
 	return sg_table;
 }
 EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
@@ -1522,6 +1539,12 @@ static inline void dma_buf_uninit_debugfs(void)
 
 static int __init dma_buf_init(void)
 {
+	int ret;
+
+	ret = dma_buf_init_sysfs_statistics();
+	if (ret)
+		return ret;
+
 	dma_buf_mnt = kern_mount(&dma_buf_fs_type);
 	if (IS_ERR(dma_buf_mnt))
 		return PTR_ERR(dma_buf_mnt);
@@ -1537,5 +1560,6 @@ static void __exit dma_buf_deinit(void)
 {
 	dma_buf_uninit_debugfs();
 	kern_unmount(dma_buf_mnt);
+	dma_buf_uninit_sysfs_statistics();
 }
 __exitcall(dma_buf_deinit);

drivers/dma-buf/dma-fence-chain.c

@@ -137,6 +137,7 @@ static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb)
 	struct dma_fence_chain *chain;
 
 	chain = container_of(cb, typeof(*chain), cb);
+	init_irq_work(&chain->work, dma_fence_chain_irq_work);
 	irq_work_queue(&chain->work);
 	dma_fence_put(f);
 }
@@ -239,7 +240,6 @@ void dma_fence_chain_init(struct dma_fence_chain *chain,
 	rcu_assign_pointer(chain->prev, prev);
 	chain->fence = fence;
 	chain->prev_seqno = 0;
-	init_irq_work(&chain->work, dma_fence_chain_irq_work);
 
 	/* Try to reuse the context of the previous chain node. */
 	if (prev_chain && __dma_fence_is_later(seqno, prev->seqno, prev->ops)) {

drivers/dma-buf/dma-resv.c

@@ -615,25 +615,21 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence)
  */
 bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all)
 {
-	unsigned int seq, shared_count;
+	struct dma_fence *fence;
+	unsigned int seq;
 	int ret;
 
 	rcu_read_lock();
 retry:
 	ret = true;
-	shared_count = 0;
 	seq = read_seqcount_begin(&obj->seq);
 
 	if (test_all) {
 		struct dma_resv_list *fobj = dma_resv_shared_list(obj);
-		unsigned int i;
+		unsigned int i, shared_count;
-
-		if (fobj)
-			shared_count = fobj->shared_count;
 
+		shared_count = fobj ? fobj->shared_count : 0;
 		for (i = 0; i < shared_count; ++i) {
-			struct dma_fence *fence;
-
 			fence = rcu_dereference(fobj->shared[i]);
 			ret = dma_resv_test_signaled_single(fence);
 			if (ret < 0)
@@ -641,23 +637,18 @@ retry:
 			else if (!ret)
 				break;
 		}
+	}
 
-		if (read_seqcount_retry(&obj->seq, seq))
+	fence = dma_resv_excl_fence(obj);
+	if (ret && fence) {
+		ret = dma_resv_test_signaled_single(fence);
+		if (ret < 0)
 			goto retry;
+
 	}
 
-	if (!shared_count) {
+	if (read_seqcount_retry(&obj->seq, seq))
-		struct dma_fence *fence_excl = dma_resv_excl_fence(obj);
+		goto retry;
-
-		if (fence_excl) {
-			ret = dma_resv_test_signaled_single(fence_excl);
-			if (ret < 0)
-				goto retry;
-
-			if (read_seqcount_retry(&obj->seq, seq))
-				goto retry;
-		}
-	}
 
 	rcu_read_unlock();
 	return ret;

drivers/dma-buf/st-dma-fence-chain.c

@@ -58,28 +58,20 @@ static struct dma_fence *mock_fence(void)
 	return &f->base;
 }
 
-static inline struct mock_chain {
-	struct dma_fence_chain base;
-} *to_mock_chain(struct dma_fence *f) {
-	return container_of(f, struct mock_chain, base.base);
-}
-
 static struct dma_fence *mock_chain(struct dma_fence *prev,
 				    struct dma_fence *fence,
 				    u64 seqno)
 {
-	struct mock_chain *f;
+	struct dma_fence_chain *f;
 
-	f = kmalloc(sizeof(*f), GFP_KERNEL);
+	f = dma_fence_chain_alloc();
 	if (!f)
 		return NULL;
 
-	dma_fence_chain_init(&f->base,
+	dma_fence_chain_init(f, dma_fence_get(prev), dma_fence_get(fence),
-			     dma_fence_get(prev),
-			     dma_fence_get(fence),
 			     seqno);
 
-	return &f->base.base;
+	return &f->base;
 }
 
 static int sanitycheck(void *arg)

drivers/dma-buf/udmabuf.c

@@ -11,9 +11,15 @@
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/udmabuf.h>
+#include <linux/hugetlb.h>
 
-static const u32    list_limit = 1024;  /* udmabuf_create_list->count limit */
+static int list_limit = 1024;
-static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes  */
+module_param(list_limit, int, 0644);
+MODULE_PARM_DESC(list_limit, "udmabuf_create_list->count limit. Default is 1024.");
+
+static int size_limit_mb = 64;
+module_param(size_limit_mb, int, 0644);
+MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64.");
 
 struct udmabuf {
 	pgoff_t pagecount;
@@ -160,10 +166,13 @@ static long udmabuf_create(struct miscdevice *device,
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct file *memfd = NULL;
+	struct address_space *mapping = NULL;
 	struct udmabuf *ubuf;
 	struct dma_buf *buf;
 	pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
-	struct page *page;
+	struct page *page, *hpage = NULL;
+	pgoff_t subpgoff, maxsubpgs;
+	struct hstate *hpstate;
 	int seals, ret = -EINVAL;
 	u32 i, flags;
 
@@ -194,7 +203,8 @@ static long udmabuf_create(struct miscdevice *device,
 		memfd = fget(list[i].memfd);
 		if (!memfd)
 			goto err;
-		if (!shmem_mapping(file_inode(memfd)->i_mapping))
+		mapping = file_inode(memfd)->i_mapping;
+		if (!shmem_mapping(mapping) && !is_file_hugepages(memfd))
 			goto err;
 		seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
 		if (seals == -EINVAL)
@@ -205,17 +215,48 @@ static long udmabuf_create(struct miscdevice *device,
 			goto err;
 		pgoff = list[i].offset >> PAGE_SHIFT;
 		pgcnt = list[i].size   >> PAGE_SHIFT;
+		if (is_file_hugepages(memfd)) {
+			hpstate = hstate_file(memfd);
+			pgoff = list[i].offset >> huge_page_shift(hpstate);
+			subpgoff = (list[i].offset &
+				    ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
+			maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
+		}
 		for (pgidx = 0; pgidx < pgcnt; pgidx++) {
-			page = shmem_read_mapping_page(
+			if (is_file_hugepages(memfd)) {
-				file_inode(memfd)->i_mapping, pgoff + pgidx);
+				if (!hpage) {
-			if (IS_ERR(page)) {
+					hpage = find_get_page_flags(mapping, pgoff,
-				ret = PTR_ERR(page);
+								    FGP_ACCESSED);
-				goto err;
+					if (!hpage) {
+						ret = -EINVAL;
+						goto err;
+					}
+				}
+				page = hpage + subpgoff;
+				get_page(page);
+				subpgoff++;
+				if (subpgoff == maxsubpgs) {
+					put_page(hpage);
+					hpage = NULL;
+					subpgoff = 0;
+					pgoff++;
+				}
+			} else {
+				page = shmem_read_mapping_page(mapping,
+							       pgoff + pgidx);
+				if (IS_ERR(page)) {
+					ret = PTR_ERR(page);
+					goto err;
+				}
 			}
 			ubuf->pages[pgbuf++] = page;
 		}
 		fput(memfd);
 		memfd = NULL;
+		if (hpage) {
+			put_page(hpage);
+			hpage = NULL;
+		}
 	}
 
 	exp_info.ops  = &udmabuf_ops;

drivers/firmware/Kconfig

@@ -251,6 +251,38 @@ config QCOM_SCM_DOWNLOAD_MODE_DEFAULT
 
 	  Say Y here to enable "download mode" by default.
 
+config SYSFB
+	bool
+	default y
+	depends on X86 || EFI
+
+config SYSFB_SIMPLEFB
+	bool "Mark VGA/VBE/EFI FB as generic system framebuffer"
+	depends on SYSFB
+	help
+	  Firmwares often provide initial graphics framebuffers so the BIOS,
+	  bootloader or kernel can show basic video-output during boot for
+	  user-guidance and debugging. Historically, x86 used the VESA BIOS
+	  Extensions and EFI-framebuffers for this, which are mostly limited
+	  to x86 BIOS or EFI systems.
+	  This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
+	  framebuffers so the new generic system-framebuffer drivers can be
+	  used instead. If the framebuffer is not compatible with the generic
+	  modes, it is advertised as fallback platform framebuffer so legacy
+	  drivers like efifb, vesafb and uvesafb can pick it up.
+	  If this option is not selected, all system framebuffers are always
+	  marked as fallback platform framebuffers as usual.
+
+	  Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will
+	  not be able to pick up generic system framebuffers if this option
+	  is selected. You are highly encouraged to enable simplefb as
+	  replacement if you select this option. simplefb can correctly deal
+	  with generic system framebuffers. But you should still keep vesafb
+	  and others enabled as fallback if a system framebuffer is
+	  incompatible with simplefb.
+
+	  If unsure, say Y.
+
 config TI_SCI_PROTOCOL
 	tristate "TI System Control Interface (TISCI) Message Protocol"
 	depends on TI_MESSAGE_MANAGER

drivers/firmware/Makefile

@@ -19,6 +19,8 @@ obj-$(CONFIG_RASPBERRYPI_FIRMWARE) += raspberrypi.o
 obj-$(CONFIG_FW_CFG_SYSFS)	+= qemu_fw_cfg.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom-scm.o
 qcom-scm-objs += qcom_scm.o qcom_scm-smc.o qcom_scm-legacy.o
+obj-$(CONFIG_SYSFB)		+= sysfb.o
+obj-$(CONFIG_SYSFB_SIMPLEFB)	+= sysfb_simplefb.o
 obj-$(CONFIG_TI_SCI_PROTOCOL)	+= ti_sci.o
 obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
 obj-$(CONFIG_TURRIS_MOX_RWTM)	+= turris-mox-rwtm.o

drivers/firmware/efi/Makefile

@@ -36,6 +36,8 @@ obj-$(CONFIG_LOAD_UEFI_KEYS)		+= mokvar-table.o
 fake_map-y				+= fake_mem.o
 fake_map-$(CONFIG_X86)			+= x86_fake_mem.o
 
+obj-$(CONFIG_SYSFB)			+= sysfb_efi.o
+
 arm-obj-$(CONFIG_EFI)			:= efi-init.o arm-runtime.o
 obj-$(CONFIG_ARM)			+= $(arm-obj-y)
 obj-$(CONFIG_ARM64)			+= $(arm-obj-y)

drivers/firmware/efi/efi-init.c

@@ -275,93 +275,3 @@ void __init efi_init(void)
 	}
 #endif
 }
-
-static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
-{
-	u64 fb_base = screen_info.lfb_base;
-
-	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
-		fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32;
-
-	return fb_base >= range->cpu_addr &&
-	       fb_base < (range->cpu_addr + range->size);
-}
-
-static struct device_node *find_pci_overlap_node(void)
-{
-	struct device_node *np;
-
-	for_each_node_by_type(np, "pci") {
-		struct of_pci_range_parser parser;
-		struct of_pci_range range;
-		int err;
-
-		err = of_pci_range_parser_init(&parser, np);
-		if (err) {
-			pr_warn("of_pci_range_parser_init() failed: %d\n", err);
-			continue;
-		}
-
-		for_each_of_pci_range(&parser, &range)
-			if (efifb_overlaps_pci_range(&range))
-				return np;
-	}
-	return NULL;
-}
-
-/*
- * If the efifb framebuffer is backed by a PCI graphics controller, we have
- * to ensure that this relation is expressed using a device link when
- * running in DT mode, or the probe order may be reversed, resulting in a
- * resource reservation conflict on the memory window that the efifb
- * framebuffer steals from the PCIe host bridge.
- */
-static int efifb_add_links(struct fwnode_handle *fwnode)
-{
-	struct device_node *sup_np;
-
-	sup_np = find_pci_overlap_node();
-
-	/*
-	 * If there's no PCI graphics controller backing the efifb, we are
-	 * done here.
-	 */
-	if (!sup_np)
-		return 0;
-
-	fwnode_link_add(fwnode, of_fwnode_handle(sup_np));
-	of_node_put(sup_np);
-
-	return 0;
-}
-
-static const struct fwnode_operations efifb_fwnode_ops = {
-	.add_links = efifb_add_links,
-};
-
-static struct fwnode_handle efifb_fwnode;
-
-static int __init register_gop_device(void)
-{
-	struct platform_device *pd;
-	int err;
-
-	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
-		return 0;
-
-	pd = platform_device_alloc("efi-framebuffer", 0);
-	if (!pd)
-		return -ENOMEM;
-
-	if (IS_ENABLED(CONFIG_PCI)) {
-		fwnode_init(&efifb_fwnode, &efifb_fwnode_ops);
-		pd->dev.fwnode = &efifb_fwnode;
-	}
-
-	err = platform_device_add_data(pd, &screen_info, sizeof(screen_info));
-	if (err)
-		return err;
-
-	return platform_device_add(pd);
-}
-subsys_initcall(register_gop_device);

drivers/firmware/efi/sysfb_efi.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Generic System Framebuffers on x86
+ * Generic System Framebuffers
  * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
  *
  * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.com>
@@ -19,12 +19,14 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/of_address.h>
 #include <linux/pci.h>
+#include <linux/platform_device.h>
 #include <linux/screen_info.h>
+#include <linux/sysfb.h>
 #include <video/vga.h>
 
 #include <asm/efi.h>
-#include <asm/sysfb.h>
 
 enum {
 	OVERRIDE_NONE = 0x0,
@@ -267,7 +269,73 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = {
 	{},
 };
 
-__init void sysfb_apply_efi_quirks(void)
+static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
+{
+	u64 fb_base = screen_info.lfb_base;
+
+	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32;
+
+	return fb_base >= range->cpu_addr &&
+	       fb_base < (range->cpu_addr + range->size);
+}
+
+static struct device_node *find_pci_overlap_node(void)
+{
+	struct device_node *np;
+
+	for_each_node_by_type(np, "pci") {
+		struct of_pci_range_parser parser;
+		struct of_pci_range range;
+		int err;
+
+		err = of_pci_range_parser_init(&parser, np);
+		if (err) {
+			pr_warn("of_pci_range_parser_init() failed: %d\n", err);
+			continue;
+		}
+
+		for_each_of_pci_range(&parser, &range)
+			if (efifb_overlaps_pci_range(&range))
+				return np;
+	}
+	return NULL;
+}
+
+/*
+ * If the efifb framebuffer is backed by a PCI graphics controller, we have
+ * to ensure that this relation is expressed using a device link when
+ * running in DT mode, or the probe order may be reversed, resulting in a
+ * resource reservation conflict on the memory window that the efifb
+ * framebuffer steals from the PCIe host bridge.
+ */
+static int efifb_add_links(struct fwnode_handle *fwnode)
+{
+	struct device_node *sup_np;
+
+	sup_np = find_pci_overlap_node();
+
+	/*
+	 * If there's no PCI graphics controller backing the efifb, we are
+	 * done here.
+	 */
+	if (!sup_np)
+		return 0;
+
+	fwnode_link_add(fwnode, of_fwnode_handle(sup_np));
+	of_node_put(sup_np);
+
+	return 0;
+}
+
+static const struct fwnode_operations efifb_fwnode_ops = {
+	.add_links = efifb_add_links,
+};
+
+#ifdef CONFIG_EFI
+static struct fwnode_handle efifb_fwnode;
+
+__init void sysfb_apply_efi_quirks(struct platform_device *pd)
 {
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
 	    !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
@@ -281,4 +349,10 @@ __init void sysfb_apply_efi_quirks(void)
 		screen_info.lfb_height = temp;
 		screen_info.lfb_linelength = 4 * screen_info.lfb_width;
 	}
+
+	if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && IS_ENABLED(CONFIG_PCI)) {
+		fwnode_init(&efifb_fwnode, &efifb_fwnode_ops);
+		pd->dev.fwnode = &efifb_fwnode;
+	}
 }
+#endif

drivers/firmware/sysfb.c

@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Generic System Framebuffers on x86
+ * Generic System Framebuffers
  * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
  */
 
 /*
- * Simple-Framebuffer support for x86 systems
+ * Simple-Framebuffer support
  * Create a platform-device for any available boot framebuffer. The
  * simple-framebuffer platform device is already available on DT systems, so
  * this module parses the global "screen_info" object and creates a suitable
@@ -16,12 +16,12 @@
  * to pick these devices up without messing with simple-framebuffer drivers.
  * The global "screen_info" is still valid at all times.
  *
- * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer"
+ * If CONFIG_SYSFB_SIMPLEFB is not selected, never register "simple-framebuffer"
  * platform devices, but only use legacy framebuffer devices for
  * backwards compatibility.
  *
  * TODO: We set the dev_id field of all platform-devices to 0. This allows
- * other x86 OF/DT parsers to create such devices, too. However, they must
+ * other OF/DT parsers to create such devices, too. However, they must
  * start at offset 1 for this to work.
  */
 
@@ -32,7 +32,7 @@
 #include <linux/platform_data/simplefb.h>
 #include <linux/platform_device.h>
 #include <linux/screen_info.h>
-#include <asm/sysfb.h>
+#include <linux/sysfb.h>
 
 static __init int sysfb_init(void)
 {
@@ -43,12 +43,10 @@ static __init int sysfb_init(void)
 	bool compatible;
 	int ret;
 
-	sysfb_apply_efi_quirks();
-
 	/* try to create a simple-framebuffer device */
-	compatible = parse_mode(si, &mode);
+	compatible = sysfb_parse_mode(si, &mode);
 	if (compatible) {
-		ret = create_simplefb(si, &mode);
+		ret = sysfb_create_simplefb(si, &mode);
 		if (!ret)
 			return 0;
 	}
@@ -61,9 +59,24 @@ static __init int sysfb_init(void)
 	else
 		name = "platform-framebuffer";
 
-	pd = platform_device_register_resndata(NULL, name, 0,
+	pd = platform_device_alloc(name, 0);
-					       NULL, 0, si, sizeof(*si));
+	if (!pd)
-	return PTR_ERR_OR_ZERO(pd);
+		return -ENOMEM;
+
+	sysfb_apply_efi_quirks(pd);
+
+	ret = platform_device_add_data(pd, si, sizeof(*si));
+	if (ret)
+		goto err;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	platform_device_put(pd);
+	return ret;
 }
 
 /* must execute after PCI subsystem for EFI quirks */

drivers/firmware/sysfb_simplefb.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Generic System Framebuffers on x86
+ * Generic System Framebuffers
  * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
  */
 
@@ -18,14 +18,14 @@
 #include <linux/platform_data/simplefb.h>
 #include <linux/platform_device.h>
 #include <linux/screen_info.h>
-#include <asm/sysfb.h>
+#include <linux/sysfb.h>
 
 static const char simplefb_resname[] = "BOOTFB";
 static const struct simplefb_format formats[] = SIMPLEFB_FORMATS;
 
-/* try parsing x86 screen_info into a simple-framebuffer mode struct */
+/* try parsing screen_info into a simple-framebuffer mode struct */
-__init bool parse_mode(const struct screen_info *si,
+__init bool sysfb_parse_mode(const struct screen_info *si,
-		       struct simplefb_platform_data *mode)
+			     struct simplefb_platform_data *mode)
 {
 	const struct simplefb_format *f;
 	__u8 type;
@@ -57,13 +57,14 @@ __init bool parse_mode(const struct screen_info *si,
 	return false;
 }
 
-__init int create_simplefb(const struct screen_info *si,
+__init int sysfb_create_simplefb(const struct screen_info *si,
-			   const struct simplefb_platform_data *mode)
+				 const struct simplefb_platform_data *mode)
 {
 	struct platform_device *pd;
 	struct resource res;
 	u64 base, size;
 	u32 length;
+	int ret;
 
 	/*
 	 * If the 64BIT_BASE capability is set, ext_lfb_base will contain the
@@ -105,7 +106,19 @@ __init int create_simplefb(const struct screen_info *si,
 	if (res.end <= res.start)
 		return -EINVAL;
 
-	pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0,
+	pd = platform_device_alloc("simple-framebuffer", 0);
-					       &res, 1, mode, sizeof(*mode));
+	if (!pd)
-	return PTR_ERR_OR_ZERO(pd);
+		return -ENOMEM;
+
+	sysfb_apply_efi_quirks(pd);
+
+	ret = platform_device_add_resources(pd, &res, 1);
+	if (ret)
+		return ret;
+
+	ret = platform_device_add_data(pd, mode, sizeof(*mode));
+	if (ret)
+		return ret;
+
+	return platform_device_add(pd);
 }

drivers/gpu/drm/Kconfig

@@ -35,6 +35,11 @@ config DRM_MIPI_DSI
 	bool
 	depends on DRM
 
+config DRM_DP_AUX_BUS
+	tristate
+	depends on DRM
+	depends on OF
+
 config DRM_DP_AUX_CHARDEV
 	bool "DRM DP AUX Interface"
 	depends on DRM
@@ -251,7 +256,6 @@ config DRM_AMDGPU
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
 	select INTERVAL_TREE
-	select CHASH
 	help
 	  Choose this option if you have a recent AMD Radeon graphics card.
 
@@ -317,8 +321,6 @@ source "drivers/gpu/drm/tilcdc/Kconfig"
 
 source "drivers/gpu/drm/qxl/Kconfig"
 
-source "drivers/gpu/drm/bochs/Kconfig"
-
 source "drivers/gpu/drm/virtio/Kconfig"
 
 source "drivers/gpu/drm/msm/Kconfig"

drivers/gpu/drm/Makefile

@@ -33,6 +33,8 @@ drm-$(CONFIG_PCI) += drm_pci.o
 drm-$(CONFIG_DEBUG_FS) += drm_debugfs.o drm_debugfs_crc.o
 drm-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
 
+obj-$(CONFIG_DRM_DP_AUX_BUS) += drm_dp_aux_bus.o
+
 drm_vram_helper-y := drm_gem_vram_helper.o
 obj-$(CONFIG_DRM_VRAM_HELPER) += drm_vram_helper.o
 
@@ -96,7 +98,6 @@ obj-y			+= omapdrm/
 obj-$(CONFIG_DRM_SUN4I) += sun4i/
 obj-y			+= tilcdc/
 obj-$(CONFIG_DRM_QXL) += qxl/
-obj-$(CONFIG_DRM_BOCHS) += bochs/
 obj-$(CONFIG_DRM_VIRTIO_GPU) += virtio/
 obj-$(CONFIG_DRM_MSM) += msm/
 obj-$(CONFIG_DRM_TEGRA) += tegra/

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -57,7 +57,8 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
 	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \
 	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
-	amdgpu_fw_attestation.o amdgpu_securedisplay.o amdgpu_hdp.o
+	amdgpu_fw_attestation.o amdgpu_securedisplay.o amdgpu_hdp.o \
+	amdgpu_eeprom.o amdgpu_mca.o
 
 amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
 
@@ -75,7 +76,7 @@ amdgpu-y += \
 	vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o navi10_reg_init.o navi14_reg_init.o \
 	arct_reg_init.o navi12_reg_init.o mxgpu_nv.o sienna_cichlid_reg_init.o vangogh_reg_init.o \
 	nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o \
-	beige_goby_reg_init.o yellow_carp_reg_init.o
+	beige_goby_reg_init.o yellow_carp_reg_init.o cyan_skillfish_reg_init.o
 
 # add DF block
 amdgpu-y += \
@@ -111,6 +112,7 @@ amdgpu-y += \
 	psp_v3_1.o \
 	psp_v10_0.o \
 	psp_v11_0.o \
+	psp_v11_0_8.o \
 	psp_v12_0.o \
 	psp_v13_0.o
 
@@ -118,7 +120,7 @@ amdgpu-y += \
 amdgpu-y += \
 	dce_v10_0.o \
 	dce_v11_0.o \
-	dce_virtual.o
+	amdgpu_vkms.o
 
 # add GFX block
 amdgpu-y += \
@@ -187,6 +189,10 @@ amdgpu-y += \
 amdgpu-y += \
 	amdgpu_reset.o
 
+# add MCA block
+amdgpu-y += \
+	mca_v3_0.o
+
 # add amdkfd interfaces
 amdgpu-y += amdgpu_amdkfd.o
 

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -108,6 +108,7 @@
 #include "amdgpu_df.h"
 #include "amdgpu_smuio.h"
 #include "amdgpu_fdinfo.h"
+#include "amdgpu_mca.h"
 
 #define MAX_GPU_INSTANCE		16
 
@@ -916,6 +917,7 @@ struct amdgpu_device {
 
 	/* display */
 	bool				enable_virtual_display;
+	struct amdgpu_vkms_output       *amdgpu_vkms_output;
 	struct amdgpu_mode_info		mode_info;
 	/* For pre-DCE11. DCE11 and later are in "struct amdgpu_device->dm" */
 	struct work_struct		hotplug_work;
@@ -1008,6 +1010,9 @@ struct amdgpu_device {
 	/* df */
 	struct amdgpu_df                df;
 
+	/* MCA */
+	struct amdgpu_mca               mca;
+
 	struct amdgpu_ip_block          ip_blocks[AMDGPU_MAX_IP_NUM];
 	uint32_t		        harvest_ip_mask;
 	int				num_ip_blocks;
@@ -1108,8 +1113,13 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev);
 
 int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
 
+void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
+			     void *buf, size_t size, bool write);
+size_t amdgpu_device_aper_access(struct amdgpu_device *adev, loff_t pos,
+				 void *buf, size_t size, bool write);
+
 void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
-			       uint32_t *buf, size_t size, bool write);
+			       void *buf, size_t size, bool write);
 uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
 			    uint32_t reg, uint32_t acc_flags);
 void amdgpu_device_wreg(struct amdgpu_device *adev,
@@ -1265,6 +1275,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
+#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+
 /* Common functions */
 bool amdgpu_device_has_job_running(struct amdgpu_device *adev);
 bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev);
@@ -1385,12 +1397,12 @@ int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_sta
 int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev);
 
 void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps);
-bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev);
+bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
 void amdgpu_acpi_detect(void);
 #else
 static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; }
 static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { }
-static inline bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev) { return false; }
+static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline void amdgpu_acpi_detect(void) { }
 static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; }
 static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,

drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c

@@ -160,17 +160,28 @@ static int acp_poweron(struct generic_pm_domain *genpd)
 	return 0;
 }
 
-static struct device *get_mfd_cell_dev(const char *device_name, int r)
+static int acp_genpd_add_device(struct device *dev, void *data)
 {
-	char auto_dev_name[25];
+	struct generic_pm_domain *gpd = data;
-	struct device *dev;
+	int ret;
 
-	snprintf(auto_dev_name, sizeof(auto_dev_name),
+	ret = pm_genpd_add_device(gpd, dev);
-		 "%s.%d.auto", device_name, r);
+	if (ret)
-	dev = bus_find_device_by_name(&platform_bus_type, NULL, auto_dev_name);
+		dev_err(dev, "Failed to add dev to genpd %d\n", ret);
-	dev_info(dev, "device %s added to pm domain\n", auto_dev_name);
 
-	return dev;
+	return ret;
+}
+
+static int acp_genpd_remove_device(struct device *dev, void *data)
+{
+	int ret;
+
+	ret = pm_genpd_remove_device(dev);
+	if (ret)
+		dev_err(dev, "Failed to remove dev from genpd %d\n", ret);
+
+	/* Continue to remove */
+	return 0;
 }
 
 /**
@@ -181,11 +192,10 @@ static struct device *get_mfd_cell_dev(const char *device_name, int r)
  */
 static int acp_hw_init(void *handle)
 {
-	int r, i;
+	int r;
 	uint64_t acp_base;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -341,15 +351,10 @@ static int acp_hw_init(void *handle)
 	if (r)
 		goto failure;
 
-	for (i = 0; i < ACP_DEVS ; i++) {
+	r = device_for_each_child(adev->acp.parent, &adev->acp.acp_genpd->gpd,
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
+				  acp_genpd_add_device);
-		r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
+	if (r)
-		if (r) {
+		goto failure;
-			dev_err(dev, "Failed to add dev to genpd\n");
-			goto failure;
-		}
-	}
-
 
 	/* Assert Soft reset of ACP */
 	val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
@@ -410,10 +415,8 @@ failure:
  */
 static int acp_hw_fini(void *handle)
 {
-	int i, ret;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* return early if no ACP */
@@ -458,13 +461,8 @@ static int acp_hw_fini(void *handle)
 		udelay(100);
 	}
 
-	for (i = 0; i < ACP_DEVS ; i++) {
+	device_for_each_child(adev->acp.parent, NULL,
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
+			      acp_genpd_remove_device);
-		ret = pm_genpd_remove_device(dev);
-		/* If removal fails, dont giveup and try rest */
-		if (ret)
-			dev_err(dev, "remove dev from genpd failed\n");
-	}
 
 	mfd_remove_devices(adev->acp.parent);
 	kfree(adev->acp.acp_res);

drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c

@@ -854,8 +854,8 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 		if (amdgpu_device_has_dc_support(adev)) {
 #if defined(CONFIG_DRM_AMD_DC)
 			struct amdgpu_display_manager *dm = &adev->dm;
-			if (dm->backlight_dev)
+			if (dm->backlight_dev[0])
-				atif->bd = dm->backlight_dev;
+				atif->bd = dm->backlight_dev[0];
 #endif
 		} else {
 			struct drm_encoder *tmp;
@@ -1032,13 +1032,13 @@ void amdgpu_acpi_detect(void)
 }
 
 /**
- * amdgpu_acpi_is_s0ix_supported
+ * amdgpu_acpi_is_s0ix_active
  *
  * @adev: amdgpu_device_pointer
  *
  * returns true if supported, false if not.
  */
-bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
+bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 {
 #if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_SUSPEND)
 	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -21,6 +21,7 @@
  */
 
 #include "amdgpu_amdkfd.h"
+#include "amd_pcie.h"
 #include "amd_shared.h"
 
 #include "amdgpu.h"
@@ -553,6 +554,88 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 	return  (uint8_t)ret;
 }
 
+int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct kgd_dev *dst, struct kgd_dev *src, bool is_min)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)dst, *peer_adev;
+	int num_links;
+
+	if (adev->asic_type != CHIP_ALDEBARAN)
+		return 0;
+
+	if (src)
+		peer_adev = (struct amdgpu_device *)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 kgd_dev *dev, bool is_min)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)dev;
+	int num_lanes_shift = (is_min ? ffs(adev->pm.pcie_mlw_mask) :
+							fls(adev->pm.pcie_mlw_mask)) - 1;
+	int gen_speed_shift = (is_min ? ffs(adev->pm.pcie_gen_mask &
+						CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) :
+					fls(adev->pm.pcie_gen_mask &
+						CAIL_PCIE_LINK_SPEED_SUPPORT_MASK)) - 1;
+	uint32_t num_lanes_mask = 1 << num_lanes_shift;
+	uint32_t gen_speed_mask = 1 << gen_speed_shift;
+	int num_lanes_factor = 0, gen_speed_mbits_factor = 0;
+
+	switch (num_lanes_mask) {
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X1:
+		num_lanes_factor = 1;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X2:
+		num_lanes_factor = 2;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X4:
+		num_lanes_factor = 4;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X8:
+		num_lanes_factor = 8;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X12:
+		num_lanes_factor = 12;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X16:
+		num_lanes_factor = 16;
+		break;
+	case CAIL_PCIE_LINK_WIDTH_SUPPORT_X32:
+		num_lanes_factor = 32;
+		break;
+	}
+
+	switch (gen_speed_mask) {
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1:
+		gen_speed_mbits_factor = 2500;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2:
+		gen_speed_mbits_factor = 5000;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3:
+		gen_speed_mbits_factor = 8000;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4:
+		gen_speed_mbits_factor = 16000;
+		break;
+	case CAIL_PCIE_LINK_SPEED_SUPPORT_GEN5:
+		gen_speed_mbits_factor = 32000;
+		break;
+	}
+
+	return (num_lanes_factor * gen_speed_mbits_factor)/BITS_PER_BYTE;
+}
+
 uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
@@ -631,7 +714,6 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 	ret = dma_fence_wait(f, false);
 
 err_ib_sched:
-	dma_fence_put(f);
 	amdgpu_job_free(job);
 err:
 	return ret;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

@@ -226,6 +226,8 @@ uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
 int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);
 uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
+int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct kgd_dev *dst, struct kgd_dev *src, bool is_min);
+int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct kgd_dev *dev, bool is_min);
 
 /* Read user wptr from a specified user address space with page fault
  * disabled. The memory must be pinned and mapped to the hardware when
@@ -269,7 +271,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
 		uint64_t *size);
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
+		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
@@ -330,7 +332,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
-void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask);
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask);
 #else
 static inline int kgd2kfd_init(void)
 {
@@ -389,7 +391,7 @@ void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 }
 
 static inline
-void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint64_t throttle_bitmask)
 {
 }
 #endif

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c

@@ -44,4 +44,5 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c

@@ -305,5 +305,6 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base =
 				kgd_gfx_v9_set_vm_context_page_table_base,
-	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy
+	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c

@@ -560,6 +560,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
 		type = RESET_WAVES;
 		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+		type = SAVE_WAVES;
+		break;
 	default:
 		type = DRAIN_PIPE;
 		break;
@@ -754,6 +757,33 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
+static void program_trap_handler_settings(struct kgd_dev *kgd,
+		uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	/*
+	 * Program TBA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+			lower_32_bits(tba_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+			upper_32_bits(tba_addr >> 8) |
+			(1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT));
+
+	/*
+	 * Program TMA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+			lower_32_bits(tma_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+			upper_32_bits(tma_addr >> 8));
+
+	unlock_srbm(kgd);
+}
+
 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,
@@ -774,4 +804,5 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.program_trap_handler_settings = program_trap_handler_settings,
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c

@@ -537,6 +537,9 @@ static int hqd_destroy_v10_3(struct kgd_dev *kgd, void *mqd,
 	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
 		type = RESET_WAVES;
 		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+		type = SAVE_WAVES;
+		break;
 	default:
 		type = DRAIN_PIPE;
 		break;
@@ -658,6 +661,33 @@ static void set_vm_context_page_table_base_v10_3(struct kgd_dev *kgd, uint32_t v
 	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
+static void program_trap_handler_settings_v10_3(struct kgd_dev *kgd,
+			uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	/*
+	 * Program TBA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+			lower_32_bits(tba_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+			upper_32_bits(tba_addr >> 8) |
+			(1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT));
+
+	/*
+	 * Program TMA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+			lower_32_bits(tma_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+			 upper_32_bits(tma_addr >> 8));
+
+	unlock_srbm(kgd);
+}
+
 #if 0
 uint32_t enable_debug_trap_v10_3(struct kgd_dev *kgd,
 				uint32_t trap_debug_wave_launch_mode,
@@ -820,6 +850,7 @@ const struct kfd2kgd_calls gfx_v10_3_kfd2kgd = {
 	.address_watch_get_offset = address_watch_get_offset_v10_3,
 	.get_atc_vmid_pasid_mapping_info = NULL,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base_v10_3,
+	.program_trap_handler_settings = program_trap_handler_settings_v10_3,
 #if 0
 	.enable_debug_trap = enable_debug_trap_v10_3,
 	.disable_debug_trap = disable_debug_trap_v10_3,

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

@@ -42,7 +42,8 @@
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
 	DRAIN_PIPE,
-	RESET_WAVES
+	RESET_WAVES,
+	SAVE_WAVES
 };
 
 static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
@@ -566,6 +567,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	case KFD_PREEMPT_TYPE_WAVEFRONT_RESET:
 		type = RESET_WAVES;
 		break;
+	case KFD_PREEMPT_TYPE_WAVEFRONT_SAVE:
+		type = SAVE_WAVES;
+		break;
 	default:
 		type = DRAIN_PIPE;
 		break;
@@ -878,6 +882,32 @@ void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid,
 				adev->gfx.cu_info.max_waves_per_simd;
 }
 
+void kgd_gfx_v9_program_trap_handler_settings(struct kgd_dev *kgd,
+                        uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	lock_srbm(kgd, 0, 0, 0, vmid);
+
+	/*
+	 * Program TBA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO),
+                        lower_32_bits(tba_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI),
+                        upper_32_bits(tba_addr >> 8));
+
+	/*
+	 * Program TMA registers
+	 */
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO),
+			lower_32_bits(tma_addr >> 8));
+	WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI),
+			upper_32_bits(tma_addr >> 8));
+
+	unlock_srbm(kgd);
+}
+
 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,
@@ -899,4 +929,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
 	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h

@@ -65,3 +65,5 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base);
 void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid,
 		int *pasid_wave_cnt, int *max_waves_per_cu);
+void kgd_gfx_v9_program_trap_handler_settings(struct kgd_dev *kgd,
+		uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -1057,7 +1057,8 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 static int update_gpuvm_pte(struct kgd_mem *mem,
 			    struct kfd_mem_attachment *entry,
-			    struct amdgpu_sync *sync)
+			    struct amdgpu_sync *sync,
+			    bool *table_freed)
 {
 	struct amdgpu_bo_va *bo_va = entry->bo_va;
 	struct amdgpu_device *adev = entry->adev;
@@ -1068,7 +1069,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 		return ret;
 
 	/* Update the page tables  */
-	ret = amdgpu_vm_bo_update(adev, bo_va, false);
+	ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed);
 	if (ret) {
 		pr_err("amdgpu_vm_bo_update failed\n");
 		return ret;
@@ -1080,7 +1081,8 @@ static int update_gpuvm_pte(struct kgd_mem *mem,
 static int map_bo_to_gpuvm(struct kgd_mem *mem,
 			   struct kfd_mem_attachment *entry,
 			   struct amdgpu_sync *sync,
-			   bool no_update_pte)
+			   bool no_update_pte,
+			   bool *table_freed)
 {
 	int ret;
 
@@ -1097,7 +1099,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem,
 	if (no_update_pte)
 		return 0;
 
-	ret = update_gpuvm_pte(mem, entry, sync);
+	ret = update_gpuvm_pte(mem, entry, sync, table_freed);
 	if (ret) {
 		pr_err("update_gpuvm_pte() failed\n");
 		goto update_gpuvm_pte_failed;
@@ -1285,11 +1287,22 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
 	if (avm->process_info)
 		return -EINVAL;
 
+	/* Free the original amdgpu allocated pasid,
+	 * will be replaced with kfd allocated pasid.
+	 */
+	if (avm->pasid) {
+		amdgpu_pasid_free(avm->pasid);
+		amdgpu_vm_set_pasid(adev, avm, 0);
+	}
+
 	/* Convert VM into a compute VM */
-	ret = amdgpu_vm_make_compute(adev, avm, pasid);
+	ret = amdgpu_vm_make_compute(adev, avm);
 	if (ret)
 		return ret;
 
+	ret = amdgpu_vm_set_pasid(adev, avm, pasid);
+	if (ret)
+		return ret;
 	/* Initialize KFD part of the VM and process info */
 	ret = init_kfd_vm(avm, process_info, ef);
 	if (ret)
@@ -1594,7 +1607,8 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 }
 
 int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-		struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv)
+		struct kgd_dev *kgd, struct kgd_mem *mem,
+		void *drm_priv, bool *table_freed)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
@@ -1682,7 +1696,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 			 entry->va, entry->va + bo_size, entry);
 
 		ret = map_bo_to_gpuvm(mem, entry, ctx.sync,
-				      is_invalid_userptr);
+				      is_invalid_userptr, table_freed);
 		if (ret) {
 			pr_err("Failed to map bo to gpuvm\n");
 			goto out_unreserve;
@@ -1706,6 +1720,12 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 				true);
 	ret = unreserve_bo_and_vms(&ctx, false, false);
 
+	/* Only apply no TLB flush on Aldebaran to
+	 * workaround regressions on other Asics.
+	 */
+	if (table_freed && (adev->asic_type != CHIP_ALDEBARAN))
+		*table_freed = true;
+
 	goto out;
 
 out_unreserve:
@@ -2132,7 +2152,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync);
+			ret = update_gpuvm_pte(mem, attachment, &sync, NULL);
 			if (ret) {
 				pr_err("%s: update PTE failed\n", __func__);
 				/* make sure this gets validated again */
@@ -2338,7 +2358,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 				continue;
 
 			kfd_mem_dmaunmap_attachment(mem, attachment);
-			ret = update_gpuvm_pte(mem, attachment, &sync_obj);
+			ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL);
 			if (ret) {
 				pr_debug("Memory eviction: update PTE failed. Try again\n");
 				goto validate_map_fail;

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

@@ -34,6 +34,7 @@ struct amdgpu_fpriv;
 struct amdgpu_bo_list_entry {
 	struct ttm_validate_buffer	tv;
 	struct amdgpu_bo_va		*bo_va;
+	struct dma_fence_chain		*chain;
 	uint32_t			priority;
 	struct page			**user_pages;
 	bool				user_invalidated;

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -572,6 +572,20 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		goto out;
 	}
 
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
+
+		e->bo_va = amdgpu_vm_bo_find(vm, bo);
+
+		if (bo->tbo.base.dma_buf && !amdgpu_bo_explicit_sync(bo)) {
+			e->chain = dma_fence_chain_alloc();
+			if (!e->chain) {
+				r = -ENOMEM;
+				goto error_validate;
+			}
+		}
+	}
+
 	amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
 					  &p->bytes_moved_vis_threshold);
 	p->bytes_moved = 0;
@@ -599,15 +613,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	gws = p->bo_list->gws_obj;
 	oa = p->bo_list->oa_obj;
 
-	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
-
-		/* Make sure we use the exclusive slot for shared BOs */
-		if (bo->prime_shared_count)
-			e->tv.num_shared = 0;
-		e->bo_va = amdgpu_vm_bo_find(vm, bo);
-	}
-
 	if (gds) {
 		p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT;
 		p->job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT;
@@ -629,8 +634,13 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	}
 
 error_validate:
-	if (r)
+	if (r) {
+		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+			dma_fence_chain_free(e->chain);
+			e->chain = NULL;
+		}
 		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
+	}
 out:
 	return r;
 }
@@ -670,9 +680,17 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 {
 	unsigned i;
 
-	if (error && backoff)
+	if (error && backoff) {
+		struct amdgpu_bo_list_entry *e;
+
+		amdgpu_bo_list_for_each_entry(e, parser->bo_list) {
+			dma_fence_chain_free(e->chain);
+			e->chain = NULL;
+		}
+
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
+	}
 
 	for (i = 0; i < parser->num_post_deps; i++) {
 		drm_syncobj_put(parser->post_deps[i].syncobj);
@@ -781,7 +799,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
+	r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL);
 	if (r)
 		return r;
 
@@ -792,7 +810,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
 		bo_va = fpriv->csa_va;
 		BUG_ON(!bo_va);
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 
@@ -811,7 +829,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (bo_va == NULL)
 			continue;
 
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			return r;
 
@@ -1109,7 +1127,7 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p
 
 		dep->chain = NULL;
 		if (syncobj_deps[i].point) {
-			dep->chain = kmalloc(sizeof(*dep->chain), GFP_KERNEL);
+			dep->chain = dma_fence_chain_alloc();
 			if (!dep->chain)
 				return -ENOMEM;
 		}
@@ -1117,7 +1135,7 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p
 		dep->syncobj = drm_syncobj_find(p->filp,
 						syncobj_deps[i].handle);
 		if (!dep->syncobj) {
-			kfree(dep->chain);
+			dma_fence_chain_free(dep->chain);
 			return -EINVAL;
 		}
 		dep->point = syncobj_deps[i].point;
@@ -1245,6 +1263,28 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm);
 
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct dma_resv *resv = e->tv.bo->base.resv;
+		struct dma_fence_chain *chain = e->chain;
+
+		if (!chain)
+			continue;
+
+		/*
+		 * Work around dma_resv shortcommings by wrapping up the
+		 * submission in a dma_fence_chain and add it as exclusive
+		 * fence, but first add the submission as shared fence to make
+		 * sure that shared fences never signal before the exclusive
+		 * one.
+		 */
+		dma_fence_chain_init(chain, dma_resv_excl_fence(resv),
+				     dma_fence_get(p->fence), 1);
+
+		dma_resv_add_shared_fence(resv, p->fence);
+		rcu_assign_pointer(resv->fence_excl, &chain->base);
+		e->chain = NULL;
+	}
+
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	mutex_unlock(&p->adev->notifier_lock);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c

@@ -1414,7 +1414,7 @@ no_preempt:
 			continue;
 		}
 		job = to_amdgpu_job(s_job);
-		if (preempted && job->fence == fence)
+		if (preempted && (&job->hw_fence) == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -116,6 +116,7 @@ const char *amdgpu_asic_name[] = {
 	"RENOIR",
 	"ALDEBARAN",
 	"NAVI10",
+	"CYAN_SKILLFISH",
 	"NAVI14",
 	"NAVI12",
 	"SIENNA_CICHLID",
@@ -287,7 +288,7 @@ bool amdgpu_device_supports_smart_shift(struct drm_device *dev)
  */
 
 /**
- * amdgpu_device_vram_access - read/write a buffer in vram
+ * amdgpu_device_mm_access - access vram by MM_INDEX/MM_DATA
  *
  * @adev: amdgpu_device pointer
  * @pos: offset of the buffer in vram
@@ -295,22 +296,65 @@ bool amdgpu_device_supports_smart_shift(struct drm_device *dev)
  * @size: read/write size, sizeof(@buf) must > @size
  * @write: true - write to vram, otherwise - read from vram
  */
-void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
+void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
-			       uint32_t *buf, size_t size, bool write)
+			     void *buf, size_t size, bool write)
 {
 	unsigned long flags;
-	uint32_t hi = ~0;
+	uint32_t hi = ~0, tmp = 0;
+	uint32_t *data = buf;
 	uint64_t last;
 	int idx;
 
 	if (!drm_dev_enter(&adev->ddev, &idx))
 		return;
 
+	BUG_ON(!IS_ALIGNED(pos, 4) || !IS_ALIGNED(size, 4));
+
+	spin_lock_irqsave(&adev->mmio_idx_lock, flags);
+	for (last = pos + size; pos < last; pos += 4) {
+		tmp = pos >> 31;
+
+		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
+		if (tmp != hi) {
+			WREG32_NO_KIQ(mmMM_INDEX_HI, tmp);
+			hi = tmp;
+		}
+		if (write)
+			WREG32_NO_KIQ(mmMM_DATA, *data++);
+		else
+			*data++ = RREG32_NO_KIQ(mmMM_DATA);
+	}
+
+	spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+	drm_dev_exit(idx);
+}
+
+/**
+ * amdgpu_device_vram_access - access vram by vram aperature
+ *
+ * @adev: amdgpu_device pointer
+ * @pos: offset of the buffer in vram
+ * @buf: virtual address of the buffer in system memory
+ * @size: read/write size, sizeof(@buf) must > @size
+ * @write: true - write to vram, otherwise - read from vram
+ *
+ * The return value means how many bytes have been transferred.
+ */
+size_t amdgpu_device_aper_access(struct amdgpu_device *adev, loff_t pos,
+				 void *buf, size_t size, bool write)
+{
 #ifdef CONFIG_64BIT
+	void __iomem *addr;
+	size_t count = 0;
+	uint64_t last;
+
+	if (!adev->mman.aper_base_kaddr)
+		return 0;
+
 	last = min(pos + size, adev->gmc.visible_vram_size);
 	if (last > pos) {
-		void __iomem *addr = adev->mman.aper_base_kaddr + pos;
+		addr = adev->mman.aper_base_kaddr + pos;
-		size_t count = last - pos;
+		count = last - pos;
 
 		if (write) {
 			memcpy_toio(addr, buf, count);
@@ -322,35 +366,37 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 			memcpy_fromio(buf, addr, count);
 		}
 
-		if (count == size)
+	}
-			goto exit;
 
+	return count;
+#else
+	return 0;
+#endif
+}
+
+/**
+ * amdgpu_device_vram_access - read/write a buffer in vram
+ *
+ * @adev: amdgpu_device pointer
+ * @pos: offset of the buffer in vram
+ * @buf: virtual address of the buffer in system memory
+ * @size: read/write size, sizeof(@buf) must > @size
+ * @write: true - write to vram, otherwise - read from vram
+ */
+void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
+			       void *buf, size_t size, bool write)
+{
+	size_t count;
+
+	/* try to using vram apreature to access vram first */
+	count = amdgpu_device_aper_access(adev, pos, buf, size, write);
+	size -= count;
+	if (size) {
+		/* using MM to access rest vram */
 		pos += count;
-		buf += count / 4;
+		buf += count;
-		size -= count;
+		amdgpu_device_mm_access(adev, pos, buf, size, write);
 	}
-#endif
-
-	spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-	for (last = pos + size; pos < last; pos += 4) {
-		uint32_t tmp = pos >> 31;
-
-		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
-		if (tmp != hi) {
-			WREG32_NO_KIQ(mmMM_INDEX_HI, tmp);
-			hi = tmp;
-		}
-		if (write)
-			WREG32_NO_KIQ(mmMM_DATA, *buf++);
-		else
-			*buf++ = RREG32_NO_KIQ(mmMM_DATA);
-	}
-	spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-
-#ifdef CONFIG_64BIT
-exit:
-#endif
-	drm_dev_exit(idx);
 }
 
 /*
@@ -518,7 +564,7 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 	    adev->gfx.rlc.funcs &&
 	    adev->gfx.rlc.funcs->is_rlcg_access_range) {
 		if (adev->gfx.rlc.funcs->is_rlcg_access_range(adev, reg))
-			return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v, 0, 0);
+			return adev->gfx.rlc.funcs->sriov_wreg(adev, reg, v, 0, 0);
 	} else {
 		writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
 	}
@@ -1266,15 +1312,16 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 /**
  * amdgpu_device_vga_set_decode - enable/disable vga decode
  *
- * @cookie: amdgpu_device pointer
+ * @pdev: PCI device pointer
  * @state: enable/disable vga decode
  *
  * Enable/disable vga decode (all asics).
  * Returns VGA resource flags.
  */
-static unsigned int amdgpu_device_vga_set_decode(void *cookie, bool state)
+static unsigned int amdgpu_device_vga_set_decode(struct pci_dev *pdev,
+		bool state)
 {
-	struct amdgpu_device *adev = cookie;
+	struct amdgpu_device *adev = drm_to_adev(pci_get_drvdata(pdev));
 	amdgpu_asic_set_vga_state(adev, state);
 	if (state)
 		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
@@ -1394,6 +1441,10 @@ static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev)
 		break;
 	case CHIP_YELLOW_CARP:
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		if (adev->pdev->device == 0x13FE)
+			adev->apu_flags |= AMD_APU_IS_CYAN_SKILLFISH2;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -2100,6 +2151,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	case  CHIP_BEIGE_GOBY:
 	case CHIP_VANGOGH:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		if (adev->asic_type == CHIP_VANGOGH)
 			adev->family = AMDGPU_FAMILY_VGH;
 		else if (adev->asic_type == CHIP_YELLOW_CARP)
@@ -3594,9 +3646,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 fence_driver_init:
 	/* Fence driver */
-	r = amdgpu_fence_driver_init(adev);
+	r = amdgpu_fence_driver_sw_init(adev);
 	if (r) {
-		dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
+		dev_err(adev->dev, "amdgpu_fence_driver_sw_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
 		goto failed;
 	}
@@ -3623,6 +3675,8 @@ fence_driver_init:
 		goto release_ras_con;
 	}
 
+	amdgpu_fence_driver_hw_init(adev);
+
 	dev_info(adev->dev,
 		"SE %d, SH per SE %d, CU per SH %d, active_cu_number %d\n",
 			adev->gfx.config.max_shader_engines,
@@ -3714,7 +3768,7 @@ fence_driver_init:
 	/* this will fail for cards that aren't VGA class devices, just
 	 * ignore it */
 	if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
-		vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode);
+		vga_client_register(adev->pdev, amdgpu_device_vga_set_decode);
 
 	if (amdgpu_device_supports_px(ddev)) {
 		px = true;
@@ -3771,7 +3825,10 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 {
 	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
-	ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
+	if (adev->mman.initialized) {
+		flush_delayed_work(&adev->mman.bdev.wq);
+		ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
+	}
 	adev->shutdown = true;
 
 	/* make sure IB test finished before entering exclusive mode
@@ -3790,7 +3847,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		else
 			drm_atomic_helper_shutdown(adev_to_drm(adev));
 	}
-	amdgpu_fence_driver_fini_hw(adev);
+	amdgpu_fence_driver_hw_fini(adev);
 
 	if (adev->pm_sysfs_en)
 		amdgpu_pm_sysfs_fini(adev);
@@ -3812,7 +3869,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 {
 	amdgpu_device_ip_fini(adev);
-	amdgpu_fence_driver_fini_sw(adev);
+	amdgpu_fence_driver_sw_fini(adev);
 	release_firmware(adev->firmware.gpu_info_fw);
 	adev->firmware.gpu_info_fw = NULL;
 	adev->accel_working = false;
@@ -3833,7 +3890,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 	}
 	if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
-		vga_client_register(adev->pdev, NULL, NULL, NULL);
+		vga_client_unregister(adev->pdev);
 
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
@@ -3887,7 +3944,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
-	amdgpu_fence_driver_suspend(adev);
+	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
 	/* evict remaining vram memory
@@ -3932,8 +3989,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
 		return r;
 	}
-	amdgpu_fence_driver_resume(adev);
+	amdgpu_fence_driver_hw_init(adev);
-
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
@@ -4394,7 +4450,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 				 struct amdgpu_reset_context *reset_context)
 {
-	int i, r = 0;
+	int i, j, r = 0;
 	struct amdgpu_job *job = NULL;
 	bool need_full_reset =
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@@ -4418,11 +4474,22 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		if (!ring || !ring->sched.thread)
 			continue;
 
+		/*clear job fence from fence drv to avoid force_completion
+		 *leave NULL and vm flush fence in fence drv */
+		for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) {
+			struct dma_fence *old, **ptr;
+
+			ptr = &ring->fence_drv.fences[j];
+			old = rcu_dereference_protected(*ptr, 1);
+			if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) {
+				RCU_INIT_POINTER(*ptr, NULL);
+			}
+		}
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}
 
-	if(job)
+	if (job && job->vm)
 		drm_sched_increase_karma(&job->base);
 
 	r = amdgpu_reset_prepare_hwcontext(adev, reset_context);
@@ -4886,7 +4953,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			DRM_INFO("Bailing on TDR for s_job:%llx, hive: %llx as another already in progress",
 				job ? job->base.id : -1, hive->hive_id);
 			amdgpu_put_xgmi_hive(hive);
-			if (job)
+			if (job && job->vm)
 				drm_sched_increase_karma(&job->base);
 			return 0;
 		}
@@ -4910,7 +4977,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 					job ? job->base.id : -1);
 
 		/* even we skipped this reset, still need to set the job to guilty */
-		if (job)
+		if (job && job->vm)
 			drm_sched_increase_karma(&job->base);
 		goto skip_recovery;
 	}
@@ -5277,6 +5344,10 @@ int amdgpu_device_baco_exit(struct drm_device *dev)
 	    adev->nbio.funcs->enable_doorbell_interrupt)
 		adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
 
+	if (amdgpu_passthrough(adev) &&
+	    adev->nbio.funcs->clear_doorbell_interrupt)
+		adev->nbio.funcs->clear_doorbell_interrupt(adev);
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c

@@ -42,48 +42,6 @@
 #include <linux/pci-p2pdma.h>
 #include <linux/pm_runtime.h>
 
-static int
-__dma_resv_make_exclusive(struct dma_resv *obj)
-{
-	struct dma_fence **fences;
-	unsigned int count;
-	int r;
-
-	if (!dma_resv_shared_list(obj)) /* no shared fences to convert */
-		return 0;
-
-	r = dma_resv_get_fences(obj, NULL, &count, &fences);
-	if (r)
-		return r;
-
-	if (count == 0) {
-		/* Now that was unexpected. */
-	} else if (count == 1) {
-		dma_resv_add_excl_fence(obj, fences[0]);
-		dma_fence_put(fences[0]);
-		kfree(fences);
-	} else {
-		struct dma_fence_array *array;
-
-		array = dma_fence_array_create(count, fences,
-					       dma_fence_context_alloc(1), 0,
-					       false);
-		if (!array)
-			goto err_fences_put;
-
-		dma_resv_add_excl_fence(obj, &array->base);
-		dma_fence_put(&array->base);
-	}
-
-	return 0;
-
-err_fences_put:
-	while (count--)
-		dma_fence_put(fences[count]);
-	kfree(fences);
-	return -ENOMEM;
-}
-
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
  *
@@ -110,24 +68,6 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	if (r < 0)
 		goto out;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (unlikely(r != 0))
-		goto out;
-
-	/*
-	 * We only create shared fences for internal use, but importers
-	 * of the dmabuf rely on exclusive fences for implicitly
-	 * tracking write hazards. As any of the current fences may
-	 * correspond to a write, we need to convert all existing
-	 * fences on the reservation object into a single exclusive
-	 * fence.
-	 */
-	r = __dma_resv_make_exclusive(bo->tbo.base.resv);
-	if (r)
-		goto out;
-
-	bo->prime_shared_count++;
-	amdgpu_bo_unreserve(bo);
 	return 0;
 
 out:
@@ -150,9 +90,6 @@ static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
-		bo->prime_shared_count--;
-
 	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 }
@@ -418,8 +355,6 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
 	bo = gem_to_amdgpu_bo(gobj);
 	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
 	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
-	if (dma_buf->ops != &amdgpu_dmabuf_ops)
-		bo->prime_shared_count = 1;
 
 	dma_resv_unlock(resv);
 	return gobj;

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -870,11 +870,10 @@ MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legac
 module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 
 /**
- * DOC: bad_page_threshold (int)
+ * DOC: bad_page_threshold (int) Bad page threshold is specifies the
- * Bad page threshold is to specify the threshold value of faulty pages
+ * threshold value of faulty pages detected by RAS ECC, which may
- * detected by RAS ECC, that may result in GPU entering bad status if total
+ * result in the GPU entering bad status when the number of total
- * faulty pages by ECC exceed threshold value and leave it for user's further
+ * faulty pages by ECC exceeds the threshold value.
- * check.
  */
 MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
 module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
@@ -1213,6 +1212,9 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x740F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
 	{0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
 
+	/* CYAN_SKILLFISH */
+	{0x1002, 0x13FE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+
 	/* BEIGE_GOBY */
 	{0x1002, 0x7420, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 	{0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
@@ -1236,7 +1238,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	int ret, retry = 0;
 	bool supports_atomic = false;
 
-	if (!amdgpu_virtual_display &&
+	if (amdgpu_virtual_display ||
 	    amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
 		supports_atomic = true;
 
@@ -1292,7 +1294,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 #endif
 
 	/* Get rid of things like offb */
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "amdgpudrmfb");
+	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
 	if (ret)
 		return ret;
 
@@ -1474,7 +1476,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
-	if (amdgpu_acpi_is_s0ix_supported(adev))
+	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	adev->in_s3 = true;
 	r = amdgpu_device_suspend(drm_dev, true);
@@ -1490,7 +1492,7 @@ static int amdgpu_pmops_resume(struct device *dev)
 	int r;
 
 	r = amdgpu_device_resume(drm_dev, true);
-	if (amdgpu_acpi_is_s0ix_supported(adev))
+	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = false;
 	return r;
 }
@@ -1784,7 +1786,6 @@ static const struct drm_driver amdgpu_kms_driver = {
 	.open = amdgpu_driver_open_kms,
 	.postclose = amdgpu_driver_postclose_kms,
 	.lastclose = amdgpu_driver_lastclose_kms,
-	.irq_handler = amdgpu_irq_handler,
 	.ioctls = amdgpu_ioctls_kms,
 	.num_ioctls = ARRAY_SIZE(amdgpu_ioctls_kms),
 	.dumb_create = amdgpu_mode_dumb_create,

drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c

@@ -0,0 +1,239 @@
+/*
+ * 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.
+ *
+ */
+
+#include "amdgpu_eeprom.h"
+#include "amdgpu.h"
+
+/* AT24CM02 and M24M02-R have a 256-byte write page size.
+ */
+#define EEPROM_PAGE_BITS   8
+#define EEPROM_PAGE_SIZE   (1U << EEPROM_PAGE_BITS)
+#define EEPROM_PAGE_MASK   (EEPROM_PAGE_SIZE - 1)
+
+#define EEPROM_OFFSET_SIZE 2
+
+/* EEPROM memory addresses are 19-bits long, which can
+ * be partitioned into 3, 8, 8 bits, for a total of 19.
+ * The upper 3 bits are sent as part of the 7-bit
+ * "Device Type Identifier"--an I2C concept, which for EEPROM devices
+ * is hard-coded as 1010b, indicating that it is an EEPROM
+ * device--this is the wire format, followed by the upper
+ * 3 bits of the 19-bit address, followed by the direction,
+ * followed by two bytes holding the rest of the 16-bits of
+ * the EEPROM memory address. The format on the wire for EEPROM
+ * devices is: 1010XYZD, A15:A8, A7:A0,
+ * Where D is the direction and sequenced out by the hardware.
+ * Bits XYZ are memory address bits 18, 17 and 16.
+ * These bits are compared to how pins 1-3 of the part are connected,
+ * depending on the size of the part, more on that later.
+ *
+ * Note that of this wire format, a client is in control
+ * of, and needs to specify only XYZ, A15:A8, A7:0, bits,
+ * which is exactly the EEPROM memory address, or offset,
+ * in order to address up to 8 EEPROM devices on the I2C bus.
+ *
+ * For instance, a 2-Mbit I2C EEPROM part, addresses all its bytes,
+ * using an 18-bit address, bit 17 to 0 and thus would use all but one bit of
+ * the 19 bits previously mentioned. The designer would then not connect
+ * pins 1 and 2, and pin 3 usually named "A_2" or "E2", would be connected to
+ * either Vcc or GND. This would allow for up to two 2-Mbit parts on
+ * the same bus, where one would be addressable with bit 18 as 1, and
+ * the other with bit 18 of the address as 0.
+ *
+ * For a 2-Mbit part, bit 18 is usually known as the "Chip Enable" or
+ * "Hardware Address Bit". This bit is compared to the load on pin 3
+ * of the device, described above, and if there is a match, then this
+ * device responds to the command. This way, you can connect two
+ * 2-Mbit EEPROM devices on the same bus, but see one contiguous
+ * memory from 0 to 7FFFFh, where address 0 to 3FFFF is in the device
+ * whose pin 3 is connected to GND, and address 40000 to 7FFFFh is in
+ * the 2nd device, whose pin 3 is connected to Vcc.
+ *
+ * This addressing you encode in the 32-bit "eeprom_addr" below,
+ * namely the 19-bits "XYZ,A15:A0", as a single 19-bit address. For
+ * instance, eeprom_addr = 0x6DA01, is 110_1101_1010_0000_0001, where
+ * XYZ=110b, and A15:A0=DA01h. The XYZ bits become part of the device
+ * address, and the rest of the address bits are sent as the memory
+ * address bytes.
+ *
+ * That is, for an I2C EEPROM driver everything is controlled by
+ * the "eeprom_addr".
+ *
+ * P.S. If you need to write, lock and read the Identification Page,
+ * (M24M02-DR device only, which we do not use), change the "7" to
+ * "0xF" in the macro below, and let the client set bit 20 to 1 in
+ * "eeprom_addr", and set A10 to 0 to write into it, and A10 and A1 to
+ * 1 to lock it permanently.
+ */
+#define MAKE_I2C_ADDR(_aa) ((0xA << 3) | (((_aa) >> 16) & 7))
+
+static int __amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+				u8 *eeprom_buf, u16 buf_size, bool read)
+{
+	u8 eeprom_offset_buf[EEPROM_OFFSET_SIZE];
+	struct i2c_msg msgs[] = {
+		{
+			.flags = 0,
+			.len = EEPROM_OFFSET_SIZE,
+			.buf = eeprom_offset_buf,
+		},
+		{
+			.flags = read ? I2C_M_RD : 0,
+		},
+	};
+	const u8 *p = eeprom_buf;
+	int r;
+	u16 len;
+
+	for (r = 0; buf_size > 0;
+	      buf_size -= len, eeprom_addr += len, eeprom_buf += len) {
+		/* Set the EEPROM address we want to write to/read from.
+		 */
+		msgs[0].addr = MAKE_I2C_ADDR(eeprom_addr);
+		msgs[1].addr = msgs[0].addr;
+		msgs[0].buf[0] = (eeprom_addr >> 8) & 0xff;
+		msgs[0].buf[1] = eeprom_addr & 0xff;
+
+		if (!read) {
+			/* Write the maximum amount of data, without
+			 * crossing the device's page boundary, as per
+			 * its spec. Partial page writes are allowed,
+			 * starting at any location within the page,
+			 * so long as the page boundary isn't crossed
+			 * over (actually the page pointer rolls
+			 * over).
+			 *
+			 * As per the AT24CM02 EEPROM spec, after
+			 * writing into a page, the I2C driver should
+			 * terminate the transfer, i.e. in
+			 * "i2c_transfer()" below, with a STOP
+			 * condition, so that the self-timed write
+			 * cycle begins. This is implied for the
+			 * "i2c_transfer()" abstraction.
+			 */
+			len = min(EEPROM_PAGE_SIZE - (eeprom_addr &
+						      EEPROM_PAGE_MASK),
+				  (u32)buf_size);
+		} else {
+			/* Reading from the EEPROM has no limitation
+			 * on the number of bytes read from the EEPROM
+			 * device--they are simply sequenced out.
+			 */
+			len = buf_size;
+		}
+		msgs[1].len = len;
+		msgs[1].buf = eeprom_buf;
+
+		/* This constitutes a START-STOP transaction.
+		 */
+		r = i2c_transfer(i2c_adap, msgs, ARRAY_SIZE(msgs));
+		if (r != ARRAY_SIZE(msgs))
+			break;
+
+		if (!read) {
+			/* According to EEPROM specs the length of the
+			 * self-writing cycle, tWR (tW), is 10 ms.
+			 *
+			 * TODO: Use polling on ACK, aka Acknowledge
+			 * Polling, to minimize waiting for the
+			 * internal write cycle to complete, as it is
+			 * usually smaller than tWR (tW).
+			 */
+			msleep(10);
+		}
+	}
+
+	return r < 0 ? r : eeprom_buf - p;
+}
+
+/**
+ * amdgpu_eeprom_xfer -- Read/write from/to an I2C EEPROM device
+ * @i2c_adap: pointer to the I2C adapter to use
+ * @eeprom_addr: EEPROM address from which to read/write
+ * @eeprom_buf: pointer to data buffer to read into/write from
+ * @buf_size: the size of @eeprom_buf
+ * @read: True if reading from the EEPROM, false if writing
+ *
+ * Returns the number of bytes read/written; -errno on error.
+ */
+static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+			      u8 *eeprom_buf, u16 buf_size, bool read)
+{
+	const struct i2c_adapter_quirks *quirks = i2c_adap->quirks;
+	u16 limit;
+
+	if (!quirks)
+		limit = 0;
+	else if (read)
+		limit = quirks->max_read_len;
+	else
+		limit = quirks->max_write_len;
+
+	if (limit == 0) {
+		return __amdgpu_eeprom_xfer(i2c_adap, eeprom_addr,
+					    eeprom_buf, buf_size, read);
+	} else if (limit <= EEPROM_OFFSET_SIZE) {
+		dev_err_ratelimited(&i2c_adap->dev,
+				    "maddr:0x%04X size:0x%02X:quirk max_%s_len must be > %d",
+				    eeprom_addr, buf_size,
+				    read ? "read" : "write", EEPROM_OFFSET_SIZE);
+		return -EINVAL;
+	} else {
+		u16 ps; /* Partial size */
+		int res = 0, r;
+
+		/* The "limit" includes all data bytes sent/received,
+		 * which would include the EEPROM_OFFSET_SIZE bytes.
+		 * Account for them here.
+		 */
+		limit -= EEPROM_OFFSET_SIZE;
+		for ( ; buf_size > 0;
+		      buf_size -= ps, eeprom_addr += ps, eeprom_buf += ps) {
+			ps = min(limit, buf_size);
+
+			r = __amdgpu_eeprom_xfer(i2c_adap, eeprom_addr,
+						 eeprom_buf, ps, read);
+			if (r < 0)
+				return r;
+			res += r;
+		}
+
+		return res;
+	}
+}
+
+int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+		       u32 eeprom_addr, u8 *eeprom_buf,
+		       u16 bytes)
+{
+	return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes,
+				  true);
+}
+
+int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap,
+			u32 eeprom_addr, u8 *eeprom_buf,
+			u16 bytes)
+{
+	return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes,
+				  false);
+}

drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h

@@ -0,0 +1,37 @@
+/*
+ * 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 _AMDGPU_EEPROM_H
+#define _AMDGPU_EEPROM_H
+
+#include <linux/i2c.h>
+
+int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+		       u32 eeprom_addr, u8 *eeprom_buf,
+		       u16 bytes);
+
+int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap,
+			u32 eeprom_addr, u8 *eeprom_buf,
+			u16 bytes);
+
+#endif

drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c

@@ -273,9 +273,6 @@ static int amdgpufb_create(struct drm_fb_helper *helper,
 	return 0;
 
 out:
-	if (abo) {
-
-	}
 	if (fb && ret) {
 		drm_gem_object_put(gobj);
 		drm_framebuffer_unregister_private(fb);
@@ -344,7 +341,7 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev)
 	}
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
-	if (!amdgpu_device_has_dc_support(adev))
+	if (!amdgpu_device_has_dc_support(adev) && !amdgpu_virtual_display)
 		drm_helper_disable_unused_functions(adev_to_drm(adev));
 
 	drm_fb_helper_initial_config(&rfbdev->helper, bpp_sel);

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -129,30 +129,50 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
  *
  * @ring: ring the fence is associated with
  * @f: resulting fence object
+ * @job: job the fence is embedded in
  * @flags: flags to pass into the subordinate .emit_fence() call
  *
  * Emits a fence command on the requested ring (all asics).
  * Returns 0 on success, -ENOMEM on failure.
  */
-int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
+int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amdgpu_job *job,
 		      unsigned flags)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_fence *fence;
+	struct dma_fence *fence;
+	struct amdgpu_fence *am_fence;
 	struct dma_fence __rcu **ptr;
 	uint32_t seq;
 	int r;
 
-	fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL);
+	if (job == NULL) {
-	if (fence == NULL)
+		/* create a sperate hw fence */
-		return -ENOMEM;
+		am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC);
+		if (am_fence == NULL)
+			return -ENOMEM;
+		fence = &am_fence->base;
+		am_fence->ring = ring;
+	} else {
+		/* take use of job-embedded fence */
+		fence = &job->hw_fence;
+	}
 
 	seq = ++ring->fence_drv.sync_seq;
-	fence->ring = ring;
+	if (job != NULL && job->job_run_counter) {
-	dma_fence_init(&fence->base, &amdgpu_fence_ops,
+		/* reinit seq for resubmitted jobs */
-		       &ring->fence_drv.lock,
+		fence->seqno = seq;
-		       adev->fence_context + ring->idx,
+	} else {
-		       seq);
+		dma_fence_init(fence, &amdgpu_fence_ops,
+				&ring->fence_drv.lock,
+				adev->fence_context + ring->idx,
+				seq);
+	}
+
+	if (job != NULL) {
+		/* mark this fence has a parent job */
+		set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags);
+	}
+
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
 	pm_runtime_get_noresume(adev_to_drm(adev)->dev);
@@ -175,9 +195,9 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 	/* This function can't be called concurrently anyway, otherwise
 	 * emitting the fence would mess up the hardware ring buffer.
 	 */
-	rcu_assign_pointer(*ptr, dma_fence_get(&fence->base));
+	rcu_assign_pointer(*ptr, dma_fence_get(fence));
 
-	*f = &fence->base;
+	*f = fence;
 
 	return 0;
 }
@@ -417,9 +437,6 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
 	}
 	amdgpu_fence_write(ring, atomic_read(&ring->fence_drv.last_seq));
 
-	if (irq_src)
-		amdgpu_irq_get(adev, irq_src, irq_type);
-
 	ring->fence_drv.irq_src = irq_src;
 	ring->fence_drv.irq_type = irq_type;
 	ring->fence_drv.initialized = true;
@@ -490,7 +507,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 
 	r = drm_sched_init(&ring->sched, &amdgpu_sched_ops,
 			   num_hw_submission, amdgpu_job_hang_limit,
-			   timeout, sched_score, ring->name);
+			   timeout, NULL, sched_score, ring->name);
 	if (r) {
 		DRM_ERROR("Failed to create scheduler on ring %s.\n",
 			  ring->name);
@@ -501,7 +518,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 }
 
 /**
- * amdgpu_fence_driver_init - init the fence driver
+ * amdgpu_fence_driver_sw_init - init the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
@@ -512,20 +529,20 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
  * amdgpu_fence_driver_start_ring().
  * Returns 0 for success.
  */
-int amdgpu_fence_driver_init(struct amdgpu_device *adev)
+int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
 {
 	return 0;
 }
 
 /**
- * amdgpu_fence_driver_fini - tear down the fence driver
+ * amdgpu_fence_driver_hw_fini - tear down the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
  *
  * Tear down the fence driver for all possible rings (all asics).
  */
-void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
+void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -534,8 +551,7 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
-		if (!ring->no_scheduler)
+
-			drm_sched_fini(&ring->sched);
 		/* You can't wait for HW to signal if it's gone */
 		if (!drm_dev_is_unplugged(&adev->ddev))
 			r = amdgpu_fence_wait_empty(ring);
@@ -553,7 +569,7 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 	}
 }
 
-void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
+void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
 {
 	unsigned int i, j;
 
@@ -563,6 +579,9 @@ void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler)
+			drm_sched_fini(&ring->sched);
+
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
 			dma_fence_put(ring->fence_drv.fences[j]);
 		kfree(ring->fence_drv.fences);
@@ -572,49 +591,18 @@ void amdgpu_fence_driver_fini_sw(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_fence_driver_suspend - suspend the fence driver
+ * amdgpu_fence_driver_hw_init - enable the fence driver
  * for all possible rings.
  *
  * @adev: amdgpu device pointer
  *
- * Suspend the fence driver for all possible rings (all asics).
+ * Enable the fence driver for all possible rings (all asics).
- */
-void amdgpu_fence_driver_suspend(struct amdgpu_device *adev)
-{
-	int i, r;
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		if (!ring || !ring->fence_drv.initialized)
-			continue;
-
-		/* wait for gpu to finish processing current batch */
-		r = amdgpu_fence_wait_empty(ring);
-		if (r) {
-			/* delay GPU reset to resume */
-			amdgpu_fence_driver_force_completion(ring);
-		}
-
-		/* disable the interrupt */
-		if (ring->fence_drv.irq_src)
-			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
-				       ring->fence_drv.irq_type);
-	}
-}
-
-/**
- * amdgpu_fence_driver_resume - resume the fence driver
- * for all possible rings.
- *
- * @adev: amdgpu device pointer
- *
- * Resume the fence driver for all possible rings (all asics).
  * Not all asics have all rings, so each asic will only
  * start the fence driver on the rings it has using
  * amdgpu_fence_driver_start_ring().
  * Returns 0 for success.
  */
-void amdgpu_fence_driver_resume(struct amdgpu_device *adev)
+void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 {
 	int i;
 
@@ -653,8 +641,16 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence)
 
 static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 {
-	struct amdgpu_fence *fence = to_amdgpu_fence(f);
+	struct amdgpu_ring *ring;
-	return (const char *)fence->ring->name;
+
+	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
+		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+
+		ring = to_amdgpu_ring(job->base.sched);
+	} else {
+		ring = to_amdgpu_fence(f)->ring;
+	}
+	return (const char *)ring->name;
 }
 
 /**
@@ -667,13 +663,20 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
  */
 static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 {
-	struct amdgpu_fence *fence = to_amdgpu_fence(f);
+	struct amdgpu_ring *ring;
-	struct amdgpu_ring *ring = fence->ring;
+
+	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
+		struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+
+		ring = to_amdgpu_ring(job->base.sched);
+	} else {
+		ring = to_amdgpu_fence(f)->ring;
+	}
 
 	if (!timer_pending(&ring->fence_drv.fallback_timer))
 		amdgpu_fence_schedule_fallback(ring);
 
-	DMA_FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx);
+	DMA_FENCE_TRACE(f, "armed on ring %i!\n", ring->idx);
 
 	return true;
 }
@@ -688,8 +691,20 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 static void amdgpu_fence_free(struct rcu_head *rcu)
 {
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
-	struct amdgpu_fence *fence = to_amdgpu_fence(f);
+
-	kmem_cache_free(amdgpu_fence_slab, fence);
+	if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
+	/* free job if fence has a parent job */
+		struct amdgpu_job *job;
+
+		job = container_of(f, struct amdgpu_job, hw_fence);
+		kfree(job);
+	} else {
+	/* free fence_slab if it's separated fence*/
+		struct amdgpu_fence *fence;
+
+		fence = to_amdgpu_fence(f);
+		kmem_cache_free(amdgpu_fence_slab, fence);
+	}
 }
 
 /**
@@ -712,6 +727,7 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
 	.release = amdgpu_fence_release,
 };
 
+
 /*
  * Fence debugfs
  */

drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c

@@ -27,10 +27,10 @@
 #include "smu_v11_0_i2c.h"
 #include "atom.h"
 #include "amdgpu_fru_eeprom.h"
+#include "amdgpu_eeprom.h"
 
-#define I2C_PRODUCT_INFO_ADDR		0xAC
+#define FRU_EEPROM_MADDR        0x60000
-#define I2C_PRODUCT_INFO_ADDR_SIZE	0x2
+#define I2C_PRODUCT_INFO_OFFSET 0xC0
-#define I2C_PRODUCT_INFO_OFFSET		0xC0
 
 static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 {
@@ -62,19 +62,11 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 }
 
 static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
-			   unsigned char *buff)
+				  unsigned char *buff)
 {
 	int ret, size;
-	struct i2c_msg msg = {
-			.addr   = I2C_PRODUCT_INFO_ADDR,
-			.flags  = I2C_M_RD,
-			.buf    = buff,
-	};
-	buff[0] = 0;
-	buff[1] = addrptr;
-	msg.len = I2C_PRODUCT_INFO_ADDR_SIZE + 1;
-	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
 
+	ret = amdgpu_eeprom_read(&adev->pm.smu_i2c, addrptr, buff, 1);
 	if (ret < 1) {
 		DRM_WARN("FRU: Failed to get size field");
 		return ret;
@@ -83,13 +75,9 @@ static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
 	/* The size returned by the i2c requires subtraction of 0xC0 since the
 	 * size apparently always reports as 0xC0+actual size.
 	 */
-	size = buff[2] - I2C_PRODUCT_INFO_OFFSET;
+	size = buff[0] - I2C_PRODUCT_INFO_OFFSET;
-	/* Add 1 since address field was 1 byte */
-	buff[1] = addrptr + 1;
-
-	msg.len = I2C_PRODUCT_INFO_ADDR_SIZE + size;
-	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
 
+	ret = amdgpu_eeprom_read(&adev->pm.smu_i2c, addrptr + 1, buff, size);
 	if (ret < 1) {
 		DRM_WARN("FRU: Failed to get data field");
 		return ret;
@@ -101,8 +89,8 @@ static int amdgpu_fru_read_eeprom(struct amdgpu_device *adev, uint32_t addrptr,
 int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 {
 	unsigned char buff[34];
-	int addrptr, size;
+	u32 addrptr;
-	int len;
+	int size, len;
 
 	if (!is_fru_eeprom_supported(adev))
 		return 0;
@@ -125,7 +113,7 @@ int amdgpu_fru_get_product_info(struct amdgpu_device *adev)
 	 * Bytes 8-a are all 1-byte and refer to the size of the entire struct,
 	 * and the language field, so just start from 0xb, manufacturer size
 	 */
-	addrptr = 0xb;
+	addrptr = FRU_EEPROM_MADDR + 0xb;
 	size = amdgpu_fru_read_eeprom(adev, addrptr, buff);
 	if (size < 1) {
 		DRM_ERROR("Failed to read FRU Manufacturer, ret:%d", size);

drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c

@@ -76,7 +76,7 @@ static int amdgpu_gart_dummy_page_init(struct amdgpu_device *adev)
 	if (adev->dummy_page_addr)
 		return 0;
 	adev->dummy_page_addr = dma_map_page(&adev->pdev->dev, dummy_page, 0,
-					     PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+					     PAGE_SIZE, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(&adev->pdev->dev, adev->dummy_page_addr)) {
 		dev_err(&adev->pdev->dev, "Failed to DMA MAP the dummy page\n");
 		adev->dummy_page_addr = 0;
@@ -96,8 +96,8 @@ void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev)
 {
 	if (!adev->dummy_page_addr)
 		return;
-	pci_unmap_page(adev->pdev, adev->dummy_page_addr,
+	dma_unmap_page(&adev->pdev->dev, adev->dummy_page_addr, PAGE_SIZE,
-		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+		       DMA_BIDIRECTIONAL);
 	adev->dummy_page_addr = 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

@@ -621,7 +621,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 
 	if (operation == AMDGPU_VA_OP_MAP ||
 	    operation == AMDGPU_VA_OP_REPLACE) {
-		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
 		if (r)
 			goto error;
 	}
@@ -838,7 +838,8 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	case AMDGPU_GEM_OP_SET_PLACEMENT:
-		if (robj->prime_shared_count && (args->value & AMDGPU_GEM_DOMAIN_VRAM)) {
+		if (robj->tbo.base.import_attach &&
+		    args->value & AMDGPU_GEM_DOMAIN_VRAM) {
 			r = -EINVAL;
 			amdgpu_bo_unreserve(robj);
 			break;
@@ -903,7 +904,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 					 DIV_ROUND_UP(args->bpp, 8), 0);
 	args->size = (u64)args->pitch * args->height;
 	args->size = ALIGN(args->size, PAGE_SIZE);
-	domain = amdgpu_bo_get_preferred_pin_domain(adev,
+	domain = amdgpu_bo_get_preferred_domain(adev,
 				amdgpu_display_supported_domains(adev, flags));
 	r = amdgpu_gem_object_create(adev, args->size, 0, domain, flags,
 				     ttm_bo_type_device, NULL, &gobj);

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c

@@ -629,7 +629,6 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
 		adev->gfx.ras_if->block = AMDGPU_RAS_BLOCK__GFX;
 		adev->gfx.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->gfx.ras_if->sub_block_index = 0;
-		strcpy(adev->gfx.ras_if->name, "gfx");
 	}
 	fs_info.head = ih_info.head = *adev->gfx.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->gfx.ras_if,

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

@@ -471,6 +471,27 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev)
 			return r;
 	}
 
+	if (adev->mca.mp0.ras_funcs &&
+	    adev->mca.mp0.ras_funcs->ras_late_init) {
+		r = adev->mca.mp0.ras_funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
+	if (adev->mca.mp1.ras_funcs &&
+	    adev->mca.mp1.ras_funcs->ras_late_init) {
+		r = adev->mca.mp1.ras_funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
+	if (adev->mca.mpio.ras_funcs &&
+	    adev->mca.mpio.ras_funcs->ras_late_init) {
+		r = adev->mca.mpio.ras_funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c

@@ -132,14 +132,11 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	struct amdgpu_gtt_node *node;
 	int r;
 
-	spin_lock(&mgr->lock);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY) &&
-	if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT &&
+	    atomic64_add_return(num_pages, &mgr->used) >  man->size) {
-	    atomic64_read(&mgr->available) < num_pages) {
+		atomic64_sub(num_pages, &mgr->used);
-		spin_unlock(&mgr->lock);
 		return -ENOSPC;
 	}
-	atomic64_sub(num_pages, &mgr->available);
-	spin_unlock(&mgr->lock);
 
 	node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL);
 	if (!node) {
@@ -175,7 +172,8 @@ err_free:
 	kfree(node);
 
 err_out:
-	atomic64_add(num_pages, &mgr->available);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
+		atomic64_sub(num_pages, &mgr->used);
 
 	return r;
 }
@@ -198,7 +196,9 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 	if (drm_mm_node_allocated(&node->base.mm_nodes[0]))
 		drm_mm_remove_node(&node->base.mm_nodes[0]);
 	spin_unlock(&mgr->lock);
-	atomic64_add(res->num_pages, &mgr->available);
+
+	if (!(res->placement & TTM_PL_FLAG_TEMPORARY))
+		atomic64_sub(res->num_pages, &mgr->used);
 
 	kfree(node);
 }
@@ -213,9 +213,8 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
-	s64 result = man->size - atomic64_read(&mgr->available);
 
-	return (result > 0 ? result : 0) * PAGE_SIZE;
+	return atomic64_read(&mgr->used) * PAGE_SIZE;
 }
 
 /**
@@ -265,9 +264,8 @@ static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man,
 	drm_mm_print(&mgr->mm, printer);
 	spin_unlock(&mgr->lock);
 
-	drm_printf(printer, "man size:%llu pages, gtt available:%lld pages, usage:%lluMB\n",
+	drm_printf(printer, "man size:%llu pages,  gtt used:%llu pages\n",
-		   man->size, (u64)atomic64_read(&mgr->available),
+		   man->size, atomic64_read(&mgr->used));
-		   amdgpu_gtt_mgr_usage(man) >> 20);
 }
 
 static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = {
@@ -299,7 +297,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
 	drm_mm_init(&mgr->mm, start, size);
 	spin_lock_init(&mgr->lock);
-	atomic64_set(&mgr->available, gtt_size >> PAGE_SHIFT);
+	atomic64_set(&mgr->used, 0);
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, &mgr->manager);
 	ttm_resource_manager_set_used(man, true);

drivers/gpu/drm/amd/amdgpu/amdgpu_hdp.c

@@ -41,7 +41,6 @@ int amdgpu_hdp_ras_late_init(struct amdgpu_device *adev)
 		adev->hdp.ras_if->block = AMDGPU_RAS_BLOCK__HDP;
 		adev->hdp.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->hdp.ras_if->sub_block_index = 0;
-		strcpy(adev->hdp.ras_if->name, "hdp");
 	}
 	ih_info.head = fs_info.head = *adev->hdp.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->hdp.ras_if,

drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c

@@ -339,7 +339,7 @@ static void amdgpu_i2c_put_byte(struct amdgpu_i2c_chan *i2c_bus,
 void
 amdgpu_i2c_router_select_ddc_port(const struct amdgpu_connector *amdgpu_connector)
 {
-	u8 val;
+	u8 val = 0;
 
 	if (!amdgpu_connector->router.ddc_valid)
 		return;

drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c

@@ -262,7 +262,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
 	}
 
-	r = amdgpu_fence_emit(ring, f, fence_flags);
+	r = amdgpu_fence_emit(ring, f, job, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
 		if (job && job->vmid)

drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c

@@ -46,7 +46,6 @@
 #include <linux/pci.h>
 
 #include <drm/drm_crtc_helper.h>
-#include <drm/drm_irq.h>
 #include <drm/drm_vblank.h>
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_drv.h>
@@ -184,7 +183,7 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev)
  * Returns:
  * result of handling the IRQ, as defined by &irqreturn_t
  */
-irqreturn_t amdgpu_irq_handler(int irq, void *arg)
+static irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	struct amdgpu_device *adev = drm_to_adev(dev);
@@ -307,6 +306,7 @@ static void amdgpu_restore_msix(struct amdgpu_device *adev)
 int amdgpu_irq_init(struct amdgpu_device *adev)
 {
 	int r = 0;
+	unsigned int irq;
 
 	spin_lock_init(&adev->irq.lock);
 
@@ -349,15 +349,22 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	INIT_WORK(&adev->irq.ih2_work, amdgpu_irq_handle_ih2);
 	INIT_WORK(&adev->irq.ih_soft_work, amdgpu_irq_handle_ih_soft);
 
-	adev->irq.installed = true;
+	/* Use vector 0 for MSI-X. */
-	/* Use vector 0 for MSI-X */
+	r = pci_irq_vector(adev->pdev, 0);
-	r = drm_irq_install(adev_to_drm(adev), pci_irq_vector(adev->pdev, 0));
+	if (r < 0)
+		return r;
+	irq = r;
+
+	/* PCI devices require shared interrupts. */
+	r = request_irq(irq, amdgpu_irq_handler, IRQF_SHARED, adev_to_drm(adev)->driver->name,
+			adev_to_drm(adev));
 	if (r) {
-		adev->irq.installed = false;
 		if (!amdgpu_device_has_dc_support(adev))
 			flush_work(&adev->hotplug_work);
 		return r;
 	}
+	adev->irq.installed = true;
+	adev->irq.irq = irq;
 	adev_to_drm(adev)->max_vblank_count = 0x00ffffff;
 
 	DRM_DEBUG("amdgpu: irq initialized.\n");
@@ -368,7 +375,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
 {
 	if (adev->irq.installed) {
-		drm_irq_uninstall(&adev->ddev);
+		free_irq(adev->irq.irq, adev_to_drm(adev));
 		adev->irq.installed = false;
 		if (adev->irq.msi_enabled)
 			pci_free_irq_vectors(adev->pdev);
@@ -584,7 +591,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 {
 	int i, j, k;
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) || amdgpu_passthrough(adev))
 		amdgpu_restore_msix(adev);
 
 	for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
@@ -617,7 +624,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
 {
-	if (!adev_to_drm(adev)->irq_enabled)
+	if (!adev->irq.installed)
 		return -ENOENT;
 
 	if (type >= src->num_types)
@@ -647,7 +654,7 @@ int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
 {
-	if (!adev_to_drm(adev)->irq_enabled)
+	if (!adev->irq.installed)
 		return -ENOENT;
 
 	if (type >= src->num_types)
@@ -678,7 +685,7 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 			unsigned type)
 {
-	if (!adev_to_drm(adev)->irq_enabled)
+	if (!adev->irq.installed)
 		return false;
 
 	if (type >= src->num_types)

drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h

@@ -80,6 +80,7 @@ struct amdgpu_irq_src_funcs {
 
 struct amdgpu_irq {
 	bool				installed;
+	unsigned int			irq;
 	spinlock_t			lock;
 	/* interrupt sources */
 	struct amdgpu_irq_client	client[AMDGPU_IRQ_CLIENTID_MAX];
@@ -100,7 +101,6 @@ struct amdgpu_irq {
 };
 
 void amdgpu_irq_disable_all(struct amdgpu_device *adev);
-irqreturn_t amdgpu_irq_handler(int irq, void *arg);
 
 int amdgpu_irq_init(struct amdgpu_device *adev);
 void amdgpu_irq_fini_sw(struct amdgpu_device *adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c

@@ -127,11 +127,16 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
 	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	struct dma_fence *f;
+	struct dma_fence *hw_fence;
 	unsigned i;
 
-	/* use sched fence if available */
+	if (job->hw_fence.ops == NULL)
-	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
+		hw_fence = job->external_hw_fence;
+	else
+		hw_fence = &job->hw_fence;
 
+	/* use sched fence if available */
+	f = job->base.s_fence ? &job->base.s_fence->finished : hw_fence;
 	for (i = 0; i < job->num_ibs; ++i)
 		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }
@@ -142,20 +147,27 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 
 	drm_sched_job_cleanup(s_job);
 
-	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
-	kfree(job);
+
+    /* only put the hw fence if has embedded fence */
+	if (job->hw_fence.ops != NULL)
+		dma_fence_put(&job->hw_fence);
+	else
+		kfree(job);
 }
 
 void amdgpu_job_free(struct amdgpu_job *job)
 {
 	amdgpu_job_free_resources(job);
-
-	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
-	kfree(job);
+
+	/* only put the hw fence if has embedded fence */
+	if (job->hw_fence.ops != NULL)
+		dma_fence_put(&job->hw_fence);
+	else
+		kfree(job);
 }
 
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
@@ -184,11 +196,14 @@ int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
 
 	job->base.sched = &ring->sched;
 	r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, NULL, fence);
-	job->fence = dma_fence_get(*fence);
+	/* record external_hw_fence for direct submit */
+	job->external_hw_fence = dma_fence_get(*fence);
 	if (r)
 		return r;
 
 	amdgpu_job_free(job);
+	dma_fence_put(*fence);
+
 	return 0;
 }
 
@@ -246,10 +261,12 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 		if (r)
 			DRM_ERROR("Error scheduling IBs (%d)\n", r);
 	}
-	/* if gpu reset, hw fence will be replaced here */
-	dma_fence_put(job->fence);
-	job->fence = dma_fence_get(fence);
 
+	if (!job->job_run_counter)
+		dma_fence_get(fence);
+	else if (finished->error < 0)
+		dma_fence_put(&job->hw_fence);
+	job->job_run_counter++;
 	amdgpu_job_free_resources(job);
 
 	fence = r ? ERR_PTR(r) : fence;

drivers/gpu/drm/amd/amdgpu/amdgpu_job.h

@@ -46,7 +46,8 @@ struct amdgpu_job {
 	struct amdgpu_sync	sync;
 	struct amdgpu_sync	sched_sync;
 	struct amdgpu_ib	*ibs;
-	struct dma_fence	*fence; /* the hw fence */
+	struct dma_fence	hw_fence;
+	struct dma_fence	*external_hw_fence;
 	uint32_t		preamble_status;
 	uint32_t                preemption_status;
 	uint32_t		num_ibs;
@@ -62,6 +63,9 @@ struct amdgpu_job {
 	/* user fence handling */
 	uint64_t		uf_addr;
 	uint64_t		uf_sequence;
+
+	/* job_run_counter >= 1 means a resubmit job */
+	uint32_t		job_run_counter;
 };
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,

drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c

@@ -47,8 +47,6 @@ int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
 {
 	int i;
 
-	cancel_delayed_work_sync(&adev->jpeg.idle_work);
-
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
 			continue;

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -341,27 +341,27 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		switch (query_fw->index) {
 		case TA_FW_TYPE_PSP_XGMI:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_xgmi_ucode_version;
+			fw_info->feature = adev->psp.xgmi.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_RAS:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_ras_ucode_version;
+			fw_info->feature = adev->psp.ras.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_HDCP:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_hdcp_ucode_version;
+			fw_info->feature = adev->psp.hdcp.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_DTM:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_dtm_ucode_version;
+			fw_info->feature = adev->psp.dtm.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_RAP:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_rap_ucode_version;
+			fw_info->feature = adev->psp.rap.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_SECUREDISPLAY:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ta_securedisplay_ucode_version;
+			fw_info->feature = adev->psp.securedisplay.feature_version;
 			break;
 		default:
 			return -EINVAL;
@@ -374,12 +374,12 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->feature = adev->sdma.instance[query_fw->index].feature_version;
 		break;
 	case AMDGPU_INFO_FW_SOS:
-		fw_info->ver = adev->psp.sos_fw_version;
+		fw_info->ver = adev->psp.sos.fw_version;
-		fw_info->feature = adev->psp.sos_feature_version;
+		fw_info->feature = adev->psp.sos.feature_version;
 		break;
 	case AMDGPU_INFO_FW_ASD:
-		fw_info->ver = adev->psp.asd_fw_version;
+		fw_info->ver = adev->psp.asd.fw_version;
-		fw_info->feature = adev->psp.asd_feature_version;
+		fw_info->feature = adev->psp.asd.feature_version;
 		break;
 	case AMDGPU_INFO_FW_DMCU:
 		fw_info->ver = adev->dm.dmcu_fw_version;
@@ -390,8 +390,8 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->feature = 0;
 		break;
 	case AMDGPU_INFO_FW_TOC:
-		fw_info->ver = adev->psp.toc_fw_version;
+		fw_info->ver = adev->psp.toc.fw_version;
-		fw_info->feature = adev->psp.toc_feature_version;
+		fw_info->feature = adev->psp.toc.feature_version;
 		break;
 	default:
 		return -EINVAL;
@@ -1179,10 +1179,14 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		pasid = 0;
 	}
 
-	r = amdgpu_vm_init(adev, &fpriv->vm, pasid);
+	r = amdgpu_vm_init(adev, &fpriv->vm);
 	if (r)
 		goto error_pasid;
 
+	r = amdgpu_vm_set_pasid(adev, &fpriv->vm, pasid);
+	if (r)
+		goto error_vm;
+
 	fpriv->prt_va = amdgpu_vm_bo_add(adev, &fpriv->vm, NULL);
 	if (!fpriv->prt_va) {
 		r = -ENOMEM;
@@ -1210,8 +1214,10 @@ error_vm:
 	amdgpu_vm_fini(adev, &fpriv->vm);
 
 error_pasid:
-	if (pasid)
+	if (pasid) {
 		amdgpu_pasid_free(pasid);
+		amdgpu_vm_set_pasid(adev, &fpriv->vm, 0);
+	}
 
 	kfree(fpriv);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c

@@ -0,0 +1,117 @@
+/*
+ * 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.
+ *
+ */
+#include "amdgpu_ras.h"
+#include "amdgpu.h"
+#include "amdgpu_mca.h"
+
+#include "umc/umc_6_7_0_offset.h"
+#include "umc/umc_6_7_0_sh_mask.h"
+
+void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
+					      uint64_t mc_status_addr,
+					      unsigned long *error_count)
+{
+	uint64_t mc_status = RREG64_PCIE(mc_status_addr * 4);
+
+	if (REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
+		*error_count += 1;
+}
+
+void amdgpu_mca_query_uncorrectable_error_count(struct amdgpu_device *adev,
+						uint64_t mc_status_addr,
+						unsigned long *error_count)
+{
+	uint64_t mc_status = RREG64_PCIE(mc_status_addr * 4);
+
+	if ((REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
+	    (REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
+	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1))
+		*error_count += 1;
+}
+
+void amdgpu_mca_reset_error_count(struct amdgpu_device *adev,
+				  uint64_t mc_status_addr)
+{
+	WREG64_PCIE(mc_status_addr * 4, 0x0ULL);
+}
+
+void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev,
+				      uint64_t mc_status_addr,
+				      void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+
+	amdgpu_mca_query_correctable_error_count(adev, mc_status_addr, &(err_data->ce_count));
+	amdgpu_mca_query_uncorrectable_error_count(adev, mc_status_addr, &(err_data->ue_count));
+
+	amdgpu_mca_reset_error_count(adev, mc_status_addr);
+}
+
+int amdgpu_mca_ras_late_init(struct amdgpu_device *adev,
+			     struct amdgpu_mca_ras *mca_dev)
+{
+	int r;
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+	struct ras_fs_if fs_info = {
+		.sysfs_name = mca_dev->ras_funcs->sysfs_name,
+	};
+
+	if (!mca_dev->ras_if) {
+		mca_dev->ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!mca_dev->ras_if)
+			return -ENOMEM;
+		mca_dev->ras_if->block = mca_dev->ras_funcs->ras_block;
+		mca_dev->ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		mca_dev->ras_if->sub_block_index = 0;
+	}
+	ih_info.head = fs_info.head = *mca_dev->ras_if;
+	r = amdgpu_ras_late_init(adev, mca_dev->ras_if,
+				 &fs_info, &ih_info);
+	if (r || !amdgpu_ras_is_supported(adev, mca_dev->ras_if->block)) {
+		kfree(mca_dev->ras_if);
+		mca_dev->ras_if = NULL;
+	}
+
+	return r;
+}
+
+void amdgpu_mca_ras_fini(struct amdgpu_device *adev,
+			 struct amdgpu_mca_ras *mca_dev)
+{
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+
+	if (!mca_dev->ras_if)
+		return;
+
+	amdgpu_ras_late_fini(adev, mca_dev->ras_if, &ih_info);
+	kfree(mca_dev->ras_if);
+	mca_dev->ras_if = NULL;
+}

drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h

@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 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) 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 __AMDGPU_MCA_H__
+#define __AMDGPU_MCA_H__
+
+struct amdgpu_mca_ras_funcs {
+	int (*ras_late_init)(struct amdgpu_device *adev);
+	void (*ras_fini)(struct amdgpu_device *adev);
+	void (*query_ras_error_count)(struct amdgpu_device *adev,
+				      void *ras_error_status);
+	void (*query_ras_error_address)(struct amdgpu_device *adev,
+					void *ras_error_status);
+	uint32_t ras_block;
+	const char* sysfs_name;
+};
+
+struct amdgpu_mca_ras {
+	struct ras_common_if *ras_if;
+	const struct amdgpu_mca_ras_funcs *ras_funcs;
+};
+
+struct amdgpu_mca_funcs {
+	void (*init)(struct amdgpu_device *adev);
+};
+
+struct amdgpu_mca {
+	const struct amdgpu_mca_funcs *funcs;
+	struct amdgpu_mca_ras mp0;
+	struct amdgpu_mca_ras mp1;
+	struct amdgpu_mca_ras mpio;
+};
+
+void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
+					      uint64_t mc_status_addr,
+					      unsigned long *error_count);
+
+void amdgpu_mca_query_uncorrectable_error_count(struct amdgpu_device *adev,
+						uint64_t mc_status_addr,
+						unsigned long *error_count);
+
+void amdgpu_mca_reset_error_count(struct amdgpu_device *adev,
+				  uint64_t mc_status_addr);
+
+void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev,
+				      uint64_t mc_status_addr,
+				      void *ras_error_status);
+
+int amdgpu_mca_ras_late_init(struct amdgpu_device *adev,
+			     struct amdgpu_mca_ras *mca_dev);
+
+void amdgpu_mca_ras_fini(struct amdgpu_device *adev,
+			 struct amdgpu_mca_ras *mca_dev);
+
+#endif

drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c

@@ -41,7 +41,6 @@ int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev)
 		adev->mmhub.ras_if->block = AMDGPU_RAS_BLOCK__MMHUB;
 		adev->mmhub.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->mmhub.ras_if->sub_block_index = 0;
-		strcpy(adev->mmhub.ras_if->name, "mmhub");
 	}
 	ih_info.head = fs_info.head = *adev->mmhub.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->mmhub.ras_if,

drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c

@@ -39,7 +39,6 @@ int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev)
 		adev->nbio.ras_if->block = AMDGPU_RAS_BLOCK__PCIE_BIF;
 		adev->nbio.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
 		adev->nbio.ras_if->sub_block_index = 0;
-		strcpy(adev->nbio.ras_if->name, "pcie_bif");
 	}
 	ih_info.head = fs_info.head = *adev->nbio.ras_if;
 	r = amdgpu_ras_late_init(adev, adev->nbio.ras_if,

drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h

@@ -95,6 +95,7 @@ struct amdgpu_nbio_funcs {
 	void (*program_aspm)(struct amdgpu_device *adev);
 	void (*apply_lc_spc_mode_wa)(struct amdgpu_device *adev);
 	void (*apply_l1_link_width_reconfig_wa)(struct amdgpu_device *adev);
+	void (*clear_doorbell_interrupt)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_nbio {

drivers/gpu/drm/amd/amdgpu/amdgpu_object.c

@@ -196,7 +196,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
-	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+	BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS);
 
 	placement->num_placement = c;
 	placement->placement = places;
@@ -731,7 +731,7 @@ retry:
 /**
  * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list
  *
- * @bo: BO that will be inserted into the shadow list
+ * @vmbo: BO that will be inserted into the shadow list
  *
  * Insert a BO to the shadow list.
  */
@@ -913,7 +913,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return -EINVAL;
 
 	/* A shared bo cannot be migrated to VRAM */
-	if (bo->prime_shared_count || bo->tbo.base.import_attach) {
+	if (bo->tbo.base.import_attach) {
 		if (domain & AMDGPU_GEM_DOMAIN_GTT)
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 		else
@@ -947,7 +947,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	/* This assumes only APU display buffers are pinned with (VRAM|GTT).
 	 * See function amdgpu_display_supported_domains()
 	 */
-	domain = amdgpu_bo_get_preferred_pin_domain(adev, domain);
+	domain = amdgpu_bo_get_preferred_domain(adev, domain);
 
 	if (bo->tbo.base.import_attach)
 		dma_buf_pin(bo->tbo.base.import_attach);
@@ -1518,14 +1518,14 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo)
 }
 
 /**
- * amdgpu_bo_get_preferred_pin_domain - get preferred domain for scanout
+ * amdgpu_bo_get_preferred_domain - get preferred domain
  * @adev: amdgpu device object
  * @domain: allowed :ref:`memory domains <amdgpu_memory_domains>`
  *
  * Returns:
- * Which of the allowed domains is preferred for pinning the BO for scanout.
+ * Which of the allowed domains is preferred for allocating the BO.
  */
-uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
 					    uint32_t domain)
 {
 	if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) {

drivers/gpu/drm/amd/amdgpu/amdgpu_object.h

@@ -100,7 +100,6 @@ struct amdgpu_bo {
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
 	u64				flags;
-	unsigned			prime_shared_count;
 	/* per VM structure for page tables and with virtual addresses */
 	struct amdgpu_vm_bo_base	*vm_bo;
 	/* Constant after initialization */
@@ -334,7 +333,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem,
 void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo);
 int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow,
 			     struct dma_fence **fence);
-uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
+uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
 					    uint32_t domain);
 
 /*

drivers/gpu/drm/amd/amdgpu/amdgpu_pll.c

@@ -80,12 +80,17 @@ static void amdgpu_pll_reduce_ratio(unsigned *nom, unsigned *den,
  * Calculate feedback and reference divider for a given post divider. Makes
  * sure we stay within the limits.
  */
-static void amdgpu_pll_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
+static void amdgpu_pll_get_fb_ref_div(struct amdgpu_device *adev, unsigned int nom,
-				      unsigned fb_div_max, unsigned ref_div_max,
+				      unsigned int den, unsigned int post_div,
-				      unsigned *fb_div, unsigned *ref_div)
+				      unsigned int fb_div_max, unsigned int ref_div_max,
+				      unsigned int *fb_div, unsigned int *ref_div)
 {
+
 	/* limit reference * post divider to a maximum */
-	ref_div_max = min(128 / post_div, ref_div_max);
+	if (adev->family == AMDGPU_FAMILY_SI)
+		ref_div_max = min(100 / post_div, ref_div_max);
+	else
+		ref_div_max = min(128 / post_div, ref_div_max);
 
 	/* get matching reference and feedback divider */
 	*ref_div = min(max(DIV_ROUND_CLOSEST(den, post_div), 1u), ref_div_max);
@@ -112,7 +117,8 @@ static void amdgpu_pll_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_
  * Try to calculate the PLL parameters to generate the given frequency:
  * dot_clock = (ref_freq * feedback_div) / (ref_div * post_div)
  */
-void amdgpu_pll_compute(struct amdgpu_pll *pll,
+void amdgpu_pll_compute(struct amdgpu_device *adev,
+			struct amdgpu_pll *pll,
 			u32 freq,
 			u32 *dot_clock_p,
 			u32 *fb_div_p,
@@ -199,7 +205,7 @@ void amdgpu_pll_compute(struct amdgpu_pll *pll,
 
 	for (post_div = post_div_min; post_div <= post_div_max; ++post_div) {
 		unsigned diff;
-		amdgpu_pll_get_fb_ref_div(nom, den, post_div, fb_div_max,
+		amdgpu_pll_get_fb_ref_div(adev, nom, den, post_div, fb_div_max,
 					  ref_div_max, &fb_div, &ref_div);
 		diff = abs(target_clock - (pll->reference_freq * fb_div) /
 			(ref_div * post_div));
@@ -214,7 +220,7 @@ void amdgpu_pll_compute(struct amdgpu_pll *pll,
 	post_div = post_div_best;
 
 	/* get the feedback and reference divider for the optimal value */
-	amdgpu_pll_get_fb_ref_div(nom, den, post_div, fb_div_max, ref_div_max,
+	amdgpu_pll_get_fb_ref_div(adev, nom, den, post_div, fb_div_max, ref_div_max,
 				  &fb_div, &ref_div);
 
 	/* reduce the numbers to a simpler ratio once more */

drivers/gpu/drm/amd/amdgpu/amdgpu_pll.h

@@ -24,7 +24,8 @@
 #ifndef __AMDGPU_PLL_H__
 #define __AMDGPU_PLL_H__
 
-void amdgpu_pll_compute(struct amdgpu_pll *pll,
+void amdgpu_pll_compute(struct amdgpu_device *adev,
+			 struct amdgpu_pll *pll,
 			 u32 freq,
 			 u32 *dot_clock_p,
 			 u32 *fb_div_p,

drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h

@@ -48,11 +48,15 @@
 struct psp_context;
 struct psp_xgmi_node_info;
 struct psp_xgmi_topology_info;
+struct psp_bin_desc;
 
 enum psp_bootloader_cmd {
 	PSP_BL__LOAD_SYSDRV		= 0x10000,
 	PSP_BL__LOAD_SOSDRV		= 0x20000,
 	PSP_BL__LOAD_KEY_DATABASE	= 0x80000,
+	PSP_BL__LOAD_SOCDRV             = 0xB0000,
+	PSP_BL__LOAD_INTFDRV            = 0xC0000,
+	PSP_BL__LOAD_DBGDRV             = 0xD0000,
 	PSP_BL__DRAM_LONG_TRAIN		= 0x100000,
 	PSP_BL__DRAM_SHORT_TRAIN	= 0x200000,
 	PSP_BL__LOAD_TOS_SPL_TABLE	= 0x10000000,
@@ -93,6 +97,9 @@ struct psp_funcs
 	int (*bootloader_load_kdb)(struct psp_context *psp);
 	int (*bootloader_load_spl)(struct psp_context *psp);
 	int (*bootloader_load_sysdrv)(struct psp_context *psp);
+	int (*bootloader_load_soc_drv)(struct psp_context *psp);
+	int (*bootloader_load_intf_drv)(struct psp_context *psp);
+	int (*bootloader_load_dbg_drv)(struct psp_context *psp);
 	int (*bootloader_load_sos)(struct psp_context *psp);
 	int (*ring_init)(struct psp_context *psp, enum psp_ring_type ring_type);
 	int (*ring_create)(struct psp_context *psp,
@@ -106,7 +113,7 @@ struct psp_funcs
 	int (*mem_training)(struct psp_context *psp, uint32_t ops);
 	uint32_t (*ring_get_wptr)(struct psp_context *psp);
 	void (*ring_set_wptr)(struct psp_context *psp, uint32_t value);
-	int (*load_usbc_pd_fw)(struct psp_context *psp, dma_addr_t dma_addr);
+	int (*load_usbc_pd_fw)(struct psp_context *psp, uint64_t fw_pri_mc_addr);
 	int (*read_usbc_pd_fw)(struct psp_context *psp, uint32_t *fw_ver);
 };
 
@@ -116,6 +123,7 @@ struct psp_xgmi_node_info {
 	uint8_t					num_hops;
 	uint8_t					is_sharing_enabled;
 	enum ta_xgmi_assigned_sdma_engine	sdma_engine;
+	uint8_t					num_links;
 };
 
 struct psp_xgmi_topology_info {
@@ -128,59 +136,32 @@ struct psp_asd_context {
 	uint32_t		session_id;
 };
 
+struct ta_mem_context {
+	struct amdgpu_bo		*shared_bo;
+	uint64_t		shared_mc_addr;
+	void			*shared_buf;
+};
+
+struct ta_context {
+	bool			initialized;
+	uint32_t		session_id;
+	struct ta_mem_context	mem_context;
+};
+
+struct ta_cp_context {
+	struct ta_context		context;
+	struct mutex			mutex;
+};
+
 struct psp_xgmi_context {
-	uint8_t				initialized;
+	struct ta_context		context;
-	uint32_t			session_id;
-	struct amdgpu_bo                *xgmi_shared_bo;
-	uint64_t                        xgmi_shared_mc_addr;
-	void                            *xgmi_shared_buf;
 	struct psp_xgmi_topology_info	top_info;
+	bool				supports_extended_data;
 };
 
 struct psp_ras_context {
-	/*ras fw*/
+	struct ta_context		context;
-	bool			ras_initialized;
+	struct amdgpu_ras		*ras;
-	uint32_t		session_id;
-	struct amdgpu_bo	*ras_shared_bo;
-	uint64_t		ras_shared_mc_addr;
-	void			*ras_shared_buf;
-	struct amdgpu_ras	*ras;
-};
-
-struct psp_hdcp_context {
-	bool			hdcp_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*hdcp_shared_bo;
-	uint64_t		hdcp_shared_mc_addr;
-	void			*hdcp_shared_buf;
-	struct mutex		mutex;
-};
-
-struct psp_dtm_context {
-	bool			dtm_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*dtm_shared_bo;
-	uint64_t		dtm_shared_mc_addr;
-	void			*dtm_shared_buf;
-	struct mutex		mutex;
-};
-
-struct psp_rap_context {
-	bool			rap_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*rap_shared_bo;
-	uint64_t		rap_shared_mc_addr;
-	void			*rap_shared_buf;
-	struct mutex		mutex;
-};
-
-struct psp_securedisplay_context {
-	bool			securedisplay_initialized;
-	uint32_t		session_id;
-	struct amdgpu_bo	*securedisplay_shared_bo;
-	uint64_t		securedisplay_shared_mc_addr;
-	void			*securedisplay_shared_buf;
-	struct mutex		mutex;
 };
 
 #define MEM_TRAIN_SYSTEM_SIGNATURE		0x54534942
@@ -282,6 +263,13 @@ struct psp_runtime_boot_cfg_entry {
 	uint32_t reserved;
 };
 
+struct psp_bin_desc {
+	uint32_t fw_version;
+	uint32_t feature_version;
+	uint32_t size_bytes;
+	uint8_t *start_addr;
+};
+
 struct psp_context
 {
 	struct amdgpu_device            *adev;
@@ -297,36 +285,26 @@ struct psp_context
 
 	/* sos firmware */
 	const struct firmware		*sos_fw;
-	uint32_t			sos_fw_version;
+	struct psp_bin_desc		sys;
-	uint32_t			sos_feature_version;
+	struct psp_bin_desc		sos;
-	uint32_t			sys_bin_size;
+	struct psp_bin_desc		toc;
-	uint32_t			sos_bin_size;
+	struct psp_bin_desc		kdb;
-	uint32_t			toc_bin_size;
+	struct psp_bin_desc		spl;
-	uint32_t			kdb_bin_size;
+	struct psp_bin_desc		rl;
-	uint32_t			spl_bin_size;
+	struct psp_bin_desc		soc_drv;
-	uint32_t			rl_bin_size;
+	struct psp_bin_desc		intf_drv;
-	uint8_t				*sys_start_addr;
+	struct psp_bin_desc		dbg_drv;
-	uint8_t				*sos_start_addr;
-	uint8_t				*toc_start_addr;
-	uint8_t				*kdb_start_addr;
-	uint8_t				*spl_start_addr;
-	uint8_t				*rl_start_addr;
 
 	/* tmr buffer */
 	struct amdgpu_bo		*tmr_bo;
 	uint64_t			tmr_mc_addr;
 
 	/* asd firmware */
-	const struct firmware		*asd_fw;
+	const struct firmware	*asd_fw;
-	uint32_t			asd_fw_version;
+	struct psp_bin_desc		asd;
-	uint32_t			asd_feature_version;
-	uint32_t			asd_ucode_size;
-	uint8_t				*asd_start_addr;
 
 	/* toc firmware */
 	const struct firmware		*toc_fw;
-	uint32_t			toc_fw_version;
-	uint32_t			toc_feature_version;
 
 	/* fence buffer */
 	struct amdgpu_bo		*fence_buf_bo;
@@ -348,36 +326,20 @@ struct psp_context
 	/* xgmi ta firmware and buffer */
 	const struct firmware		*ta_fw;
 	uint32_t			ta_fw_version;
-	uint32_t			ta_xgmi_ucode_version;
+	struct psp_bin_desc		xgmi;
-	uint32_t			ta_xgmi_ucode_size;
+	struct psp_bin_desc		ras;
-	uint8_t				*ta_xgmi_start_addr;
+	struct psp_bin_desc		hdcp;
-	uint32_t			ta_ras_ucode_version;
+	struct psp_bin_desc		dtm;
-	uint32_t			ta_ras_ucode_size;
+	struct psp_bin_desc		rap;
-	uint8_t				*ta_ras_start_addr;
+	struct psp_bin_desc		securedisplay;
-
-	uint32_t			ta_hdcp_ucode_version;
-	uint32_t			ta_hdcp_ucode_size;
-	uint8_t				*ta_hdcp_start_addr;
-
-	uint32_t			ta_dtm_ucode_version;
-	uint32_t			ta_dtm_ucode_size;
-	uint8_t				*ta_dtm_start_addr;
-
-	uint32_t			ta_rap_ucode_version;
-	uint32_t			ta_rap_ucode_size;
-	uint8_t				*ta_rap_start_addr;
-
-	uint32_t			ta_securedisplay_ucode_version;
-	uint32_t			ta_securedisplay_ucode_size;
-	uint8_t				*ta_securedisplay_start_addr;
 
 	struct psp_asd_context		asd_context;
 	struct psp_xgmi_context		xgmi_context;
-	struct psp_ras_context		ras;
+	struct psp_ras_context		ras_context;
-	struct psp_hdcp_context 	hdcp_context;
+	struct ta_cp_context		hdcp_context;
-	struct psp_dtm_context		dtm_context;
+	struct ta_cp_context		dtm_context;
-	struct psp_rap_context		rap_context;
+	struct ta_cp_context		rap_context;
-	struct psp_securedisplay_context	securedisplay_context;
+	struct ta_cp_context		securedisplay_context;
 	struct mutex			mutex;
 	struct psp_memory_training_context mem_train_ctx;
 
@@ -402,6 +364,12 @@ struct amdgpu_psp_funcs {
 		((psp)->funcs->bootloader_load_spl ? (psp)->funcs->bootloader_load_spl((psp)) : 0)
 #define psp_bootloader_load_sysdrv(psp) \
 		((psp)->funcs->bootloader_load_sysdrv ? (psp)->funcs->bootloader_load_sysdrv((psp)) : 0)
+#define psp_bootloader_load_soc_drv(psp) \
+		((psp)->funcs->bootloader_load_soc_drv ? (psp)->funcs->bootloader_load_soc_drv((psp)) : 0)
+#define psp_bootloader_load_intf_drv(psp) \
+		((psp)->funcs->bootloader_load_intf_drv ? (psp)->funcs->bootloader_load_intf_drv((psp)) : 0)
+#define psp_bootloader_load_dbg_drv(psp) \
+		((psp)->funcs->bootloader_load_dbg_drv ? (psp)->funcs->bootloader_load_dbg_drv((psp)) : 0)
 #define psp_bootloader_load_sos(psp) \
 		((psp)->funcs->bootloader_load_sos ? (psp)->funcs->bootloader_load_sos((psp)) : 0)
 #define psp_smu_reload_quirk(psp) \
@@ -414,9 +382,9 @@ struct amdgpu_psp_funcs {
 #define psp_ring_get_wptr(psp) (psp)->funcs->ring_get_wptr((psp))
 #define psp_ring_set_wptr(psp, value) (psp)->funcs->ring_set_wptr((psp), (value))
 
-#define psp_load_usbc_pd_fw(psp, dma_addr) \
+#define psp_load_usbc_pd_fw(psp, fw_pri_mc_addr) \
 	((psp)->funcs->load_usbc_pd_fw ? \
-	(psp)->funcs->load_usbc_pd_fw((psp), (dma_addr)) : -EINVAL)
+	(psp)->funcs->load_usbc_pd_fw((psp), (fw_pri_mc_addr)) : -EINVAL)
 
 #define psp_read_usbc_pd_fw(psp, fw_ver) \
 	((psp)->funcs->read_usbc_pd_fw ? \
@@ -427,6 +395,7 @@ extern const struct amd_ip_funcs psp_ip_funcs;
 extern const struct amdgpu_ip_block_version psp_v3_1_ip_block;
 extern const struct amdgpu_ip_block_version psp_v10_0_ip_block;
 extern const struct amdgpu_ip_block_version psp_v11_0_ip_block;
+extern const struct amdgpu_ip_block_version psp_v11_0_8_ip_block;
 extern const struct amdgpu_ip_block_version psp_v12_0_ip_block;
 extern const struct amdgpu_ip_block_version psp_v13_0_ip_block;
 
@@ -437,14 +406,15 @@ int psp_gpu_reset(struct amdgpu_device *adev);
 int psp_update_vcn_sram(struct amdgpu_device *adev, int inst_idx,
 			uint64_t cmd_gpu_addr, int cmd_size);
 
-int psp_xgmi_initialize(struct psp_context *psp);
+int psp_xgmi_initialize(struct psp_context *psp, bool set_extended_data, bool load_ta);
 int psp_xgmi_terminate(struct psp_context *psp);
 int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 int psp_xgmi_get_hive_id(struct psp_context *psp, uint64_t *hive_id);
 int psp_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id);
 int psp_xgmi_get_topology_info(struct psp_context *psp,
 			       int number_devices,
-			       struct psp_xgmi_topology_info *topology);
+			       struct psp_xgmi_topology_info *topology,
+			       bool get_extended_data);
 int psp_xgmi_set_topology_info(struct psp_context *psp,
 			       int number_devices,
 			       struct psp_xgmi_topology_info *topology);
@@ -483,4 +453,5 @@ int psp_load_fw_list(struct psp_context *psp,
 		     struct amdgpu_firmware_info **ucode_list, int ucode_count);
 void psp_copy_fw(struct psp_context *psp, uint8_t *start_addr, uint32_t bin_size);
 
+int is_psp_fw_valid(struct psp_bin_desc bin);
 #endif

drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c

@@ -76,7 +76,7 @@ static ssize_t amdgpu_rap_debugfs_write(struct file *f, const char __user *buf,
 			dev_info(adev->dev, "RAP L0 validate test success.\n");
 		} else {
 			rap_shared_mem = (struct ta_rap_shared_memory *)
-					 adev->psp.rap_context.rap_shared_buf;
+					 adev->psp.rap_context.context.mem_context.shared_buf;
 			rap_cmd_output = &(rap_shared_mem->rap_out_message.output);
 
 			dev_info(adev->dev, "RAP test failed, the output is:\n");
@@ -119,7 +119,7 @@ void amdgpu_rap_debugfs_init(struct amdgpu_device *adev)
 #if defined(CONFIG_DEBUG_FS)
 	struct drm_minor *minor = adev_to_drm(adev)->primary;
 
-	if (!adev->psp.rap_context.rap_initialized)
+	if (!adev->psp.rap_context.context.initialized)
 		return;
 
 	debugfs_create_file("rap_test", S_IWUSR, minor->debugfs_root,